High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

FOURS1					99.82 1	98.66 32	99.69 1	98.95 62	97.46 59	99.39 48

RA-MVS			99.04 4		99.80 2	99.12 13	99.32 22	99.09 44	97.80 37	99.60 34	99.42 47	97.74 6	99.93 35	98.80 43	99.82 15

aaatest				99.52 15	99.77 3	98.86 25	99.32 22	99.24 20	96.41 127	99.30 54	99.35 64		99.92 45	98.30 78	99.80 27	99.79 30

MED-MVS		99.12 2	98.97 6	99.56 9	99.77 3	98.86 25	99.32 22	99.24 20	97.87 32	99.30 54	99.54 21	97.61 7	99.92 45	98.30 78	99.80 27	99.90 6

TestfortrainingZip a		99.05 7	98.85 11	99.65 2	99.77 3	99.13 12	99.32 22	99.01 53	97.87 32	99.74 22	99.54 21	96.71 20	99.92 45	98.35 75	99.33 142	99.90 6

MTAPA		98.58 37	98.29 63	99.46 19	99.76 6	98.64 33	98.90 123	98.74 132	97.27 75	98.02 159	99.39 52	94.81 90	99.96 5	97.91 104	99.79 37	99.77 41

NormalMVS		98.07 85	97.90 89	98.59 105	99.75 7	96.60 147	98.94 110	98.60 167	97.86 34	98.71 106	99.08 140	91.22 184	99.80 112	97.40 161	99.57 101	99.37 145

lecture		98.95 10	98.78 16	99.45 20	99.75 7	98.63 34	99.43 10	99.38 8	97.60 48	99.58 36	99.47 38	95.36 67	99.93 35	98.87 40	99.57 101	99.78 34

MSP-MVS		98.74 23	98.55 31	99.29 40	99.75 7	98.23 60	99.26 34	98.88 79	97.52 52	99.41 46	98.78 196	96.00 45	99.79 124	97.79 115	99.59 97	99.85 17
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
MP-MVS		98.33 73	98.01 84	99.28 43	99.75 7	98.18 64	99.22 44	98.79 122	96.13 141	97.92 173	99.23 89	94.54 93	99.94 15	96.74 201	99.78 42	99.73 56
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
mPP-MVS		98.51 50	98.26 64	99.25 46	99.75 7	98.04 72	99.28 31	98.81 110	96.24 136	98.35 137	99.23 89	95.46 61	99.94 15	97.42 159	99.81 18	99.77 41

HPM-MVS_fast		98.38 64	98.13 76	99.12 62	99.75 7	97.86 78	99.44 9	98.82 104	94.46 266	98.94 81	99.20 97	95.16 80	99.74 137	97.58 136	99.85 7	99.77 41

region2R		98.61 32	98.38 46	99.29 40	99.74 13	98.16 66	99.23 39	98.93 66	96.15 140	98.94 81	99.17 109	95.91 49	99.94 15	97.55 141	99.79 37	99.78 34

ACMMPR		98.59 35	98.36 48	99.29 40	99.74 13	98.15 67	99.23 39	98.95 62	96.10 146	98.93 85	99.19 104	95.70 55	99.94 15	97.62 129	99.79 37	99.78 34

HPM-MVS		98.36 67	98.10 79	99.13 60	99.74 13	97.82 83	99.53 6	98.80 117	94.63 253	98.61 117	98.97 158	95.13 82	99.77 132	97.65 127	99.83 14	99.79 30
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ACMMP		98.23 77	97.95 86	99.09 64	99.74 13	97.62 87	99.03 85	99.41 6	95.98 151	97.60 210	99.36 62	94.45 98	99.93 35	97.14 171	98.85 171	99.70 69
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
ZNCC-MVS		98.49 52	98.20 73	99.35 32	99.73 17	98.39 43	99.19 52	98.86 92	95.77 165	98.31 141	99.10 129	95.46 61	99.93 35	97.57 140	99.81 18	99.74 51

DVP-MVS		99.03 8	98.83 13	99.63 5	99.72 18	99.25 2	98.97 100	98.58 179	97.62 45	99.45 42	99.46 43	97.42 11	99.94 15	98.47 66	99.81 18	99.69 72
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				99.71 1	99.72 18	99.35 1	98.97 100	98.88 79					99.94 15	98.47 66	99.81 18	99.84 19

test0726					99.72 18	99.25 2	99.06 76	98.88 79	97.62 45	99.56 37	99.50 32	97.42 11

GST-MVS		98.43 60	98.12 77	99.34 33	99.72 18	98.38 44	99.09 72	98.82 104	95.71 169	98.73 102	99.06 145	95.27 73	99.93 35	97.07 174	99.63 90	99.72 60

MP-MVS-pluss		98.31 74	97.92 87	99.49 17	99.72 18	98.88 22	98.43 268	98.78 124	94.10 278	97.69 196	99.42 47	95.25 75	99.92 45	98.09 91	99.80 27	99.67 81
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HFP-MVS		98.63 30	98.40 44	99.32 39	99.72 18	98.29 56	99.23 39	98.96 61	96.10 146	98.94 81	99.17 109	96.06 42	99.92 45	97.62 129	99.78 42	99.75 49

PGM-MVS		98.49 52	98.23 69	99.27 45	99.72 18	98.08 71	98.99 96	99.49 5	95.43 192	99.03 73	99.32 71	95.56 58	99.94 15	96.80 198	99.77 44	99.78 34

SED-MVS		99.09 3	98.91 7	99.63 5	99.71 25	99.24 5	99.02 88	98.87 86	97.65 43	99.73 24	99.48 36	97.53 9	99.94 15	98.43 70	99.81 18	99.70 69

IU-MVS					99.71 25	99.23 7		98.64 161	95.28 205	99.63 33				98.35 75	99.81 18	99.83 20

test_241102_ONE					99.71 25	99.24 5		98.87 86	97.62 45	99.73 24	99.39 52	97.53 9	99.74 137

XVS		98.70 25	98.49 38	99.34 33	99.70 28	98.35 53	99.29 29	98.88 79	97.40 61	98.46 124	99.20 97	95.90 51	99.89 71	97.85 110	99.74 60	99.78 34

X-MVStestdata		94.06 371	92.30 398	99.34 33	99.70 28	98.35 53	99.29 29	98.88 79	97.40 61	98.46 124	43.50 556	95.90 51	99.89 71	97.85 110	99.74 60	99.78 34

TSAR-MVS + MP.		98.78 21	98.62 24	99.24 47	99.69 30	98.28 57	99.14 62	98.66 156	96.84 101	99.56 37	99.31 73	96.34 35	99.70 146	98.32 77	99.73 64	99.73 56
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CSCG		97.85 95	97.74 93	98.20 151	99.67 31	95.16 254	99.22 44	99.32 12	93.04 347	97.02 235	98.92 173	95.36 67	99.91 59	97.43 157	99.64 88	99.52 103

test_one_0601					99.66 32	99.25 2		98.86 92	97.55 51	99.20 62	99.47 38	97.57 8

CP-MVS		98.57 42	98.36 48	99.19 52	99.66 32	97.86 78	99.34 17	98.87 86	95.96 153	98.60 118	99.13 120	96.05 43	99.94 15	97.77 116	99.86 2	99.77 41

test-260524					99.64 34	99.18 10		98.83 100		99.13 71		96.51 29	99.92 45	99.03 34	99.80 27

CPTT-MVS		97.72 103	97.32 126	98.92 80	99.64 34	97.10 125	99.12 66	98.81 110	92.34 375	98.09 148	99.08 140	93.01 120	99.92 45	96.06 222	99.77 44	99.75 49

test_part2					99.63 36	99.18 10				99.27 59

ACMMP_NAP		98.61 32	98.30 62	99.55 11	99.62 37	98.95 21	98.82 158	98.81 110	95.80 162	99.16 69	99.47 38	95.37 66	99.92 45	97.89 106	99.75 56	99.79 30

MCST-MVS		98.65 27	98.37 47	99.48 18	99.60 38	98.87 23	98.41 272	98.68 148	97.04 90	98.52 122	98.80 190	96.78 19	99.83 93	97.93 101	99.61 93	99.74 51

aaEdge-Enhanced		98.83 20	98.60 26	99.52 15	99.58 39	98.86 25	98.69 202	98.93 66	97.00 93	99.17 65	99.35 64	96.62 25	99.90 67	98.30 78	99.80 27	99.79 30

DPE-MVS		98.92 14	98.67 22	99.65 2	99.58 39	99.20 9	98.42 271	98.91 73	97.58 49	99.54 39	99.46 43	97.10 15	99.94 15	97.64 128	99.84 12	99.83 20
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
dcpmvs_2		98.08 83	98.59 27	96.56 320	99.57 41	90.34 428	99.15 59	98.38 252	96.82 103	99.29 56	99.49 35	95.78 53	99.57 174	98.94 37	99.86 2	99.77 41

APDe-MVS		99.02 9	98.84 12	99.55 11	99.57 41	98.96 20	99.39 11	98.93 66	97.38 64	99.41 46	99.54 21	96.66 22	99.84 91	98.86 41	99.85 7	99.87 13
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		98.59 35	98.32 61	99.41 24	99.54 43	98.71 29	99.04 82	98.81 110	95.12 217	99.32 53	99.39 52	96.22 36	99.84 91	97.72 119	99.73 64	99.67 81

patch_mono-2		98.36 67	98.87 9	96.82 290	99.53 44	90.68 416	98.64 215	99.29 15	97.88 31	99.19 64	99.52 26	96.80 18	99.97 1	99.11 31	99.86 2	99.82 24

SR-MVS		98.57 42	98.35 50	99.24 47	99.53 44	98.18 64	99.09 72	98.82 104	96.58 117	99.10 72	99.32 71	95.39 64	99.82 100	97.70 124	99.63 90	99.72 60

DP-MVS Recon		97.86 93	97.46 111	99.06 67	99.53 44	98.35 53	98.33 279	98.89 76	92.62 364	98.05 154	98.94 166	95.34 69	99.65 157	96.04 223	99.42 130	99.19 197

reproduce_model		98.94 11	98.81 14	99.34 33	99.52 47	98.26 58	98.94 110	98.84 98	98.06 26	99.35 50	99.61 6	96.39 34	99.94 15	98.77 45	99.82 15	99.83 20

SMA-MVS		98.58 37	98.25 65	99.56 9	99.51 48	99.04 19	98.95 107	98.80 117	93.67 314	99.37 49	99.52 26	96.52 28	99.89 71	98.06 93	99.81 18	99.76 48
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
APD-MVS		98.35 69	98.00 85	99.42 23	99.51 48	98.72 28	98.80 167	98.82 104	94.52 260	99.23 61	99.25 88	95.54 60	99.80 112	96.52 207	99.77 44	99.74 51
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HPM-MVS++		98.58 37	98.25 65	99.55 11	99.50 50	99.08 14	98.72 194	98.66 156	97.51 53	98.15 142	98.83 187	95.70 55	99.92 45	97.53 144	99.67 77	99.66 84

APD-MVS_3200maxsize		98.53 47	98.33 60	99.15 58	99.50 50	97.92 77	99.15 59	98.81 110	96.24 136	99.20 62	99.37 58	95.30 71	99.80 112	97.73 118	99.67 77	99.72 60

114514_t		96.93 184	96.27 205	98.92 80	99.50 50	97.63 86	98.85 150	98.90 74	84.80 486	97.77 186	99.11 127	92.84 122	99.66 156	94.85 268	99.77 44	99.47 118

PAPM_NR		97.46 136	97.11 150	98.50 119	99.50 50	96.41 162	98.63 218	98.60 167	95.18 210	97.06 233	98.06 277	94.26 103	99.57 174	93.80 316	98.87 168	99.52 103

reproduce-ours		98.93 12	98.78 16	99.38 25	99.49 54	98.38 44	98.86 145	98.83 100	98.06 26	99.29 56	99.58 17	96.40 32	99.94 15	98.68 48	99.81 18	99.81 26

our_new_method		98.93 12	98.78 16	99.38 25	99.49 54	98.38 44	98.86 145	98.83 100	98.06 26	99.29 56	99.58 17	96.40 32	99.94 15	98.68 48	99.81 18	99.81 26

SR-MVS-dyc-post		98.54 46	98.35 50	99.13 60	99.49 54	97.86 78	99.11 68	98.80 117	96.49 122	99.17 65	99.35 64	95.34 69	99.82 100	97.72 119	99.65 83	99.71 64

RE-MVS-def			98.34 56		99.49 54	97.86 78	99.11 68	98.80 117	96.49 122	99.17 65	99.35 64	95.29 72		97.72 119	99.65 83	99.71 64

9.14			98.06 80		99.47 58		98.71 195	98.82 104	94.36 270	99.16 69	99.29 77	96.05 43	99.81 105	97.00 176	99.71 71

CDPH-MVS		97.94 90	97.49 108	99.28 43	99.47 58	98.44 40	97.91 350	98.67 153	92.57 367	98.77 98	98.85 182	95.93 48	99.72 140	95.56 245	99.69 74	99.68 77

ZD-MVS					99.46 60	98.70 30		98.79 122	93.21 338	98.67 109	98.97 158	95.70 55	99.83 93	96.07 219	99.58 100

save fliter					99.46 60	98.38 44	98.21 298	98.71 140	97.95 29

EI-MVSNet-Vis-set		98.47 55	98.39 45	98.69 95	99.46 60	96.49 156	98.30 287	98.69 145	97.21 78	98.84 91	99.36 62	95.41 63	99.78 127	98.62 52	99.65 83	99.80 29

EI-MVSNet-UG-set		98.41 62	98.34 56	98.61 103	99.45 63	96.32 167	98.28 290	98.68 148	97.17 82	98.74 100	99.37 58	95.25 75	99.79 124	98.57 55	99.54 112	99.73 56

F-COLMAP		97.09 176	96.80 173	97.97 194	99.45 63	94.95 270	98.55 241	98.62 166	93.02 348	96.17 280	98.58 224	94.01 107	99.81 105	93.95 310	98.90 164	99.14 207

fmvsm_l_conf0.5_n_a		99.09 3	99.08 2	99.11 63	99.43 65	97.48 93	98.88 134	99.30 14	98.47 19	99.85 12	99.43 46	96.71 20	99.96 5	99.86 1	99.80 27	99.89 9

fmvsm_s_conf0.5_n_11		98.58 37	98.57 28	98.62 101	99.42 66	97.16 121	98.97 100	98.86 92	98.91 5	99.87 5	99.66 4	91.82 156	99.95 10	99.82 7	99.82 15	98.75 266

test_fmvsm_n_1920		98.87 19	99.01 5	98.45 126	99.42 66	96.43 159	98.96 106	99.36 10	98.63 14	99.86 9	99.51 29	95.91 49	99.97 1	99.72 15	99.75 56	98.94 242

fmvsm_l_conf0.5_n		99.07 6	99.05 3	99.14 59	99.41 68	97.54 91	98.89 127	99.31 13	98.49 18	99.86 9	99.42 47	96.45 31	99.96 5	99.86 1	99.74 60	99.90 6

fmvsm_s_conf0.5_n_9		98.63 30	98.66 23	98.54 111	99.40 69	95.83 208	98.79 175	99.17 37	98.94 3	99.92 1	99.61 6	92.49 127	99.93 35	99.86 1	99.76 50	99.86 14

fmvsm_l_mol_unc0.5_1		99.24 1	99.14 1	99.53 14	99.37 70	98.68 31	98.41 272	98.86 92	99.00 1	99.90 3	99.79 1	97.24 14	99.97 1	99.85 5	99.86 2	99.94 1

fmvsm_s_conf0.5_n_10		98.66 26	98.54 33	99.02 70	99.36 71	97.21 118	98.86 145	99.23 27	98.90 6	99.83 13	99.59 14	91.57 165	99.94 15	99.79 10	99.74 60	99.89 9

fmvsm_l_conf0.5_n_3		98.90 16	98.74 20	99.37 29	99.36 71	98.25 59	98.89 127	99.24 20	98.77 11	99.89 4	99.59 14	93.39 115	99.96 5	99.78 11	99.76 50	99.89 9

fmvsm_s_conf0.5_n_8		98.73 24	98.62 24	99.05 68	99.35 73	97.27 109	98.80 167	99.23 27	98.93 4	99.79 16	99.59 14	92.34 133	99.95 10	99.82 7	99.71 71	99.92 3

fmvsm_l_conf0.5_n_9		98.90 16	98.79 15	99.24 47	99.34 74	97.83 82	98.70 199	99.26 16	98.85 7	99.92 1	99.51 29	93.91 109	99.95 10	99.86 1	99.79 37	99.92 3

新几何1				99.16 57	99.34 74	98.01 74		98.69 145	90.06 435	98.13 144	98.95 165	94.60 92	99.89 71	91.97 379	99.47 124	99.59 96

DP-MVS		96.59 203	95.93 222	98.57 106	99.34 74	96.19 174	98.70 199	98.39 245	89.45 446	94.52 318	99.35 64	91.85 154	99.85 87	92.89 346	98.88 166	99.68 77

SD-MVS		98.64 29	98.68 21	98.53 114	99.33 77	98.36 52	98.90 123	98.85 97	97.28 71	99.72 27	99.39 52	96.63 24	97.60 456	98.17 87	99.85 7	99.64 88
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
HyFIR lowres test		96.90 186	96.49 196	98.14 161	99.33 77	95.56 225	97.38 400	99.65 2	92.34 375	97.61 207	98.20 267	89.29 252	99.10 281	96.97 178	97.60 257	99.77 41

OMC-MVS		97.55 123	97.34 125	98.20 151	99.33 77	95.92 196	98.28 290	98.59 174	95.52 187	97.97 166	99.10 129	93.28 118	99.49 194	95.09 262	98.88 166	99.19 197

原ACMM1				98.65 99	99.32 80	96.62 144		98.67 153	93.27 337	97.81 183	98.97 158	95.18 79	99.83 93	93.84 314	99.46 127	99.50 109

CNVR-MVS		98.78 21	98.56 30	99.45 20	99.32 80	98.87 23	98.47 258	98.81 110	97.72 38	98.76 99	99.16 112	97.05 16	99.78 127	98.06 93	99.66 80	99.69 72

TEST9					99.31 82	98.50 38	97.92 348	98.73 135	92.63 363	97.74 190	98.68 212	96.20 38	99.80 112

train_agg		97.97 87	97.52 106	99.33 37	99.31 82	98.50 38	97.92 348	98.73 135	92.98 349	97.74 190	98.68 212	96.20 38	99.80 112	96.59 202	99.57 101	99.68 77

test_prior				99.19 52	99.31 82	98.22 61		98.84 98					99.70 146			99.65 85

PatchMatch-RL		96.59 203	96.03 216	98.27 141	99.31 82	96.51 155	97.91 350	99.06 48	93.72 306	96.92 240	98.06 277	88.50 282	99.65 157	91.77 384	99.00 160	98.66 280

fmvsm_s_conf0.5_n		98.42 61	98.51 34	98.13 166	99.30 86	95.25 249	98.85 150	99.39 7	97.94 30	99.74 22	99.62 5	92.59 126	99.91 59	99.65 19	99.52 115	99.25 186

SDMVSNet		96.85 188	96.42 197	98.14 161	99.30 86	96.38 163	99.21 47	99.23 27	95.92 154	95.96 287	98.76 204	85.88 340	99.44 206	97.93 101	95.59 323	98.60 285

sd_testset		96.17 224	95.76 228	97.42 244	99.30 86	94.34 300	98.82 158	99.08 46	95.92 154	95.96 287	98.76 204	82.83 393	99.32 220	95.56 245	95.59 323	98.60 285

agg_prior					99.30 86	98.38 44		98.72 137		97.57 213			99.81 105

CHOSEN 1792x2688		97.12 174	96.80 173	98.08 174	99.30 86	94.56 291	98.05 332	99.71 1	93.57 322	97.09 229	98.91 174	88.17 289	99.89 71	96.87 191	99.56 109	99.81 26

test_8					99.29 91	98.44 40	97.89 356	98.72 137	92.98 349	97.70 195	98.66 215	96.20 38	99.80 112

旧先验1					99.29 91	97.48 93		98.70 143			99.09 137	95.56 58			99.47 124	99.61 92

PLC	95.07 4	97.20 167	96.78 177	98.44 128	99.29 91	96.31 169	98.14 318	98.76 128	92.41 373	96.39 271	98.31 255	94.92 89	99.78 127	94.06 308	98.77 175	99.23 188
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
COLMAP_ROB	93.27 12	95.33 275	94.87 278	96.71 299	99.29 91	93.24 355	98.58 228	98.11 321	89.92 437	93.57 370	99.10 129	86.37 330	99.79 124	90.78 405	98.10 235	97.09 344
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
NCCC		98.61 32	98.35 50	99.38 25	99.28 95	98.61 35	98.45 260	98.76 128	97.82 36	98.45 127	98.93 168	96.65 23	99.83 93	97.38 164	99.41 131	99.71 64

PVSNet_Blended_VisFu		97.70 105	97.46 111	98.44 128	99.27 96	95.91 197	98.63 218	99.16 39	94.48 265	97.67 198	98.88 178	92.80 123	99.91 59	97.11 172	99.12 152	99.50 109

MVS_111021_LR		98.34 71	98.23 69	98.67 97	99.27 96	96.90 133	97.95 343	99.58 3	97.14 85	98.44 130	99.01 154	95.03 86	99.62 167	97.91 104	99.75 56	99.50 109

MSLP-MVS++		98.56 44	98.57 28	98.55 109	99.26 98	96.80 137	98.71 195	99.05 50	97.28 71	98.84 91	99.28 78	96.47 30	99.40 210	98.52 64	99.70 73	99.47 118

fmvsm_s_conf0.5_n_2		98.30 76	98.21 71	98.57 106	99.25 99	97.11 124	98.66 212	99.20 33	98.82 8	99.79 16	99.60 11	89.38 249	99.92 45	99.80 9	99.38 136	98.69 274

AllTest		95.24 280	94.65 288	96.99 273	99.25 99	93.21 356	98.59 224	98.18 305	91.36 405	93.52 372	98.77 199	84.67 366	99.72 140	89.70 423	97.87 244	98.02 317

TestCases				96.99 273	99.25 99	93.21 356		98.18 305	91.36 405	93.52 372	98.77 199	84.67 366	99.72 140	89.70 423	97.87 244	98.02 317

PVSNet_BlendedMVS		96.73 195	96.60 189	97.12 264	99.25 99	95.35 244	98.26 293	99.26 16	94.28 272	97.94 170	97.46 335	92.74 124	99.81 105	96.88 188	93.32 361	96.20 441

PVSNet_Blended		97.38 146	97.12 149	98.14 161	99.25 99	95.35 244	97.28 412	99.26 16	93.13 343	97.94 170	98.21 266	92.74 124	99.81 105	96.88 188	99.40 134	99.27 177

DeepC-MVS	95.98 3	97.88 92	97.58 99	98.77 89	99.25 99	96.93 131	98.83 156	98.75 130	96.96 95	96.89 242	99.50 32	90.46 214	99.87 82	97.84 112	99.76 50	99.52 103
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepC-MVS_fast	96.70 1	98.55 45	98.34 56	99.18 54	99.25 99	98.04 72	98.50 252	98.78 124	97.72 38	98.92 87	99.28 78	95.27 73	99.82 100	97.55 141	99.77 44	99.69 72
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OPU-MVS				99.37 29	99.24 106	99.05 18	99.02 88				99.16 112	97.81 3	99.37 214	97.24 168	99.73 64	99.70 69

fmvsm_s_conf0.5_n_3		98.53 47	98.45 41	98.79 87	99.23 107	97.32 102	98.80 167	99.26 16	98.82 8	99.87 5	99.60 11	90.95 200	99.93 35	99.76 12	99.73 64	99.12 210

test222					99.23 107	97.17 120	97.40 398	98.66 156	88.68 456	98.05 154	98.96 163	94.14 105			99.53 114	99.61 92

TSAR-MVS + GP.		98.38 64	98.24 67	98.81 86	99.22 109	97.25 115	98.11 325	98.29 283	97.19 80	98.99 79	99.02 150	96.22 36	99.67 153	98.52 64	98.56 188	99.51 106

SteuartSystems-ACMMP		98.90 16	98.75 19	99.36 31	99.22 109	98.43 42	99.10 71	98.87 86	97.38 64	99.35 50	99.40 51	97.78 5	99.87 82	97.77 116	99.85 7	99.78 34
Skip Steuart: Steuart Systems R&D Blog.
MVS_111021_HR		98.47 55	98.34 56	98.88 84	99.22 109	97.32 102	97.91 350	99.58 3	97.20 79	98.33 139	99.00 156	95.99 46	99.64 160	98.05 95	99.76 50	99.69 72

SPE-MVS-test		98.49 52	98.50 36	98.46 125	99.20 112	97.05 127	99.64 4	98.50 202	97.45 60	98.88 88	99.14 117	95.25 75	99.15 267	98.83 42	99.56 109	99.20 193

testdata				98.26 144	99.20 112	95.36 242		98.68 148	91.89 390	98.60 118	99.10 129	94.44 99	99.82 100	94.27 298	99.44 128	99.58 100

DVP-MVS++		99.08 5	98.89 8	99.64 4	99.17 114	99.23 7	99.69 1	98.88 79	97.32 67	99.53 40	99.47 38	97.81 3	99.94 15	98.47 66	99.72 69	99.74 51

MSC_two_6792asdad				99.62 7	99.17 114	99.08 14		98.63 164					99.94 15	98.53 58	99.80 27	99.86 14

No_MVS				99.62 7	99.17 114	99.08 14		98.63 164					99.94 15	98.53 58	99.80 27	99.86 14

PVSNet	91.96 18	96.35 215	96.15 209	96.96 279	99.17 114	92.05 389	96.08 471	98.68 148	93.69 310	97.75 189	97.80 306	88.86 270	99.69 151	94.26 299	99.01 158	99.15 204

fmvsm_s_conf0.5_n_4		98.35 69	98.50 36	97.90 198	99.16 118	95.08 260	98.75 180	99.24 20	98.39 20	99.81 14	99.52 26	92.35 132	99.90 67	99.74 14	99.51 117	98.71 272

test12				99.18 54	99.16 118	98.19 63		98.53 191		98.07 150		95.13 82	99.72 140		99.56 109	99.63 90

AdaColmap		97.15 172	96.70 182	98.48 122	99.16 118	96.69 143	98.01 337	98.89 76	94.44 267	96.83 244	98.68 212	90.69 208	99.76 133	94.36 293	99.29 145	98.98 236

PHI-MVS		98.34 71	98.06 80	99.18 54	99.15 121	98.12 70	99.04 82	99.09 44	93.32 333	98.83 94	99.10 129	96.54 26	99.83 93	97.70 124	99.76 50	99.59 96

TestfortrainingZip				99.43 22	99.13 122	99.06 17	99.32 22	98.57 181	96.88 99	99.42 45	99.05 147	96.54 26	99.73 139		98.59 184	99.51 106

TAPA-MVS	93.98 7	95.35 273	94.56 293	97.74 216	99.13 122	94.83 276	98.33 279	98.64 161	86.62 472	96.29 273	98.61 218	94.00 108	99.29 228	80.00 493	99.41 131	99.09 219
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MM		98.51 50	98.24 67	99.33 37	99.12 124	98.14 69	98.93 117	97.02 437	98.96 2	99.17 65	99.47 38	91.97 152	99.94 15	99.85 5	99.69 74	99.91 5

MG-MVS		97.81 98	97.60 98	98.44 128	99.12 124	95.97 189	97.75 372	98.78 124	96.89 98	98.46 124	99.22 92	93.90 110	99.68 152	94.81 271	99.52 115	99.67 81

test_vis1_n_1920		96.71 196	96.84 170	96.31 347	99.11 126	89.74 437	99.05 78	98.58 179	98.08 25	99.87 5	99.37 58	78.48 434	99.93 35	99.29 28	99.69 74	99.27 177

Anonymous20231211		94.10 367	93.26 377	96.61 313	99.11 126	94.28 303	99.01 91	98.88 79	86.43 474	92.81 398	97.57 328	81.66 403	98.68 346	94.83 269	89.02 425	96.88 364

fmvsm_s_conf0.5_n_a		98.38 64	98.42 43	98.27 141	99.09 128	95.41 235	98.86 145	99.37 9	97.69 42	99.78 18	99.61 6	92.38 131	99.91 59	99.58 24	99.43 129	99.49 114

CS-MVS		98.44 58	98.49 38	98.31 139	99.08 129	96.73 141	99.67 3	98.47 209	97.17 82	98.94 81	99.10 129	95.73 54	99.13 272	98.71 47	99.49 120	99.09 219

fmvsm_s_conf0.5_n_5		98.53 47	98.35 50	99.08 65	99.07 130	97.46 97	98.68 205	99.20 33	97.50 54	99.87 5	99.50 32	91.96 153	99.96 5	99.76 12	99.65 83	99.82 24

CNLPA		97.45 139	97.03 157	98.73 92	99.05 131	97.44 98	98.07 330	98.53 191	95.32 203	96.80 248	98.53 229	93.32 116	99.72 140	94.31 297	99.31 144	99.02 232

DPM-MVS		97.55 123	96.99 160	99.23 50	99.04 132	98.55 36	97.17 426	98.35 259	94.85 240	97.93 172	98.58 224	95.07 84	99.71 145	92.60 358	99.34 140	99.43 132

h-mvs33		96.17 224	95.62 239	97.81 208	99.03 133	94.45 293	98.64 215	98.75 130	97.48 56	98.67 109	98.72 209	89.76 234	99.86 86	97.95 99	81.59 477	99.11 213

test2506		94.44 342	93.91 341	96.04 357	99.02 134	88.99 455	99.06 76	79.47 531	96.96 95	98.36 135	99.26 82	77.21 449	99.52 189	96.78 199	99.04 155	99.59 96

ECVR-MVS		95.95 232	95.71 233	96.65 305	99.02 134	90.86 411	99.03 85	91.80 514	96.96 95	98.10 147	99.26 82	81.31 405	99.51 190	96.90 185	99.04 155	99.59 96

SymmetryMVS		97.84 96	97.58 99	98.62 101	99.01 136	96.60 147	98.94 110	98.44 219	97.86 34	98.71 106	99.08 140	91.22 184	99.80 112	97.40 161	97.53 265	99.47 118

Anonymous20240529		95.10 289	94.22 315	97.75 215	99.01 136	94.26 305	98.87 137	98.83 100	85.79 480	96.64 255	98.97 158	78.73 431	99.85 87	96.27 214	94.89 328	99.12 210

Anonymous202405211		95.28 278	94.49 296	97.67 225	99.00 138	93.75 324	98.70 199	97.04 433	90.66 423	96.49 266	98.80 190	78.13 438	99.83 93	96.21 218	95.36 327	99.44 128

DELS-MVS		98.40 63	98.20 73	98.99 72	99.00 138	97.66 84	97.75 372	98.89 76	97.71 40	98.33 139	98.97 158	94.97 87	99.88 80	98.42 72	99.76 50	99.42 135
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
DeepPCF-MVS	96.37 2	97.93 91	98.48 40	96.30 348	99.00 138	89.54 444	97.43 397	98.87 86	98.16 23	99.26 60	99.38 57	96.12 41	99.64 160	98.30 78	99.77 44	99.72 60

test1111		95.94 235	95.78 227	96.41 339	98.99 141	90.12 430	99.04 82	92.45 513	96.99 94	98.03 157	99.27 81	81.40 404	99.48 199	96.87 191	99.04 155	99.63 90

thres100view900		95.38 269	94.70 285	97.41 245	98.98 142	94.92 271	98.87 137	96.90 445	95.38 197	96.61 258	96.88 396	84.29 372	99.56 177	88.11 444	96.29 305	97.76 323

thres600view7		95.49 259	94.77 280	97.67 225	98.98 142	95.02 262	98.85 150	96.90 445	95.38 197	96.63 256	96.90 395	84.29 372	99.59 170	88.65 440	96.33 301	98.40 299

MVSMamba_PlusPlus		98.31 74	98.19 75	98.67 97	98.96 144	97.36 100	99.24 37	98.57 181	94.81 241	98.99 79	98.90 175	95.22 78	99.59 170	99.15 30	99.84 12	99.07 227

test_cas_vis1_n_1920		97.38 146	97.36 122	97.45 241	98.95 145	93.25 354	99.00 93	98.53 191	97.70 41	99.77 19	99.35 64	84.71 365	99.85 87	98.57 55	99.66 80	99.26 184

tfpn200view9		95.32 276	94.62 289	97.43 243	98.94 146	94.98 267	98.68 205	96.93 443	95.33 201	96.55 262	96.53 415	84.23 376	99.56 177	88.11 444	96.29 305	97.76 323

thres400		95.38 269	94.62 289	97.65 229	98.94 146	94.98 267	98.68 205	96.93 443	95.33 201	96.55 262	96.53 415	84.23 376	99.56 177	88.11 444	96.29 305	98.40 299

MSDG		95.93 236	95.30 256	97.83 205	98.90 148	95.36 242	96.83 456	98.37 254	91.32 409	94.43 325	98.73 206	90.27 223	99.60 169	90.05 416	98.82 173	98.52 293

RPSCF		94.87 310	95.40 244	93.26 453	98.89 149	82.06 500	98.33 279	98.06 336	90.30 432	96.56 260	99.26 82	87.09 315	99.49 194	93.82 315	96.32 302	98.24 306

testing915		97.30 158	96.90 166	98.48 122	98.88 150	96.42 161	99.23 39	97.92 346	95.80 162	98.11 145	98.30 257	88.59 275	99.33 218	97.52 145	97.75 251	99.71 64

fmvsm_s_conf0.1_n_2		98.14 82	98.02 83	98.53 114	98.88 150	97.07 126	98.69 202	98.82 104	98.78 10	99.77 19	99.61 6	88.83 271	99.91 59	99.71 16	99.07 153	98.61 284

test_fmvsmconf_n		98.92 14	98.87 9	99.04 69	98.88 150	97.25 115	98.82 158	99.34 11	98.75 12	99.80 15	99.61 6	95.16 80	99.95 10	99.70 18	99.80 27	99.93 2

VNet		97.79 99	97.40 118	98.96 77	98.88 150	97.55 89	98.63 218	98.93 66	96.74 108	99.02 74	98.84 183	90.33 221	99.83 93	98.53 58	96.66 289	99.50 109

LFMVS		95.86 240	94.98 272	98.47 124	98.87 154	96.32 167	98.84 154	96.02 471	93.40 330	98.62 116	99.20 97	74.99 469	99.63 163	97.72 119	97.20 270	99.46 123

fmvsm_s_conf0.5_n_7		98.23 77	98.35 50	97.89 200	98.86 155	94.99 266	98.58 228	99.00 54	98.29 21	99.73 24	99.60 11	91.70 159	99.92 45	99.63 22	99.73 64	98.76 265

UA-Net		97.96 88	97.62 97	98.98 74	98.86 155	97.47 95	98.89 127	99.08 46	96.67 114	98.72 104	99.54 21	93.15 119	99.81 105	94.87 267	98.83 172	99.65 85

WTY-MVS		97.37 148	96.92 165	98.72 93	98.86 155	96.89 135	98.31 284	98.71 140	95.26 206	97.67 198	98.56 228	92.21 142	99.78 127	95.89 227	96.85 282	99.48 116

IS-MVSNet		97.22 164	96.88 167	98.25 145	98.85 158	96.36 165	99.19 52	97.97 341	95.39 196	97.23 223	98.99 157	91.11 192	98.93 316	94.60 285	98.59 184	99.47 118

VDD-MVS		95.82 243	95.23 258	97.61 233	98.84 159	93.98 315	98.68 205	97.40 400	95.02 227	97.95 168	99.34 70	74.37 475	99.78 127	98.64 51	96.80 283	99.08 223

test_fmvs1		96.42 211	96.67 185	95.66 384	98.82 160	88.53 464	98.80 167	98.20 299	96.39 129	99.64 32	99.20 97	80.35 419	99.67 153	99.04 33	99.57 101	98.78 261

CHOSEN 280x420		97.18 169	97.18 141	97.20 255	98.81 161	93.27 351	95.78 478	99.15 41	95.25 207	96.79 249	98.11 274	92.29 136	99.07 286	98.56 57	99.85 7	99.25 186

thres200		95.25 279	94.57 292	97.28 251	98.81 161	94.92 271	98.20 302	97.11 426	95.24 209	96.54 264	96.22 430	84.58 369	99.53 186	87.93 450	96.50 296	97.39 337

XVG-OURS-SEG-HR		96.51 208	96.34 202	97.02 272	98.77 163	93.76 322	97.79 369	98.50 202	95.45 191	96.94 237	99.09 137	87.87 300	99.55 184	96.76 200	95.83 322	97.74 325

XVG-OURS		96.55 207	96.41 198	96.99 273	98.75 164	93.76 322	97.50 391	98.52 194	95.67 171	96.83 244	99.30 76	88.95 268	99.53 186	95.88 228	96.26 310	97.69 328

test_yl		97.22 164	96.78 177	98.54 111	98.73 165	96.60 147	98.45 260	98.31 274	94.70 247	98.02 159	98.42 240	90.80 202	99.70 146	96.81 195	96.79 284	99.34 152

DCV-MVSNet		97.22 164	96.78 177	98.54 111	98.73 165	96.60 147	98.45 260	98.31 274	94.70 247	98.02 159	98.42 240	90.80 202	99.70 146	96.81 195	96.79 284	99.34 152

CANet		98.05 86	97.76 92	98.90 83	98.73 165	97.27 109	98.35 276	98.78 124	97.37 66	97.72 193	98.96 163	91.53 170	99.92 45	98.79 44	99.65 83	99.51 106

Vis-MVSNet (Re-imp)		96.87 187	96.55 191	97.83 205	98.73 165	95.46 232	99.20 50	98.30 281	94.96 232	96.60 259	98.87 179	90.05 227	98.59 355	93.67 320	98.60 183	99.46 123

PAPR		96.84 189	96.24 207	98.65 99	98.72 169	96.92 132	97.36 404	98.57 181	93.33 332	96.67 254	97.57 328	94.30 101	99.56 177	91.05 402	98.59 184	99.47 118

sasdasda		97.67 107	97.23 136	98.98 74	98.70 170	98.38 44	99.34 17	98.39 245	96.76 106	97.67 198	97.40 342	92.26 137	99.49 194	98.28 82	96.28 308	99.08 223

canonicalmvs		97.67 107	97.23 136	98.98 74	98.70 170	98.38 44	99.34 17	98.39 245	96.76 106	97.67 198	97.40 342	92.26 137	99.49 194	98.28 82	96.28 308	99.08 223

API-MVS		97.41 143	97.25 131	97.91 197	98.70 170	96.80 137	98.82 158	98.69 145	94.53 258	98.11 145	98.28 258	94.50 97	99.57 174	94.12 305	99.49 120	97.37 339

testing3-2		95.45 263	95.34 250	95.77 380	98.69 173	88.75 459	98.87 137	97.21 419	96.13 141	97.22 224	97.68 317	77.95 442	99.65 157	97.58 136	96.77 286	98.91 245

MAR-MVS		96.91 185	96.40 199	98.45 126	98.69 173	96.90 133	98.66 212	98.68 148	92.40 374	97.07 232	97.96 287	91.54 169	99.75 135	93.68 318	98.92 163	98.69 274
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
PS-MVSNAJ		97.73 102	97.77 91	97.62 232	98.68 175	95.58 223	97.34 406	98.51 197	97.29 69	98.66 113	97.88 296	94.51 94	99.90 67	97.87 109	99.17 151	97.39 337

test_fmvs1_n		95.90 238	95.99 220	95.63 385	98.67 176	88.32 468	99.26 34	98.22 296	96.40 128	99.67 29	99.26 82	73.91 477	99.70 146	99.02 35	99.50 118	98.87 248

MGCFI-Net		97.62 113	97.19 140	98.92 80	98.66 177	98.20 62	99.32 22	98.38 252	96.69 112	97.58 212	97.42 341	92.10 146	99.50 193	98.28 82	96.25 311	99.08 223

alignmvs		97.56 122	97.07 153	99.01 71	98.66 177	98.37 51	98.83 156	98.06 336	96.74 108	98.00 163	97.65 319	90.80 202	99.48 199	98.37 74	96.56 293	99.19 197

Vis-MVSNet		97.42 142	97.11 150	98.34 137	98.66 177	96.23 171	99.22 44	99.00 54	96.63 116	98.04 156	99.21 95	88.05 295	99.35 215	96.01 225	99.21 148	99.45 125
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
BridgeMVS		98.45 57	98.35 50	98.74 91	98.65 180	97.55 89	99.19 52	98.60 167	96.72 111	99.35 50	98.77 199	95.06 85	99.55 184	98.95 36	99.87 1	99.12 210

EPP-MVSNet		97.46 136	97.28 129	97.99 188	98.64 181	95.38 241	99.33 21	98.31 274	93.61 320	97.19 225	99.07 144	94.05 106	99.23 249	96.89 186	98.43 204	99.37 145

ab-mvs		96.42 211	95.71 233	98.55 109	98.63 182	96.75 140	97.88 357	98.74 132	93.84 296	96.54 264	98.18 269	85.34 351	99.75 135	95.93 226	96.35 300	99.15 204

PCF-MVS	93.45 11	94.68 319	93.43 372	98.42 132	98.62 183	96.77 139	95.48 485	98.20 299	84.63 487	93.34 382	98.32 254	88.55 280	99.81 105	84.80 475	98.96 162	98.68 276
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
xiu_mvs_v2_base		97.66 109	97.70 94	97.56 236	98.61 184	95.46 232	97.44 394	98.46 210	97.15 84	98.65 114	98.15 271	94.33 100	99.80 112	97.84 112	98.66 181	97.41 335

sss		97.39 145	96.98 162	98.61 103	98.60 185	96.61 146	98.22 297	98.93 66	93.97 288	98.01 162	98.48 235	91.98 150	99.85 87	96.45 209	98.15 233	99.39 140

Test_1112_low_res		96.34 216	95.66 238	98.36 136	98.56 186	95.94 192	97.71 375	98.07 331	92.10 385	94.79 311	97.29 351	91.75 158	99.56 177	94.17 303	96.50 296	99.58 100

1112_ss		96.63 201	96.00 219	98.50 119	98.56 186	96.37 164	98.18 311	98.10 324	92.92 352	94.84 307	98.43 238	92.14 144	99.58 173	94.35 294	96.51 295	99.56 102

BH-untuned		95.95 232	95.72 230	96.65 305	98.55 188	92.26 380	98.23 296	97.79 360	93.73 304	94.62 315	98.01 282	88.97 266	99.00 304	93.04 339	98.51 193	98.68 276

fmvsm_s_conf0.1_n		98.18 81	98.21 71	98.11 171	98.54 189	95.24 250	98.87 137	99.24 20	97.50 54	99.70 28	99.67 2	91.33 177	99.89 71	99.47 26	99.54 112	99.21 192

LS3D		97.16 171	96.66 186	98.68 96	98.53 190	97.19 119	98.93 117	98.90 74	92.83 357	95.99 285	99.37 58	92.12 145	99.87 82	93.67 320	99.57 101	98.97 237

guyue		97.57 120	97.37 121	98.20 151	98.50 191	95.86 205	98.89 127	97.03 434	97.29 69	98.73 102	98.90 175	89.41 248	99.32 220	98.68 48	98.86 169	99.42 135

fmvsm_s_conf0.5_n_6		98.65 27	98.55 31	98.95 79	98.50 191	97.30 105	98.79 175	99.16 39	98.14 24	99.86 9	99.41 50	93.71 112	99.91 59	99.71 16	99.64 88	99.65 85

hse-mvs2		95.71 248	95.30 256	96.93 281	98.50 191	93.53 334	98.36 275	98.10 324	97.48 56	98.67 109	97.99 284	89.76 234	99.02 301	97.95 99	80.91 483	98.22 308

AUN-MVS		94.53 333	93.73 357	96.92 284	98.50 191	93.52 335	98.34 278	98.10 324	93.83 298	95.94 289	97.98 286	85.59 346	99.03 296	94.35 294	80.94 482	98.22 308

baseline1		95.84 241	95.12 264	98.01 186	98.49 195	95.98 184	98.73 190	97.03 434	95.37 199	96.22 276	98.19 268	89.96 230	99.16 263	94.60 285	87.48 440	98.90 246

Casviewmamba		97.62 113	97.43 116	98.19 155	98.48 196	95.83 208	99.07 74	98.42 234	96.27 135	98.09 148	99.26 82	91.00 197	99.30 225	97.81 114	98.48 197	99.44 128

E3new		97.55 123	97.35 124	98.16 157	98.48 196	95.85 206	98.55 241	98.41 236	95.42 194	98.06 152	99.12 124	92.23 140	99.24 245	97.43 157	98.45 200	99.39 140

SSM_0404		97.26 161	97.00 158	98.03 182	98.46 198	95.99 183	98.62 221	98.44 219	94.77 244	97.24 222	98.93 168	91.22 184	99.28 230	96.54 204	98.74 176	98.84 252

HY-MVS	93.96 8	96.82 190	96.23 208	98.57 106	98.46 198	97.00 128	98.14 318	98.21 297	93.95 289	96.72 253	97.99 284	91.58 164	99.76 133	94.51 289	96.54 294	98.95 241

viewcassd2359sk11		97.53 129	97.32 126	98.16 157	98.45 200	95.83 208	98.57 237	98.42 234	95.52 187	98.07 150	99.12 124	91.81 157	99.25 237	97.46 155	98.48 197	99.41 138

hybridcas		97.52 130	97.29 128	98.20 151	98.44 201	96.00 182	99.02 88	98.39 245	96.12 144	97.69 196	99.23 89	90.77 207	99.17 261	97.55 141	98.42 210	99.44 128

viewdifsd2359ckpt09		97.13 173	96.79 175	98.14 161	98.43 202	95.90 198	98.52 244	98.37 254	94.32 271	97.33 217	98.86 181	90.23 225	99.16 263	96.81 195	98.25 227	99.36 149

viewdifsd2359ckpt13		97.24 163	96.97 163	98.06 178	98.43 202	95.77 215	98.59 224	98.34 263	94.81 241	97.60 210	98.94 166	90.78 206	99.09 282	96.93 181	98.33 220	99.32 160

ETV-MVS		97.96 88	97.81 90	98.40 134	98.42 204	97.27 109	98.73 190	98.55 187	96.84 101	98.38 133	97.44 338	95.39 64	99.35 215	97.62 129	98.89 165	98.58 290

casdiffmvs_mvg		97.72 103	97.48 110	98.44 128	98.42 204	96.59 151	98.92 120	98.44 219	96.20 138	97.76 187	99.20 97	91.66 162	99.23 249	98.27 85	98.41 212	99.49 114
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmanbaseed2359cas		97.47 135	97.25 131	98.14 161	98.41 206	95.84 207	98.57 237	98.43 230	95.55 183	97.97 166	99.12 124	91.26 181	99.15 267	97.42 159	98.53 191	99.43 132

tttt0517		96.07 227	95.51 242	97.78 210	98.41 206	94.84 274	99.28 31	94.33 497	94.26 274	97.64 205	98.64 217	84.05 380	99.47 203	95.34 251	97.60 257	99.03 231

E2		97.48 132	97.25 131	98.16 157	98.40 208	95.79 213	98.58 228	98.44 219	95.58 176	98.00 163	99.14 117	91.21 188	99.24 245	97.50 150	98.43 204	99.45 125

viewdifsd2359ckpt07		97.20 167	97.05 155	97.65 229	98.40 208	94.33 302	98.39 274	98.43 230	95.67 171	97.66 202	99.08 140	90.04 228	99.32 220	97.47 154	98.29 224	99.31 161

reproduce_monomvs		94.77 315	94.67 287	95.08 405	98.40 208	89.48 445	98.80 167	98.64 161	97.57 50	93.21 386	97.65 319	80.57 417	98.83 332	97.72 119	89.47 417	96.93 354

E3		97.48 132	97.25 131	98.16 157	98.38 211	95.79 213	98.58 228	98.44 219	95.58 176	98.00 163	99.14 117	91.25 182	99.24 245	97.50 150	98.44 201	99.45 125

EIA-MVS		97.75 101	97.58 99	98.27 141	98.38 211	96.44 158	99.01 91	98.60 167	95.88 157	97.26 221	97.53 332	94.97 87	99.33 218	97.38 164	99.20 149	99.05 228

thisisatest0530		96.01 229	95.36 249	97.97 194	98.38 211	95.52 229	98.88 134	94.19 501	94.04 280	97.64 205	98.31 255	83.82 387	99.46 204	95.29 256	97.70 254	98.93 243

KinetiMVS		97.48 132	97.05 155	98.78 88	98.37 214	97.30 105	98.99 96	98.70 143	97.18 81	99.02 74	99.01 154	87.50 309	99.67 153	95.33 252	99.33 142	99.37 145

FE-MVS		95.62 254	94.90 276	97.78 210	98.37 214	94.92 271	97.17 426	97.38 402	90.95 420	97.73 192	97.70 312	85.32 353	99.63 163	91.18 394	98.33 220	98.79 257

GeoE		96.58 205	96.07 213	98.10 172	98.35 216	95.89 203	99.34 17	98.12 318	93.12 344	96.09 281	98.87 179	89.71 237	98.97 306	92.95 342	98.08 236	99.43 132

xiu_mvs_v1_base_debu		97.60 115	97.56 102	97.72 217	98.35 216	95.98 184	97.86 360	98.51 197	97.13 86	99.01 76	98.40 242	91.56 166	99.80 112	98.53 58	98.68 177	97.37 339

xiu_mvs_v1_base		97.60 115	97.56 102	97.72 217	98.35 216	95.98 184	97.86 360	98.51 197	97.13 86	99.01 76	98.40 242	91.56 166	99.80 112	98.53 58	98.68 177	97.37 339

xiu_mvs_v1_base_debi		97.60 115	97.56 102	97.72 217	98.35 216	95.98 184	97.86 360	98.51 197	97.13 86	99.01 76	98.40 242	91.56 166	99.80 112	98.53 58	98.68 177	97.37 339

baseline		97.64 110	97.44 114	98.25 145	98.35 216	96.20 172	99.00 93	98.32 269	96.33 134	98.03 157	99.17 109	91.35 176	99.16 263	98.10 90	98.29 224	99.39 140

balanced_ft_v1		97.54 127	97.38 120	98.02 184	98.34 221	95.58 223	99.32 22	98.40 239	95.88 157	98.43 132	98.65 216	88.95 268	99.59 170	98.94 37	99.48 123	98.90 246

mvsmamba		97.25 162	96.99 160	98.02 184	98.34 221	95.54 228	99.18 56	97.47 391	95.04 223	98.15 142	98.57 227	89.46 245	99.31 224	97.68 126	99.01 158	99.22 190

BH-w/o		95.38 269	95.08 267	96.26 350	98.34 221	91.79 392	97.70 376	97.43 398	92.87 355	94.24 338	97.22 357	88.66 274	98.84 329	91.55 390	97.70 254	98.16 312

EC-MVSNet		98.21 80	98.11 78	98.49 121	98.34 221	97.26 114	99.61 5	98.43 230	96.78 104	98.87 89	98.84 183	93.72 111	99.01 303	98.91 39	99.50 118	99.19 197

test_fmvsmvis_n_1920		98.44 58	98.51 34	98.23 148	98.33 225	96.15 175	98.97 100	99.15 41	98.55 17	98.45 127	99.55 19	94.26 103	99.97 1	99.65 19	99.66 80	98.57 291

MVS_Test		97.28 159	97.00 158	98.13 166	98.33 225	95.97 189	98.74 184	98.07 331	94.27 273	98.44 130	98.07 276	92.48 128	99.26 233	96.43 210	98.19 232	99.16 203

casdiffmvs		97.63 112	97.41 117	98.28 140	98.33 225	96.14 176	98.82 158	98.32 269	96.38 130	97.95 168	99.21 95	91.23 183	99.23 249	98.12 89	98.37 215	99.48 116
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
diffmvs		97.58 119	97.40 118	98.13 166	98.32 228	95.81 212	98.06 331	98.37 254	96.20 138	98.74 100	98.89 177	91.31 179	99.25 237	98.16 88	98.52 192	99.34 152
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
BH-RMVSNet		95.92 237	95.32 254	97.69 221	98.32 228	94.64 283	98.19 305	97.45 396	94.56 256	96.03 283	98.61 218	85.02 356	99.12 275	90.68 407	99.06 154	99.30 166

E5new		97.37 148	97.16 143	97.98 190	98.30 230	95.41 235	98.87 137	98.45 215	95.56 178	97.84 179	99.19 104	90.39 217	99.25 237	97.61 132	98.22 228	99.29 169

E5		97.37 148	97.16 143	97.98 190	98.30 230	95.41 235	98.87 137	98.45 215	95.56 178	97.84 179	99.19 104	90.39 217	99.25 237	97.61 132	98.22 228	99.29 169

viewmacassd2359aftdt		97.32 156	97.07 153	98.08 174	98.30 230	95.69 219	98.62 221	98.44 219	95.56 178	97.86 178	99.22 92	89.91 231	99.14 270	97.29 167	98.43 204	99.42 135

GDP-MVS		97.64 110	97.28 129	98.71 94	98.30 230	97.33 101	99.05 78	98.52 194	96.34 132	98.80 95	99.05 147	89.74 236	99.51 190	96.86 194	98.86 169	99.28 176

VortexMVS		95.95 232	95.79 226	96.42 338	98.29 234	93.96 316	98.68 205	98.31 274	96.02 148	94.29 334	97.57 328	89.47 243	98.37 385	97.51 149	91.93 379	96.94 353

Fast-Effi-MVS+		96.28 221	95.70 235	98.03 182	98.29 234	95.97 189	98.58 228	98.25 293	91.74 393	95.29 300	97.23 356	91.03 195	99.15 267	92.90 344	97.96 241	98.97 237

E6new		97.37 148	97.16 143	97.98 190	98.28 236	95.40 238	98.87 137	98.45 215	95.55 183	97.84 179	99.20 97	90.44 215	99.25 237	97.61 132	98.22 228	99.29 169

E6		97.37 148	97.16 143	97.98 190	98.28 236	95.40 238	98.87 137	98.45 215	95.55 183	97.84 179	99.20 97	90.44 215	99.25 237	97.61 132	98.22 228	99.29 169

E4		97.37 148	97.13 148	98.12 169	98.27 238	95.70 218	98.59 224	98.44 219	95.56 178	97.80 184	99.18 107	90.57 211	99.26 233	97.45 156	98.28 226	99.40 139

casdiffseed414692147		96.97 182	96.55 191	98.25 145	98.26 239	96.28 170	98.93 117	98.33 265	94.99 228	96.87 243	99.09 137	88.97 266	99.07 286	95.70 240	97.77 249	99.39 140

diffmvs_AUTHOR		97.59 118	97.44 114	98.01 186	98.26 239	95.47 231	98.12 321	98.36 258	96.38 130	98.84 91	99.10 129	91.13 189	99.26 233	98.24 86	98.56 188	99.30 166

onestephybrid01		97.54 127	97.36 122	98.06 178	98.25 241	95.63 221	98.26 293	98.33 265	96.13 141	98.65 114	99.13 120	91.02 196	99.25 237	98.07 92	98.42 210	99.31 161

hybrid		97.34 154	97.16 143	97.88 201	98.25 241	95.18 253	98.18 311	98.33 265	95.36 200	98.35 137	99.06 145	90.61 209	99.18 258	97.88 108	98.40 213	99.27 177

BP-MVS1		97.82 97	97.51 107	98.76 90	98.25 241	97.39 99	99.15 59	97.68 364	96.69 112	98.47 123	99.10 129	90.29 222	99.51 190	98.60 53	99.35 139	99.37 145

hybridnocas07		97.41 143	97.21 139	97.99 188	98.24 244	95.42 234	98.21 298	98.32 269	95.97 152	98.38 133	98.93 168	90.48 213	99.21 254	97.92 103	98.46 199	99.34 152

mvsany_test1		97.69 106	97.70 94	97.66 228	98.24 244	94.18 310	97.53 388	97.53 385	95.52 187	99.66 30	99.51 29	94.30 101	99.56 177	98.38 73	98.62 182	99.23 188

UGNet		96.78 192	96.30 204	98.19 155	98.24 244	95.89 203	98.88 134	98.93 66	97.39 63	96.81 247	97.84 300	82.60 394	99.90 67	96.53 206	99.49 120	98.79 257
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
MVSTER		96.06 228	95.72 230	97.08 268	98.23 247	95.93 195	98.73 190	98.27 284	94.86 238	95.07 302	98.09 275	88.21 288	98.54 358	96.59 202	93.46 354	96.79 374

viewmamba		97.55 123	97.45 113	97.87 202	98.22 248	95.13 257	98.35 276	98.35 259	96.57 119	98.45 127	99.15 116	91.60 163	99.18 258	97.99 97	98.36 217	99.29 169

ET-MVSNet_ETH3D		94.13 363	92.98 382	97.58 234	98.22 248	96.20 172	97.31 410	95.37 482	94.53 258	79.56 505	97.63 324	86.51 324	97.53 460	96.91 182	90.74 396	99.02 232

FA-MVS(test-final)		96.41 214	95.94 221	97.82 207	98.21 250	95.20 252	97.80 367	97.58 375	93.21 338	97.36 216	97.70 312	89.47 243	99.56 177	94.12 305	97.99 239	98.71 272

GBi-Net		94.49 337	93.80 350	96.56 320	98.21 250	95.00 263	98.82 158	98.18 305	92.46 368	94.09 345	97.07 370	81.16 407	97.95 433	92.08 372	92.14 376	96.72 382

test1		94.49 337	93.80 350	96.56 320	98.21 250	95.00 263	98.82 158	98.18 305	92.46 368	94.09 345	97.07 370	81.16 407	97.95 433	92.08 372	92.14 376	96.72 382

FMVSNet2		94.47 340	93.61 363	97.04 271	98.21 250	96.43 159	98.79 175	98.27 284	92.46 368	93.50 375	97.09 367	81.16 407	98.00 430	91.09 397	91.93 379	96.70 386

mamba_0408		96.81 191	96.38 200	98.09 173	98.19 254	95.90 198	95.69 479	98.32 269	94.51 261	96.75 250	98.73 206	90.99 198	99.27 232	95.83 230	98.43 204	99.10 215

SSM_04072		96.71 196	96.38 200	97.68 223	98.19 254	95.90 198	95.69 479	98.32 269	94.51 261	96.75 250	98.73 206	90.99 198	98.02 427	95.83 230	98.43 204	99.10 215

SSM_0407		97.17 170	96.87 168	98.08 174	98.19 254	95.90 198	98.52 244	98.44 219	94.77 244	96.75 250	98.93 168	91.22 184	99.22 253	96.54 204	98.43 204	99.10 215

viewmambaseed2359dif		97.01 179	96.84 170	97.51 238	98.19 254	94.21 308	98.16 314	98.23 295	93.61 320	97.78 185	99.13 120	90.79 205	99.18 258	97.24 168	98.40 213	99.15 204

Effi-MVS+		97.12 174	96.69 183	98.39 135	98.19 254	96.72 142	97.37 402	98.43 230	93.71 307	97.65 204	98.02 280	92.20 143	99.25 237	96.87 191	97.79 247	99.19 197

mvs_anonymous		96.70 198	96.53 194	97.18 258	98.19 254	93.78 321	98.31 284	98.19 302	94.01 285	94.47 320	98.27 261	92.08 148	98.46 366	97.39 163	97.91 242	99.31 161

dtuplus		97.00 180	96.83 172	97.51 238	98.18 260	94.21 308	98.21 298	98.20 299	94.42 269	97.66 202	99.22 92	90.18 226	99.17 261	97.01 175	98.36 217	99.13 209

ETVMVS		94.50 336	93.44 371	97.68 223	98.18 260	95.35 244	98.19 305	97.11 426	93.73 304	96.40 270	95.39 458	74.53 472	98.84 329	91.10 396	96.31 303	98.84 252

LCM-MVSNet-Re		95.22 281	95.32 254	94.91 411	98.18 260	87.85 475	98.75 180	95.66 478	95.11 218	88.96 462	96.85 399	90.26 224	97.65 453	95.65 242	98.44 201	99.22 190

FMVSNet3		94.97 301	94.26 313	97.11 266	98.18 260	96.62 144	98.56 240	98.26 292	93.67 314	94.09 345	97.10 363	84.25 374	98.01 428	92.08 372	92.14 376	96.70 386

myMVS_eth3d28		95.12 287	94.62 289	96.64 309	98.17 264	92.17 381	98.02 336	97.32 406	95.41 195	96.22 276	96.05 436	78.01 440	99.13 272	95.22 260	97.16 271	98.60 285

CANet_DTU		96.96 183	96.55 191	98.21 149	98.17 264	96.07 180	97.98 341	98.21 297	97.24 76	97.13 227	98.93 168	86.88 320	99.91 59	95.00 265	99.37 138	98.66 280

PRO-TEST		97.77 100	97.67 96	98.06 178	98.15 266	96.06 181	98.94 110	98.46 210	96.88 99	98.72 104	98.59 223	92.46 129	99.03 296	97.89 106	98.97 161	99.10 215

thisisatest0515		95.61 257	94.89 277	97.76 214	98.15 266	95.15 256	96.77 457	94.41 495	92.95 351	97.18 226	97.43 339	84.78 362	99.45 205	94.63 281	97.73 253	98.68 276

AstraMVS		97.34 154	97.24 135	97.65 229	98.13 268	94.15 311	98.94 110	96.25 470	97.47 58	98.60 118	99.28 78	89.67 238	99.41 209	98.73 46	98.07 237	99.38 144

IterMVS-LS		95.46 261	95.21 259	96.22 351	98.12 269	93.72 328	98.32 283	98.13 317	93.71 307	94.26 336	97.31 350	92.24 139	98.10 412	94.63 281	90.12 405	96.84 370
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cl22		94.68 319	94.19 317	96.13 354	98.11 270	93.60 330	96.94 440	98.31 274	92.43 372	93.32 383	96.87 398	86.51 324	98.28 398	94.10 307	91.16 391	96.51 423

viewdifsd2359ckpt11		96.30 217	96.13 210	96.81 291	98.10 271	92.10 385	98.49 255	98.40 239	96.02 148	97.61 207	99.31 73	86.37 330	99.29 228	97.52 145	93.36 360	99.04 229

viewmsd2359difaftdt		96.30 217	96.13 210	96.81 291	98.10 271	92.10 385	98.49 255	98.40 239	96.02 148	97.61 207	99.31 73	86.37 330	99.30 225	97.52 145	93.37 359	99.04 229

VDDNet		95.36 272	94.53 294	97.86 203	98.10 271	95.13 257	98.85 150	97.75 362	90.46 427	98.36 135	99.39 52	73.27 479	99.64 160	97.98 98	96.58 292	98.81 255

FBQ-MVS		94.89 309	94.10 325	97.26 252	98.07 274	93.75 324	98.48 257	97.26 414	94.51 261	96.28 274	95.64 455	76.88 456	99.07 286	93.29 330	96.47 298	98.96 240

testing3		93.19 390	92.48 395	95.30 398	98.07 274	92.27 378	98.64 215	97.17 424	93.94 291	93.98 351	97.04 378	67.97 489	96.01 490	88.40 442	97.14 272	97.63 330

MVSFormer		97.57 120	97.49 108	97.84 204	98.07 274	95.76 216	99.47 7	98.40 239	94.98 230	98.79 96	98.83 187	92.34 133	98.41 378	96.91 182	99.59 97	99.34 152

lupinMVS		97.44 140	97.22 138	98.12 169	98.07 274	95.76 216	97.68 377	97.76 361	94.50 264	98.79 96	98.61 218	92.34 133	99.30 225	97.58 136	99.59 97	99.31 161

MGCNet		98.23 77	97.91 88	99.21 51	98.06 278	97.96 76	98.58 228	95.51 480	98.58 15	98.87 89	99.26 82	92.99 121	99.95 10	99.62 23	99.67 77	99.73 56

TAMVS		97.02 178	96.79 175	97.70 220	98.06 278	95.31 247	98.52 244	98.31 274	93.95 289	97.05 234	98.61 218	93.49 114	98.52 360	95.33 252	97.81 246	99.29 169

UBG		95.32 276	94.72 284	97.13 262	98.05 280	93.26 352	97.87 358	97.20 422	94.96 232	96.18 279	95.66 454	80.97 411	99.35 215	94.47 291	97.08 273	98.78 261

CDS-MVSNet		96.99 181	96.69 183	97.90 198	98.05 280	95.98 184	98.20 302	98.33 265	93.67 314	96.95 236	98.49 234	93.54 113	98.42 371	95.24 259	97.74 252	99.31 161
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Elysia		96.64 199	96.02 217	98.51 116	98.04 282	97.30 105	98.74 184	98.60 167	95.04 223	97.91 174	98.84 183	83.59 389	99.48 199	94.20 301	99.25 146	98.75 266

StellarMVS		96.64 199	96.02 217	98.51 116	98.04 282	97.30 105	98.74 184	98.60 167	95.04 223	97.91 174	98.84 183	83.59 389	99.48 199	94.20 301	99.25 146	98.75 266

WBMVS		94.56 329	94.04 328	96.10 356	98.03 284	93.08 362	97.82 366	98.18 305	94.02 282	93.77 364	96.82 401	81.28 406	98.34 387	95.47 250	91.00 394	96.88 364

SD_0403		94.28 353	94.46 299	93.73 444	98.02 285	85.32 488	98.31 284	98.40 239	94.75 246	93.59 367	98.16 270	89.01 261	96.54 481	82.32 484	97.58 259	99.34 152

testing222		94.12 365	93.03 381	97.37 250	98.02 285	94.66 281	97.94 346	96.65 461	94.63 253	95.78 290	95.76 445	71.49 482	98.92 317	91.17 395	95.88 320	98.52 293

ADS-MVSNet2		94.58 328	94.40 306	95.11 403	98.00 287	88.74 460	96.04 472	97.30 409	90.15 433	96.47 267	96.64 412	87.89 298	97.56 459	90.08 414	97.06 274	99.02 232

ADS-MVSNet		95.00 295	94.45 302	96.63 310	98.00 287	91.91 391	96.04 472	97.74 363	90.15 433	96.47 267	96.64 412	87.89 298	98.96 310	90.08 414	97.06 274	99.02 232

icg_test_0407_2		96.56 206	96.50 195	96.73 296	97.99 289	92.82 368	97.18 423	98.27 284	95.16 211	97.30 218	98.79 192	91.53 170	98.10 412	94.74 273	97.54 261	99.27 177

IMVS_0407		96.74 193	96.64 187	97.05 270	97.99 289	92.82 368	98.45 260	98.27 284	95.16 211	97.30 218	98.79 192	91.53 170	99.06 289	94.74 273	97.54 261	99.27 177

IMVS_0404		95.82 243	95.52 240	96.73 296	97.99 289	92.82 368	97.23 414	98.27 284	95.16 211	94.31 332	98.79 192	85.63 344	98.10 412	94.74 273	97.54 261	99.27 177

IMVS_0403		96.74 193	96.61 188	97.12 264	97.99 289	92.82 368	98.47 258	98.27 284	95.16 211	97.13 227	98.79 192	91.44 173	99.26 233	94.74 273	97.54 261	99.27 177

IterMVS		94.09 368	93.85 347	94.80 420	97.99 289	90.35 427	97.18 423	98.12 318	93.68 312	92.46 413	97.34 346	84.05 380	97.41 463	92.51 365	91.33 387	96.62 397
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PVSNet_0	88.72 19	91.28 415	90.03 422	95.00 408	97.99 289	87.29 478	94.84 495	98.50 202	92.06 386	89.86 453	95.19 461	79.81 422	99.39 213	92.27 369	69.79 521	98.33 304

tt0805		94.54 331	93.85 347	96.63 310	97.98 295	93.06 363	98.77 179	97.84 351	93.67 314	93.80 362	98.04 279	76.88 456	98.96 310	94.79 272	92.86 367	97.86 322

IterMVS-SCA-FT		94.11 366	93.87 345	94.85 416	97.98 295	90.56 422	97.18 423	98.11 321	93.75 301	92.58 406	97.48 334	83.97 382	97.41 463	92.48 367	91.30 388	96.58 407

testing11		95.00 295	94.28 310	97.16 260	97.96 297	93.36 345	98.09 328	97.06 432	94.94 236	95.33 299	96.15 432	76.89 455	99.40 210	95.77 236	96.30 304	98.72 269

testing91		94.98 299	94.25 314	97.20 255	97.94 298	93.41 339	98.00 339	97.58 375	94.99 228	95.45 295	96.04 438	77.20 450	99.42 208	94.97 266	96.02 318	98.78 261

testing99		94.83 311	94.08 326	97.07 269	97.94 298	93.13 358	98.10 327	97.17 424	94.86 238	95.34 296	96.00 442	76.31 459	99.40 210	95.08 263	95.90 319	98.68 276

EI-MVSNet		95.96 231	95.83 225	96.36 343	97.93 300	93.70 329	98.12 321	98.27 284	93.70 309	95.07 302	99.02 150	92.23 140	98.54 358	94.68 278	93.46 354	96.84 370

CVMVSNet		95.43 265	96.04 215	93.57 447	97.93 300	83.62 493	98.12 321	98.59 174	95.68 170	96.56 260	99.02 150	87.51 307	97.51 461	93.56 324	97.44 266	99.60 94

RRT-MVS		97.03 177	96.78 177	97.77 213	97.90 302	94.34 300	99.12 66	98.35 259	95.87 159	98.06 152	98.70 210	86.45 328	99.63 163	98.04 96	98.54 190	99.35 150

PMMVS		96.60 202	96.33 203	97.41 245	97.90 302	93.93 317	97.35 405	98.41 236	92.84 356	97.76 187	97.45 337	91.10 193	99.20 255	96.26 215	97.91 242	99.11 213

Effi-MVS+-dtu		96.29 219	96.56 190	95.51 389	97.89 304	90.22 429	98.80 167	98.10 324	96.57 119	96.45 269	96.66 409	90.81 201	98.91 319	95.72 237	97.99 239	97.40 336

QAPM		96.29 219	95.40 244	98.96 77	97.85 305	97.60 88	99.23 39	98.93 66	89.76 440	93.11 392	99.02 150	89.11 258	99.93 35	91.99 377	99.62 92	99.34 152

UWE-MVS		94.30 349	93.89 344	95.53 388	97.83 306	88.95 456	97.52 390	93.25 506	94.44 267	96.63 256	97.07 370	78.70 432	99.28 230	91.99 377	97.56 260	98.36 302

3Dnovator+	94.38 6	97.43 141	96.78 177	99.38 25	97.83 306	98.52 37	99.37 13	98.71 140	97.09 89	92.99 395	99.13 120	89.36 250	99.89 71	96.97 178	99.57 101	99.71 64

ACMH+	92.99 14	94.30 349	93.77 353	95.88 372	97.81 308	92.04 390	98.71 195	98.37 254	93.99 287	90.60 445	98.47 236	80.86 414	99.05 290	92.75 351	92.40 373	96.55 413

nomal-1		94.97 301	94.34 308	96.86 287	97.79 309	92.62 374	98.19 305	96.71 457	93.89 292	94.74 314	96.05 436	79.44 426	99.09 282	95.58 244	96.68 288	98.86 249

3Dnovator	94.51 5	97.46 136	96.93 164	99.07 66	97.78 310	97.64 85	99.35 16	99.06 48	97.02 91	93.75 365	99.16 112	89.25 253	99.92 45	97.22 170	99.75 56	99.64 88

test_vis1_n		95.47 260	95.13 262	96.49 329	97.77 311	90.41 425	99.27 33	98.11 321	96.58 117	99.66 30	99.18 107	67.00 492	99.62 167	99.21 29	99.40 134	99.44 128

miper_lstm_enhance		94.33 347	94.07 327	95.11 403	97.75 312	90.97 407	97.22 416	98.03 338	91.67 397	92.76 400	96.97 386	90.03 229	97.78 447	92.51 365	89.64 411	96.56 411

c3_l		94.79 313	94.43 304	95.89 371	97.75 312	93.12 360	97.16 428	98.03 338	92.23 380	93.46 378	97.05 377	91.39 174	98.01 428	93.58 323	89.21 421	96.53 416

TR-MVS		94.94 307	94.20 316	97.17 259	97.75 312	94.14 312	97.59 385	97.02 437	92.28 379	95.75 291	97.64 322	83.88 384	98.96 310	89.77 420	96.15 315	98.40 299

Fast-Effi-MVS+-dtu		95.87 239	95.85 224	95.91 369	97.74 315	91.74 395	98.69 202	98.15 314	95.56 178	94.92 305	97.68 317	88.98 265	98.79 337	93.19 333	97.78 248	97.20 343

test_fmvsmconf0.1_n		98.58 37	98.44 42	98.99 72	97.73 316	97.15 122	98.84 154	98.97 58	98.75 12	99.43 44	99.54 21	93.29 117	99.93 35	99.64 21	99.79 37	99.89 9

MIMVSNet		93.26 387	92.21 399	96.41 339	97.73 316	93.13 358	95.65 481	97.03 434	91.27 413	94.04 348	96.06 435	75.33 465	97.19 466	86.56 459	96.23 313	98.92 244

miper_ehance_all_eth		95.01 294	94.69 286	95.97 366	97.70 318	93.31 348	97.02 436	98.07 331	92.23 380	93.51 374	96.96 388	91.85 154	98.15 407	93.68 318	91.16 391	96.44 431

dmvs_re		94.48 339	94.18 319	95.37 395	97.68 319	90.11 431	98.54 243	97.08 428	94.56 256	94.42 326	97.24 355	84.25 374	97.76 449	91.02 403	92.83 368	98.24 306

SCA		95.46 261	95.13 262	96.46 335	97.67 320	91.29 403	97.33 407	97.60 374	94.68 250	96.92 240	97.10 363	83.97 382	98.89 323	92.59 360	98.32 223	99.20 193

ACMP	93.49 10	95.34 274	94.98 272	96.43 337	97.67 320	93.48 336	98.73 190	98.44 219	94.94 236	92.53 409	98.53 229	84.50 371	99.14 270	95.48 249	94.00 342	96.66 392
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
fmvsm_s_conf0.1_n_a		98.08 83	98.04 82	98.21 149	97.66 322	95.39 240	98.89 127	99.17 37	97.24 76	99.76 21	99.67 2	91.13 189	99.88 80	99.39 27	99.41 131	99.35 150

eth_miper_zixun_eth		94.68 319	94.41 305	95.47 391	97.64 323	91.71 396	96.73 460	98.07 331	92.71 360	93.64 366	97.21 358	90.54 212	98.17 405	93.38 326	89.76 409	96.54 414

ACMH	92.88 16	94.55 330	93.95 338	96.34 345	97.63 324	93.26 352	98.81 166	98.49 207	93.43 328	89.74 454	98.53 229	81.91 398	99.08 285	93.69 317	93.30 362	96.70 386
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMM	93.85 9	95.69 251	95.38 248	96.61 313	97.61 325	93.84 320	98.91 122	98.44 219	95.25 207	94.28 335	98.47 236	86.04 339	99.12 275	95.50 248	93.95 344	96.87 367
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mmtdpeth		93.12 393	92.61 390	94.63 426	97.60 326	89.68 441	99.21 47	97.32 406	94.02 282	97.72 193	94.42 469	77.01 454	99.44 206	99.05 32	77.18 495	94.78 477

Patchmatch-test		94.42 343	93.68 361	96.63 310	97.60 326	91.76 393	94.83 496	97.49 390	89.45 446	94.14 343	97.10 363	88.99 262	98.83 332	85.37 469	98.13 234	99.29 169

cl____		94.51 335	94.01 333	96.02 358	97.58 328	93.40 342	97.05 434	97.96 343	91.73 395	92.76 400	97.08 369	89.06 260	98.13 409	92.61 355	90.29 403	96.52 419

tpm cat1		93.36 382	92.80 385	95.07 406	97.58 328	87.97 473	96.76 458	97.86 350	82.17 494	93.53 371	96.04 438	86.13 335	99.13 272	89.24 432	95.87 321	98.10 314

MVS-HIRNet		89.46 448	88.40 446	92.64 461	97.58 328	82.15 499	94.16 508	93.05 510	75.73 512	90.90 441	82.52 523	79.42 427	98.33 389	83.53 480	98.68 177	97.43 334

PatchmatchNet		95.71 248	95.52 240	96.29 349	97.58 328	90.72 415	96.84 455	97.52 386	94.06 279	97.08 230	96.96 388	89.24 254	98.90 322	92.03 376	98.37 215	99.26 184
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DIV-MVS_self_test		94.52 334	94.03 330	95.99 362	97.57 332	93.38 343	97.05 434	97.94 344	91.74 393	92.81 398	97.10 363	89.12 257	98.07 420	92.60 358	90.30 402	96.53 416

tpmrst		95.63 253	95.69 236	95.44 393	97.54 333	88.54 463	96.97 438	97.56 378	93.50 324	97.52 214	96.93 393	89.49 241	99.16 263	95.25 258	96.42 299	98.64 282

FMVSNet1		93.19 390	92.07 400	96.56 320	97.54 333	95.00 263	98.82 158	98.18 305	90.38 430	92.27 420	97.07 370	73.68 478	97.95 433	89.36 430	91.30 388	96.72 382

miper_enhance_ethall		95.10 289	94.75 282	96.12 355	97.53 335	93.73 327	96.61 463	98.08 329	92.20 383	93.89 354	96.65 411	92.44 130	98.30 394	94.21 300	91.16 391	96.34 434

CLD-MVS		95.62 254	95.34 250	96.46 335	97.52 336	93.75 324	97.27 413	98.46 210	95.53 186	94.42 326	98.00 283	86.21 334	98.97 306	96.25 217	94.37 329	96.66 392
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
LuminaMVS		97.49 131	97.18 141	98.42 132	97.50 337	97.15 122	98.45 260	97.68 364	96.56 121	98.68 108	98.78 196	89.84 233	99.32 220	98.60 53	98.57 187	98.79 257

MDTV_nov1_ep13			95.40 244		97.48 338	88.34 467	96.85 454	97.29 410	93.74 303	97.48 215	97.26 352	89.18 255	99.05 290	91.92 380	97.43 267

IB-MVS	91.98 17	93.27 386	91.97 402	97.19 257	97.47 339	93.41 339	97.09 431	95.99 472	93.32 333	92.47 412	95.73 448	78.06 439	99.53 186	94.59 287	82.98 470	98.62 283
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
tpmvs		94.60 325	94.36 307	95.33 397	97.46 340	88.60 462	96.88 452	97.68 364	91.29 411	93.80 362	96.42 420	88.58 276	99.24 245	91.06 400	96.04 317	98.17 311

LPG-MVS_test		95.62 254	95.34 250	96.47 332	97.46 340	93.54 332	98.99 96	98.54 189	94.67 251	94.36 329	98.77 199	85.39 348	99.11 277	95.71 238	94.15 337	96.76 377

LGP-MVS_train				96.47 332	97.46 340	93.54 332		98.54 189	94.67 251	94.36 329	98.77 199	85.39 348	99.11 277	95.71 238	94.15 337	96.76 377

test_vis1_rt		91.29 413	90.65 413	93.19 455	97.45 343	86.25 484	98.57 237	90.90 519	93.30 335	86.94 478	93.59 481	62.07 502	99.11 277	97.48 153	95.58 325	94.22 484

jason		97.32 156	97.08 152	98.06 178	97.45 343	95.59 222	97.87 358	97.91 348	94.79 243	98.55 121	98.83 187	91.12 191	99.23 249	97.58 136	99.60 95	99.34 152
jason: jason.
HQP_MVS		96.14 226	95.90 223	96.85 288	97.42 345	94.60 289	98.80 167	98.56 185	97.28 71	95.34 296	98.28 258	87.09 315	99.03 296	96.07 219	94.27 331	96.92 355

plane_prior7					97.42 345	94.63 284

ITE_SJBPF				95.44 393	97.42 345	91.32 402		97.50 388	95.09 221	93.59 367	98.35 248	81.70 402	98.88 325	89.71 422	93.39 358	96.12 444

LTVRE_ROB	92.95 15	94.60 325	93.90 342	96.68 303	97.41 348	94.42 295	98.52 244	98.59 174	91.69 396	91.21 437	98.35 248	84.87 359	99.04 293	91.06 400	93.44 357	96.60 400
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
Syy-MVS		92.55 401	92.61 390	92.38 463	97.39 349	83.41 494	97.91 350	97.46 392	93.16 341	93.42 379	95.37 459	84.75 363	96.12 488	77.00 505	96.99 276	97.60 331

myMVS_eth3d		92.73 398	92.01 401	94.89 413	97.39 349	90.94 408	97.91 350	97.46 392	93.16 341	93.42 379	95.37 459	68.09 488	96.12 488	88.34 443	96.99 276	97.60 331

plane_prior1					97.37 351

plane_prior6					97.35 352	94.61 287						87.09 315

dp		94.15 362	93.90 342	94.90 412	97.31 353	86.82 481	96.97 438	97.19 423	91.22 415	96.02 284	96.61 414	85.51 347	99.02 301	90.00 418	94.30 330	98.85 250

NP-MVS					97.28 354	94.51 292					97.73 309

CostFormer		94.95 305	94.73 283	95.60 387	97.28 354	89.06 452	97.53 388	96.89 447	89.66 442	96.82 246	96.72 406	86.05 337	98.95 315	95.53 247	96.13 316	98.79 257

VPA-MVSNet		95.75 246	95.11 265	97.69 221	97.24 356	97.27 109	98.94 110	99.23 27	95.13 216	95.51 294	97.32 349	85.73 342	98.91 319	97.33 166	89.55 414	96.89 363

tpm2		94.19 358	93.76 355	95.46 392	97.23 357	89.04 453	97.31 410	96.85 451	87.08 465	96.21 278	96.79 403	83.75 388	98.74 340	92.43 368	96.23 313	98.59 288

EPMVS		94.99 297	94.48 297	96.52 326	97.22 358	91.75 394	97.23 414	91.66 515	94.11 277	97.28 220	96.81 402	85.70 343	98.84 329	93.04 339	97.28 269	98.97 237

FMVSNet5		91.81 406	90.92 411	94.49 431	97.21 359	92.09 387	98.00 339	97.55 383	89.31 449	90.86 442	95.61 456	74.48 473	95.32 496	85.57 466	89.70 410	96.07 446

HQP-NCC					97.20 360		98.05 332		96.43 124	94.45 321

ACMP_Plane					97.20 360		98.05 332		96.43 124	94.45 321

HQP-MVS		95.72 247	95.40 244	96.69 302	97.20 360	94.25 306	98.05 332	98.46 210	96.43 124	94.45 321	97.73 309	86.75 321	98.96 310	95.30 254	94.18 335	96.86 369

UniMVSNet_ETH3D		94.24 355	93.33 374	96.97 278	97.19 363	93.38 343	98.74 184	98.57 181	91.21 416	93.81 361	98.58 224	72.85 481	98.77 339	95.05 264	93.93 345	98.77 264

OpenMVS	93.04 13	95.83 242	95.00 270	98.32 138	97.18 364	97.32 102	99.21 47	98.97 58	89.96 436	91.14 438	99.05 147	86.64 323	99.92 45	93.38 326	99.47 124	97.73 326

VPNet		94.99 297	94.19 317	97.40 247	97.16 365	96.57 152	98.71 195	98.97 58	95.67 171	94.84 307	98.24 265	80.36 418	98.67 347	96.46 208	87.32 444	96.96 350

GA-MVS		94.81 312	94.03 330	97.14 261	97.15 366	93.86 319	96.76 458	97.58 375	94.00 286	94.76 313	97.04 378	80.91 412	98.48 362	91.79 383	96.25 311	99.09 219

FIs		96.51 208	96.12 212	97.67 225	97.13 367	97.54 91	99.36 14	99.22 32	95.89 156	94.03 349	98.35 248	91.98 150	98.44 369	96.40 211	92.76 369	97.01 347

1314		96.25 223	95.73 229	97.79 209	97.13 367	95.55 227	98.19 305	98.59 174	93.47 326	92.03 428	97.82 304	91.33 177	99.49 194	94.62 283	98.44 201	98.32 305

D2MVS		95.18 284	95.08 267	95.48 390	97.10 369	92.07 388	98.30 287	99.13 43	94.02 282	92.90 396	96.73 405	89.48 242	98.73 341	94.48 290	93.60 353	95.65 457

DeepMVS_CX				86.78 483	97.09 370	72.30 518		95.17 487	75.92 511	84.34 493	95.19 461	70.58 483	95.35 494	79.98 494	89.04 424	92.68 501

PAPM		94.95 305	94.00 334	97.78 210	97.04 371	95.65 220	96.03 474	98.25 293	91.23 414	94.19 341	97.80 306	91.27 180	98.86 328	82.61 483	97.61 256	98.84 252

CR-MVSNet		94.76 316	94.15 321	96.59 316	97.00 372	93.43 337	94.96 492	97.56 378	92.46 368	96.93 238	96.24 426	88.15 290	97.88 442	87.38 453	96.65 290	98.46 297

RPMNet		92.81 396	91.34 408	97.24 253	97.00 372	93.43 337	94.96 492	98.80 117	82.27 493	96.93 238	92.12 499	86.98 318	99.82 100	76.32 507	96.65 290	98.46 297

UniMVSNet (Re)		95.78 245	95.19 260	97.58 234	96.99 374	97.47 95	98.79 175	99.18 36	95.60 174	93.92 353	97.04 378	91.68 160	98.48 362	95.80 234	87.66 439	96.79 374

test_fmvs2		93.43 381	93.58 364	92.95 460	96.97 375	83.91 492	99.19 52	97.24 416	95.74 166	95.20 301	98.27 261	69.65 484	98.72 342	96.26 215	93.73 348	96.24 439

FC-MVSNet-test		96.42 211	96.05 214	97.53 237	96.95 376	97.27 109	99.36 14	99.23 27	95.83 161	93.93 352	98.37 246	92.00 149	98.32 390	96.02 224	92.72 370	97.00 348

tfpnnormal		93.66 376	92.70 388	96.55 324	96.94 377	95.94 192	98.97 100	99.19 35	91.04 418	91.38 436	97.34 346	84.94 358	98.61 351	85.45 468	89.02 425	95.11 468

TESTMET0.1,1		94.18 361	93.69 360	95.63 385	96.92 378	89.12 451	96.91 444	94.78 492	93.17 340	94.88 306	96.45 419	78.52 433	98.92 317	93.09 336	98.50 194	98.85 250

TinyColmap		92.31 404	91.53 406	94.65 425	96.92 378	89.75 436	96.92 442	96.68 458	90.45 428	89.62 456	97.85 299	76.06 462	98.81 335	86.74 457	92.51 372	95.41 460

cascas		94.63 324	93.86 346	96.93 281	96.91 380	94.27 304	96.00 475	98.51 197	85.55 483	94.54 317	96.23 428	84.20 378	98.87 326	95.80 234	96.98 279	97.66 329

nrg030		96.28 221	95.72 230	97.96 196	96.90 381	98.15 67	99.39 11	98.31 274	95.47 190	94.42 326	98.35 248	92.09 147	98.69 343	97.50 150	89.05 423	97.04 346

MVS		94.67 322	93.54 367	98.08 174	96.88 382	96.56 153	98.19 305	98.50 202	78.05 505	92.69 403	98.02 280	91.07 194	99.63 163	90.09 413	98.36 217	98.04 316

WR-MVS_H		95.05 293	94.46 299	96.81 291	96.86 383	95.82 211	99.24 37	99.24 20	93.87 295	92.53 409	96.84 400	90.37 219	98.24 400	93.24 331	87.93 435	96.38 433

UniMVSNet_NR-MVSNet		95.71 248	95.15 261	97.40 247	96.84 384	96.97 129	98.74 184	99.24 20	95.16 211	93.88 355	97.72 311	91.68 160	98.31 392	95.81 232	87.25 445	96.92 355

USDC		93.33 385	92.71 387	95.21 399	96.83 385	90.83 413	96.91 444	97.50 388	93.84 296	90.72 443	98.14 272	77.69 444	98.82 334	89.51 427	93.21 364	95.97 448

WB-MVSnew		94.19 358	94.04 328	94.66 424	96.82 386	92.14 382	97.86 360	95.96 474	93.50 324	95.64 292	96.77 404	88.06 294	97.99 431	84.87 472	96.86 280	93.85 494

SSC-MVS3.2		93.59 380	93.13 379	94.97 409	96.81 387	89.71 438	97.95 343	98.49 207	94.59 255	93.50 375	96.91 394	77.74 443	98.37 385	91.69 386	90.47 400	96.83 372

test-LLR		95.10 289	94.87 278	95.80 377	96.77 388	89.70 439	96.91 444	95.21 484	95.11 218	94.83 309	95.72 450	87.71 302	98.97 306	93.06 337	98.50 194	98.72 269

test-mter		94.08 369	93.51 368	95.80 377	96.77 388	89.70 439	96.91 444	95.21 484	92.89 354	94.83 309	95.72 450	77.69 444	98.97 306	93.06 337	98.50 194	98.72 269

Patchmtry		93.22 388	92.35 397	95.84 376	96.77 388	93.09 361	94.66 499	97.56 378	87.37 464	92.90 396	96.24 426	88.15 290	97.90 437	87.37 454	90.10 406	96.53 416

gg-mvs-nofinetune		92.21 405	90.58 415	97.13 262	96.75 391	95.09 259	95.85 476	89.40 521	85.43 484	94.50 319	81.98 525	80.80 415	98.40 384	92.16 370	98.33 220	97.88 320

XXY-MVS		95.20 283	94.45 302	97.46 240	96.75 391	96.56 153	98.86 145	98.65 160	93.30 335	93.27 384	98.27 261	84.85 360	98.87 326	94.82 270	91.26 390	96.96 350

CP-MVSNet		94.94 307	94.30 309	96.83 289	96.72 393	95.56 225	99.11 68	98.95 62	93.89 292	92.42 415	97.90 293	87.19 314	98.12 411	94.32 296	88.21 432	96.82 373

PatchT		93.06 394	91.97 402	96.35 344	96.69 394	92.67 373	94.48 503	97.08 428	86.62 472	97.08 230	92.23 498	87.94 297	97.90 437	78.89 499	96.69 287	98.49 295

PS-CasMVS		94.67 322	93.99 336	96.71 299	96.68 395	95.26 248	99.13 65	99.03 51	93.68 312	92.33 419	97.95 288	85.35 350	98.10 412	93.59 322	88.16 434	96.79 374

WR-MVS		95.15 285	94.46 299	97.22 254	96.67 396	96.45 157	98.21 298	98.81 110	94.15 276	93.16 388	97.69 314	87.51 307	98.30 394	95.29 256	88.62 429	96.90 362

baseline2		95.11 288	94.52 295	96.87 286	96.65 397	93.56 331	98.27 292	94.10 503	93.45 327	92.02 429	97.43 339	87.45 312	99.19 256	93.88 313	97.41 268	97.87 321

test_0402		91.32 412	90.27 418	94.48 432	96.60 398	91.12 405	98.50 252	97.22 417	86.10 477	88.30 471	96.98 385	77.65 446	97.99 431	78.13 501	92.94 366	94.34 480

TransMVSNet (Re)		92.67 399	91.51 407	96.15 352	96.58 399	94.65 282	98.90 123	96.73 454	90.86 421	89.46 459	97.86 297	85.62 345	98.09 416	86.45 460	81.12 480	95.71 455

XVG-ACMP-BASELINE		94.54 331	94.14 322	95.75 381	96.55 400	91.65 397	98.11 325	98.44 219	94.96 232	94.22 339	97.90 293	79.18 429	99.11 277	94.05 309	93.85 346	96.48 428

dtuonly		95.08 292	95.10 266	95.02 407	96.53 401	87.27 479	96.33 470	97.21 419	93.41 329	96.28 274	98.51 233	87.71 302	98.99 305	91.88 381	98.01 238	98.80 256

DU-MVS		95.42 266	94.76 281	97.40 247	96.53 401	96.97 129	98.66 212	98.99 57	95.43 192	93.88 355	97.69 314	88.57 277	98.31 392	95.81 232	87.25 445	96.92 355

NR-MVSNet		94.98 299	94.16 320	97.44 242	96.53 401	97.22 117	98.74 184	98.95 62	94.96 232	89.25 460	97.69 314	89.32 251	98.18 404	94.59 287	87.40 442	96.92 355

tpm		94.13 363	93.80 350	95.12 402	96.50 404	87.91 474	97.44 394	95.89 477	92.62 364	96.37 272	96.30 425	84.13 379	98.30 394	93.24 331	91.66 385	99.14 207

pm-mvs1		93.94 374	93.06 380	96.59 316	96.49 405	95.16 254	98.95 107	98.03 338	92.32 377	91.08 439	97.84 300	84.54 370	98.41 378	92.16 370	86.13 457	96.19 442

JIA-IIPM		93.35 383	92.49 394	95.92 368	96.48 406	90.65 417	95.01 490	96.96 441	85.93 478	96.08 282	87.33 518	87.70 305	98.78 338	91.35 392	95.58 325	98.34 303

UWE-MVS-28		92.79 397	92.51 393	93.62 446	96.46 407	86.28 483	97.93 347	92.71 511	94.17 275	94.78 312	97.16 360	81.05 410	96.43 484	81.45 487	96.86 280	98.14 313

TranMVSNet+NR-MVSNet		95.14 286	94.48 297	97.11 266	96.45 408	96.36 165	99.03 85	99.03 51	95.04 223	93.58 369	97.93 290	88.27 287	98.03 426	94.13 304	86.90 450	96.95 352

testgi		93.06 394	92.45 396	94.88 414	96.43 409	89.90 433	98.75 180	97.54 384	95.60 174	91.63 434	97.91 292	74.46 474	97.02 469	86.10 462	93.67 349	97.72 327

v10		94.29 351	93.55 366	96.51 327	96.39 410	94.80 278	98.99 96	98.19 302	91.35 407	93.02 394	96.99 384	88.09 292	98.41 378	90.50 409	88.41 431	96.33 436

v8		94.47 340	93.77 353	96.57 319	96.36 411	94.83 276	99.05 78	98.19 302	91.92 389	93.16 388	96.97 386	88.82 273	98.48 362	91.69 386	87.79 436	96.39 432

GG-mvs-BLEND				96.59 316	96.34 412	94.98 267	96.51 467	88.58 523		93.10 393	94.34 475	80.34 420	98.05 424	89.53 426	96.99 276	96.74 379

V42		94.78 314	94.14 322	96.70 301	96.33 413	95.22 251	98.97 100	98.09 328	92.32 377	94.31 332	97.06 374	88.39 283	98.55 357	92.90 344	88.87 427	96.34 434

PEN-MVS		94.42 343	93.73 357	96.49 329	96.28 414	94.84 274	99.17 57	99.00 54	93.51 323	92.23 421	97.83 303	86.10 336	97.90 437	92.55 363	86.92 449	96.74 379

v1144		94.59 327	93.92 339	96.60 315	96.21 415	94.78 280	98.59 224	98.14 316	91.86 392	94.21 340	97.02 381	87.97 296	98.41 378	91.72 385	89.57 412	96.61 398

Baseline_NR-MVSNet		94.35 346	93.81 349	95.96 367	96.20 416	94.05 314	98.61 223	96.67 459	91.44 403	93.85 359	97.60 325	88.57 277	98.14 408	94.39 292	86.93 448	95.68 456

tt0320-xc		89.79 442	88.11 450	94.84 418	96.19 417	90.61 420	98.16 314	97.22 417	77.35 507	88.75 468	96.70 408	65.94 496	97.63 455	89.31 431	83.39 468	96.28 438

MS-PatchMatch		93.84 375	93.63 362	94.46 434	96.18 418	89.45 446	97.76 371	98.27 284	92.23 380	92.13 426	97.49 333	79.50 425	98.69 343	89.75 421	99.38 136	95.25 464

v2v482		94.69 317	94.03 330	96.65 305	96.17 419	94.79 279	98.67 210	98.08 329	92.72 359	94.00 350	97.16 360	87.69 306	98.45 367	92.91 343	88.87 427	96.72 382

EPNet_dtu		95.21 282	94.95 274	95.99 362	96.17 419	90.45 423	98.16 314	97.27 413	96.77 105	93.14 391	98.33 253	90.34 220	98.42 371	85.57 466	98.81 174	99.09 219
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OPM-MVS		95.69 251	95.33 253	96.76 295	96.16 421	94.63 284	98.43 268	98.39 245	96.64 115	95.02 304	98.78 196	85.15 355	99.05 290	95.21 261	94.20 334	96.60 400
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tt0320		90.26 438	88.73 444	94.86 415	96.12 422	90.62 419	98.17 313	97.63 371	77.46 506	89.68 455	96.04 438	69.19 486	97.79 445	88.98 435	85.29 461	96.16 443

v1192		94.32 348	93.58 364	96.53 325	96.10 423	94.45 293	98.50 252	98.17 311	91.54 400	94.19 341	97.06 374	86.95 319	98.43 370	90.14 412	89.57 412	96.70 386

v148		94.29 351	93.76 355	95.91 369	96.10 423	92.93 366	98.58 228	97.97 341	92.59 366	93.47 377	96.95 390	88.53 281	98.32 390	92.56 362	87.06 447	96.49 426

v144192		94.39 345	93.70 359	96.48 331	96.06 425	94.35 299	98.58 228	98.16 313	91.45 402	94.33 331	97.02 381	87.50 309	98.45 367	91.08 399	89.11 422	96.63 394

DTE-MVSNet		93.98 373	93.26 377	96.14 353	96.06 425	94.39 297	99.20 50	98.86 92	93.06 346	91.78 430	97.81 305	85.87 341	97.58 458	90.53 408	86.17 454	96.46 430

v1240		94.06 371	93.29 376	96.34 345	96.03 427	93.90 318	98.44 266	98.17 311	91.18 417	94.13 344	97.01 383	86.05 337	98.42 371	89.13 434	89.50 416	96.70 386

sc_t1		91.01 423	89.39 431	95.85 375	95.99 428	90.39 426	98.43 268	97.64 370	78.79 502	92.20 423	97.94 289	66.00 495	98.60 354	91.59 389	85.94 458	98.57 291

APD_test1		88.22 453	88.01 452	88.86 479	95.98 429	74.66 517	97.21 417	96.44 466	83.96 489	86.66 481	97.90 293	60.95 503	97.84 444	82.73 481	90.23 404	94.09 487

v1921920		94.20 357	93.47 370	96.40 341	95.98 429	94.08 313	98.52 244	98.15 314	91.33 408	94.25 337	97.20 359	86.41 329	98.42 371	90.04 417	89.39 419	96.69 391

EU-MVSNet		93.66 376	94.14 322	92.25 467	95.96 431	83.38 495	98.52 244	98.12 318	94.69 249	92.61 405	98.13 273	87.36 313	96.39 486	91.82 382	90.00 407	96.98 349

usedtu_dtu_shiyan1		94.96 303	94.28 310	96.98 276	95.93 432	96.11 178	97.08 432	98.39 245	93.62 318	93.86 357	96.40 421	88.28 285	98.21 401	92.61 355	92.36 374	96.63 394

FE-MVSNET3		94.96 303	94.28 310	96.98 276	95.93 432	96.11 178	97.08 432	98.39 245	93.62 318	93.86 357	96.40 421	88.28 285	98.21 401	92.61 355	92.36 374	96.63 394

ArgMatch-SfM		90.55 432	89.69 426	93.14 456	95.91 434	86.12 485	97.20 418	96.81 453	92.91 353	91.39 435	96.95 390	65.65 497	97.72 451	88.03 447	82.36 471	95.57 458

v7n		94.19 358	93.43 372	96.47 332	95.90 435	94.38 298	99.26 34	98.34 263	91.99 387	92.76 400	97.13 362	88.31 284	98.52 360	89.48 428	87.70 437	96.52 419

gm-plane-assit					95.88 436	87.47 476			89.74 441		96.94 392		99.19 256	93.32 329

LF4IMVS		93.14 392	92.79 386	94.20 439	95.88 436	88.67 461	97.66 379	97.07 430	93.81 299	91.71 431	97.65 319	77.96 441	98.81 335	91.47 391	91.92 381	95.12 467

PS-MVSNAJss		96.43 210	96.26 206	96.92 284	95.84 438	95.08 260	99.16 58	98.50 202	95.87 159	93.84 360	98.34 252	94.51 94	98.61 351	96.88 188	93.45 356	97.06 345

ArgMatch-Sym		90.92 425	90.22 419	93.02 457	95.81 439	86.50 482	97.32 408	97.01 440	92.67 361	91.02 440	97.35 345	66.90 493	97.17 467	88.53 441	85.40 460	95.39 461

pmmvs4		94.69 317	93.99 336	96.81 291	95.74 440	95.94 192	97.40 398	97.67 367	90.42 429	93.37 381	97.59 326	89.08 259	98.20 403	92.97 341	91.67 384	96.30 437

test_djsdf		96.00 230	95.69 236	96.93 281	95.72 441	95.49 230	99.47 7	98.40 239	94.98 230	94.58 316	97.86 297	89.16 256	98.41 378	96.91 182	94.12 339	96.88 364

SixPastTwentyTwo		93.34 384	92.86 384	94.75 421	95.67 442	89.41 448	98.75 180	96.67 459	93.89 292	90.15 451	98.25 264	80.87 413	98.27 399	90.90 404	90.64 397	96.57 409

K. test v3		92.55 401	91.91 405	94.48 432	95.64 443	89.24 449	99.07 74	94.88 491	94.04 280	86.78 479	97.59 326	77.64 447	97.64 454	92.08 372	89.43 418	96.57 409

dtuonlycased		91.29 413	91.26 409	91.36 471	95.63 444	84.25 491	96.93 441	97.21 419	92.16 384	88.34 470	96.47 417	79.56 424	95.18 499	87.37 454	87.70 437	94.64 478

OurMVSNet-221017-0		94.21 356	94.00 334	94.85 416	95.60 445	89.22 450	98.89 127	97.43 398	95.29 204	92.18 424	98.52 232	82.86 392	98.59 355	93.46 325	91.76 382	96.74 379

mvs_tets		95.41 268	95.00 270	96.65 305	95.58 446	94.42 295	99.00 93	98.55 187	95.73 168	93.21 386	98.38 245	83.45 391	98.63 349	97.09 173	94.00 342	96.91 360

MonoMVSNet		95.51 258	95.45 243	95.68 382	95.54 447	90.87 410	98.92 120	97.37 403	95.79 164	95.53 293	97.38 344	89.58 240	97.68 452	96.40 211	92.59 371	98.49 295

Gipuma		78.40 479	76.75 483	83.38 495	95.54 447	80.43 502	79.42 533	97.40 400	64.67 522	73.46 512	80.82 527	45.65 513	93.14 512	66.32 521	87.43 441	76.56 530
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		94.08 369	93.51 368	95.80 377	95.53 449	92.89 367	97.38 400	95.97 473	95.11 218	92.51 411	96.66 409	87.71 302	96.94 471	87.03 456	93.67 349	97.57 333

pmmvs5		93.65 378	92.97 383	95.68 382	95.49 450	92.37 377	98.20 302	97.28 412	89.66 442	92.58 406	97.26 352	82.14 397	98.09 416	93.18 334	90.95 395	96.58 407

test_fmvsmconf0.01_n		97.86 93	97.54 105	98.83 85	95.48 451	96.83 136	98.95 107	98.60 167	98.58 15	98.93 85	99.55 19	88.57 277	99.91 59	99.54 25	99.61 93	99.77 41

N_pmnet		87.12 458	87.77 456	85.17 488	95.46 452	61.92 534	97.37 402	70.66 546	85.83 479	88.73 469	96.04 438	85.33 352	97.76 449	80.02 491	90.48 399	95.84 452

our_test_3		93.65 378	93.30 375	94.69 422	95.45 453	89.68 441	96.91 444	97.65 368	91.97 388	91.66 433	96.88 396	89.67 238	97.93 436	88.02 448	91.49 386	96.48 428

ppachtmachnet_test		93.22 388	92.63 389	94.97 409	95.45 453	90.84 412	96.88 452	97.88 349	90.60 424	92.08 427	97.26 352	88.08 293	97.86 443	85.12 471	90.33 401	96.22 440

jajsoiax		95.45 263	95.03 269	96.73 296	95.42 455	94.63 284	99.14 62	98.52 194	95.74 166	93.22 385	98.36 247	83.87 385	98.65 348	96.95 180	94.04 340	96.91 360

dmvs_testset		87.64 455	88.93 443	83.79 493	95.25 456	63.36 530	97.20 418	91.17 516	93.07 345	85.64 487	95.98 443	85.30 354	91.52 516	69.42 518	87.33 443	96.49 426

MDA-MVSNet-bldmvs		89.97 441	88.35 447	94.83 419	95.21 457	91.34 401	97.64 381	97.51 387	88.36 460	71.17 517	96.13 433	79.22 428	96.63 480	83.65 479	86.27 453	96.52 419

dongtai		82.47 468	81.88 471	84.22 492	95.19 458	76.03 508	94.59 502	74.14 536	82.63 491	87.19 477	96.09 434	64.10 499	87.85 524	58.91 526	84.11 466	88.78 517

anonymousdsp		95.42 266	94.91 275	96.94 280	95.10 459	95.90 198	99.14 62	98.41 236	93.75 301	93.16 388	97.46 335	87.50 309	98.41 378	95.63 243	94.03 341	96.50 425

EPNet		97.28 159	96.87 168	98.51 116	94.98 460	96.14 176	98.90 123	97.02 437	98.28 22	95.99 285	99.11 127	91.36 175	99.89 71	96.98 177	99.19 150	99.50 109
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVP-Stereo		94.28 353	93.92 339	95.35 396	94.95 461	92.60 375	97.97 342	97.65 368	91.61 398	90.68 444	97.09 367	86.32 333	98.42 371	89.70 423	99.34 140	95.02 472
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lessismore_v0				94.45 435	94.93 462	88.44 466		91.03 518		86.77 480	97.64 322	76.23 460	98.42 371	90.31 411	85.64 459	96.51 423

MDA-MVSNet_test_wron		90.71 430	89.38 433	94.68 423	94.83 463	90.78 414	97.19 421	97.46 392	87.60 462	72.41 515	95.72 450	86.51 324	96.71 478	85.92 464	86.80 451	96.56 411

EGC-MVSNET		75.22 483	69.54 488	92.28 465	94.81 464	89.58 443	97.64 381	96.50 464	1.82 561	5.57 563	95.74 446	68.21 487	96.26 487	73.80 513	91.71 383	90.99 508

YYNet1		90.70 431	89.39 431	94.62 427	94.79 465	90.65 417	97.20 418	97.46 392	87.54 463	72.54 514	95.74 446	86.51 324	96.66 479	86.00 463	86.76 452	96.54 414

EG-PatchMatch MVS		91.13 420	90.12 421	94.17 441	94.73 466	89.00 454	98.13 320	97.81 359	89.22 450	85.32 489	96.46 418	67.71 490	98.42 371	87.89 452	93.82 347	95.08 469

pmmvs6		91.77 407	90.63 414	95.17 401	94.69 467	91.24 404	98.67 210	97.92 346	86.14 476	89.62 456	97.56 331	75.79 463	98.34 387	90.75 406	84.56 463	95.94 449

MVStest1		89.53 447	87.99 453	94.14 442	94.39 468	90.42 424	98.25 295	96.84 452	82.81 490	81.18 500	97.33 348	77.09 453	96.94 471	85.27 470	78.79 488	95.06 470

new_pmnet		90.06 440	89.00 440	93.22 454	94.18 469	88.32 468	96.42 469	96.89 447	86.19 475	85.67 486	93.62 480	77.18 451	97.10 468	81.61 486	89.29 420	94.23 483

DenseAffine		84.37 464	82.38 468	90.31 474	94.17 470	82.89 497	94.98 491	94.23 500	82.16 495	79.68 504	94.33 476	46.28 510	94.25 505	80.01 492	75.62 502	93.78 495

0.4-1-1-0.1		90.89 426	88.97 441	96.67 304	94.15 471	92.76 372	95.28 487	95.03 489	89.11 451	90.43 447	89.57 513	75.41 464	99.04 293	94.70 277	77.06 496	98.20 310

DSMNet-mixed		92.52 403	92.58 392	92.33 464	94.15 471	82.65 498	98.30 287	94.26 499	89.08 452	92.65 404	95.73 448	85.01 357	95.76 492	86.24 461	97.76 250	98.59 288

ttmdpeth		92.61 400	91.96 404	94.55 428	94.10 473	90.60 421	98.52 244	97.29 410	92.67 361	90.18 449	97.92 291	79.75 423	97.79 445	91.09 397	86.15 456	95.26 463

UnsupCasMVSNet_eth		90.99 424	89.92 423	94.19 440	94.08 474	89.83 434	97.13 430	98.67 153	93.69 310	85.83 485	96.19 431	75.15 468	96.74 475	89.14 433	79.41 487	96.00 447

KD-MVS_2432*1600		89.61 445	87.96 454	94.54 429	94.06 475	91.59 398	95.59 482	97.63 371	89.87 438	88.95 463	94.38 472	78.28 436	96.82 473	84.83 473	68.05 522	95.21 465

miper_refine_blended		89.61 445	87.96 454	94.54 429	94.06 475	91.59 398	95.59 482	97.63 371	89.87 438	88.95 463	94.38 472	78.28 436	96.82 473	84.83 473	68.05 522	95.21 465

Anonymous20231206		91.66 408	91.10 410	93.33 451	94.02 477	87.35 477	98.58 228	97.26 414	90.48 426	90.16 450	96.31 424	83.83 386	96.53 482	79.36 496	89.90 408	96.12 444

ALIKED-MNN		65.35 497	62.68 503	73.35 510	93.70 478	61.07 535	88.63 525	70.76 545	47.76 534	57.06 536	80.59 528	34.03 534	85.39 529	32.73 544	58.87 532	73.59 533

Anonymous20240521		91.18 417	90.44 416	93.42 448	93.70 478	88.47 465	98.94 110	97.56 378	88.46 458	89.56 458	95.08 464	77.15 452	96.97 470	83.92 478	89.55 414	94.82 474

0.3-1-1-0.015		90.29 436	88.21 449	96.51 327	93.56 480	92.44 376	94.41 504	95.03 489	88.71 455	89.20 461	88.50 515	73.12 480	99.04 293	94.67 280	76.70 499	98.05 315

test20.03		90.89 426	90.38 417	92.43 462	93.48 481	88.14 471	98.33 279	97.56 378	93.40 330	87.96 472	96.71 407	80.69 416	94.13 506	79.15 497	86.17 454	95.01 473

ALIKED-NN		66.93 494	64.81 498	73.32 511	93.41 482	62.03 533	87.55 528	71.25 541	50.21 530	59.98 532	82.57 522	39.72 520	84.03 530	34.94 542	63.64 527	73.90 532

0.4-1-1-0.2		90.43 433	88.45 445	96.38 342	93.34 483	92.12 383	93.88 509	95.04 488	88.62 457	90.00 452	88.31 516	75.31 466	99.03 296	94.61 284	76.91 498	98.01 319

RoMa-SfM		83.81 466	82.08 470	89.00 478	93.33 484	79.94 504	95.51 484	92.48 512	79.75 500	79.89 503	95.69 453	46.23 511	93.20 511	78.90 498	76.93 497	93.87 493

ALIKED-LG		67.40 492	65.16 497	74.11 509	93.21 485	62.30 532	88.98 524	71.99 540	55.04 524	59.47 533	82.33 524	39.27 522	85.49 528	32.61 545	63.58 528	74.55 531

CMPMVS	66.06 21	89.70 443	89.67 428	89.78 475	93.19 486	76.56 507	97.00 437	98.35 259	80.97 497	81.57 498	97.75 308	74.75 471	98.61 351	89.85 419	93.63 351	94.17 485
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
OpenMVS_ROB	86.42 20	89.00 449	87.43 458	93.69 445	93.08 487	89.42 447	97.91 350	96.89 447	78.58 503	85.86 484	94.69 466	69.48 485	98.29 397	77.13 504	93.29 363	93.36 497

KD-MVS_self_test		90.38 434	89.38 433	93.40 450	92.85 488	88.94 457	97.95 343	97.94 344	90.35 431	90.25 448	93.96 478	79.82 421	95.94 491	84.62 477	76.69 500	95.33 462

MIMVSNet1		89.67 444	88.28 448	93.82 443	92.81 489	91.08 406	98.01 337	97.45 396	87.95 461	87.90 473	95.87 444	67.63 491	94.56 504	78.73 500	88.18 433	95.83 453

kuosan		78.45 478	77.69 478	80.72 501	92.73 490	75.32 512	94.63 501	74.51 535	75.96 509	80.87 502	93.19 486	63.23 501	79.99 534	42.56 538	81.56 478	86.85 524

DKM		81.60 469	79.57 473	87.68 481	92.65 491	78.36 505	94.65 500	91.17 516	79.69 501	76.11 508	93.98 477	37.88 526	91.54 515	79.64 495	70.38 518	93.15 500

LoFTR		83.16 467	80.62 472	90.80 473	92.28 492	80.01 503	95.35 486	94.33 497	80.44 498	70.79 518	92.93 489	46.38 509	98.17 405	75.01 509	78.03 492	94.24 482

mvs5depth		91.23 416	90.17 420	94.41 436	92.09 493	89.79 435	95.26 488	96.50 464	90.73 422	91.69 432	97.06 374	76.12 461	98.62 350	88.02 448	84.11 466	94.82 474

UnsupCasMVSNet_bld		87.17 456	85.12 465	93.31 452	91.94 494	88.77 458	94.92 494	98.30 281	84.30 488	82.30 496	90.04 511	63.96 500	97.25 465	85.85 465	74.47 513	93.93 492

CL-MVSNet_self_test		90.11 439	89.14 437	93.02 457	91.86 495	88.23 470	96.51 467	98.07 331	90.49 425	90.49 446	94.41 470	84.75 363	95.34 495	80.79 489	74.95 505	95.50 459

MatchFormer		80.21 470	77.20 480	89.24 477	91.79 496	77.21 506	95.16 489	93.59 505	72.46 516	67.08 521	89.93 512	43.14 517	97.90 437	67.07 520	74.55 512	92.61 503

blend_shiyan4		90.76 429	89.01 439	95.99 362	91.69 497	93.35 346	97.44 394	97.83 352	86.93 467	92.23 421	91.98 500	75.19 467	98.09 416	92.88 347	74.96 504	96.52 419

blended_shiyan8		91.42 410	89.89 424	96.01 359	91.50 498	93.30 349	97.48 392	97.83 352	86.93 467	92.57 408	92.37 496	82.46 395	98.13 409	92.86 349	74.99 503	96.61 398

blended_shiyan6		91.37 411	89.84 425	95.98 365	91.49 499	93.28 350	97.48 392	97.83 352	86.93 467	92.43 414	92.36 497	82.44 396	98.06 421	92.74 354	74.82 506	96.59 403

gbinet_0.2-2-1-0.02		91.03 422	89.37 435	96.01 359	91.39 500	93.41 339	97.19 421	97.82 355	87.00 466	92.18 424	91.87 502	78.97 430	98.04 425	93.13 335	74.75 510	96.60 400

Patchmatch-RL test		91.49 409	90.85 412	93.41 449	91.37 501	84.40 489	92.81 512	95.93 476	91.87 391	87.25 475	94.87 465	88.99 262	96.53 482	92.54 364	82.00 474	99.30 166

wanda-best-256-512		91.17 418	89.60 429	95.88 372	91.33 502	92.99 364	96.89 449	97.82 355	86.89 470	92.36 416	91.75 503	81.83 399	98.06 421	92.75 351	74.82 506	96.59 403

FE-blended-shiyan7		91.17 418	89.60 429	95.88 372	91.33 502	92.99 364	96.89 449	97.82 355	86.89 470	92.36 416	91.75 503	81.83 399	98.06 421	92.75 351	74.82 506	96.59 403

usedtu_blend_shiyan5		90.87 428	89.15 436	96.01 359	91.33 502	93.35 346	98.12 321	97.36 404	81.93 496	92.36 416	91.75 503	81.83 399	98.09 416	92.88 347	74.82 506	96.59 403

test_fmvs3		87.17 456	87.06 460	87.50 482	91.21 505	75.66 510	99.05 78	96.61 462	92.79 358	88.85 465	92.78 492	43.72 514	93.49 508	93.95 310	84.56 463	93.34 498

DKM-HiRes		79.25 472	77.01 482	85.98 485	91.20 506	75.07 513	93.65 510	87.84 524	75.94 510	73.36 513	92.80 491	34.20 531	90.26 518	76.66 506	67.44 525	92.62 502

pmmvs-eth3d		90.36 435	89.05 438	94.32 438	91.10 507	92.12 383	97.63 384	96.95 442	88.86 454	84.91 490	93.13 487	78.32 435	96.74 475	88.70 438	81.81 476	94.09 487

SP-LightGlue		68.17 490	66.54 493	73.06 513	91.08 508	55.79 541	91.09 518	72.78 539	48.55 533	60.77 529	79.95 531	38.55 524	74.10 538	45.47 533	70.64 517	89.28 513

PM-MVS		87.77 454	86.55 461	91.40 470	91.03 509	83.36 496	96.92 442	95.18 486	91.28 412	86.48 483	93.42 483	53.27 507	96.74 475	89.43 429	81.97 475	94.11 486

RoMa-HiRes		79.77 471	77.89 475	85.41 487	90.81 510	74.77 516	94.26 506	86.78 525	75.97 508	77.00 506	94.37 474	39.39 521	90.60 517	74.98 510	67.46 524	90.84 509

SP-NN		67.39 493	65.69 495	72.49 517	90.68 511	55.34 543	90.33 522	71.01 544	46.77 535	59.09 534	79.83 532	37.26 528	73.38 541	44.68 535	71.51 516	88.74 518

SP-SuperGlue		68.14 491	66.58 492	72.81 515	90.65 512	55.53 542	91.37 517	73.04 538	49.07 532	61.03 527	80.24 530	38.13 525	74.06 539	45.46 534	70.26 519	88.84 514

FE-MVSNET2		90.29 436	88.94 442	94.36 437	90.48 513	92.27 378	98.45 260	97.82 355	91.59 399	84.90 491	93.10 488	73.92 476	96.42 485	87.92 451	82.26 472	94.39 479

SP-MNN		66.66 495	64.70 499	72.53 516	90.32 514	55.08 544	91.01 519	71.05 543	44.81 536	56.48 537	79.62 533	35.87 530	74.11 537	43.13 537	69.98 520	88.39 519

new-patchmatchnet		88.50 452	87.45 457	91.67 469	90.31 515	85.89 486	97.16 428	97.33 405	89.47 445	83.63 495	92.77 493	76.38 458	95.06 500	82.70 482	77.29 494	94.06 489

MASt3R-SfM		85.54 461	85.89 462	84.50 491	90.13 516	66.13 528	92.89 511	95.33 483	85.73 481	88.77 467	96.36 423	52.50 508	94.89 502	86.66 458	84.65 462	92.50 504

FE-MVSNET		88.56 451	87.09 459	92.99 459	89.93 517	89.99 432	98.15 317	95.59 479	88.42 459	84.87 492	92.90 490	74.82 470	94.99 501	77.88 502	81.21 479	93.99 490

mvsany_test3		88.80 450	88.04 451	91.09 472	89.78 518	81.57 501	97.83 365	95.49 481	93.81 299	87.53 474	93.95 479	56.14 505	97.43 462	94.68 278	83.13 469	94.26 481

WB-MVS		84.86 462	85.33 464	83.46 494	89.48 519	69.56 522	98.19 305	96.42 467	89.55 444	81.79 497	94.67 467	84.80 361	90.12 519	52.44 528	80.64 484	90.69 510

test_f		86.07 460	85.39 463	88.10 480	89.28 520	75.57 511	97.73 374	96.33 468	89.41 448	85.35 488	91.56 506	43.31 516	95.53 493	91.32 393	84.23 465	93.21 499

SSC-MVS		84.27 465	84.71 467	82.96 499	89.19 521	68.83 523	98.08 329	96.30 469	89.04 453	81.37 499	94.47 468	84.60 368	89.89 520	49.80 531	79.52 486	90.15 511

pmmvs3		86.67 459	84.86 466	92.11 468	88.16 522	87.19 480	96.63 462	94.75 493	79.88 499	87.22 476	92.75 494	66.56 494	95.20 498	81.24 488	76.56 501	93.96 491

testf1		79.02 475	77.70 476	82.99 497	88.10 523	66.90 526	94.67 497	93.11 507	71.08 518	74.02 510	93.41 484	34.15 532	93.25 509	72.25 514	78.50 490	88.82 515

APD_test2		79.02 475	77.70 476	82.99 497	88.10 523	66.90 526	94.67 497	93.11 507	71.08 518	74.02 510	93.41 484	34.15 532	93.25 509	72.25 514	78.50 490	88.82 515

ambc				89.49 476	86.66 525	75.78 509	92.66 513	96.72 455		86.55 482	92.50 495	46.01 512	97.90 437	90.32 410	82.09 473	94.80 476

test_vis3_rt		79.22 473	77.40 479	84.67 489	86.44 526	74.85 515	97.66 379	81.43 529	84.98 485	67.12 520	81.91 526	28.09 540	97.60 456	88.96 436	80.04 485	81.55 527

usedtu_dtu_shiyan2		84.80 463	82.31 469	92.27 466	86.38 527	85.55 487	97.77 370	96.56 463	78.34 504	83.90 494	93.50 482	54.16 506	95.32 496	77.55 503	72.62 514	95.92 450

test_method		79.03 474	78.17 474	81.63 500	86.06 528	54.40 545	82.75 532	96.89 447	39.54 537	80.98 501	95.57 457	58.37 504	94.73 503	84.74 476	78.61 489	95.75 454

PDCNetPlus		71.79 485	69.26 489	79.39 504	85.67 529	69.92 521	90.34 521	62.32 548	72.62 515	65.36 523	90.26 508	39.20 523	86.38 526	75.32 508	42.24 543	81.88 526

TDRefinement		91.06 421	89.68 427	95.21 399	85.35 530	91.49 400	98.51 251	97.07 430	91.47 401	88.83 466	97.84 300	77.31 448	99.09 282	92.79 350	77.98 493	95.04 471

PMatch-SfM		73.49 484	70.32 487	83.00 496	85.01 531	68.63 524	90.17 523	79.05 532	71.64 517	63.27 524	91.93 501	17.27 551	89.10 522	74.59 511	59.95 531	91.26 505

ELoFTR		75.37 482	72.33 486	84.51 490	84.48 532	68.41 525	91.57 516	88.78 522	73.84 513	62.84 525	90.14 509	27.38 541	94.11 507	71.45 517	60.46 530	91.00 507

SIFT-NN		49.27 506	49.25 510	49.32 523	83.88 533	45.20 548	74.57 537	53.44 550	32.44 541	42.88 545	64.93 542	20.60 545	61.35 544	16.59 548	53.96 534	41.40 541

PMMVS2		77.95 480	75.44 485	85.46 486	82.54 534	74.95 514	94.23 507	93.08 509	72.80 514	74.68 509	87.38 517	36.36 529	91.56 514	73.95 512	63.94 526	89.87 512

E-PMN		64.94 498	64.25 500	67.02 518	82.28 535	59.36 538	91.83 515	85.63 526	52.69 526	60.22 530	77.28 535	41.06 519	80.12 533	46.15 532	41.14 544	61.57 538

PMatch-Up-SfM		70.03 487	66.48 494	80.70 502	82.00 536	63.20 531	88.10 527	71.07 542	67.59 520	60.07 531	90.10 510	14.49 556	87.80 525	71.95 516	52.95 536	91.09 506

EMVS		64.07 499	63.26 502	66.53 519	81.73 537	58.81 539	91.85 514	84.75 527	51.93 528	59.09 534	75.13 538	43.32 515	79.09 535	42.03 539	39.47 545	61.69 537

SIFT-MNN		47.78 507	47.47 511	48.69 524	81.04 538	44.17 549	73.46 538	53.36 551	31.82 542	38.54 546	63.76 543	18.11 549	61.27 545	15.96 550	51.17 538	40.64 544

SIFT-NCM-Cal		44.98 510	44.20 514	47.33 527	79.81 539	43.05 553	72.12 540	49.31 554	30.81 547	25.90 555	61.87 551	15.80 552	60.28 547	14.09 559	48.07 541	38.66 547

SIFT-NN-NCMNet		47.55 508	47.18 512	48.67 525	79.60 540	44.09 550	73.43 539	52.90 552	31.82 542	38.38 547	63.56 546	18.47 546	61.19 546	15.91 551	50.50 539	40.74 543

FPMVS		77.62 481	77.14 481	79.05 505	79.25 541	60.97 536	95.79 477	95.94 475	65.96 521	67.93 519	94.40 471	37.73 527	88.88 523	68.83 519	88.46 430	87.29 521

wuyk23d		30.17 521	30.18 526	30.16 539	78.61 542	43.29 551	66.79 547	14.21 566	17.31 557	14.82 562	11.93 561	11.55 562	41.43 559	37.08 541	19.30 559	5.76 558

SIFT-ConvMatch		43.26 512	42.18 517	46.50 529	78.34 543	43.05 553	68.67 545	47.17 556	31.06 546	30.28 551	62.56 548	15.43 553	58.95 552	14.92 555	31.22 550	37.51 549

SP-DiffGlue		70.13 486	69.16 490	73.04 514	77.73 544	57.48 540	88.44 526	74.91 534	50.96 529	66.64 522	85.99 519	41.44 518	73.46 540	64.21 522	72.15 515	88.19 520

SIFT-CM-Cal		41.25 515	40.03 519	44.88 531	77.37 545	41.08 559	65.71 549	41.18 560	30.42 550	28.83 553	61.42 552	14.88 555	56.40 553	14.13 558	26.37 556	37.16 550

LCM-MVSNet		78.70 477	76.24 484	86.08 484	77.26 546	71.99 519	94.34 505	96.72 455	61.62 523	76.53 507	89.33 514	33.91 535	92.78 513	81.85 485	74.60 511	93.46 496

SIFT-NN-CMatch		45.31 509	44.49 513	47.75 526	76.46 547	42.98 555	70.17 543	49.20 555	31.63 545	37.94 548	63.68 545	18.19 548	59.32 550	15.91 551	37.27 548	40.95 542

SIFT-UMatch		42.35 514	41.04 518	46.29 530	76.09 548	41.80 558	70.21 542	45.21 558	30.75 548	27.33 554	62.62 547	15.13 554	59.11 551	14.72 556	27.30 554	37.95 548

SIFT-UM-Cal		39.93 516	38.61 521	43.88 533	76.08 549	39.30 560	68.10 546	37.89 561	30.49 549	22.74 557	62.27 549	13.89 557	56.16 554	14.17 557	21.90 557	36.17 551

SIFT-NN-UMatch		44.69 511	43.84 515	47.24 528	74.56 550	42.59 556	71.89 541	49.78 553	31.80 544	29.27 552	63.70 544	18.26 547	59.43 548	15.86 553	39.43 546	39.71 545

MVE	62.14 22	63.28 500	59.38 504	74.99 506	74.33 551	65.47 529	85.55 530	80.50 530	52.02 527	51.10 540	75.00 539	10.91 563	80.50 532	51.60 530	53.40 535	78.99 528
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SIFT-NN-PointCN		43.09 513	42.61 516	44.51 532	72.48 552	37.95 561	70.10 544	46.55 557	30.16 551	34.48 550	61.93 550	18.02 550	55.90 555	15.40 554	34.41 549	39.69 546

XFeat-NN		56.16 502	56.10 506	56.36 521	72.10 553	42.54 557	76.45 536	61.18 549	38.16 539	53.08 538	76.48 536	32.95 537	65.67 543	44.15 536	50.31 540	60.87 539

SIFT-PointCN		37.89 517	37.50 522	39.07 535	71.45 554	31.31 563	66.27 548	41.69 559	27.82 553	22.63 558	56.73 554	12.00 561	50.56 557	12.18 561	26.71 555	35.34 552

SIFT-PCN-Cal		36.85 519	36.40 523	38.19 536	71.43 555	30.42 564	64.34 551	37.72 562	27.48 554	22.98 556	57.03 553	12.99 559	51.22 556	12.51 560	21.13 558	32.92 553

GLUNet-SfM		61.12 501	56.63 505	74.58 508	69.78 556	53.99 546	78.71 534	76.81 533	49.09 531	49.42 543	80.47 529	24.43 543	85.82 527	51.80 529	29.17 552	83.92 525

XFeat-MNN		55.84 503	55.19 508	57.82 520	69.33 557	43.25 552	78.25 535	62.64 547	37.53 540	50.90 541	76.32 537	32.43 538	68.13 542	42.00 540	47.26 542	62.07 536

SIFT-NCMNet		32.45 520	31.84 525	34.30 537	68.74 558	28.10 565	57.85 553	24.54 564	27.25 555	19.31 559	52.59 555	9.75 564	45.69 558	10.92 562	15.56 560	29.13 555

MVS_clip		51.49 505	54.55 509	42.29 534	67.55 559	32.35 562	60.25 552	21.09 565	22.72 556	71.30 516	91.13 507	33.91 535	28.07 560	61.97 525	61.05 529	66.44 534

ANet_high		69.08 488	65.37 496	80.22 503	65.99 560	71.96 520	90.91 520	90.09 520	82.62 492	49.93 542	78.39 534	29.36 539	81.75 531	62.49 523	38.52 547	86.95 523

PMVS	61.03 23	65.95 496	63.57 501	73.09 512	57.90 561	51.22 547	85.05 531	93.93 504	54.45 525	44.32 544	83.57 520	13.22 558	89.15 521	58.68 527	81.00 481	78.91 529
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		68.90 489	66.97 491	74.68 507	50.78 562	59.95 537	87.13 529	83.47 528	38.80 538	62.21 526	96.23 428	64.70 498	76.91 536	88.91 437	30.49 551	87.19 522

VLMVS_CLIP		53.81 504	55.23 507	49.55 522	44.37 563	26.59 566	64.46 550	73.52 537	28.42 552	60.82 528	83.22 521	22.09 544	59.35 549	62.16 524	58.00 533	62.70 535

VLMVS		37.31 518	39.19 520	31.67 538	40.61 564	24.46 567	44.56 554	28.63 563	5.66 560	51.94 539	71.15 540	25.03 542	27.90 561	33.30 543	51.87 537	42.64 540

MVS_baseline		19.65 525	22.57 529	10.89 542	26.60 565	2.25 570	14.08 555	3.93 569	1.15 562	37.00 549	69.35 541	4.91 566	0.00 564	17.88 546	28.24 553	30.42 554

testmvs		21.48 523	24.95 527	11.09 541	14.89 566	6.47 569	96.56 464	9.87 567	7.55 558	17.93 560	39.02 557	9.43 565	5.90 563	16.56 549	12.72 561	20.91 557

test123		20.95 524	23.72 528	12.64 540	13.54 567	8.19 568	96.55 466	6.13 568	7.48 559	16.74 561	37.98 558	12.97 560	6.05 562	16.69 547	5.43 562	23.68 556

PatchmatchNet2					0.00 568	88.11 472	96.56 464	97.31 408	85.66 482
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
mmdepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

monomultidepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

test_blank		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

eth-test2					0.00 568

eth-test					0.00 568

uanet_test		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

DCPMVS		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

cdsmvs_eth3d_5k		23.98 522	31.98 524	0.00 543	0.00 568	0.00 571	0.00 556	98.59 174	0.00 563	0.00 564	98.61 218	90.60 210	0.00 564	0.00 563	0.00 563	0.00 559

pcd_1.5k_mvsjas		7.88 527	10.50 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	94.51 94	0.00 564	0.00 563	0.00 563	0.00 559

sosnet-low-res		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

sosnet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uncertanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

Regformer		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

ab-mvs-re		8.20 526	10.94 530	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	98.43 238	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

Meshroom													0.00 564
: In preparation.
AliceVision / Meshro													0.00 564
: In preparation.
AliceVision_Meshroom													0.00 564
: In preparation.
PatchmatchNet1														80.13 490	90.51 398	95.88 451
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													97.78 447
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						90.94 408								88.66 439

PC_three_1452									95.08 222	99.60 34	99.16 112	97.86 2	98.47 365	97.52 145	99.72 69	99.74 51

test_241102_TWO								98.87 86	97.65 43	99.53 40	99.48 36	97.34 13	99.94 15	98.43 70	99.80 27	99.83 20

test_0728_THIRD									97.32 67	99.45 42	99.46 43	97.88 1	99.94 15	98.47 66	99.86 2	99.85 17

GSMVS																99.20 193

sam_mvs1												89.45 246				99.20 193

sam_mvs												88.99 262

MTGPA								98.74 132

test_post1							96.68 461				30.43 560	87.85 301	98.69 343	92.59 360

test_post											31.83 559	88.83 271	98.91 319

patchmatchnet-post											95.10 463	89.42 247	98.89 323

MTMP							98.89 127	94.14 502

test9_res														96.39 213	99.57 101	99.69 72

agg_prior2														95.87 229	99.57 101	99.68 77

test_prior4						98.01 74	97.86 360

test_prior2							97.80 367		96.12 144	97.89 177	98.69 211	95.96 47		96.89 186	99.60 95

旧先验2							97.57 387		91.30 410	98.67 109			99.80 112	95.70 240

新几何2							97.64 381

无先验							97.58 386	98.72 137	91.38 404				99.87 82	93.36 328		99.60 94

原ACMM2							97.67 378

testdata2													99.89 71	91.65 388

segment_acmp												96.85 17

testdata1							97.32 408		96.34 132

plane_prior5								98.56 185					99.03 296	96.07 219	94.27 331	96.92 355

plane_prior4											98.28 258

plane_prior3						94.61 287			97.02 91	95.34 296

plane_prior2							98.80 167		97.28 71

plane_prior						94.60 289	98.44 266		96.74 108						94.22 333

n2								0.00 570

nn								0.00 570

door-mid								94.37 496

test11								98.66 156

door								94.64 494

HQP5-MVS						94.25 306

BP-MVS														95.30 254

HQP4-MVS										94.45 321			98.96 310			96.87 367

HQP3-MVS								98.46 210							94.18 335

HQP2-MVS												86.75 321

MDTV_nov1_ep13_2view						84.26 490	96.89 449		90.97 419	97.90 176		89.89 232		93.91 312		99.18 202

ACMMP++_ref															92.97 365

ACMMP++															93.61 352

Test By Simon												94.64 91

High-resolution multi-view benchmark