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 28	99.69 1	98.95 61	97.46 55	99.39 44

MED-MVS test				99.52 13	99.77 2	98.86 22	99.32 22	99.24 20	96.41 121	99.30 50	99.35 60		99.92 43	98.30 75	99.80 25	99.79 28

MED-MVS		99.02 6	98.85 8	99.52 13	99.77 2	98.86 22	99.32 22	99.24 20	97.00 89	99.30 50	99.35 60	97.61 6	99.92 43	98.30 75	99.80 25	99.79 28

TestfortrainingZip a		99.02 6	98.79 12	99.70 2	99.77 2	99.30 2	99.32 22	99.24 20	96.41 121	99.30 50	99.35 60	97.61 6	99.92 43	98.35 72	99.80 25	99.88 10

MTAPA		98.58 36	98.29 61	99.46 18	99.76 5	98.64 29	98.90 117	98.74 129	97.27 71	98.02 148	99.39 48	94.81 86	99.96 4	97.91 98	99.79 35	99.77 40

NormalMVS		98.07 84	97.90 87	98.59 103	99.75 6	96.60 143	98.94 106	98.60 164	97.86 31	98.71 101	99.08 132	91.22 178	99.80 109	97.40 150	99.57 99	99.37 139

lecture		98.95 9	98.78 14	99.45 19	99.75 6	98.63 30	99.43 10	99.38 8	97.60 44	99.58 33	99.47 35	95.36 63	99.93 34	98.87 38	99.57 99	99.78 33

MSP-MVS		98.74 22	98.55 29	99.29 38	99.75 6	98.23 56	99.26 33	98.88 78	97.52 48	99.41 42	98.78 185	96.00 41	99.79 121	97.79 106	99.59 95	99.85 15
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 72	98.01 82	99.28 41	99.75 6	98.18 60	99.22 42	98.79 119	96.13 135	97.92 162	99.23 86	94.54 89	99.94 14	96.74 189	99.78 40	99.73 55
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
mPP-MVS		98.51 49	98.26 62	99.25 44	99.75 6	98.04 68	99.28 30	98.81 107	96.24 130	98.35 129	99.23 86	95.46 57	99.94 14	97.42 148	99.81 16	99.77 40

HPM-MVS_fast		98.38 63	98.13 74	99.12 60	99.75 6	97.86 74	99.44 9	98.82 101	94.46 253	98.94 77	99.20 92	95.16 76	99.74 134	97.58 127	99.85 6	99.77 40

region2R		98.61 31	98.38 44	99.29 38	99.74 12	98.16 62	99.23 38	98.93 65	96.15 134	98.94 77	99.17 104	95.91 45	99.94 14	97.55 132	99.79 35	99.78 33

ACMMPR		98.59 34	98.36 46	99.29 38	99.74 12	98.15 63	99.23 38	98.95 61	96.10 138	98.93 81	99.19 99	95.70 51	99.94 14	97.62 120	99.79 35	99.78 33

HPM-MVS		98.36 66	98.10 77	99.13 58	99.74 12	97.82 79	99.53 6	98.80 114	94.63 241	98.61 111	98.97 148	95.13 78	99.77 129	97.65 118	99.83 13	99.79 28
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ACMMP		98.23 76	97.95 84	99.09 62	99.74 12	97.62 83	99.03 82	99.41 6	95.98 143	97.60 197	99.36 58	94.45 94	99.93 34	97.14 160	98.85 167	99.70 67
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 51	98.20 71	99.35 30	99.73 16	98.39 39	99.19 50	98.86 91	95.77 155	98.31 132	99.10 122	95.46 57	99.93 34	97.57 131	99.81 16	99.74 50

DVP-MVS		99.03 5	98.83 10	99.63 5	99.72 17	99.25 3	98.97 96	98.58 176	97.62 41	99.45 39	99.46 40	97.42 11	99.94 14	98.47 63	99.81 16	99.69 70
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 17	99.35 1	98.97 96	98.88 78					99.94 14	98.47 63	99.81 16	99.84 17

test0726					99.72 17	99.25 3	99.06 73	98.88 78	97.62 41	99.56 34	99.50 29	97.42 11

GST-MVS		98.43 59	98.12 75	99.34 31	99.72 17	98.38 40	99.09 70	98.82 101	95.71 159	98.73 98	99.06 137	95.27 69	99.93 34	97.07 163	99.63 88	99.72 59

MP-MVS-pluss		98.31 73	97.92 85	99.49 16	99.72 17	98.88 19	98.43 261	98.78 121	94.10 264	97.69 185	99.42 44	95.25 71	99.92 43	98.09 88	99.80 25	99.67 79
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HFP-MVS		98.63 29	98.40 42	99.32 37	99.72 17	98.29 52	99.23 38	98.96 60	96.10 138	98.94 77	99.17 104	96.06 38	99.92 43	97.62 120	99.78 40	99.75 48

PGM-MVS		98.49 51	98.23 67	99.27 43	99.72 17	98.08 67	98.99 92	99.49 5	95.43 182	99.03 69	99.32 69	95.56 54	99.94 14	96.80 186	99.77 42	99.78 33

SED-MVS		99.09 1	98.91 4	99.63 5	99.71 24	99.24 6	99.02 85	98.87 85	97.65 39	99.73 22	99.48 33	97.53 9	99.94 14	98.43 67	99.81 16	99.70 67

IU-MVS					99.71 24	99.23 8		98.64 158	95.28 194	99.63 31				98.35 72	99.81 16	99.83 18

test_241102_ONE					99.71 24	99.24 6		98.87 85	97.62 41	99.73 22	99.39 48	97.53 9	99.74 134

XVS		98.70 24	98.49 36	99.34 31	99.70 27	98.35 49	99.29 28	98.88 78	97.40 57	98.46 118	99.20 92	95.90 47	99.89 68	97.85 102	99.74 58	99.78 33

X-MVStestdata		94.06 357	92.30 383	99.34 31	99.70 27	98.35 49	99.29 28	98.88 78	97.40 57	98.46 118	43.50 493	95.90 47	99.89 68	97.85 102	99.74 58	99.78 33

TSAR-MVS + MP.		98.78 20	98.62 22	99.24 45	99.69 29	98.28 53	99.14 60	98.66 153	96.84 96	99.56 34	99.31 71	96.34 31	99.70 142	98.32 74	99.73 62	99.73 55
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 94	97.74 91	98.20 147	99.67 30	95.16 242	99.22 42	99.32 12	93.04 331	97.02 222	98.92 162	95.36 63	99.91 56	97.43 146	99.64 86	99.52 101

test_one_0601					99.66 31	99.25 3		98.86 91	97.55 47	99.20 59	99.47 35	97.57 8

CP-MVS		98.57 41	98.36 46	99.19 50	99.66 31	97.86 74	99.34 17	98.87 85	95.96 144	98.60 112	99.13 114	96.05 39	99.94 14	97.77 107	99.86 2	99.77 40

CPTT-MVS		97.72 101	97.32 120	98.92 78	99.64 33	97.10 121	99.12 64	98.81 107	92.34 357	98.09 138	99.08 132	93.01 116	99.92 43	96.06 210	99.77 42	99.75 48

test_part2					99.63 34	99.18 11				99.27 56

ACMMP_NAP		98.61 31	98.30 60	99.55 10	99.62 35	98.95 18	98.82 152	98.81 107	95.80 153	99.16 66	99.47 35	95.37 62	99.92 43	97.89 100	99.75 54	99.79 28

MCST-MVS		98.65 26	98.37 45	99.48 17	99.60 36	98.87 20	98.41 265	98.68 145	97.04 86	98.52 116	98.80 179	96.78 18	99.83 90	97.93 96	99.61 91	99.74 50

ME-MVS		98.83 19	98.60 24	99.52 13	99.58 37	98.86 22	98.69 196	98.93 65	97.00 89	99.17 62	99.35 60	96.62 23	99.90 64	98.30 75	99.80 25	99.79 28

DPE-MVS		98.92 13	98.67 20	99.65 3	99.58 37	99.20 10	98.42 264	98.91 72	97.58 45	99.54 36	99.46 40	97.10 14	99.94 14	97.64 119	99.84 11	99.83 18
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
dcpmvs_2		98.08 82	98.59 25	96.56 305	99.57 39	90.34 409	99.15 57	98.38 245	96.82 98	99.29 53	99.49 32	95.78 49	99.57 170	98.94 35	99.86 2	99.77 40

APDe-MVS		99.02 6	98.84 9	99.55 10	99.57 39	98.96 17	99.39 11	98.93 65	97.38 60	99.41 42	99.54 20	96.66 20	99.84 88	98.86 39	99.85 6	99.87 11
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		98.59 34	98.32 59	99.41 22	99.54 41	98.71 26	99.04 79	98.81 107	95.12 206	99.32 49	99.39 48	96.22 32	99.84 88	97.72 110	99.73 62	99.67 79

patch_mono-2		98.36 66	98.87 6	96.82 276	99.53 42	90.68 397	98.64 209	99.29 15	97.88 30	99.19 61	99.52 23	96.80 17	99.97 1	99.11 30	99.86 2	99.82 22

SR-MVS		98.57 41	98.35 48	99.24 45	99.53 42	98.18 60	99.09 70	98.82 101	96.58 112	99.10 68	99.32 69	95.39 60	99.82 97	97.70 115	99.63 88	99.72 59

DP-MVS Recon		97.86 92	97.46 108	99.06 65	99.53 42	98.35 49	98.33 270	98.89 75	92.62 346	98.05 143	98.94 156	95.34 65	99.65 153	96.04 211	99.42 128	99.19 187

reproduce_model		98.94 10	98.81 11	99.34 31	99.52 45	98.26 54	98.94 106	98.84 96	98.06 25	99.35 46	99.61 5	96.39 30	99.94 14	98.77 42	99.82 14	99.83 18

SMA-MVS		98.58 36	98.25 63	99.56 9	99.51 46	99.04 16	98.95 103	98.80 114	93.67 299	99.37 45	99.52 23	96.52 25	99.89 68	98.06 89	99.81 16	99.76 47
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 68	98.00 83	99.42 21	99.51 46	98.72 25	98.80 161	98.82 101	94.52 248	99.23 58	99.25 85	95.54 56	99.80 109	96.52 195	99.77 42	99.74 50
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HPM-MVS++		98.58 36	98.25 63	99.55 10	99.50 48	99.08 12	98.72 188	98.66 153	97.51 49	98.15 133	98.83 176	95.70 51	99.92 43	97.53 134	99.67 75	99.66 82

APD-MVS_3200maxsize		98.53 46	98.33 58	99.15 56	99.50 48	97.92 73	99.15 57	98.81 107	96.24 130	99.20 59	99.37 54	95.30 67	99.80 109	97.73 109	99.67 75	99.72 59

114514_t		96.93 173	96.27 193	98.92 78	99.50 48	97.63 82	98.85 144	98.90 73	84.80 462	97.77 175	99.11 120	92.84 118	99.66 152	94.85 254	99.77 42	99.47 115

PAPM_NR		97.46 130	97.11 141	98.50 117	99.50 48	96.41 157	98.63 212	98.60 164	95.18 199	97.06 220	98.06 263	94.26 99	99.57 170	93.80 300	98.87 164	99.52 101

reproduce-ours		98.93 11	98.78 14	99.38 23	99.49 52	98.38 40	98.86 139	98.83 98	98.06 25	99.29 53	99.58 16	96.40 28	99.94 14	98.68 45	99.81 16	99.81 24

our_new_method		98.93 11	98.78 14	99.38 23	99.49 52	98.38 40	98.86 139	98.83 98	98.06 25	99.29 53	99.58 16	96.40 28	99.94 14	98.68 45	99.81 16	99.81 24

SR-MVS-dyc-post		98.54 45	98.35 48	99.13 58	99.49 52	97.86 74	99.11 66	98.80 114	96.49 116	99.17 62	99.35 60	95.34 65	99.82 97	97.72 110	99.65 81	99.71 63

RE-MVS-def			98.34 54		99.49 52	97.86 74	99.11 66	98.80 114	96.49 116	99.17 62	99.35 60	95.29 68		97.72 110	99.65 81	99.71 63

9.14			98.06 78		99.47 56		98.71 189	98.82 101	94.36 256	99.16 66	99.29 75	96.05 39	99.81 102	97.00 164	99.71 69

CDPH-MVS		97.94 89	97.49 105	99.28 41	99.47 56	98.44 36	97.91 336	98.67 150	92.57 349	98.77 94	98.85 171	95.93 44	99.72 136	95.56 231	99.69 72	99.68 75

ZD-MVS					99.46 58	98.70 27		98.79 119	93.21 322	98.67 104	98.97 148	95.70 51	99.83 90	96.07 207	99.58 98

save fliter					99.46 58	98.38 40	98.21 288	98.71 137	97.95 28

EI-MVSNet-Vis-set		98.47 54	98.39 43	98.69 93	99.46 58	96.49 152	98.30 278	98.69 142	97.21 74	98.84 87	99.36 58	95.41 59	99.78 124	98.62 49	99.65 81	99.80 27

EI-MVSNet-UG-set		98.41 61	98.34 54	98.61 101	99.45 61	96.32 162	98.28 281	98.68 145	97.17 78	98.74 96	99.37 54	95.25 71	99.79 121	98.57 52	99.54 110	99.73 55

F-COLMAP		97.09 167	96.80 162	97.97 185	99.45 61	94.95 257	98.55 235	98.62 163	93.02 332	96.17 264	98.58 212	94.01 103	99.81 102	93.95 294	98.90 160	99.14 197

fmvsm_l_conf0.5_n_a		99.09 1	99.08 1	99.11 61	99.43 63	97.48 89	98.88 128	99.30 14	98.47 18	99.85 11	99.43 43	96.71 19	99.96 4	99.86 1	99.80 25	99.89 6

fmvsm_s_conf0.5_n_11		98.58 36	98.57 26	98.62 99	99.42 64	97.16 117	98.97 96	98.86 91	98.91 4	99.87 4	99.66 3	91.82 151	99.95 9	99.82 6	99.82 14	98.75 251

test_fmvsm_n_1920		98.87 18	99.01 3	98.45 123	99.42 64	96.43 155	98.96 102	99.36 10	98.63 13	99.86 8	99.51 26	95.91 45	99.97 1	99.72 14	99.75 54	98.94 229

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 57	99.41 66	97.54 87	98.89 121	99.31 13	98.49 17	99.86 8	99.42 44	96.45 27	99.96 4	99.86 1	99.74 58	99.90 5

fmvsm_s_conf0.5_n_9		98.63 29	98.66 21	98.54 109	99.40 67	95.83 200	98.79 169	99.17 38	98.94 2	99.92 1	99.61 5	92.49 123	99.93 34	99.86 1	99.76 48	99.86 12

fmvsm_s_conf0.5_n_10		98.66 25	98.54 31	99.02 68	99.36 68	97.21 114	98.86 139	99.23 28	98.90 5	99.83 12	99.59 13	91.57 159	99.94 14	99.79 9	99.74 58	99.89 6

fmvsm_l_conf0.5_n_3		98.90 15	98.74 18	99.37 27	99.36 68	98.25 55	98.89 121	99.24 20	98.77 10	99.89 3	99.59 13	93.39 111	99.96 4	99.78 10	99.76 48	99.89 6

fmvsm_s_conf0.5_n_8		98.73 23	98.62 22	99.05 66	99.35 70	97.27 105	98.80 161	99.23 28	98.93 3	99.79 15	99.59 13	92.34 128	99.95 9	99.82 6	99.71 69	99.92 2

fmvsm_l_conf0.5_n_9		98.90 15	98.79 12	99.24 45	99.34 71	97.83 78	98.70 193	99.26 16	98.85 6	99.92 1	99.51 26	93.91 105	99.95 9	99.86 1	99.79 35	99.92 2

新几何1				99.16 55	99.34 71	98.01 70		98.69 142	90.06 416	98.13 135	98.95 155	94.60 88	99.89 68	91.97 361	99.47 122	99.59 94

DP-MVS		96.59 192	95.93 210	98.57 104	99.34 71	96.19 168	98.70 193	98.39 239	89.45 427	94.52 301	99.35 60	91.85 149	99.85 84	92.89 328	98.88 162	99.68 75

SD-MVS		98.64 28	98.68 19	98.53 112	99.33 74	98.36 48	98.90 117	98.85 95	97.28 67	99.72 25	99.39 48	96.63 22	97.60 432	98.17 84	99.85 6	99.64 86
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		96.90 175	96.49 184	98.14 155	99.33 74	95.56 215	97.38 386	99.65 2	92.34 357	97.61 194	98.20 253	89.29 240	99.10 269	96.97 166	97.60 242	99.77 40

OMC-MVS		97.55 120	97.34 119	98.20 147	99.33 74	95.92 188	98.28 281	98.59 171	95.52 177	97.97 155	99.10 122	93.28 114	99.49 190	95.09 248	98.88 162	99.19 187

原ACMM1				98.65 97	99.32 77	96.62 140		98.67 150	93.27 321	97.81 172	98.97 148	95.18 75	99.83 90	93.84 298	99.46 125	99.50 106

CNVR-MVS		98.78 20	98.56 28	99.45 19	99.32 77	98.87 20	98.47 251	98.81 107	97.72 34	98.76 95	99.16 107	97.05 15	99.78 124	98.06 89	99.66 78	99.69 70

TEST9					99.31 79	98.50 34	97.92 334	98.73 132	92.63 345	97.74 179	98.68 201	96.20 34	99.80 109

train_agg		97.97 86	97.52 103	99.33 35	99.31 79	98.50 34	97.92 334	98.73 132	92.98 333	97.74 179	98.68 201	96.20 34	99.80 109	96.59 190	99.57 99	99.68 75

test_prior				99.19 50	99.31 79	98.22 57		98.84 96					99.70 142			99.65 83

PatchMatch-RL		96.59 192	96.03 204	98.27 138	99.31 79	96.51 151	97.91 336	99.06 48	93.72 291	96.92 227	98.06 263	88.50 268	99.65 153	91.77 365	99.00 157	98.66 265

fmvsm_s_conf0.5_n		98.42 60	98.51 32	98.13 160	99.30 83	95.25 238	98.85 144	99.39 7	97.94 29	99.74 21	99.62 4	92.59 122	99.91 56	99.65 18	99.52 113	99.25 176

SDMVSNet		96.85 177	96.42 185	98.14 155	99.30 83	96.38 158	99.21 45	99.23 28	95.92 145	95.96 271	98.76 193	85.88 325	99.44 202	97.93 96	95.59 306	98.60 270

sd_testset		96.17 213	95.76 216	97.42 232	99.30 83	94.34 287	98.82 152	99.08 46	95.92 145	95.96 271	98.76 193	82.83 378	99.32 215	95.56 231	95.59 306	98.60 270

agg_prior					99.30 83	98.38 40		98.72 134		97.57 200			99.81 102

CHOSEN 1792x2688		97.12 165	96.80 162	98.08 168	99.30 83	94.56 278	98.05 318	99.71 1	93.57 307	97.09 216	98.91 163	88.17 275	99.89 68	96.87 179	99.56 107	99.81 24

test_8					99.29 88	98.44 36	97.89 342	98.72 134	92.98 333	97.70 184	98.66 204	96.20 34	99.80 109

旧先验1					99.29 88	97.48 89		98.70 140			99.09 130	95.56 54			99.47 122	99.61 90

PLC	95.07 4	97.20 158	96.78 166	98.44 125	99.29 88	96.31 164	98.14 304	98.76 125	92.41 355	96.39 257	98.31 242	94.92 85	99.78 124	94.06 292	98.77 171	99.23 178
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
COLMAP_ROB	93.27 12	95.33 264	94.87 265	96.71 285	99.29 88	93.24 339	98.58 222	98.11 308	89.92 418	93.57 353	99.10 122	86.37 315	99.79 121	90.78 386	98.10 223	97.09 327
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
NCCC		98.61 31	98.35 48	99.38 23	99.28 92	98.61 31	98.45 253	98.76 125	97.82 33	98.45 121	98.93 158	96.65 21	99.83 90	97.38 153	99.41 129	99.71 63

PVSNet_Blended_VisFu		97.70 103	97.46 108	98.44 125	99.27 93	95.91 189	98.63 212	99.16 40	94.48 252	97.67 186	98.88 167	92.80 119	99.91 56	97.11 161	99.12 149	99.50 106

MVS_111021_LR		98.34 70	98.23 67	98.67 95	99.27 93	96.90 129	97.95 329	99.58 3	97.14 81	98.44 123	99.01 144	95.03 82	99.62 163	97.91 98	99.75 54	99.50 106

MSLP-MVS++		98.56 43	98.57 26	98.55 107	99.26 95	96.80 133	98.71 189	99.05 50	97.28 67	98.84 87	99.28 76	96.47 26	99.40 206	98.52 61	99.70 71	99.47 115

fmvsm_s_conf0.5_n_2		98.30 75	98.21 69	98.57 104	99.25 96	97.11 120	98.66 206	99.20 34	98.82 7	99.79 15	99.60 10	89.38 237	99.92 43	99.80 8	99.38 134	98.69 259

AllTest		95.24 269	94.65 275	96.99 260	99.25 96	93.21 340	98.59 218	98.18 292	91.36 386	93.52 355	98.77 188	84.67 351	99.72 136	89.70 404	97.87 231	98.02 300

TestCases				96.99 260	99.25 96	93.21 340		98.18 292	91.36 386	93.52 355	98.77 188	84.67 351	99.72 136	89.70 404	97.87 231	98.02 300

PVSNet_BlendedMVS		96.73 184	96.60 178	97.12 251	99.25 96	95.35 233	98.26 284	99.26 16	94.28 258	97.94 159	97.46 321	92.74 120	99.81 102	96.88 176	93.32 344	96.20 423

PVSNet_Blended		97.38 139	97.12 140	98.14 155	99.25 96	95.35 233	97.28 397	99.26 16	93.13 327	97.94 159	98.21 252	92.74 120	99.81 102	96.88 176	99.40 132	99.27 168

DeepC-MVS	95.98 3	97.88 91	97.58 96	98.77 87	99.25 96	96.93 127	98.83 150	98.75 127	96.96 92	96.89 229	99.50 29	90.46 203	99.87 79	97.84 104	99.76 48	99.52 101
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 44	98.34 54	99.18 52	99.25 96	98.04 68	98.50 246	98.78 121	97.72 34	98.92 83	99.28 76	95.27 69	99.82 97	97.55 132	99.77 42	99.69 70
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 27	99.24 103	99.05 15	99.02 85				99.16 107	97.81 3	99.37 210	97.24 157	99.73 62	99.70 67

fmvsm_s_conf0.5_n_3		98.53 46	98.45 39	98.79 85	99.23 104	97.32 98	98.80 161	99.26 16	98.82 7	99.87 4	99.60 10	90.95 192	99.93 34	99.76 11	99.73 62	99.12 199

test222					99.23 104	97.17 116	97.40 384	98.66 153	88.68 435	98.05 143	98.96 153	94.14 101			99.53 112	99.61 90

TSAR-MVS + GP.		98.38 63	98.24 65	98.81 84	99.22 106	97.25 111	98.11 311	98.29 271	97.19 76	98.99 75	99.02 140	96.22 32	99.67 149	98.52 61	98.56 183	99.51 104

SteuartSystems-ACMMP		98.90 15	98.75 17	99.36 29	99.22 106	98.43 38	99.10 69	98.87 85	97.38 60	99.35 46	99.40 47	97.78 5	99.87 79	97.77 107	99.85 6	99.78 33
Skip Steuart: Steuart Systems R&D Blog.
MVS_111021_HR		98.47 54	98.34 54	98.88 82	99.22 106	97.32 98	97.91 336	99.58 3	97.20 75	98.33 130	99.00 146	95.99 42	99.64 156	98.05 91	99.76 48	99.69 70

SPE-MVS-test		98.49 51	98.50 34	98.46 122	99.20 109	97.05 123	99.64 4	98.50 198	97.45 56	98.88 84	99.14 111	95.25 71	99.15 255	98.83 40	99.56 107	99.20 183

testdata				98.26 141	99.20 109	95.36 231		98.68 145	91.89 371	98.60 112	99.10 122	94.44 95	99.82 97	94.27 282	99.44 126	99.58 98

DVP-MVS++		99.08 3	98.89 5	99.64 4	99.17 111	99.23 8	99.69 1	98.88 78	97.32 63	99.53 37	99.47 35	97.81 3	99.94 14	98.47 63	99.72 67	99.74 50

MSC_two_6792asdad				99.62 7	99.17 111	99.08 12		98.63 161					99.94 14	98.53 55	99.80 25	99.86 12

No_MVS				99.62 7	99.17 111	99.08 12		98.63 161					99.94 14	98.53 55	99.80 25	99.86 12

PVSNet	91.96 18	96.35 204	96.15 197	96.96 266	99.17 111	92.05 370	96.08 451	98.68 145	93.69 295	97.75 178	97.80 292	88.86 257	99.69 147	94.26 283	99.01 155	99.15 194

fmvsm_s_conf0.5_n_4		98.35 68	98.50 34	97.90 189	99.16 115	95.08 247	98.75 174	99.24 20	98.39 19	99.81 13	99.52 23	92.35 127	99.90 64	99.74 13	99.51 115	98.71 257

test12				99.18 52	99.16 115	98.19 59		98.53 187		98.07 139		95.13 78	99.72 136		99.56 107	99.63 88

AdaColmap		97.15 163	96.70 171	98.48 120	99.16 115	96.69 139	98.01 323	98.89 75	94.44 254	96.83 230	98.68 201	90.69 199	99.76 130	94.36 277	99.29 142	98.98 224

PHI-MVS		98.34 70	98.06 78	99.18 52	99.15 118	98.12 66	99.04 79	99.09 45	93.32 317	98.83 90	99.10 122	96.54 24	99.83 90	97.70 115	99.76 48	99.59 94

TAPA-MVS	93.98 7	95.35 262	94.56 280	97.74 205	99.13 119	94.83 263	98.33 270	98.64 158	86.62 450	96.29 259	98.61 207	94.00 104	99.29 222	80.00 468	99.41 129	99.09 207
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MM		98.51 49	98.24 65	99.33 35	99.12 120	98.14 65	98.93 112	97.02 418	98.96 1	99.17 62	99.47 35	91.97 147	99.94 14	99.85 5	99.69 72	99.91 4

MG-MVS		97.81 97	97.60 95	98.44 125	99.12 120	95.97 181	97.75 358	98.78 121	96.89 95	98.46 118	99.22 88	93.90 106	99.68 148	94.81 257	99.52 113	99.67 79

test_vis1_n_1920		96.71 185	96.84 160	96.31 331	99.11 122	89.74 418	99.05 75	98.58 176	98.08 24	99.87 4	99.37 54	78.48 416	99.93 34	99.29 27	99.69 72	99.27 168

Anonymous20231211		94.10 353	93.26 362	96.61 298	99.11 122	94.28 290	99.01 87	98.88 78	86.43 452	92.81 381	97.57 314	81.66 388	98.68 327	94.83 255	89.02 407	96.88 347

fmvsm_s_conf0.5_n_a		98.38 63	98.42 41	98.27 138	99.09 124	95.41 224	98.86 139	99.37 9	97.69 38	99.78 17	99.61 5	92.38 126	99.91 56	99.58 23	99.43 127	99.49 111

CS-MVS		98.44 57	98.49 36	98.31 136	99.08 125	96.73 137	99.67 3	98.47 205	97.17 78	98.94 77	99.10 122	95.73 50	99.13 260	98.71 44	99.49 118	99.09 207

fmvsm_s_conf0.5_n_5		98.53 46	98.35 48	99.08 63	99.07 126	97.46 93	98.68 199	99.20 34	97.50 50	99.87 4	99.50 29	91.96 148	99.96 4	99.76 11	99.65 81	99.82 22

CNLPA		97.45 133	97.03 148	98.73 90	99.05 127	97.44 94	98.07 316	98.53 187	95.32 192	96.80 234	98.53 217	93.32 112	99.72 136	94.31 281	99.31 141	99.02 220

DPM-MVS		97.55 120	96.99 151	99.23 48	99.04 128	98.55 32	97.17 409	98.35 252	94.85 228	97.93 161	98.58 212	95.07 80	99.71 141	92.60 340	99.34 138	99.43 127

h-mvs33		96.17 213	95.62 227	97.81 197	99.03 129	94.45 280	98.64 209	98.75 127	97.48 52	98.67 104	98.72 198	89.76 222	99.86 83	97.95 94	81.59 455	99.11 202

test2506		94.44 328	93.91 326	96.04 341	99.02 130	88.99 436	99.06 73	79.47 498	96.96 92	98.36 127	99.26 80	77.21 431	99.52 185	96.78 187	99.04 152	99.59 94

ECVR-MVS		95.95 221	95.71 221	96.65 290	99.02 130	90.86 392	99.03 82	91.80 485	96.96 92	98.10 137	99.26 80	81.31 390	99.51 186	96.90 173	99.04 152	99.59 94

SymmetryMVS		97.84 95	97.58 96	98.62 99	99.01 132	96.60 143	98.94 106	98.44 214	97.86 31	98.71 101	99.08 132	91.22 178	99.80 109	97.40 150	97.53 250	99.47 115

Anonymous20240529		95.10 278	94.22 301	97.75 204	99.01 132	94.26 292	98.87 131	98.83 98	85.79 458	96.64 241	98.97 148	78.73 413	99.85 84	96.27 202	94.89 311	99.12 199

Anonymous202405211		95.28 267	94.49 283	97.67 214	99.00 134	93.75 310	98.70 193	97.04 414	90.66 404	96.49 252	98.80 179	78.13 420	99.83 90	96.21 206	95.36 310	99.44 125

DELS-MVS		98.40 62	98.20 71	98.99 70	99.00 134	97.66 80	97.75 358	98.89 75	97.71 36	98.33 130	98.97 148	94.97 83	99.88 77	98.42 69	99.76 48	99.42 130
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 90	98.48 38	96.30 332	99.00 134	89.54 425	97.43 383	98.87 85	98.16 22	99.26 57	99.38 53	96.12 37	99.64 156	98.30 75	99.77 42	99.72 59

test1111		95.94 224	95.78 215	96.41 323	98.99 137	90.12 411	99.04 79	92.45 484	96.99 91	98.03 146	99.27 79	81.40 389	99.48 195	96.87 179	99.04 152	99.63 88

thres100view900		95.38 258	94.70 272	97.41 233	98.98 138	94.92 258	98.87 131	96.90 425	95.38 187	96.61 244	96.88 380	84.29 357	99.56 173	88.11 424	96.29 288	97.76 306

thres600view7		95.49 248	94.77 267	97.67 214	98.98 138	95.02 249	98.85 144	96.90 425	95.38 187	96.63 242	96.90 379	84.29 357	99.59 166	88.65 421	96.33 284	98.40 284

MVSMamba_PlusPlus		98.31 73	98.19 73	98.67 95	98.96 140	97.36 96	99.24 36	98.57 178	94.81 229	98.99 75	98.90 164	95.22 74	99.59 166	99.15 29	99.84 11	99.07 215

test_cas_vis1_n_1920		97.38 139	97.36 117	97.45 229	98.95 141	93.25 338	99.00 89	98.53 187	97.70 37	99.77 18	99.35 60	84.71 350	99.85 84	98.57 52	99.66 78	99.26 174

tfpn200view9		95.32 265	94.62 276	97.43 231	98.94 142	94.98 254	98.68 199	96.93 423	95.33 190	96.55 248	96.53 399	84.23 361	99.56 173	88.11 424	96.29 288	97.76 306

thres400		95.38 258	94.62 276	97.65 218	98.94 142	94.98 254	98.68 199	96.93 423	95.33 190	96.55 248	96.53 399	84.23 361	99.56 173	88.11 424	96.29 288	98.40 284

MSDG		95.93 225	95.30 244	97.83 194	98.90 144	95.36 231	96.83 438	98.37 247	91.32 390	94.43 308	98.73 195	90.27 212	99.60 165	90.05 397	98.82 169	98.52 278

RPSCF		94.87 296	95.40 232	93.26 435	98.89 145	82.06 475	98.33 270	98.06 323	90.30 413	96.56 246	99.26 80	87.09 300	99.49 190	93.82 299	96.32 285	98.24 291

fmvsm_s_conf0.1_n_2		98.14 81	98.02 81	98.53 112	98.88 146	97.07 122	98.69 196	98.82 101	98.78 9	99.77 18	99.61 5	88.83 258	99.91 56	99.71 15	99.07 150	98.61 269

test_fmvsmconf_n		98.92 13	98.87 6	99.04 67	98.88 146	97.25 111	98.82 152	99.34 11	98.75 11	99.80 14	99.61 5	95.16 76	99.95 9	99.70 17	99.80 25	99.93 1

VNet		97.79 98	97.40 113	98.96 75	98.88 146	97.55 85	98.63 212	98.93 65	96.74 103	99.02 70	98.84 172	90.33 210	99.83 90	98.53 55	96.66 273	99.50 106

LFMVS		95.86 229	94.98 259	98.47 121	98.87 149	96.32 162	98.84 148	96.02 449	93.40 314	98.62 110	99.20 92	74.99 449	99.63 159	97.72 110	97.20 255	99.46 120

fmvsm_s_conf0.5_n_7		98.23 76	98.35 48	97.89 191	98.86 150	94.99 253	98.58 222	99.00 53	98.29 20	99.73 22	99.60 10	91.70 154	99.92 43	99.63 21	99.73 62	98.76 250

UA-Net		97.96 87	97.62 94	98.98 72	98.86 150	97.47 91	98.89 121	99.08 46	96.67 109	98.72 100	99.54 20	93.15 115	99.81 102	94.87 253	98.83 168	99.65 83

WTY-MVS		97.37 141	96.92 156	98.72 91	98.86 150	96.89 131	98.31 275	98.71 137	95.26 195	97.67 186	98.56 216	92.21 137	99.78 124	95.89 215	96.85 267	99.48 113

IS-MVSNet		97.22 155	96.88 157	98.25 142	98.85 153	96.36 160	99.19 50	97.97 328	95.39 186	97.23 210	98.99 147	91.11 186	98.93 297	94.60 269	98.59 180	99.47 115

VDD-MVS		95.82 232	95.23 246	97.61 222	98.84 154	93.98 301	98.68 199	97.40 385	95.02 216	97.95 157	99.34 68	74.37 455	99.78 124	98.64 48	96.80 268	99.08 211

test_fmvs1		96.42 200	96.67 174	95.66 367	98.82 155	88.53 445	98.80 161	98.20 287	96.39 124	99.64 30	99.20 92	80.35 404	99.67 149	99.04 32	99.57 99	98.78 246

CHOSEN 280x420		97.18 160	97.18 133	97.20 242	98.81 156	93.27 335	95.78 458	99.15 42	95.25 196	96.79 235	98.11 260	92.29 131	99.07 273	98.56 54	99.85 6	99.25 176

thres200		95.25 268	94.57 279	97.28 239	98.81 156	94.92 258	98.20 290	97.11 407	95.24 198	96.54 250	96.22 412	84.58 354	99.53 182	87.93 429	96.50 280	97.39 320

XVG-OURS-SEG-HR		96.51 197	96.34 190	97.02 259	98.77 158	93.76 308	97.79 355	98.50 198	95.45 181	96.94 224	99.09 130	87.87 286	99.55 180	96.76 188	95.83 305	97.74 308

XVG-OURS		96.55 196	96.41 186	96.99 260	98.75 159	93.76 308	97.50 377	98.52 190	95.67 161	96.83 230	99.30 74	88.95 255	99.53 182	95.88 216	96.26 293	97.69 311

test_yl		97.22 155	96.78 166	98.54 109	98.73 160	96.60 143	98.45 253	98.31 262	94.70 235	98.02 148	98.42 227	90.80 194	99.70 142	96.81 183	96.79 269	99.34 146

DCV-MVSNet		97.22 155	96.78 166	98.54 109	98.73 160	96.60 143	98.45 253	98.31 262	94.70 235	98.02 148	98.42 227	90.80 194	99.70 142	96.81 183	96.79 269	99.34 146

CANet		98.05 85	97.76 90	98.90 81	98.73 160	97.27 105	98.35 268	98.78 121	97.37 62	97.72 182	98.96 153	91.53 164	99.92 43	98.79 41	99.65 81	99.51 104

Vis-MVSNet (Re-imp)		96.87 176	96.55 180	97.83 194	98.73 160	95.46 222	99.20 48	98.30 269	94.96 220	96.60 245	98.87 168	90.05 215	98.59 336	93.67 304	98.60 179	99.46 120

PAPR		96.84 178	96.24 195	98.65 97	98.72 164	96.92 128	97.36 390	98.57 178	93.33 316	96.67 240	97.57 314	94.30 97	99.56 173	91.05 383	98.59 180	99.47 115

sasdasda		97.67 105	97.23 129	98.98 72	98.70 165	98.38 40	99.34 17	98.39 239	96.76 101	97.67 186	97.40 328	92.26 132	99.49 190	98.28 79	96.28 291	99.08 211

canonicalmvs		97.67 105	97.23 129	98.98 72	98.70 165	98.38 40	99.34 17	98.39 239	96.76 101	97.67 186	97.40 328	92.26 132	99.49 190	98.28 79	96.28 291	99.08 211

API-MVS		97.41 137	97.25 124	97.91 188	98.70 165	96.80 133	98.82 152	98.69 142	94.53 246	98.11 136	98.28 244	94.50 93	99.57 170	94.12 289	99.49 118	97.37 322

testing3-2		95.45 252	95.34 238	95.77 363	98.69 168	88.75 440	98.87 131	97.21 402	96.13 135	97.22 211	97.68 303	77.95 424	99.65 153	97.58 127	96.77 271	98.91 232

MAR-MVS		96.91 174	96.40 187	98.45 123	98.69 168	96.90 129	98.66 206	98.68 145	92.40 356	97.07 219	97.96 273	91.54 163	99.75 132	93.68 302	98.92 159	98.69 259
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		97.73 100	97.77 89	97.62 221	98.68 170	95.58 213	97.34 392	98.51 193	97.29 65	98.66 108	97.88 282	94.51 90	99.90 64	97.87 101	99.17 148	97.39 320

test_fmvs1_n		95.90 227	95.99 208	95.63 368	98.67 171	88.32 449	99.26 33	98.22 284	96.40 123	99.67 27	99.26 80	73.91 457	99.70 142	99.02 33	99.50 116	98.87 235

MGCFI-Net		97.62 111	97.19 132	98.92 78	98.66 172	98.20 58	99.32 22	98.38 245	96.69 107	97.58 199	97.42 327	92.10 141	99.50 189	98.28 79	96.25 294	99.08 211

alignmvs		97.56 119	97.07 144	99.01 69	98.66 172	98.37 47	98.83 150	98.06 323	96.74 103	98.00 152	97.65 305	90.80 194	99.48 195	98.37 71	96.56 277	99.19 187

Vis-MVSNet		97.42 136	97.11 141	98.34 134	98.66 172	96.23 165	99.22 42	99.00 53	96.63 111	98.04 145	99.21 90	88.05 281	99.35 211	96.01 213	99.21 145	99.45 122
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
balanced_conf03		98.45 56	98.35 48	98.74 89	98.65 175	97.55 85	99.19 50	98.60 164	96.72 106	99.35 46	98.77 188	95.06 81	99.55 180	98.95 34	99.87 1	99.12 199

EPP-MVSNet		97.46 130	97.28 122	97.99 180	98.64 176	95.38 230	99.33 21	98.31 262	93.61 305	97.19 212	99.07 136	94.05 102	99.23 242	96.89 174	98.43 197	99.37 139

ab-mvs		96.42 200	95.71 221	98.55 107	98.63 177	96.75 136	97.88 343	98.74 129	93.84 281	96.54 250	98.18 255	85.34 336	99.75 132	95.93 214	96.35 283	99.15 194

PCF-MVS	93.45 11	94.68 305	93.43 357	98.42 129	98.62 178	96.77 135	95.48 464	98.20 287	84.63 463	93.34 365	98.32 241	88.55 266	99.81 102	84.80 452	98.96 158	98.68 261
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
xiu_mvs_v2_base		97.66 107	97.70 92	97.56 225	98.61 179	95.46 222	97.44 380	98.46 206	97.15 80	98.65 109	98.15 257	94.33 96	99.80 109	97.84 104	98.66 177	97.41 318

sss		97.39 138	96.98 153	98.61 101	98.60 180	96.61 142	98.22 287	98.93 65	93.97 274	98.01 151	98.48 222	91.98 145	99.85 84	96.45 197	98.15 221	99.39 135

Test_1112_low_res		96.34 205	95.66 226	98.36 133	98.56 181	95.94 184	97.71 361	98.07 318	92.10 366	94.79 295	97.29 336	91.75 153	99.56 173	94.17 287	96.50 280	99.58 98

1112_ss		96.63 190	96.00 207	98.50 117	98.56 181	96.37 159	98.18 298	98.10 311	92.92 336	94.84 291	98.43 225	92.14 139	99.58 169	94.35 278	96.51 279	99.56 100

BH-untuned		95.95 221	95.72 218	96.65 290	98.55 183	92.26 361	98.23 286	97.79 345	93.73 289	94.62 298	98.01 268	88.97 254	99.00 286	93.04 321	98.51 188	98.68 261

fmvsm_s_conf0.1_n		98.18 80	98.21 69	98.11 165	98.54 184	95.24 239	98.87 131	99.24 20	97.50 50	99.70 26	99.67 1	91.33 171	99.89 68	99.47 25	99.54 110	99.21 182

LS3D		97.16 162	96.66 175	98.68 94	98.53 185	97.19 115	98.93 112	98.90 73	92.83 340	95.99 269	99.37 54	92.12 140	99.87 79	93.67 304	99.57 99	98.97 225

guyue		97.57 117	97.37 116	98.20 147	98.50 186	95.86 197	98.89 121	97.03 415	97.29 65	98.73 98	98.90 164	89.41 236	99.32 215	98.68 45	98.86 165	99.42 130

fmvsm_s_conf0.5_n_6		98.65 26	98.55 29	98.95 77	98.50 186	97.30 101	98.79 169	99.16 40	98.14 23	99.86 8	99.41 46	93.71 108	99.91 56	99.71 15	99.64 86	99.65 83

hse-mvs2		95.71 237	95.30 244	96.93 268	98.50 186	93.53 319	98.36 267	98.10 311	97.48 52	98.67 104	97.99 270	89.76 222	99.02 283	97.95 94	80.91 461	98.22 293

AUN-MVS		94.53 319	93.73 342	96.92 271	98.50 186	93.52 320	98.34 269	98.10 311	93.83 283	95.94 273	97.98 272	85.59 331	99.03 279	94.35 278	80.94 460	98.22 293

baseline1		95.84 230	95.12 252	98.01 178	98.49 190	95.98 176	98.73 184	97.03 415	95.37 189	96.22 260	98.19 254	89.96 218	99.16 251	94.60 269	87.48 421	98.90 233

E3new		97.55 120	97.35 118	98.16 151	98.48 191	95.85 198	98.55 235	98.41 230	95.42 184	98.06 141	99.12 117	92.23 135	99.24 238	97.43 146	98.45 193	99.39 135

SSM_0404		97.26 152	97.00 149	98.03 174	98.46 192	95.99 175	98.62 215	98.44 214	94.77 232	97.24 209	98.93 158	91.22 178	99.28 224	96.54 192	98.74 172	98.84 238

HY-MVS	93.96 8	96.82 179	96.23 196	98.57 104	98.46 192	97.00 124	98.14 304	98.21 285	93.95 275	96.72 239	97.99 270	91.58 158	99.76 130	94.51 273	96.54 278	98.95 228

viewcassd2359sk11		97.53 124	97.32 120	98.16 151	98.45 194	95.83 200	98.57 231	98.42 229	95.52 177	98.07 139	99.12 117	91.81 152	99.25 231	97.46 144	98.48 192	99.41 133

viewdifsd2359ckpt09		97.13 164	96.79 164	98.14 155	98.43 195	95.90 190	98.52 238	98.37 247	94.32 257	97.33 204	98.86 170	90.23 214	99.16 251	96.81 183	98.25 215	99.36 143

viewdifsd2359ckpt13		97.24 154	96.97 154	98.06 172	98.43 195	95.77 206	98.59 218	98.34 255	94.81 229	97.60 197	98.94 156	90.78 198	99.09 270	96.93 169	98.33 208	99.32 153

ETV-MVS		97.96 87	97.81 88	98.40 131	98.42 197	97.27 105	98.73 184	98.55 183	96.84 96	98.38 126	97.44 324	95.39 60	99.35 211	97.62 120	98.89 161	98.58 275

casdiffmvs_mvg		97.72 101	97.48 107	98.44 125	98.42 197	96.59 147	98.92 114	98.44 214	96.20 132	97.76 176	99.20 92	91.66 157	99.23 242	98.27 82	98.41 203	99.49 111
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		97.47 129	97.25 124	98.14 155	98.41 199	95.84 199	98.57 231	98.43 225	95.55 173	97.97 155	99.12 117	91.26 175	99.15 255	97.42 148	98.53 186	99.43 127

tttt0517		96.07 216	95.51 230	97.78 199	98.41 199	94.84 261	99.28 30	94.33 472	94.26 260	97.64 192	98.64 206	84.05 365	99.47 199	95.34 237	97.60 242	99.03 219

E2		97.48 126	97.25 124	98.16 151	98.40 201	95.79 204	98.58 222	98.44 214	95.58 166	98.00 152	99.14 111	91.21 182	99.24 238	97.50 139	98.43 197	99.45 122

viewdifsd2359ckpt07		97.20 158	97.05 146	97.65 218	98.40 201	94.33 289	98.39 266	98.43 225	95.67 161	97.66 190	99.08 132	90.04 216	99.32 215	97.47 143	98.29 212	99.31 154

reproduce_monomvs		94.77 301	94.67 274	95.08 388	98.40 201	89.48 426	98.80 161	98.64 158	97.57 46	93.21 369	97.65 305	80.57 402	98.83 313	97.72 110	89.47 399	96.93 337

E3		97.48 126	97.25 124	98.16 151	98.38 204	95.79 204	98.58 222	98.44 214	95.58 166	98.00 152	99.14 111	91.25 176	99.24 238	97.50 139	98.44 194	99.45 122

EIA-MVS		97.75 99	97.58 96	98.27 138	98.38 204	96.44 154	99.01 87	98.60 164	95.88 148	97.26 208	97.53 318	94.97 83	99.33 214	97.38 153	99.20 146	99.05 216

thisisatest0530		96.01 218	95.36 237	97.97 185	98.38 204	95.52 219	98.88 128	94.19 474	94.04 266	97.64 192	98.31 242	83.82 372	99.46 200	95.29 242	97.70 239	98.93 230

KinetiMVS		97.48 126	97.05 146	98.78 86	98.37 207	97.30 101	98.99 92	98.70 140	97.18 77	99.02 70	99.01 144	87.50 294	99.67 149	95.33 238	99.33 140	99.37 139

FE-MVS		95.62 243	94.90 263	97.78 199	98.37 207	94.92 258	97.17 409	97.38 387	90.95 401	97.73 181	97.70 298	85.32 338	99.63 159	91.18 375	98.33 208	98.79 242

GeoE		96.58 194	96.07 201	98.10 166	98.35 209	95.89 195	99.34 17	98.12 305	93.12 328	96.09 265	98.87 168	89.71 225	98.97 287	92.95 324	98.08 224	99.43 127

xiu_mvs_v1_base_debu		97.60 112	97.56 99	97.72 206	98.35 209	95.98 176	97.86 346	98.51 193	97.13 82	99.01 72	98.40 229	91.56 160	99.80 109	98.53 55	98.68 173	97.37 322

xiu_mvs_v1_base		97.60 112	97.56 99	97.72 206	98.35 209	95.98 176	97.86 346	98.51 193	97.13 82	99.01 72	98.40 229	91.56 160	99.80 109	98.53 55	98.68 173	97.37 322

xiu_mvs_v1_base_debi		97.60 112	97.56 99	97.72 206	98.35 209	95.98 176	97.86 346	98.51 193	97.13 82	99.01 72	98.40 229	91.56 160	99.80 109	98.53 55	98.68 173	97.37 322

baseline		97.64 108	97.44 110	98.25 142	98.35 209	96.20 166	99.00 89	98.32 258	96.33 129	98.03 146	99.17 104	91.35 170	99.16 251	98.10 87	98.29 212	99.39 135

balanced_ft_v1		97.54 123	97.38 115	98.02 176	98.34 214	95.58 213	99.32 22	98.40 233	95.88 148	98.43 125	98.65 205	88.95 255	99.59 166	98.94 35	99.48 121	98.90 233

mvsmamba		97.25 153	96.99 151	98.02 176	98.34 214	95.54 218	99.18 54	97.47 376	95.04 212	98.15 133	98.57 215	89.46 233	99.31 219	97.68 117	99.01 155	99.22 180

BH-w/o		95.38 258	95.08 254	96.26 334	98.34 214	91.79 373	97.70 362	97.43 383	92.87 338	94.24 321	97.22 342	88.66 261	98.84 310	91.55 371	97.70 239	98.16 296

EC-MVSNet		98.21 79	98.11 76	98.49 119	98.34 214	97.26 110	99.61 5	98.43 225	96.78 99	98.87 85	98.84 172	93.72 107	99.01 285	98.91 37	99.50 116	99.19 187

test_fmvsmvis_n_1920		98.44 57	98.51 32	98.23 144	98.33 218	96.15 169	98.97 96	99.15 42	98.55 16	98.45 121	99.55 18	94.26 99	99.97 1	99.65 18	99.66 78	98.57 276

MVS_Test		97.28 150	97.00 149	98.13 160	98.33 218	95.97 181	98.74 178	98.07 318	94.27 259	98.44 123	98.07 262	92.48 124	99.26 227	96.43 198	98.19 220	99.16 193

casdiffmvs		97.63 110	97.41 112	98.28 137	98.33 218	96.14 170	98.82 152	98.32 258	96.38 125	97.95 157	99.21 90	91.23 177	99.23 242	98.12 86	98.37 205	99.48 113
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		97.58 116	97.40 113	98.13 160	98.32 221	95.81 203	98.06 317	98.37 247	96.20 132	98.74 96	98.89 166	91.31 173	99.25 231	98.16 85	98.52 187	99.34 146
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		95.92 226	95.32 242	97.69 210	98.32 221	94.64 270	98.19 293	97.45 381	94.56 244	96.03 267	98.61 207	85.02 341	99.12 263	90.68 388	99.06 151	99.30 158

E5new		97.37 141	97.16 135	97.98 181	98.30 223	95.41 224	98.87 131	98.45 210	95.56 168	97.84 168	99.19 99	90.39 206	99.25 231	97.61 123	98.22 216	99.29 161

E5		97.37 141	97.16 135	97.98 181	98.30 223	95.41 224	98.87 131	98.45 210	95.56 168	97.84 168	99.19 99	90.39 206	99.25 231	97.61 123	98.22 216	99.29 161

viewmacassd2359aftdt		97.32 148	97.07 144	98.08 168	98.30 223	95.69 210	98.62 215	98.44 214	95.56 168	97.86 167	99.22 88	89.91 219	99.14 258	97.29 156	98.43 197	99.42 130

GDP-MVS		97.64 108	97.28 122	98.71 92	98.30 223	97.33 97	99.05 75	98.52 190	96.34 127	98.80 91	99.05 138	89.74 224	99.51 186	96.86 182	98.86 165	99.28 167

VortexMVS		95.95 221	95.79 214	96.42 322	98.29 227	93.96 302	98.68 199	98.31 262	96.02 140	94.29 317	97.57 314	89.47 231	98.37 366	97.51 138	91.93 362	96.94 336

Fast-Effi-MVS+		96.28 210	95.70 223	98.03 174	98.29 227	95.97 181	98.58 222	98.25 281	91.74 374	95.29 284	97.23 341	91.03 189	99.15 255	92.90 326	97.96 228	98.97 225

E6new		97.37 141	97.16 135	97.98 181	98.28 229	95.40 227	98.87 131	98.45 210	95.55 173	97.84 168	99.20 92	90.44 204	99.25 231	97.61 123	98.22 216	99.29 161

E6		97.37 141	97.16 135	97.98 181	98.28 229	95.40 227	98.87 131	98.45 210	95.55 173	97.84 168	99.20 92	90.44 204	99.25 231	97.61 123	98.22 216	99.29 161

E4		97.37 141	97.13 139	98.12 163	98.27 231	95.70 209	98.59 218	98.44 214	95.56 168	97.80 173	99.18 102	90.57 201	99.26 227	97.45 145	98.28 214	99.40 134

diffmvs_AUTHOR		97.59 115	97.44 110	98.01 178	98.26 232	95.47 221	98.12 307	98.36 251	96.38 125	98.84 87	99.10 122	91.13 183	99.26 227	98.24 83	98.56 183	99.30 158

BP-MVS1		97.82 96	97.51 104	98.76 88	98.25 233	97.39 95	99.15 57	97.68 349	96.69 107	98.47 117	99.10 122	90.29 211	99.51 186	98.60 50	99.35 137	99.37 139

mvsany_test1		97.69 104	97.70 92	97.66 217	98.24 234	94.18 296	97.53 374	97.53 370	95.52 177	99.66 28	99.51 26	94.30 97	99.56 173	98.38 70	98.62 178	99.23 178

UGNet		96.78 181	96.30 192	98.19 150	98.24 234	95.89 195	98.88 128	98.93 65	97.39 59	96.81 233	97.84 286	82.60 379	99.90 64	96.53 194	99.49 118	98.79 242
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		96.06 217	95.72 218	97.08 255	98.23 236	95.93 187	98.73 184	98.27 272	94.86 226	95.07 286	98.09 261	88.21 274	98.54 339	96.59 190	93.46 337	96.79 357

ET-MVSNet_ETH3D		94.13 349	92.98 367	97.58 223	98.22 237	96.20 166	97.31 395	95.37 460	94.53 246	79.56 479	97.63 310	86.51 309	97.53 436	96.91 170	90.74 379	99.02 220

FA-MVS(test-final)		96.41 203	95.94 209	97.82 196	98.21 238	95.20 241	97.80 353	97.58 360	93.21 322	97.36 203	97.70 298	89.47 231	99.56 173	94.12 289	97.99 226	98.71 257

GBi-Net		94.49 323	93.80 335	96.56 305	98.21 238	95.00 250	98.82 152	98.18 292	92.46 350	94.09 328	97.07 355	81.16 392	97.95 412	92.08 354	92.14 359	96.72 365

test1		94.49 323	93.80 335	96.56 305	98.21 238	95.00 250	98.82 152	98.18 292	92.46 350	94.09 328	97.07 355	81.16 392	97.95 412	92.08 354	92.14 359	96.72 365

FMVSNet2		94.47 326	93.61 348	97.04 258	98.21 238	96.43 155	98.79 169	98.27 272	92.46 350	93.50 358	97.09 352	81.16 392	98.00 409	91.09 378	91.93 362	96.70 369

mamba_0408		96.81 180	96.38 188	98.09 167	98.19 242	95.90 190	95.69 459	98.32 258	94.51 249	96.75 236	98.73 195	90.99 190	99.27 226	95.83 218	98.43 197	99.10 204

SSM_04072		96.71 185	96.38 188	97.68 212	98.19 242	95.90 190	95.69 459	98.32 258	94.51 249	96.75 236	98.73 195	90.99 190	98.02 406	95.83 218	98.43 197	99.10 204

SSM_0407		97.17 161	96.87 158	98.08 168	98.19 242	95.90 190	98.52 238	98.44 214	94.77 232	96.75 236	98.93 158	91.22 178	99.22 246	96.54 192	98.43 197	99.10 204

viewmambaseed2359dif		97.01 170	96.84 160	97.51 227	98.19 242	94.21 295	98.16 300	98.23 283	93.61 305	97.78 174	99.13 114	90.79 197	99.18 250	97.24 157	98.40 204	99.15 194

Effi-MVS+		97.12 165	96.69 172	98.39 132	98.19 242	96.72 138	97.37 388	98.43 225	93.71 292	97.65 191	98.02 266	92.20 138	99.25 231	96.87 179	97.79 234	99.19 187

mvs_anonymous		96.70 187	96.53 182	97.18 245	98.19 242	93.78 307	98.31 275	98.19 289	94.01 271	94.47 303	98.27 247	92.08 143	98.46 347	97.39 152	97.91 229	99.31 154

ETVMVS		94.50 322	93.44 356	97.68 212	98.18 248	95.35 233	98.19 293	97.11 407	93.73 289	96.40 256	95.39 437	74.53 452	98.84 310	91.10 377	96.31 286	98.84 238

LCM-MVSNet-Re		95.22 270	95.32 242	94.91 393	98.18 248	87.85 455	98.75 174	95.66 456	95.11 207	88.96 440	96.85 383	90.26 213	97.65 429	95.65 229	98.44 194	99.22 180

FMVSNet3		94.97 289	94.26 299	97.11 253	98.18 248	96.62 140	98.56 234	98.26 280	93.67 299	94.09 328	97.10 348	84.25 359	98.01 407	92.08 354	92.14 359	96.70 369

myMVS_eth3d28		95.12 276	94.62 276	96.64 294	98.17 251	92.17 362	98.02 322	97.32 391	95.41 185	96.22 260	96.05 418	78.01 422	99.13 260	95.22 246	97.16 256	98.60 270

CANet_DTU		96.96 172	96.55 180	98.21 145	98.17 251	96.07 174	97.98 327	98.21 285	97.24 72	97.13 214	98.93 158	86.88 305	99.91 56	95.00 251	99.37 136	98.66 265

thisisatest0515		95.61 246	94.89 264	97.76 203	98.15 253	95.15 244	96.77 439	94.41 470	92.95 335	97.18 213	97.43 325	84.78 347	99.45 201	94.63 265	97.73 238	98.68 261

AstraMVS		97.34 147	97.24 128	97.65 218	98.13 254	94.15 297	98.94 106	96.25 448	97.47 54	98.60 112	99.28 76	89.67 226	99.41 205	98.73 43	98.07 225	99.38 138

IterMVS-LS		95.46 250	95.21 247	96.22 335	98.12 255	93.72 313	98.32 274	98.13 304	93.71 292	94.26 319	97.31 335	92.24 134	98.10 392	94.63 265	90.12 387	96.84 353
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cl22		94.68 305	94.19 303	96.13 338	98.11 256	93.60 315	96.94 423	98.31 262	92.43 354	93.32 366	96.87 382	86.51 309	98.28 379	94.10 291	91.16 374	96.51 405

viewdifsd2359ckpt11		96.30 206	96.13 198	96.81 277	98.10 257	92.10 366	98.49 249	98.40 233	96.02 140	97.61 194	99.31 71	86.37 315	99.29 222	97.52 135	93.36 343	99.04 217

viewmsd2359difaftdt		96.30 206	96.13 198	96.81 277	98.10 257	92.10 366	98.49 249	98.40 233	96.02 140	97.61 194	99.31 71	86.37 315	99.30 220	97.52 135	93.37 342	99.04 217

VDDNet		95.36 261	94.53 281	97.86 192	98.10 257	95.13 245	98.85 144	97.75 347	90.46 408	98.36 127	99.39 48	73.27 459	99.64 156	97.98 93	96.58 276	98.81 241

testing3		93.19 376	92.48 380	95.30 381	98.07 260	92.27 359	98.64 209	97.17 405	93.94 277	93.98 334	97.04 363	67.97 468	96.01 465	88.40 422	97.14 257	97.63 313

MVSFormer		97.57 117	97.49 105	97.84 193	98.07 260	95.76 207	99.47 7	98.40 233	94.98 218	98.79 92	98.83 176	92.34 128	98.41 359	96.91 170	99.59 95	99.34 146

lupinMVS		97.44 134	97.22 131	98.12 163	98.07 260	95.76 207	97.68 363	97.76 346	94.50 251	98.79 92	98.61 207	92.34 128	99.30 220	97.58 127	99.59 95	99.31 154

MGCNet		98.23 76	97.91 86	99.21 49	98.06 263	97.96 72	98.58 222	95.51 458	98.58 14	98.87 85	99.26 80	92.99 117	99.95 9	99.62 22	99.67 75	99.73 55

TAMVS		97.02 169	96.79 164	97.70 209	98.06 263	95.31 236	98.52 238	98.31 262	93.95 275	97.05 221	98.61 207	93.49 110	98.52 341	95.33 238	97.81 233	99.29 161

UBG		95.32 265	94.72 271	97.13 249	98.05 265	93.26 336	97.87 344	97.20 403	94.96 220	96.18 263	95.66 434	80.97 396	99.35 211	94.47 275	97.08 258	98.78 246

CDS-MVSNet		96.99 171	96.69 172	97.90 189	98.05 265	95.98 176	98.20 290	98.33 257	93.67 299	96.95 223	98.49 221	93.54 109	98.42 352	95.24 245	97.74 237	99.31 154
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Elysia		96.64 188	96.02 205	98.51 114	98.04 267	97.30 101	98.74 178	98.60 164	95.04 212	97.91 163	98.84 172	83.59 374	99.48 195	94.20 285	99.25 143	98.75 251

StellarMVS		96.64 188	96.02 205	98.51 114	98.04 267	97.30 101	98.74 178	98.60 164	95.04 212	97.91 163	98.84 172	83.59 374	99.48 195	94.20 285	99.25 143	98.75 251

WBMVS		94.56 315	94.04 313	96.10 340	98.03 269	93.08 346	97.82 352	98.18 292	94.02 268	93.77 347	96.82 385	81.28 391	98.34 368	95.47 236	91.00 377	96.88 347

SD_0403		94.28 339	94.46 286	93.73 426	98.02 270	85.32 465	98.31 275	98.40 233	94.75 234	93.59 350	98.16 256	89.01 249	96.54 456	82.32 461	97.58 244	99.34 146

testing222		94.12 351	93.03 366	97.37 238	98.02 270	94.66 268	97.94 332	96.65 439	94.63 241	95.78 274	95.76 426	71.49 461	98.92 298	91.17 376	95.88 303	98.52 278

ADS-MVSNet2		94.58 314	94.40 293	95.11 386	98.00 272	88.74 441	96.04 452	97.30 393	90.15 414	96.47 253	96.64 396	87.89 284	97.56 435	90.08 395	97.06 259	99.02 220

ADS-MVSNet		95.00 283	94.45 289	96.63 295	98.00 272	91.91 372	96.04 452	97.74 348	90.15 414	96.47 253	96.64 396	87.89 284	98.96 291	90.08 395	97.06 259	99.02 220

icg_test_0407_2		96.56 195	96.50 183	96.73 282	97.99 274	92.82 352	97.18 406	98.27 272	95.16 200	97.30 205	98.79 181	91.53 164	98.10 392	94.74 259	97.54 246	99.27 168

IMVS_0407		96.74 182	96.64 176	97.05 257	97.99 274	92.82 352	98.45 253	98.27 272	95.16 200	97.30 205	98.79 181	91.53 164	99.06 274	94.74 259	97.54 246	99.27 168

IMVS_0404		95.82 232	95.52 228	96.73 282	97.99 274	92.82 352	97.23 399	98.27 272	95.16 200	94.31 315	98.79 181	85.63 329	98.10 392	94.74 259	97.54 246	99.27 168

IMVS_0403		96.74 182	96.61 177	97.12 251	97.99 274	92.82 352	98.47 251	98.27 272	95.16 200	97.13 214	98.79 181	91.44 167	99.26 227	94.74 259	97.54 246	99.27 168

IterMVS		94.09 354	93.85 332	94.80 402	97.99 274	90.35 408	97.18 406	98.12 305	93.68 297	92.46 396	97.34 331	84.05 365	97.41 439	92.51 347	91.33 370	96.62 380
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PVSNet_0	88.72 19	91.28 400	90.03 405	95.00 390	97.99 274	87.29 458	94.84 470	98.50 198	92.06 367	89.86 432	95.19 440	79.81 407	99.39 209	92.27 351	69.79 486	98.33 289

tt0805		94.54 317	93.85 332	96.63 295	97.98 280	93.06 347	98.77 173	97.84 337	93.67 299	93.80 345	98.04 265	76.88 438	98.96 291	94.79 258	92.86 350	97.86 305

IterMVS-SCA-FT		94.11 352	93.87 330	94.85 398	97.98 280	90.56 403	97.18 406	98.11 308	93.75 286	92.58 389	97.48 320	83.97 367	97.41 439	92.48 349	91.30 371	96.58 389

testing11		95.00 283	94.28 296	97.16 247	97.96 282	93.36 329	98.09 314	97.06 413	94.94 224	95.33 283	96.15 414	76.89 437	99.40 206	95.77 224	96.30 287	98.72 254

testing91		94.98 287	94.25 300	97.20 242	97.94 283	93.41 324	98.00 325	97.58 360	94.99 217	95.45 279	96.04 419	77.20 432	99.42 204	94.97 252	96.02 301	98.78 246

testing99		94.83 297	94.08 311	97.07 256	97.94 283	93.13 342	98.10 313	97.17 405	94.86 226	95.34 280	96.00 423	76.31 440	99.40 206	95.08 249	95.90 302	98.68 261

EI-MVSNet		95.96 220	95.83 213	96.36 327	97.93 285	93.70 314	98.12 307	98.27 272	93.70 294	95.07 286	99.02 140	92.23 135	98.54 339	94.68 263	93.46 337	96.84 353

CVMVSNet		95.43 254	96.04 203	93.57 429	97.93 285	83.62 469	98.12 307	98.59 171	95.68 160	96.56 246	99.02 140	87.51 292	97.51 437	93.56 308	97.44 251	99.60 92

RRT-MVS		97.03 168	96.78 166	97.77 202	97.90 287	94.34 287	99.12 64	98.35 252	95.87 150	98.06 141	98.70 199	86.45 313	99.63 159	98.04 92	98.54 185	99.35 144

PMMVS		96.60 191	96.33 191	97.41 233	97.90 287	93.93 303	97.35 391	98.41 230	92.84 339	97.76 176	97.45 323	91.10 187	99.20 247	96.26 203	97.91 229	99.11 202

Effi-MVS+-dtu		96.29 208	96.56 179	95.51 372	97.89 289	90.22 410	98.80 161	98.10 311	96.57 114	96.45 255	96.66 393	90.81 193	98.91 300	95.72 225	97.99 226	97.40 319

QAPM		96.29 208	95.40 232	98.96 75	97.85 290	97.60 84	99.23 38	98.93 65	89.76 421	93.11 375	99.02 140	89.11 246	99.93 34	91.99 359	99.62 90	99.34 146

UWE-MVS		94.30 335	93.89 329	95.53 371	97.83 291	88.95 437	97.52 376	93.25 478	94.44 254	96.63 242	97.07 355	78.70 414	99.28 224	91.99 359	97.56 245	98.36 287

3Dnovator+	94.38 6	97.43 135	96.78 166	99.38 23	97.83 291	98.52 33	99.37 13	98.71 137	97.09 85	92.99 378	99.13 114	89.36 238	99.89 68	96.97 166	99.57 99	99.71 63

ACMH+	92.99 14	94.30 335	93.77 338	95.88 355	97.81 293	92.04 371	98.71 189	98.37 247	93.99 273	90.60 425	98.47 223	80.86 399	99.05 275	92.75 333	92.40 356	96.55 395

3Dnovator	94.51 5	97.46 130	96.93 155	99.07 64	97.78 294	97.64 81	99.35 16	99.06 48	97.02 87	93.75 348	99.16 107	89.25 241	99.92 43	97.22 159	99.75 54	99.64 86

test_vis1_n		95.47 249	95.13 250	96.49 313	97.77 295	90.41 406	99.27 32	98.11 308	96.58 112	99.66 28	99.18 102	67.00 471	99.62 163	99.21 28	99.40 132	99.44 125

miper_lstm_enhance		94.33 333	94.07 312	95.11 386	97.75 296	90.97 388	97.22 401	98.03 325	91.67 378	92.76 383	96.97 371	90.03 217	97.78 425	92.51 347	89.64 393	96.56 393

c3_l		94.79 299	94.43 291	95.89 354	97.75 296	93.12 344	97.16 411	98.03 325	92.23 362	93.46 361	97.05 362	91.39 168	98.01 407	93.58 307	89.21 403	96.53 398

TR-MVS		94.94 294	94.20 302	97.17 246	97.75 296	94.14 298	97.59 371	97.02 418	92.28 361	95.75 275	97.64 308	83.88 369	98.96 291	89.77 401	96.15 298	98.40 284

Fast-Effi-MVS+-dtu		95.87 228	95.85 212	95.91 352	97.74 299	91.74 376	98.69 196	98.15 301	95.56 168	94.92 289	97.68 303	88.98 253	98.79 318	93.19 316	97.78 235	97.20 326

test_fmvsmconf0.1_n		98.58 36	98.44 40	98.99 70	97.73 300	97.15 118	98.84 148	98.97 57	98.75 11	99.43 41	99.54 20	93.29 113	99.93 34	99.64 20	99.79 35	99.89 6

MIMVSNet		93.26 373	92.21 384	96.41 323	97.73 300	93.13 342	95.65 461	97.03 415	91.27 394	94.04 331	96.06 417	75.33 445	97.19 442	86.56 436	96.23 296	98.92 231

miper_ehance_all_eth		95.01 282	94.69 273	95.97 349	97.70 302	93.31 332	97.02 419	98.07 318	92.23 362	93.51 357	96.96 373	91.85 149	98.15 387	93.68 302	91.16 374	96.44 413

dmvs_re		94.48 325	94.18 305	95.37 378	97.68 303	90.11 412	98.54 237	97.08 409	94.56 244	94.42 309	97.24 340	84.25 359	97.76 426	91.02 384	92.83 351	98.24 291

SCA		95.46 250	95.13 250	96.46 319	97.67 304	91.29 384	97.33 393	97.60 359	94.68 238	96.92 227	97.10 348	83.97 367	98.89 304	92.59 342	98.32 211	99.20 183

ACMP	93.49 10	95.34 263	94.98 259	96.43 321	97.67 304	93.48 321	98.73 184	98.44 214	94.94 224	92.53 392	98.53 217	84.50 356	99.14 258	95.48 235	94.00 325	96.66 375
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
fmvsm_s_conf0.1_n_a		98.08 82	98.04 80	98.21 145	97.66 306	95.39 229	98.89 121	99.17 38	97.24 72	99.76 20	99.67 1	91.13 183	99.88 77	99.39 26	99.41 129	99.35 144

eth_miper_zixun_eth		94.68 305	94.41 292	95.47 374	97.64 307	91.71 377	96.73 442	98.07 318	92.71 343	93.64 349	97.21 343	90.54 202	98.17 386	93.38 310	89.76 391	96.54 396

ACMH	92.88 16	94.55 316	93.95 323	96.34 329	97.63 308	93.26 336	98.81 160	98.49 203	93.43 313	89.74 433	98.53 217	81.91 383	99.08 272	93.69 301	93.30 345	96.70 369
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMM	93.85 9	95.69 240	95.38 236	96.61 298	97.61 309	93.84 306	98.91 116	98.44 214	95.25 196	94.28 318	98.47 223	86.04 324	99.12 263	95.50 234	93.95 327	96.87 350
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mmtdpeth		93.12 379	92.61 375	94.63 408	97.60 310	89.68 422	99.21 45	97.32 391	94.02 268	97.72 182	94.42 448	77.01 436	99.44 202	99.05 31	77.18 472	94.78 456

Patchmatch-test		94.42 329	93.68 346	96.63 295	97.60 310	91.76 374	94.83 471	97.49 375	89.45 427	94.14 326	97.10 348	88.99 250	98.83 313	85.37 446	98.13 222	99.29 161

cl____		94.51 321	94.01 318	96.02 342	97.58 312	93.40 326	97.05 417	97.96 330	91.73 376	92.76 383	97.08 354	89.06 248	98.13 389	92.61 337	90.29 385	96.52 401

tpm cat1		93.36 368	92.80 370	95.07 389	97.58 312	87.97 453	96.76 440	97.86 336	82.17 470	93.53 354	96.04 419	86.13 320	99.13 260	89.24 413	95.87 304	98.10 298

MVS-HIRNet		89.46 428	88.40 426	92.64 441	97.58 312	82.15 474	94.16 480	93.05 482	75.73 482	90.90 421	82.52 485	79.42 410	98.33 370	83.53 457	98.68 173	97.43 317

PatchmatchNet		95.71 237	95.52 228	96.29 333	97.58 312	90.72 396	96.84 437	97.52 371	94.06 265	97.08 217	96.96 373	89.24 242	98.90 303	92.03 358	98.37 205	99.26 174
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DIV-MVS_self_test		94.52 320	94.03 315	95.99 345	97.57 316	93.38 327	97.05 417	97.94 331	91.74 374	92.81 381	97.10 348	89.12 245	98.07 400	92.60 340	90.30 384	96.53 398

tpmrst		95.63 242	95.69 224	95.44 376	97.54 317	88.54 444	96.97 421	97.56 363	93.50 309	97.52 201	96.93 377	89.49 229	99.16 251	95.25 244	96.42 282	98.64 267

FMVSNet1		93.19 376	92.07 385	96.56 305	97.54 317	95.00 250	98.82 152	98.18 292	90.38 411	92.27 403	97.07 355	73.68 458	97.95 412	89.36 411	91.30 371	96.72 365

miper_enhance_ethall		95.10 278	94.75 269	96.12 339	97.53 319	93.73 312	96.61 445	98.08 316	92.20 365	93.89 337	96.65 395	92.44 125	98.30 375	94.21 284	91.16 374	96.34 416

CLD-MVS		95.62 243	95.34 238	96.46 319	97.52 320	93.75 310	97.27 398	98.46 206	95.53 176	94.42 309	98.00 269	86.21 319	98.97 287	96.25 205	94.37 312	96.66 375
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
LuminaMVS		97.49 125	97.18 133	98.42 129	97.50 321	97.15 118	98.45 253	97.68 349	96.56 115	98.68 103	98.78 185	89.84 221	99.32 215	98.60 50	98.57 182	98.79 242

MDTV_nov1_ep13			95.40 232		97.48 322	88.34 448	96.85 436	97.29 394	93.74 288	97.48 202	97.26 337	89.18 243	99.05 275	91.92 362	97.43 252

IB-MVS	91.98 17	93.27 372	91.97 387	97.19 244	97.47 323	93.41 324	97.09 414	95.99 450	93.32 317	92.47 395	95.73 429	78.06 421	99.53 182	94.59 271	82.98 449	98.62 268
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		94.60 311	94.36 294	95.33 380	97.46 324	88.60 443	96.88 434	97.68 349	91.29 392	93.80 345	96.42 403	88.58 262	99.24 238	91.06 381	96.04 300	98.17 295

LPG-MVS_test		95.62 243	95.34 238	96.47 316	97.46 324	93.54 317	98.99 92	98.54 185	94.67 239	94.36 312	98.77 188	85.39 333	99.11 265	95.71 226	94.15 320	96.76 360

LGP-MVS_train				96.47 316	97.46 324	93.54 317		98.54 185	94.67 239	94.36 312	98.77 188	85.39 333	99.11 265	95.71 226	94.15 320	96.76 360

test_vis1_rt		91.29 399	90.65 397	93.19 437	97.45 327	86.25 462	98.57 231	90.90 489	93.30 319	86.94 454	93.59 457	62.07 479	99.11 265	97.48 142	95.58 308	94.22 461

jason		97.32 148	97.08 143	98.06 172	97.45 327	95.59 212	97.87 344	97.91 334	94.79 231	98.55 115	98.83 176	91.12 185	99.23 242	97.58 127	99.60 93	99.34 146
jason: jason.
HQP_MVS		96.14 215	95.90 211	96.85 274	97.42 329	94.60 276	98.80 161	98.56 181	97.28 67	95.34 280	98.28 244	87.09 300	99.03 279	96.07 207	94.27 314	96.92 338

plane_prior7					97.42 329	94.63 271

ITE_SJBPF				95.44 376	97.42 329	91.32 383		97.50 373	95.09 210	93.59 350	98.35 235	81.70 387	98.88 306	89.71 403	93.39 341	96.12 426

LTVRE_ROB	92.95 15	94.60 311	93.90 327	96.68 289	97.41 332	94.42 282	98.52 238	98.59 171	91.69 377	91.21 418	98.35 235	84.87 344	99.04 278	91.06 381	93.44 340	96.60 383
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		92.55 387	92.61 375	92.38 443	97.39 333	83.41 470	97.91 336	97.46 377	93.16 325	93.42 362	95.37 438	84.75 348	96.12 463	77.00 478	96.99 261	97.60 314

myMVS_eth3d		92.73 384	92.01 386	94.89 395	97.39 333	90.94 389	97.91 336	97.46 377	93.16 325	93.42 362	95.37 438	68.09 467	96.12 463	88.34 423	96.99 261	97.60 314

plane_prior1					97.37 335

plane_prior6					97.35 336	94.61 274						87.09 300

dp		94.15 348	93.90 327	94.90 394	97.31 337	86.82 460	96.97 421	97.19 404	91.22 396	96.02 268	96.61 398	85.51 332	99.02 283	90.00 399	94.30 313	98.85 236

NP-MVS					97.28 338	94.51 279					97.73 295

CostFormer		94.95 292	94.73 270	95.60 370	97.28 338	89.06 433	97.53 374	96.89 427	89.66 423	96.82 232	96.72 390	86.05 322	98.95 296	95.53 233	96.13 299	98.79 242

VPA-MVSNet		95.75 235	95.11 253	97.69 210	97.24 340	97.27 105	98.94 106	99.23 28	95.13 205	95.51 278	97.32 334	85.73 327	98.91 300	97.33 155	89.55 396	96.89 346

tpm2		94.19 344	93.76 340	95.46 375	97.23 341	89.04 434	97.31 395	96.85 431	87.08 444	96.21 262	96.79 387	83.75 373	98.74 321	92.43 350	96.23 296	98.59 273

EPMVS		94.99 285	94.48 284	96.52 311	97.22 342	91.75 375	97.23 399	91.66 486	94.11 263	97.28 207	96.81 386	85.70 328	98.84 310	93.04 321	97.28 254	98.97 225

FMVSNet5		91.81 392	90.92 395	94.49 413	97.21 343	92.09 368	98.00 325	97.55 368	89.31 430	90.86 422	95.61 435	74.48 453	95.32 471	85.57 443	89.70 392	96.07 428

HQP-NCC					97.20 344		98.05 318		96.43 118	94.45 304

ACMP_Plane					97.20 344		98.05 318		96.43 118	94.45 304

HQP-MVS		95.72 236	95.40 232	96.69 288	97.20 344	94.25 293	98.05 318	98.46 206	96.43 118	94.45 304	97.73 295	86.75 306	98.96 291	95.30 240	94.18 318	96.86 352

UniMVSNet_ETH3D		94.24 341	93.33 359	96.97 265	97.19 347	93.38 327	98.74 178	98.57 178	91.21 397	93.81 344	98.58 212	72.85 460	98.77 320	95.05 250	93.93 328	98.77 249

OpenMVS	93.04 13	95.83 231	95.00 257	98.32 135	97.18 348	97.32 98	99.21 45	98.97 57	89.96 417	91.14 419	99.05 138	86.64 308	99.92 43	93.38 310	99.47 122	97.73 309

VPNet		94.99 285	94.19 303	97.40 235	97.16 349	96.57 148	98.71 189	98.97 57	95.67 161	94.84 291	98.24 251	80.36 403	98.67 328	96.46 196	87.32 425	96.96 333

GA-MVS		94.81 298	94.03 315	97.14 248	97.15 350	93.86 305	96.76 440	97.58 360	94.00 272	94.76 297	97.04 363	80.91 397	98.48 343	91.79 364	96.25 294	99.09 207

FIs		96.51 197	96.12 200	97.67 214	97.13 351	97.54 87	99.36 14	99.22 33	95.89 147	94.03 332	98.35 235	91.98 145	98.44 350	96.40 199	92.76 352	97.01 330

1314		96.25 212	95.73 217	97.79 198	97.13 351	95.55 217	98.19 293	98.59 171	93.47 311	92.03 410	97.82 290	91.33 171	99.49 190	94.62 267	98.44 194	98.32 290

D2MVS		95.18 273	95.08 254	95.48 373	97.10 353	92.07 369	98.30 278	99.13 44	94.02 268	92.90 379	96.73 389	89.48 230	98.73 322	94.48 274	93.60 336	95.65 438

DeepMVS_CX				86.78 457	97.09 354	72.30 487		95.17 464	75.92 481	84.34 469	95.19 440	70.58 462	95.35 469	79.98 469	89.04 406	92.68 475

PAPM		94.95 292	94.00 319	97.78 199	97.04 355	95.65 211	96.03 454	98.25 281	91.23 395	94.19 324	97.80 292	91.27 174	98.86 309	82.61 460	97.61 241	98.84 238

CR-MVSNet		94.76 302	94.15 307	96.59 301	97.00 356	93.43 322	94.96 467	97.56 363	92.46 350	96.93 225	96.24 408	88.15 276	97.88 420	87.38 432	96.65 274	98.46 282

RPMNet		92.81 382	91.34 393	97.24 240	97.00 356	93.43 322	94.96 467	98.80 114	82.27 469	96.93 225	92.12 473	86.98 303	99.82 97	76.32 479	96.65 274	98.46 282

UniMVSNet (Re)		95.78 234	95.19 248	97.58 223	96.99 358	97.47 91	98.79 169	99.18 37	95.60 164	93.92 336	97.04 363	91.68 155	98.48 343	95.80 222	87.66 420	96.79 357

test_fmvs2		93.43 367	93.58 349	92.95 440	96.97 359	83.91 468	99.19 50	97.24 399	95.74 156	95.20 285	98.27 247	69.65 463	98.72 323	96.26 203	93.73 331	96.24 421

FC-MVSNet-test		96.42 200	96.05 202	97.53 226	96.95 360	97.27 105	99.36 14	99.23 28	95.83 152	93.93 335	98.37 233	92.00 144	98.32 371	96.02 212	92.72 353	97.00 331

tfpnnormal		93.66 362	92.70 373	96.55 309	96.94 361	95.94 184	98.97 96	99.19 36	91.04 399	91.38 417	97.34 331	84.94 343	98.61 332	85.45 445	89.02 407	95.11 447

TESTMET0.1,1		94.18 347	93.69 345	95.63 368	96.92 362	89.12 432	96.91 426	94.78 467	93.17 324	94.88 290	96.45 402	78.52 415	98.92 298	93.09 318	98.50 189	98.85 236

TinyColmap		92.31 390	91.53 391	94.65 407	96.92 362	89.75 417	96.92 424	96.68 436	90.45 409	89.62 435	97.85 285	76.06 443	98.81 316	86.74 435	92.51 355	95.41 440

cascas		94.63 310	93.86 331	96.93 268	96.91 364	94.27 291	96.00 455	98.51 193	85.55 459	94.54 300	96.23 410	84.20 363	98.87 307	95.80 222	96.98 264	97.66 312

nrg030		96.28 210	95.72 218	97.96 187	96.90 365	98.15 63	99.39 11	98.31 262	95.47 180	94.42 309	98.35 235	92.09 142	98.69 324	97.50 139	89.05 405	97.04 329

MVS		94.67 308	93.54 352	98.08 168	96.88 366	96.56 149	98.19 293	98.50 198	78.05 477	92.69 386	98.02 266	91.07 188	99.63 159	90.09 394	98.36 207	98.04 299

WR-MVS_H		95.05 281	94.46 286	96.81 277	96.86 367	95.82 202	99.24 36	99.24 20	93.87 280	92.53 392	96.84 384	90.37 208	98.24 381	93.24 314	87.93 417	96.38 415

UniMVSNet_NR-MVSNet		95.71 237	95.15 249	97.40 235	96.84 368	96.97 125	98.74 178	99.24 20	95.16 200	93.88 338	97.72 297	91.68 155	98.31 373	95.81 220	87.25 426	96.92 338

USDC		93.33 371	92.71 372	95.21 382	96.83 369	90.83 394	96.91 426	97.50 373	93.84 281	90.72 423	98.14 258	77.69 426	98.82 315	89.51 408	93.21 347	95.97 430

WB-MVSnew		94.19 344	94.04 313	94.66 406	96.82 370	92.14 363	97.86 346	95.96 452	93.50 309	95.64 276	96.77 388	88.06 280	97.99 410	84.87 449	96.86 265	93.85 470

SSC-MVS3.2		93.59 366	93.13 364	94.97 391	96.81 371	89.71 419	97.95 329	98.49 203	94.59 243	93.50 358	96.91 378	77.74 425	98.37 366	91.69 367	90.47 382	96.83 355

test-LLR		95.10 278	94.87 265	95.80 360	96.77 372	89.70 420	96.91 426	95.21 461	95.11 207	94.83 293	95.72 431	87.71 288	98.97 287	93.06 319	98.50 189	98.72 254

test-mter		94.08 355	93.51 353	95.80 360	96.77 372	89.70 420	96.91 426	95.21 461	92.89 337	94.83 293	95.72 431	77.69 426	98.97 287	93.06 319	98.50 189	98.72 254

Patchmtry		93.22 374	92.35 382	95.84 359	96.77 372	93.09 345	94.66 474	97.56 363	87.37 443	92.90 379	96.24 408	88.15 276	97.90 416	87.37 433	90.10 388	96.53 398

gg-mvs-nofinetune		92.21 391	90.58 399	97.13 249	96.75 375	95.09 246	95.85 456	89.40 491	85.43 460	94.50 302	81.98 486	80.80 400	98.40 365	92.16 352	98.33 208	97.88 303

XXY-MVS		95.20 272	94.45 289	97.46 228	96.75 375	96.56 149	98.86 139	98.65 157	93.30 319	93.27 367	98.27 247	84.85 345	98.87 307	94.82 256	91.26 373	96.96 333

CP-MVSNet		94.94 294	94.30 295	96.83 275	96.72 377	95.56 215	99.11 66	98.95 61	93.89 278	92.42 398	97.90 279	87.19 299	98.12 391	94.32 280	88.21 414	96.82 356

PatchT		93.06 380	91.97 387	96.35 328	96.69 378	92.67 356	94.48 477	97.08 409	86.62 450	97.08 217	92.23 472	87.94 283	97.90 416	78.89 472	96.69 272	98.49 280

PS-CasMVS		94.67 308	93.99 321	96.71 285	96.68 379	95.26 237	99.13 63	99.03 51	93.68 297	92.33 402	97.95 274	85.35 335	98.10 392	93.59 306	88.16 416	96.79 357

WR-MVS		95.15 274	94.46 286	97.22 241	96.67 380	96.45 153	98.21 288	98.81 107	94.15 262	93.16 371	97.69 300	87.51 292	98.30 375	95.29 242	88.62 411	96.90 345

baseline2		95.11 277	94.52 282	96.87 273	96.65 381	93.56 316	98.27 283	94.10 476	93.45 312	92.02 411	97.43 325	87.45 297	99.19 248	93.88 297	97.41 253	97.87 304

test_0402		91.32 398	90.27 402	94.48 414	96.60 382	91.12 386	98.50 246	97.22 400	86.10 455	88.30 447	96.98 370	77.65 428	97.99 410	78.13 474	92.94 349	94.34 458

TransMVSNet (Re)		92.67 385	91.51 392	96.15 336	96.58 383	94.65 269	98.90 117	96.73 433	90.86 402	89.46 438	97.86 283	85.62 330	98.09 396	86.45 437	81.12 458	95.71 436

XVG-ACMP-BASELINE		94.54 317	94.14 308	95.75 364	96.55 384	91.65 378	98.11 311	98.44 214	94.96 220	94.22 322	97.90 279	79.18 412	99.11 265	94.05 293	93.85 329	96.48 410

DU-MVS		95.42 255	94.76 268	97.40 235	96.53 385	96.97 125	98.66 206	98.99 56	95.43 182	93.88 338	97.69 300	88.57 263	98.31 373	95.81 220	87.25 426	96.92 338

NR-MVSNet		94.98 287	94.16 306	97.44 230	96.53 385	97.22 113	98.74 178	98.95 61	94.96 220	89.25 439	97.69 300	89.32 239	98.18 385	94.59 271	87.40 423	96.92 338

tpm		94.13 349	93.80 335	95.12 385	96.50 387	87.91 454	97.44 380	95.89 455	92.62 346	96.37 258	96.30 407	84.13 364	98.30 375	93.24 314	91.66 368	99.14 197

pm-mvs1		93.94 360	93.06 365	96.59 301	96.49 388	95.16 242	98.95 103	98.03 325	92.32 359	91.08 420	97.84 286	84.54 355	98.41 359	92.16 352	86.13 438	96.19 424

JIA-IIPM		93.35 369	92.49 379	95.92 351	96.48 389	90.65 398	95.01 466	96.96 421	85.93 456	96.08 266	87.33 483	87.70 290	98.78 319	91.35 373	95.58 308	98.34 288

UWE-MVS-28		92.79 383	92.51 378	93.62 428	96.46 390	86.28 461	97.93 333	92.71 483	94.17 261	94.78 296	97.16 345	81.05 395	96.43 459	81.45 464	96.86 265	98.14 297

TranMVSNet+NR-MVSNet		95.14 275	94.48 284	97.11 253	96.45 391	96.36 160	99.03 82	99.03 51	95.04 212	93.58 352	97.93 276	88.27 273	98.03 405	94.13 288	86.90 431	96.95 335

testgi		93.06 380	92.45 381	94.88 396	96.43 392	89.90 414	98.75 174	97.54 369	95.60 164	91.63 416	97.91 278	74.46 454	97.02 444	86.10 439	93.67 332	97.72 310

v10		94.29 337	93.55 351	96.51 312	96.39 393	94.80 265	98.99 92	98.19 289	91.35 388	93.02 377	96.99 369	88.09 278	98.41 359	90.50 390	88.41 413	96.33 418

v8		94.47 326	93.77 338	96.57 304	96.36 394	94.83 263	99.05 75	98.19 289	91.92 370	93.16 371	96.97 371	88.82 260	98.48 343	91.69 367	87.79 418	96.39 414

GG-mvs-BLEND				96.59 301	96.34 395	94.98 254	96.51 448	88.58 492		93.10 376	94.34 453	80.34 405	98.05 404	89.53 407	96.99 261	96.74 362

V42		94.78 300	94.14 308	96.70 287	96.33 396	95.22 240	98.97 96	98.09 315	92.32 359	94.31 315	97.06 359	88.39 269	98.55 338	92.90 326	88.87 409	96.34 416

PEN-MVS		94.42 329	93.73 342	96.49 313	96.28 397	94.84 261	99.17 55	99.00 53	93.51 308	92.23 404	97.83 289	86.10 321	97.90 416	92.55 345	86.92 430	96.74 362

v1144		94.59 313	93.92 324	96.60 300	96.21 398	94.78 267	98.59 218	98.14 303	91.86 373	94.21 323	97.02 366	87.97 282	98.41 359	91.72 366	89.57 394	96.61 381

Baseline_NR-MVSNet		94.35 332	93.81 334	95.96 350	96.20 399	94.05 300	98.61 217	96.67 437	91.44 384	93.85 342	97.60 311	88.57 263	98.14 388	94.39 276	86.93 429	95.68 437

tt0320-xc		89.79 422	88.11 429	94.84 400	96.19 400	90.61 401	98.16 300	97.22 400	77.35 479	88.75 445	96.70 392	65.94 474	97.63 431	89.31 412	83.39 447	96.28 420

MS-PatchMatch		93.84 361	93.63 347	94.46 416	96.18 401	89.45 427	97.76 357	98.27 272	92.23 362	92.13 408	97.49 319	79.50 409	98.69 324	89.75 402	99.38 134	95.25 443

v2v482		94.69 303	94.03 315	96.65 290	96.17 402	94.79 266	98.67 204	98.08 316	92.72 342	94.00 333	97.16 345	87.69 291	98.45 348	92.91 325	88.87 409	96.72 365

EPNet_dtu		95.21 271	94.95 261	95.99 345	96.17 402	90.45 404	98.16 300	97.27 397	96.77 100	93.14 374	98.33 240	90.34 209	98.42 352	85.57 443	98.81 170	99.09 207
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OPM-MVS		95.69 240	95.33 241	96.76 281	96.16 404	94.63 271	98.43 261	98.39 239	96.64 110	95.02 288	98.78 185	85.15 340	99.05 275	95.21 247	94.20 317	96.60 383
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tt0320		90.26 418	88.73 424	94.86 397	96.12 405	90.62 400	98.17 299	97.63 356	77.46 478	89.68 434	96.04 419	69.19 465	97.79 423	88.98 416	85.29 441	96.16 425

v1192		94.32 334	93.58 349	96.53 310	96.10 406	94.45 280	98.50 246	98.17 298	91.54 381	94.19 324	97.06 359	86.95 304	98.43 351	90.14 393	89.57 394	96.70 369

v148		94.29 337	93.76 340	95.91 352	96.10 406	92.93 350	98.58 222	97.97 328	92.59 348	93.47 360	96.95 375	88.53 267	98.32 371	92.56 344	87.06 428	96.49 408

v144192		94.39 331	93.70 344	96.48 315	96.06 408	94.35 286	98.58 222	98.16 300	91.45 383	94.33 314	97.02 366	87.50 294	98.45 348	91.08 380	89.11 404	96.63 377

DTE-MVSNet		93.98 359	93.26 362	96.14 337	96.06 408	94.39 284	99.20 48	98.86 91	93.06 330	91.78 412	97.81 291	85.87 326	97.58 434	90.53 389	86.17 435	96.46 412

v1240		94.06 357	93.29 361	96.34 329	96.03 410	93.90 304	98.44 259	98.17 298	91.18 398	94.13 327	97.01 368	86.05 322	98.42 352	89.13 415	89.50 398	96.70 369

sc_t1		91.01 407	89.39 413	95.85 358	95.99 411	90.39 407	98.43 261	97.64 355	78.79 474	92.20 406	97.94 275	66.00 473	98.60 335	91.59 370	85.94 439	98.57 276

APD_test1		88.22 433	88.01 431	88.86 454	95.98 412	74.66 486	97.21 402	96.44 444	83.96 465	86.66 457	97.90 279	60.95 480	97.84 422	82.73 458	90.23 386	94.09 464

v1921920		94.20 343	93.47 355	96.40 325	95.98 412	94.08 299	98.52 238	98.15 301	91.33 389	94.25 320	97.20 344	86.41 314	98.42 352	90.04 398	89.39 401	96.69 374

EU-MVSNet		93.66 362	94.14 308	92.25 447	95.96 414	83.38 471	98.52 238	98.12 305	94.69 237	92.61 388	98.13 259	87.36 298	96.39 461	91.82 363	90.00 389	96.98 332

usedtu_dtu_shiyan1		94.96 290	94.28 296	96.98 263	95.93 415	96.11 172	97.08 415	98.39 239	93.62 303	93.86 340	96.40 404	88.28 271	98.21 382	92.61 337	92.36 357	96.63 377

FE-MVSNET3		94.96 290	94.28 296	96.98 263	95.93 415	96.11 172	97.08 415	98.39 239	93.62 303	93.86 340	96.40 404	88.28 271	98.21 382	92.61 337	92.36 357	96.63 377

v7n		94.19 344	93.43 357	96.47 316	95.90 417	94.38 285	99.26 33	98.34 255	91.99 368	92.76 383	97.13 347	88.31 270	98.52 341	89.48 409	87.70 419	96.52 401

gm-plane-assit					95.88 418	87.47 456			89.74 422		96.94 376		99.19 248	93.32 313

LF4IMVS		93.14 378	92.79 371	94.20 421	95.88 418	88.67 442	97.66 365	97.07 411	93.81 284	91.71 413	97.65 305	77.96 423	98.81 316	91.47 372	91.92 364	95.12 446

PS-MVSNAJss		96.43 199	96.26 194	96.92 271	95.84 420	95.08 247	99.16 56	98.50 198	95.87 150	93.84 343	98.34 239	94.51 90	98.61 332	96.88 176	93.45 339	97.06 328

pmmvs4		94.69 303	93.99 321	96.81 277	95.74 421	95.94 184	97.40 384	97.67 352	90.42 410	93.37 364	97.59 312	89.08 247	98.20 384	92.97 323	91.67 367	96.30 419

test_djsdf		96.00 219	95.69 224	96.93 268	95.72 422	95.49 220	99.47 7	98.40 233	94.98 218	94.58 299	97.86 283	89.16 244	98.41 359	96.91 170	94.12 322	96.88 347

SixPastTwentyTwo		93.34 370	92.86 369	94.75 403	95.67 423	89.41 429	98.75 174	96.67 437	93.89 278	90.15 430	98.25 250	80.87 398	98.27 380	90.90 385	90.64 380	96.57 391

K. test v3		92.55 387	91.91 390	94.48 414	95.64 424	89.24 430	99.07 72	94.88 466	94.04 266	86.78 455	97.59 312	77.64 429	97.64 430	92.08 354	89.43 400	96.57 391

OurMVSNet-221017-0		94.21 342	94.00 319	94.85 398	95.60 425	89.22 431	98.89 121	97.43 383	95.29 193	92.18 407	98.52 220	82.86 377	98.59 336	93.46 309	91.76 365	96.74 362

mvs_tets		95.41 257	95.00 257	96.65 290	95.58 426	94.42 282	99.00 89	98.55 183	95.73 158	93.21 369	98.38 232	83.45 376	98.63 330	97.09 162	94.00 325	96.91 343

MonoMVSNet		95.51 247	95.45 231	95.68 365	95.54 427	90.87 391	98.92 114	97.37 388	95.79 154	95.53 277	97.38 330	89.58 228	97.68 428	96.40 199	92.59 354	98.49 280

Gipuma		78.40 451	76.75 454	83.38 465	95.54 427	80.43 477	79.42 491	97.40 385	64.67 487	73.46 484	80.82 488	45.65 486	93.14 482	66.32 486	87.43 422	76.56 490
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		94.08 355	93.51 353	95.80 360	95.53 429	92.89 351	97.38 386	95.97 451	95.11 207	92.51 394	96.66 393	87.71 288	96.94 446	87.03 434	93.67 332	97.57 316

pmmvs5		93.65 364	92.97 368	95.68 365	95.49 430	92.37 358	98.20 290	97.28 396	89.66 423	92.58 389	97.26 337	82.14 382	98.09 396	93.18 317	90.95 378	96.58 389

test_fmvsmconf0.01_n		97.86 92	97.54 102	98.83 83	95.48 431	96.83 132	98.95 103	98.60 164	98.58 14	98.93 81	99.55 18	88.57 263	99.91 56	99.54 24	99.61 91	99.77 40

N_pmnet		87.12 438	87.77 435	85.17 460	95.46 432	61.92 496	97.37 388	70.66 501	85.83 457	88.73 446	96.04 419	85.33 337	97.76 426	80.02 467	90.48 381	95.84 433

our_test_3		93.65 364	93.30 360	94.69 404	95.45 433	89.68 422	96.91 426	97.65 353	91.97 369	91.66 415	96.88 380	89.67 226	97.93 415	88.02 427	91.49 369	96.48 410

ppachtmachnet_test		93.22 374	92.63 374	94.97 391	95.45 433	90.84 393	96.88 434	97.88 335	90.60 405	92.08 409	97.26 337	88.08 279	97.86 421	85.12 448	90.33 383	96.22 422

jajsoiax		95.45 252	95.03 256	96.73 282	95.42 435	94.63 271	99.14 60	98.52 190	95.74 156	93.22 368	98.36 234	83.87 370	98.65 329	96.95 168	94.04 323	96.91 343

dmvs_testset		87.64 435	88.93 423	83.79 463	95.25 436	63.36 495	97.20 403	91.17 487	93.07 329	85.64 463	95.98 424	85.30 339	91.52 485	69.42 484	87.33 424	96.49 408

MDA-MVSNet-bldmvs		89.97 421	88.35 427	94.83 401	95.21 437	91.34 382	97.64 367	97.51 372	88.36 439	71.17 487	96.13 415	79.22 411	96.63 455	83.65 456	86.27 434	96.52 401

dongtai		82.47 444	81.88 447	84.22 462	95.19 438	76.03 479	94.59 476	74.14 500	82.63 467	87.19 453	96.09 416	64.10 476	87.85 490	58.91 488	84.11 445	88.78 482

anonymousdsp		95.42 255	94.91 262	96.94 267	95.10 439	95.90 190	99.14 60	98.41 230	93.75 286	93.16 371	97.46 321	87.50 294	98.41 359	95.63 230	94.03 324	96.50 407

EPNet		97.28 150	96.87 158	98.51 114	94.98 440	96.14 170	98.90 117	97.02 418	98.28 21	95.99 269	99.11 120	91.36 169	99.89 68	96.98 165	99.19 147	99.50 106
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVP-Stereo		94.28 339	93.92 324	95.35 379	94.95 441	92.60 357	97.97 328	97.65 353	91.61 379	90.68 424	97.09 352	86.32 318	98.42 352	89.70 404	99.34 138	95.02 451
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lessismore_v0				94.45 417	94.93 442	88.44 447		91.03 488		86.77 456	97.64 308	76.23 441	98.42 352	90.31 392	85.64 440	96.51 405

MDA-MVSNet_test_wron		90.71 412	89.38 415	94.68 405	94.83 443	90.78 395	97.19 405	97.46 377	87.60 441	72.41 486	95.72 431	86.51 309	96.71 453	85.92 441	86.80 432	96.56 393

EGC-MVSNET		75.22 454	69.54 457	92.28 445	94.81 444	89.58 424	97.64 367	96.50 442	1.82 498	5.57 499	95.74 427	68.21 466	96.26 462	73.80 481	91.71 366	90.99 476

YYNet1		90.70 413	89.39 413	94.62 409	94.79 445	90.65 398	97.20 403	97.46 377	87.54 442	72.54 485	95.74 427	86.51 309	96.66 454	86.00 440	86.76 433	96.54 396

EG-PatchMatch MVS		91.13 405	90.12 404	94.17 423	94.73 446	89.00 435	98.13 306	97.81 344	89.22 431	85.32 465	96.46 401	67.71 469	98.42 352	87.89 431	93.82 330	95.08 448

pmmvs6		91.77 393	90.63 398	95.17 384	94.69 447	91.24 385	98.67 204	97.92 333	86.14 454	89.62 435	97.56 317	75.79 444	98.34 368	90.75 387	84.56 442	95.94 431

MVStest1		89.53 427	87.99 432	94.14 424	94.39 448	90.42 405	98.25 285	96.84 432	82.81 466	81.18 476	97.33 333	77.09 435	96.94 446	85.27 447	78.79 466	95.06 449

new_pmnet		90.06 420	89.00 421	93.22 436	94.18 449	88.32 449	96.42 450	96.89 427	86.19 453	85.67 462	93.62 456	77.18 433	97.10 443	81.61 463	89.29 402	94.23 460

DSMNet-mixed		92.52 389	92.58 377	92.33 444	94.15 450	82.65 473	98.30 278	94.26 473	89.08 432	92.65 387	95.73 429	85.01 342	95.76 467	86.24 438	97.76 236	98.59 273

ttmdpeth		92.61 386	91.96 389	94.55 410	94.10 451	90.60 402	98.52 238	97.29 394	92.67 344	90.18 428	97.92 277	79.75 408	97.79 423	91.09 378	86.15 437	95.26 442

UnsupCasMVSNet_eth		90.99 408	89.92 406	94.19 422	94.08 452	89.83 415	97.13 413	98.67 150	93.69 295	85.83 461	96.19 413	75.15 448	96.74 450	89.14 414	79.41 465	96.00 429

KD-MVS_2432*1600		89.61 425	87.96 433	94.54 411	94.06 453	91.59 379	95.59 462	97.63 356	89.87 419	88.95 441	94.38 451	78.28 418	96.82 448	84.83 450	68.05 487	95.21 444

miper_refine_blended		89.61 425	87.96 433	94.54 411	94.06 453	91.59 379	95.59 462	97.63 356	89.87 419	88.95 441	94.38 451	78.28 418	96.82 448	84.83 450	68.05 487	95.21 444

Anonymous20231206		91.66 394	91.10 394	93.33 433	94.02 455	87.35 457	98.58 222	97.26 398	90.48 407	90.16 429	96.31 406	83.83 371	96.53 457	79.36 470	89.90 390	96.12 426

Anonymous20240521		91.18 402	90.44 400	93.42 430	93.70 456	88.47 446	98.94 106	97.56 363	88.46 437	89.56 437	95.08 443	77.15 434	96.97 445	83.92 455	89.55 396	94.82 453

test20.03		90.89 409	90.38 401	92.43 442	93.48 457	88.14 452	98.33 270	97.56 363	93.40 314	87.96 448	96.71 391	80.69 401	94.13 478	79.15 471	86.17 435	95.01 452

0.4-1-1-0.2		90.43 414	88.45 425	96.38 326	93.34 458	92.12 364	93.88 481	95.04 465	88.62 436	90.00 431	88.31 481	75.31 446	99.03 279	94.61 268	76.91 473	98.01 302

CMPMVS	66.06 21	89.70 423	89.67 410	89.78 452	93.19 459	76.56 478	97.00 420	98.35 252	80.97 472	81.57 474	97.75 294	74.75 451	98.61 332	89.85 400	93.63 334	94.17 462
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
OpenMVS_ROB	86.42 20	89.00 429	87.43 437	93.69 427	93.08 460	89.42 428	97.91 336	96.89 427	78.58 475	85.86 460	94.69 445	69.48 464	98.29 378	77.13 477	93.29 346	93.36 472

KD-MVS_self_test		90.38 415	89.38 415	93.40 432	92.85 461	88.94 438	97.95 329	97.94 331	90.35 412	90.25 427	93.96 454	79.82 406	95.94 466	84.62 454	76.69 474	95.33 441

MIMVSNet1		89.67 424	88.28 428	93.82 425	92.81 462	91.08 387	98.01 323	97.45 381	87.95 440	87.90 449	95.87 425	67.63 470	94.56 477	78.73 473	88.18 415	95.83 434

kuosan		78.45 450	77.69 451	80.72 470	92.73 463	75.32 483	94.63 475	74.51 499	75.96 480	80.87 478	93.19 462	63.23 478	79.99 494	42.56 494	81.56 456	86.85 486

mvs5depth		91.23 401	90.17 403	94.41 418	92.09 464	89.79 416	95.26 465	96.50 442	90.73 403	91.69 414	97.06 359	76.12 442	98.62 331	88.02 427	84.11 445	94.82 453

UnsupCasMVSNet_bld		87.17 436	85.12 443	93.31 434	91.94 465	88.77 439	94.92 469	98.30 269	84.30 464	82.30 472	90.04 479	63.96 477	97.25 441	85.85 442	74.47 484	93.93 469

CL-MVSNet_self_test		90.11 419	89.14 418	93.02 438	91.86 466	88.23 451	96.51 448	98.07 318	90.49 406	90.49 426	94.41 449	84.75 348	95.34 470	80.79 466	74.95 478	95.50 439

blend_shiyan4		90.76 411	89.01 420	95.99 345	91.69 467	93.35 330	97.44 380	97.83 338	86.93 445	92.23 404	91.98 474	75.19 447	98.09 396	92.88 329	74.96 477	96.52 401

blended_shiyan8		91.42 396	89.89 407	96.01 343	91.50 468	93.30 333	97.48 378	97.83 338	86.93 445	92.57 391	92.37 470	82.46 380	98.13 389	92.86 331	74.99 476	96.61 381

blended_shiyan6		91.37 397	89.84 408	95.98 348	91.49 469	93.28 334	97.48 378	97.83 338	86.93 445	92.43 397	92.36 471	82.44 381	98.06 401	92.74 336	74.82 479	96.59 385

Patchmatch-RL test		91.49 395	90.85 396	93.41 431	91.37 470	84.40 466	92.81 482	95.93 454	91.87 372	87.25 451	94.87 444	88.99 250	96.53 457	92.54 346	82.00 452	99.30 158

wanda-best-256-512		91.17 403	89.60 411	95.88 355	91.33 471	92.99 348	96.89 431	97.82 341	86.89 448	92.36 399	91.75 475	81.83 384	98.06 401	92.75 333	74.82 479	96.59 385

FE-blended-shiyan7		91.17 403	89.60 411	95.88 355	91.33 471	92.99 348	96.89 431	97.82 341	86.89 448	92.36 399	91.75 475	81.83 384	98.06 401	92.75 333	74.82 479	96.59 385

usedtu_blend_shiyan5		90.87 410	89.15 417	96.01 343	91.33 471	93.35 330	98.12 307	97.36 389	81.93 471	92.36 399	91.75 475	81.83 384	98.09 396	92.88 329	74.82 479	96.59 385

test_fmvs3		87.17 436	87.06 439	87.50 456	91.21 474	75.66 481	99.05 75	96.61 440	92.79 341	88.85 443	92.78 466	43.72 487	93.49 479	93.95 294	84.56 442	93.34 473

pmmvs-eth3d		90.36 416	89.05 419	94.32 420	91.10 475	92.12 364	97.63 370	96.95 422	88.86 434	84.91 466	93.13 463	78.32 417	96.74 450	88.70 419	81.81 454	94.09 464

PM-MVS		87.77 434	86.55 440	91.40 450	91.03 476	83.36 472	96.92 424	95.18 463	91.28 393	86.48 459	93.42 459	53.27 484	96.74 450	89.43 410	81.97 453	94.11 463

FE-MVSNET2		90.29 417	88.94 422	94.36 419	90.48 477	92.27 359	98.45 253	97.82 341	91.59 380	84.90 467	93.10 464	73.92 456	96.42 460	87.92 430	82.26 450	94.39 457

new-patchmatchnet		88.50 432	87.45 436	91.67 449	90.31 478	85.89 463	97.16 411	97.33 390	89.47 426	83.63 471	92.77 467	76.38 439	95.06 474	82.70 459	77.29 471	94.06 466

FE-MVSNET		88.56 431	87.09 438	92.99 439	89.93 479	89.99 413	98.15 303	95.59 457	88.42 438	84.87 468	92.90 465	74.82 450	94.99 475	77.88 475	81.21 457	93.99 467

mvsany_test3		88.80 430	88.04 430	91.09 451	89.78 480	81.57 476	97.83 351	95.49 459	93.81 284	87.53 450	93.95 455	56.14 482	97.43 438	94.68 263	83.13 448	94.26 459

WB-MVS		84.86 441	85.33 442	83.46 464	89.48 481	69.56 490	98.19 293	96.42 445	89.55 425	81.79 473	94.67 446	84.80 346	90.12 486	52.44 490	80.64 462	90.69 477

test_f		86.07 440	85.39 441	88.10 455	89.28 482	75.57 482	97.73 360	96.33 446	89.41 429	85.35 464	91.56 478	43.31 489	95.53 468	91.32 374	84.23 444	93.21 474

SSC-MVS		84.27 443	84.71 445	82.96 468	89.19 483	68.83 491	98.08 315	96.30 447	89.04 433	81.37 475	94.47 447	84.60 353	89.89 487	49.80 492	79.52 464	90.15 478

pmmvs3		86.67 439	84.86 444	92.11 448	88.16 484	87.19 459	96.63 444	94.75 468	79.88 473	87.22 452	92.75 468	66.56 472	95.20 473	81.24 465	76.56 475	93.96 468

testf1		79.02 447	77.70 449	82.99 466	88.10 485	66.90 492	94.67 472	93.11 479	71.08 484	74.02 482	93.41 460	34.15 493	93.25 480	72.25 482	78.50 468	88.82 480

APD_test2		79.02 447	77.70 449	82.99 466	88.10 485	66.90 492	94.67 472	93.11 479	71.08 484	74.02 482	93.41 460	34.15 493	93.25 480	72.25 482	78.50 468	88.82 480

ambc				89.49 453	86.66 487	75.78 480	92.66 483	96.72 434		86.55 458	92.50 469	46.01 485	97.90 416	90.32 391	82.09 451	94.80 455

test_vis3_rt		79.22 445	77.40 452	84.67 461	86.44 488	74.85 485	97.66 365	81.43 496	84.98 461	67.12 489	81.91 487	28.09 497	97.60 432	88.96 417	80.04 463	81.55 487

usedtu_dtu_shiyan2		84.80 442	82.31 446	92.27 446	86.38 489	85.55 464	97.77 356	96.56 441	78.34 476	83.90 470	93.50 458	54.16 483	95.32 471	77.55 476	72.62 485	95.92 432

test_method		79.03 446	78.17 448	81.63 469	86.06 490	54.40 501	82.75 490	96.89 427	39.54 493	80.98 477	95.57 436	58.37 481	94.73 476	84.74 453	78.61 467	95.75 435

TDRefinement		91.06 406	89.68 409	95.21 382	85.35 491	91.49 381	98.51 245	97.07 411	91.47 382	88.83 444	97.84 286	77.31 430	99.09 270	92.79 332	77.98 470	95.04 450

PMMVS2		77.95 452	75.44 456	85.46 459	82.54 492	74.95 484	94.23 479	93.08 481	72.80 483	74.68 481	87.38 482	36.36 492	91.56 484	73.95 480	63.94 489	89.87 479

E-PMN		64.94 458	64.25 460	67.02 476	82.28 493	59.36 499	91.83 485	85.63 493	52.69 490	60.22 491	77.28 490	41.06 490	80.12 493	46.15 493	41.14 491	61.57 492

EMVS		64.07 459	63.26 462	66.53 477	81.73 494	58.81 500	91.85 484	84.75 494	51.93 492	59.09 492	75.13 491	43.32 488	79.09 495	42.03 495	39.47 492	61.69 491

FPMVS		77.62 453	77.14 453	79.05 472	79.25 495	60.97 497	95.79 457	95.94 453	65.96 486	67.93 488	94.40 450	37.73 491	88.88 489	68.83 485	88.46 412	87.29 483

wuyk23d		30.17 461	30.18 465	30.16 478	78.61 496	43.29 503	66.79 492	14.21 502	17.31 495	14.82 498	11.93 498	11.55 500	41.43 497	37.08 496	19.30 495	5.76 495

LCM-MVSNet		78.70 449	76.24 455	86.08 458	77.26 497	71.99 488	94.34 478	96.72 434	61.62 488	76.53 480	89.33 480	33.91 495	92.78 483	81.85 462	74.60 483	93.46 471

MVE	62.14 22	63.28 460	59.38 463	74.99 473	74.33 498	65.47 494	85.55 488	80.50 497	52.02 491	51.10 493	75.00 492	10.91 501	80.50 492	51.60 491	53.40 490	78.99 488
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		69.08 455	65.37 459	80.22 471	65.99 499	71.96 489	90.91 486	90.09 490	82.62 468	49.93 494	78.39 489	29.36 496	81.75 491	62.49 487	38.52 493	86.95 485

PMVS	61.03 23	65.95 457	63.57 461	73.09 475	57.90 500	51.22 502	85.05 489	93.93 477	54.45 489	44.32 495	83.57 484	13.22 498	89.15 488	58.68 489	81.00 459	78.91 489
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		68.90 456	66.97 458	74.68 474	50.78 501	59.95 498	87.13 487	83.47 495	38.80 494	62.21 490	96.23 410	64.70 475	76.91 496	88.91 418	30.49 494	87.19 484

testmvs		21.48 463	24.95 466	11.09 480	14.89 502	6.47 505	96.56 446	9.87 503	7.55 496	17.93 496	39.02 494	9.43 502	5.90 499	16.56 498	12.72 496	20.91 494

test123		20.95 464	23.72 467	12.64 479	13.54 503	8.19 504	96.55 447	6.13 504	7.48 497	16.74 497	37.98 495	12.97 499	6.05 498	16.69 497	5.43 497	23.68 493

mmdepth		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

monomultidepth		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

test_blank		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

eth-test2					0.00 504

eth-test					0.00 504

uanet_test		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

DCPMVS		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

cdsmvs_eth3d_5k		23.98 462	31.98 464	0.00 481	0.00 504	0.00 506	0.00 493	98.59 171	0.00 499	0.00 500	98.61 207	90.60 200	0.00 500	0.00 499	0.00 498	0.00 496

pcd_1.5k_mvsjas		7.88 466	10.50 469	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	94.51 90	0.00 500	0.00 499	0.00 498	0.00 496

sosnet-low-res		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

sosnet		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

uncertanet		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

Regformer		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

ab-mvs-re		8.20 465	10.94 468	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	98.43 225	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

uanet		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

TestfortrainingZip							99.32 22

WAC-MVS						90.94 389								88.66 420

PC_three_1452									95.08 211	99.60 32	99.16 107	97.86 2	98.47 346	97.52 135	99.72 67	99.74 50

test_241102_TWO								98.87 85	97.65 39	99.53 37	99.48 33	97.34 13	99.94 14	98.43 67	99.80 25	99.83 18

test_0728_THIRD									97.32 63	99.45 39	99.46 40	97.88 1	99.94 14	98.47 63	99.86 2	99.85 15

GSMVS																99.20 183

sam_mvs1												89.45 234				99.20 183

sam_mvs												88.99 250

MTGPA								98.74 129

test_post1							96.68 443				30.43 497	87.85 287	98.69 324	92.59 342

test_post											31.83 496	88.83 258	98.91 300

patchmatchnet-post											95.10 442	89.42 235	98.89 304

MTMP							98.89 121	94.14 475

test9_res														96.39 201	99.57 99	99.69 70

agg_prior2														95.87 217	99.57 99	99.68 75

test_prior4						98.01 70	97.86 346

test_prior2							97.80 353		96.12 137	97.89 166	98.69 200	95.96 43		96.89 174	99.60 93

旧先验2							97.57 373		91.30 391	98.67 104			99.80 109	95.70 228

新几何2							97.64 367

无先验							97.58 372	98.72 134	91.38 385				99.87 79	93.36 312		99.60 92

原ACMM2							97.67 364

testdata2													99.89 68	91.65 369

segment_acmp												96.85 16

testdata1							97.32 394		96.34 127

plane_prior5								98.56 181					99.03 279	96.07 207	94.27 314	96.92 338

plane_prior4											98.28 244

plane_prior3						94.61 274			97.02 87	95.34 280

plane_prior2							98.80 161		97.28 67

plane_prior						94.60 276	98.44 259		96.74 103						94.22 316

n2								0.00 505

nn								0.00 505

door-mid								94.37 471

test11								98.66 153

door								94.64 469

HQP5-MVS						94.25 293

BP-MVS														95.30 240

HQP4-MVS										94.45 304			98.96 291			96.87 350

HQP3-MVS								98.46 206							94.18 318

HQP2-MVS												86.75 306

MDTV_nov1_ep13_2view						84.26 467	96.89 431		90.97 400	97.90 165		89.89 220		93.91 296		99.18 192

ACMMP++_ref															92.97 348

ACMMP++															93.61 335

Test By Simon												94.64 87

High-resolution multi-view benchmark