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 24	99.69 1	98.95 57	97.46 53	99.39 42

MTAPA		98.58 32	98.29 56	99.46 14	99.76 2	98.64 25	98.90 111	98.74 123	97.27 69	98.02 139	99.39 46	94.81 84	99.96 4	97.91 92	99.79 30	99.77 35

NormalMVS		98.07 79	97.90 83	98.59 97	99.75 3	96.60 137	98.94 100	98.60 159	97.86 29	98.71 95	99.08 117	91.22 171	99.80 103	97.40 134	99.57 94	99.37 129

lecture		98.95 7	98.78 12	99.45 15	99.75 3	98.63 26	99.43 10	99.38 8	97.60 42	99.58 31	99.47 33	95.36 61	99.93 32	98.87 36	99.57 94	99.78 28

MSP-MVS		98.74 19	98.55 25	99.29 34	99.75 3	98.23 52	99.26 28	98.88 73	97.52 46	99.41 40	98.78 168	96.00 39	99.79 115	97.79 100	99.59 90	99.85 13
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 67	98.01 78	99.28 37	99.75 3	98.18 56	99.22 37	98.79 113	96.13 129	97.92 151	99.23 80	94.54 87	99.94 13	96.74 171	99.78 35	99.73 50
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
mPP-MVS		98.51 44	98.26 57	99.25 40	99.75 3	98.04 64	99.28 25	98.81 101	96.24 124	98.35 122	99.23 80	95.46 55	99.94 13	97.42 132	99.81 15	99.77 35

HPM-MVS_fast		98.38 58	98.13 69	99.12 56	99.75 3	97.86 70	99.44 9	98.82 95	94.46 236	98.94 71	99.20 86	95.16 74	99.74 128	97.58 117	99.85 6	99.77 35

region2R		98.61 27	98.38 39	99.29 34	99.74 9	98.16 58	99.23 33	98.93 61	96.15 128	98.94 71	99.17 93	95.91 43	99.94 13	97.55 122	99.79 30	99.78 28

ACMMPR		98.59 30	98.36 41	99.29 34	99.74 9	98.15 59	99.23 33	98.95 57	96.10 132	98.93 75	99.19 91	95.70 49	99.94 13	97.62 114	99.79 30	99.78 28

HPM-MVS		98.36 61	98.10 73	99.13 54	99.74 9	97.82 75	99.53 6	98.80 108	94.63 223	98.61 105	98.97 132	95.13 76	99.77 123	97.65 112	99.83 13	99.79 26
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ACMMP		98.23 71	97.95 80	99.09 58	99.74 9	97.62 79	99.03 77	99.41 6	95.98 137	97.60 181	99.36 56	94.45 92	99.93 32	97.14 144	98.85 161	99.70 62
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 46	98.20 66	99.35 26	99.73 13	98.39 35	99.19 45	98.86 86	95.77 148	98.31 125	99.10 107	95.46 55	99.93 32	97.57 121	99.81 15	99.74 45

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 14	99.25 2	98.97 91	98.58 171	97.62 39	99.45 37	99.46 38	97.42 9	99.94 13	98.47 61	99.81 15	99.69 65
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 14	99.35 1	98.97 91	98.88 73					99.94 13	98.47 61	99.81 15	99.84 15

test0726					99.72 14	99.25 2	99.06 68	98.88 73	97.62 39	99.56 32	99.50 27	97.42 9

GST-MVS		98.43 54	98.12 70	99.34 27	99.72 14	98.38 36	99.09 65	98.82 95	95.71 152	98.73 92	99.06 121	95.27 67	99.93 32	97.07 147	99.63 83	99.72 54

MP-MVS-pluss		98.31 68	97.92 81	99.49 12	99.72 14	98.88 18	98.43 242	98.78 115	94.10 246	97.69 170	99.42 42	95.25 69	99.92 41	98.09 82	99.80 24	99.67 74
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HFP-MVS		98.63 25	98.40 37	99.32 33	99.72 14	98.29 48	99.23 33	98.96 56	96.10 132	98.94 71	99.17 93	96.06 36	99.92 41	97.62 114	99.78 35	99.75 43

PGM-MVS		98.49 46	98.23 62	99.27 39	99.72 14	98.08 63	98.99 87	99.49 5	95.43 166	99.03 63	99.32 63	95.56 52	99.94 13	96.80 168	99.77 37	99.78 28

SED-MVS		99.09 1	98.91 4	99.63 4	99.71 21	99.24 5	99.02 80	98.87 80	97.65 37	99.73 20	99.48 31	97.53 7	99.94 13	98.43 65	99.81 15	99.70 62

IU-MVS					99.71 21	99.23 7		98.64 153	95.28 177	99.63 29				98.35 70	99.81 15	99.83 16

test_241102_ONE					99.71 21	99.24 5		98.87 80	97.62 39	99.73 20	99.39 46	97.53 7	99.74 128

XVS		98.70 21	98.49 31	99.34 27	99.70 24	98.35 45	99.29 23	98.88 73	97.40 55	98.46 112	99.20 86	95.90 45	99.89 62	97.85 96	99.74 54	99.78 28

X-MVStestdata		94.06 338	92.30 364	99.34 27	99.70 24	98.35 45	99.29 23	98.88 73	97.40 55	98.46 112	43.50 463	95.90 45	99.89 62	97.85 96	99.74 54	99.78 28

TSAR-MVS + MP.		98.78 17	98.62 20	99.24 41	99.69 26	98.28 49	99.14 55	98.66 148	96.84 92	99.56 32	99.31 65	96.34 28	99.70 136	98.32 71	99.73 57	99.73 50
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 89	97.74 87	98.20 141	99.67 27	95.16 222	99.22 37	99.32 12	93.04 311	97.02 204	98.92 145	95.36 61	99.91 51	97.43 131	99.64 81	99.52 96

test_one_0601					99.66 28	99.25 2		98.86 86	97.55 45	99.20 54	99.47 33	97.57 6

CP-MVS		98.57 36	98.36 41	99.19 46	99.66 28	97.86 70	99.34 17	98.87 80	95.96 138	98.60 106	99.13 101	96.05 37	99.94 13	97.77 101	99.86 2	99.77 35

CPTT-MVS		97.72 96	97.32 114	98.92 73	99.64 30	97.10 115	99.12 59	98.81 101	92.34 337	98.09 131	99.08 117	93.01 114	99.92 41	96.06 192	99.77 37	99.75 43

test_part2					99.63 31	99.18 10				99.27 51

ACMMP_NAP		98.61 27	98.30 55	99.55 9	99.62 32	98.95 17	98.82 141	98.81 101	95.80 146	99.16 60	99.47 33	95.37 60	99.92 41	97.89 94	99.75 50	99.79 26

MCST-MVS		98.65 22	98.37 40	99.48 13	99.60 33	98.87 19	98.41 246	98.68 140	97.04 84	98.52 110	98.80 162	96.78 16	99.83 84	97.93 90	99.61 86	99.74 45

DPE-MVS		98.92 11	98.67 18	99.65 2	99.58 34	99.20 9	98.42 245	98.91 67	97.58 43	99.54 34	99.46 38	97.10 12	99.94 13	97.64 113	99.84 11	99.83 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
dcpmvs_2		98.08 77	98.59 22	96.56 284	99.57 35	90.34 380	99.15 52	98.38 227	96.82 94	99.29 48	99.49 30	95.78 47	99.57 163	98.94 34	99.86 2	99.77 35

APDe-MVS		99.02 6	98.84 8	99.55 9	99.57 35	98.96 16	99.39 11	98.93 61	97.38 58	99.41 40	99.54 18	96.66 18	99.84 82	98.86 37	99.85 6	99.87 9
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		98.59 30	98.32 54	99.41 18	99.54 37	98.71 22	99.04 74	98.81 101	95.12 189	99.32 47	99.39 46	96.22 30	99.84 82	97.72 104	99.73 57	99.67 74

patch_mono-2		98.36 61	98.87 6	96.82 255	99.53 38	90.68 368	98.64 198	99.29 15	97.88 28	99.19 56	99.52 21	96.80 15	99.97 1	99.11 29	99.86 2	99.82 20

SR-MVS		98.57 36	98.35 43	99.24 41	99.53 38	98.18 56	99.09 65	98.82 95	96.58 108	99.10 62	99.32 63	95.39 58	99.82 91	97.70 109	99.63 83	99.72 54

DP-MVS Recon		97.86 87	97.46 104	99.06 61	99.53 38	98.35 45	98.33 250	98.89 70	92.62 326	98.05 134	98.94 140	95.34 63	99.65 147	96.04 193	99.42 122	99.19 171

reproduce_model		98.94 8	98.81 10	99.34 27	99.52 41	98.26 50	98.94 100	98.84 90	98.06 23	99.35 44	99.61 4	96.39 27	99.94 13	98.77 40	99.82 14	99.83 16

SMA-MVS		98.58 32	98.25 58	99.56 8	99.51 42	99.04 15	98.95 97	98.80 108	93.67 281	99.37 43	99.52 21	96.52 22	99.89 62	98.06 83	99.81 15	99.76 42
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 63	98.00 79	99.42 17	99.51 42	98.72 21	98.80 150	98.82 95	94.52 231	99.23 53	99.25 79	95.54 54	99.80 103	96.52 177	99.77 37	99.74 45
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HPM-MVS++		98.58 32	98.25 58	99.55 9	99.50 44	99.08 11	98.72 177	98.66 148	97.51 47	98.15 126	98.83 159	95.70 49	99.92 41	97.53 124	99.67 70	99.66 77

APD-MVS_3200maxsize		98.53 41	98.33 53	99.15 52	99.50 44	97.92 69	99.15 52	98.81 101	96.24 124	99.20 54	99.37 52	95.30 65	99.80 103	97.73 103	99.67 70	99.72 54

114514_t		96.93 156	96.27 176	98.92 73	99.50 44	97.63 78	98.85 133	98.90 68	84.80 434	97.77 160	99.11 105	92.84 116	99.66 146	94.85 236	99.77 37	99.47 110

PAPM_NR		97.46 120	97.11 127	98.50 111	99.50 44	96.41 151	98.63 201	98.60 159	95.18 182	97.06 202	98.06 245	94.26 97	99.57 163	93.80 281	98.87 158	99.52 96

reproduce-ours		98.93 9	98.78 12	99.38 19	99.49 48	98.38 36	98.86 129	98.83 92	98.06 23	99.29 48	99.58 14	96.40 25	99.94 13	98.68 43	99.81 15	99.81 22

our_new_method		98.93 9	98.78 12	99.38 19	99.49 48	98.38 36	98.86 129	98.83 92	98.06 23	99.29 48	99.58 14	96.40 25	99.94 13	98.68 43	99.81 15	99.81 22

SR-MVS-dyc-post		98.54 40	98.35 43	99.13 54	99.49 48	97.86 70	99.11 61	98.80 108	96.49 112	99.17 57	99.35 58	95.34 63	99.82 91	97.72 104	99.65 76	99.71 58

RE-MVS-def			98.34 49		99.49 48	97.86 70	99.11 61	98.80 108	96.49 112	99.17 57	99.35 58	95.29 66		97.72 104	99.65 76	99.71 58

9.14			98.06 74		99.47 52		98.71 178	98.82 95	94.36 239	99.16 60	99.29 69	96.05 37	99.81 96	97.00 148	99.71 64

CDPH-MVS		97.94 84	97.49 101	99.28 37	99.47 52	98.44 32	97.91 314	98.67 145	92.57 329	98.77 88	98.85 154	95.93 42	99.72 130	95.56 213	99.69 67	99.68 70

ZD-MVS					99.46 54	98.70 23		98.79 113	93.21 302	98.67 98	98.97 132	95.70 49	99.83 84	96.07 189	99.58 93

save fliter					99.46 54	98.38 36	98.21 268	98.71 131	97.95 26

EI-MVSNet-Vis-set		98.47 49	98.39 38	98.69 88	99.46 54	96.49 146	98.30 258	98.69 137	97.21 72	98.84 81	99.36 56	95.41 57	99.78 118	98.62 47	99.65 76	99.80 25

EI-MVSNet-UG-set		98.41 56	98.34 49	98.61 95	99.45 57	96.32 156	98.28 261	98.68 140	97.17 76	98.74 90	99.37 52	95.25 69	99.79 115	98.57 50	99.54 105	99.73 50

F-COLMAP		97.09 150	96.80 146	97.97 167	99.45 57	94.95 237	98.55 219	98.62 158	93.02 312	96.17 246	98.58 194	94.01 101	99.81 96	93.95 275	98.90 154	99.14 181

fmvsm_l_conf0.5_n_a		99.09 1	99.08 1	99.11 57	99.43 59	97.48 85	98.88 122	99.30 14	98.47 16	99.85 10	99.43 41	96.71 17	99.96 4	99.86 1	99.80 24	99.89 6

test_fmvsm_n_1920		98.87 16	99.01 3	98.45 117	99.42 60	96.43 149	98.96 96	99.36 10	98.63 11	99.86 7	99.51 24	95.91 43	99.97 1	99.72 12	99.75 50	98.94 213

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 53	99.41 61	97.54 83	98.89 115	99.31 13	98.49 15	99.86 7	99.42 42	96.45 24	99.96 4	99.86 1	99.74 54	99.90 5

fmvsm_s_conf0.5_n_9		98.63 25	98.66 19	98.54 103	99.40 62	95.83 190	98.79 158	99.17 34	98.94 2	99.92 1	99.61 4	92.49 121	99.93 32	99.86 1	99.76 43	99.86 10

fmvsm_l_conf0.5_n_3		98.90 13	98.74 16	99.37 23	99.36 63	98.25 51	98.89 115	99.24 20	98.77 8	99.89 3	99.59 12	93.39 109	99.96 4	99.78 8	99.76 43	99.89 6

fmvsm_s_conf0.5_n_8		98.73 20	98.62 20	99.05 62	99.35 64	97.27 101	98.80 150	99.23 25	98.93 3	99.79 13	99.59 12	92.34 126	99.95 9	99.82 6	99.71 64	99.92 2

fmvsm_l_conf0.5_n_9		98.90 13	98.79 11	99.24 41	99.34 65	97.83 74	98.70 182	99.26 16	98.85 4	99.92 1	99.51 24	93.91 103	99.95 9	99.86 1	99.79 30	99.92 2

新几何1				99.16 51	99.34 65	98.01 66		98.69 137	90.06 395	98.13 128	98.95 139	94.60 86	99.89 62	91.97 334	99.47 116	99.59 89

DP-MVS		96.59 175	95.93 193	98.57 98	99.34 65	96.19 162	98.70 182	98.39 223	89.45 406	94.52 283	99.35 58	91.85 146	99.85 78	92.89 309	98.88 156	99.68 70

SD-MVS		98.64 24	98.68 17	98.53 106	99.33 68	98.36 44	98.90 111	98.85 89	97.28 65	99.72 23	99.39 46	96.63 20	97.60 405	98.17 78	99.85 6	99.64 81
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		96.90 158	96.49 167	98.14 145	99.33 68	95.56 199	97.38 360	99.65 2	92.34 337	97.61 178	98.20 235	89.29 224	99.10 252	96.97 150	97.60 224	99.77 35

OMC-MVS		97.55 115	97.34 113	98.20 141	99.33 68	95.92 180	98.28 261	98.59 166	95.52 162	97.97 144	99.10 107	93.28 112	99.49 184	95.09 230	98.88 156	99.19 171

原ACMM1				98.65 92	99.32 71	96.62 134		98.67 145	93.27 301	97.81 158	98.97 132	95.18 73	99.83 84	93.84 279	99.46 119	99.50 101

CNVR-MVS		98.78 17	98.56 24	99.45 15	99.32 71	98.87 19	98.47 233	98.81 101	97.72 32	98.76 89	99.16 96	97.05 13	99.78 118	98.06 83	99.66 73	99.69 65

TEST9					99.31 73	98.50 30	97.92 312	98.73 126	92.63 325	97.74 164	98.68 184	96.20 32	99.80 103

train_agg		97.97 81	97.52 99	99.33 31	99.31 73	98.50 30	97.92 312	98.73 126	92.98 313	97.74 164	98.68 184	96.20 32	99.80 103	96.59 172	99.57 94	99.68 70

test_prior				99.19 46	99.31 73	98.22 53		98.84 90					99.70 136			99.65 78

PatchMatch-RL		96.59 175	96.03 187	98.27 132	99.31 73	96.51 145	97.91 314	99.06 44	93.72 273	96.92 209	98.06 245	88.50 251	99.65 147	91.77 338	99.00 151	98.66 247

fmvsm_s_conf0.5_n		98.42 55	98.51 27	98.13 149	99.30 77	95.25 218	98.85 133	99.39 7	97.94 27	99.74 19	99.62 3	92.59 120	99.91 51	99.65 16	99.52 108	99.25 160

SDMVSNet		96.85 160	96.42 168	98.14 145	99.30 77	96.38 152	99.21 40	99.23 25	95.92 139	95.96 253	98.76 176	85.88 306	99.44 196	97.93 90	95.59 288	98.60 252

sd_testset		96.17 196	95.76 199	97.42 213	99.30 77	94.34 267	98.82 141	99.08 42	95.92 139	95.96 253	98.76 176	82.83 359	99.32 209	95.56 213	95.59 288	98.60 252

agg_prior					99.30 77	98.38 36		98.72 128		97.57 183			99.81 96

CHOSEN 1792x2688		97.12 148	96.80 146	98.08 156	99.30 77	94.56 258	98.05 296	99.71 1	93.57 287	97.09 198	98.91 146	88.17 256	99.89 62	96.87 162	99.56 102	99.81 22

test_8					99.29 82	98.44 32	97.89 320	98.72 128	92.98 313	97.70 169	98.66 187	96.20 32	99.80 103

旧先验1					99.29 82	97.48 85		98.70 135			99.09 115	95.56 52			99.47 116	99.61 85

PLC	95.07 4	97.20 142	96.78 149	98.44 119	99.29 82	96.31 158	98.14 283	98.76 119	92.41 335	96.39 239	98.31 224	94.92 83	99.78 118	94.06 273	98.77 165	99.23 162
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
COLMAP_ROB	93.27 12	95.33 247	94.87 248	96.71 264	99.29 82	93.24 314	98.58 209	98.11 288	89.92 397	93.57 333	99.10 107	86.37 296	99.79 115	90.78 359	98.10 205	97.09 308
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
NCCC		98.61 27	98.35 43	99.38 19	99.28 86	98.61 27	98.45 235	98.76 119	97.82 31	98.45 115	98.93 141	96.65 19	99.83 84	97.38 137	99.41 123	99.71 58

PVSNet_Blended_VisFu		97.70 98	97.46 104	98.44 119	99.27 87	95.91 181	98.63 201	99.16 36	94.48 235	97.67 171	98.88 151	92.80 117	99.91 51	97.11 145	99.12 143	99.50 101

MVS_111021_LR		98.34 65	98.23 62	98.67 90	99.27 87	96.90 123	97.95 307	99.58 3	97.14 79	98.44 117	99.01 128	95.03 80	99.62 157	97.91 92	99.75 50	99.50 101

MSLP-MVS++		98.56 38	98.57 23	98.55 101	99.26 89	96.80 127	98.71 178	99.05 46	97.28 65	98.84 81	99.28 70	96.47 23	99.40 200	98.52 59	99.70 66	99.47 110

fmvsm_s_conf0.5_n_2		98.30 70	98.21 64	98.57 98	99.25 90	97.11 114	98.66 194	99.20 30	98.82 5	99.79 13	99.60 9	89.38 221	99.92 41	99.80 7	99.38 128	98.69 241

AllTest		95.24 252	94.65 258	96.99 241	99.25 90	93.21 315	98.59 207	98.18 272	91.36 365	93.52 335	98.77 171	84.67 332	99.72 130	89.70 377	97.87 213	98.02 282

TestCases				96.99 241	99.25 90	93.21 315		98.18 272	91.36 365	93.52 335	98.77 171	84.67 332	99.72 130	89.70 377	97.87 213	98.02 282

PVSNet_BlendedMVS		96.73 167	96.60 161	97.12 232	99.25 90	95.35 213	98.26 264	99.26 16	94.28 240	97.94 148	97.46 303	92.74 118	99.81 96	96.88 159	93.32 326	96.20 396

PVSNet_Blended		97.38 129	97.12 126	98.14 145	99.25 90	95.35 213	97.28 371	99.26 16	93.13 307	97.94 148	98.21 234	92.74 118	99.81 96	96.88 159	99.40 126	99.27 151

DeepC-MVS	95.98 3	97.88 86	97.58 92	98.77 82	99.25 90	96.93 121	98.83 139	98.75 121	96.96 88	96.89 211	99.50 27	90.46 193	99.87 73	97.84 98	99.76 43	99.52 96
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 39	98.34 49	99.18 48	99.25 90	98.04 64	98.50 228	98.78 115	97.72 32	98.92 77	99.28 70	95.27 67	99.82 91	97.55 122	99.77 37	99.69 65
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 23	99.24 97	99.05 14	99.02 80				99.16 96	97.81 3	99.37 204	97.24 141	99.73 57	99.70 62

fmvsm_s_conf0.5_n_3		98.53 41	98.45 34	98.79 80	99.23 98	97.32 94	98.80 150	99.26 16	98.82 5	99.87 4	99.60 9	90.95 184	99.93 32	99.76 9	99.73 57	99.12 183

test222					99.23 98	97.17 111	97.40 358	98.66 148	88.68 414	98.05 134	98.96 137	94.14 99			99.53 107	99.61 85

TSAR-MVS + GP.		98.38 58	98.24 60	98.81 79	99.22 100	97.25 107	98.11 289	98.29 251	97.19 74	98.99 69	99.02 124	96.22 30	99.67 143	98.52 59	98.56 177	99.51 99

SteuartSystems-ACMMP		98.90 13	98.75 15	99.36 25	99.22 100	98.43 34	99.10 64	98.87 80	97.38 58	99.35 44	99.40 45	97.78 5	99.87 73	97.77 101	99.85 6	99.78 28
Skip Steuart: Steuart Systems R&D Blog.
MVS_111021_HR		98.47 49	98.34 49	98.88 77	99.22 100	97.32 94	97.91 314	99.58 3	97.20 73	98.33 123	99.00 130	95.99 40	99.64 150	98.05 85	99.76 43	99.69 65

SPE-MVS-test		98.49 46	98.50 29	98.46 116	99.20 103	97.05 117	99.64 4	98.50 193	97.45 54	98.88 78	99.14 100	95.25 69	99.15 238	98.83 38	99.56 102	99.20 167

testdata				98.26 135	99.20 103	95.36 211		98.68 140	91.89 351	98.60 106	99.10 107	94.44 93	99.82 91	94.27 263	99.44 120	99.58 93

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 105	99.23 7	99.69 1	98.88 73	97.32 61	99.53 35	99.47 33	97.81 3	99.94 13	98.47 61	99.72 62	99.74 45

MSC_two_6792asdad				99.62 6	99.17 105	99.08 11		98.63 156					99.94 13	98.53 53	99.80 24	99.86 10

No_MVS				99.62 6	99.17 105	99.08 11		98.63 156					99.94 13	98.53 53	99.80 24	99.86 10

PVSNet	91.96 18	96.35 187	96.15 180	96.96 245	99.17 105	92.05 341	96.08 421	98.68 140	93.69 277	97.75 163	97.80 274	88.86 240	99.69 141	94.26 264	99.01 149	99.15 178

fmvsm_s_conf0.5_n_4		98.35 63	98.50 29	97.90 171	99.16 109	95.08 227	98.75 163	99.24 20	98.39 17	99.81 11	99.52 21	92.35 125	99.90 59	99.74 11	99.51 110	98.71 239

test12				99.18 48	99.16 109	98.19 55		98.53 182		98.07 132		95.13 76	99.72 130		99.56 102	99.63 83

AdaColmap		97.15 146	96.70 154	98.48 114	99.16 109	96.69 133	98.01 301	98.89 70	94.44 237	96.83 212	98.68 184	90.69 190	99.76 124	94.36 258	99.29 136	98.98 208

PHI-MVS		98.34 65	98.06 74	99.18 48	99.15 112	98.12 62	99.04 74	99.09 41	93.32 297	98.83 84	99.10 107	96.54 21	99.83 84	97.70 109	99.76 43	99.59 89

TAPA-MVS	93.98 7	95.35 245	94.56 263	97.74 187	99.13 113	94.83 243	98.33 250	98.64 153	86.62 422	96.29 241	98.61 189	94.00 102	99.29 215	80.00 440	99.41 123	99.09 191
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MM		98.51 44	98.24 60	99.33 31	99.12 114	98.14 61	98.93 106	97.02 391	98.96 1	99.17 57	99.47 33	91.97 144	99.94 13	99.85 5	99.69 67	99.91 4

MG-MVS		97.81 92	97.60 91	98.44 119	99.12 114	95.97 173	97.75 335	98.78 115	96.89 91	98.46 112	99.22 82	93.90 104	99.68 142	94.81 239	99.52 108	99.67 74

test_vis1_n_1920		96.71 168	96.84 144	96.31 309	99.11 116	89.74 388	99.05 70	98.58 171	98.08 22	99.87 4	99.37 52	78.48 392	99.93 32	99.29 25	99.69 67	99.27 151

Anonymous20231211		94.10 334	93.26 343	96.61 277	99.11 116	94.28 269	99.01 82	98.88 73	86.43 424	92.81 361	97.57 296	81.66 364	98.68 308	94.83 237	89.02 387	96.88 328

fmvsm_s_conf0.5_n_a		98.38 58	98.42 36	98.27 132	99.09 118	95.41 208	98.86 129	99.37 9	97.69 36	99.78 15	99.61 4	92.38 124	99.91 51	99.58 21	99.43 121	99.49 106

CS-MVS		98.44 52	98.49 31	98.31 130	99.08 119	96.73 131	99.67 3	98.47 200	97.17 76	98.94 71	99.10 107	95.73 48	99.13 243	98.71 42	99.49 113	99.09 191

fmvsm_s_conf0.5_n_5		98.53 41	98.35 43	99.08 59	99.07 120	97.46 89	98.68 187	99.20 30	97.50 48	99.87 4	99.50 27	91.96 145	99.96 4	99.76 9	99.65 76	99.82 20

CNLPA		97.45 123	97.03 133	98.73 85	99.05 121	97.44 90	98.07 294	98.53 182	95.32 175	96.80 216	98.53 199	93.32 110	99.72 130	94.31 262	99.31 135	99.02 204

DPM-MVS		97.55 115	96.99 136	99.23 44	99.04 122	98.55 28	97.17 383	98.35 233	94.85 211	97.93 150	98.58 194	95.07 78	99.71 135	92.60 313	99.34 132	99.43 120

h-mvs33		96.17 196	95.62 210	97.81 179	99.03 123	94.45 260	98.64 198	98.75 121	97.48 50	98.67 98	98.72 181	89.76 206	99.86 77	97.95 88	81.59 434	99.11 186

test2506		94.44 309	93.91 307	96.04 319	99.02 124	88.99 406	99.06 68	79.47 468	96.96 88	98.36 120	99.26 74	77.21 407	99.52 179	96.78 169	99.04 146	99.59 89

ECVR-MVS		95.95 204	95.71 204	96.65 269	99.02 124	90.86 363	99.03 77	91.80 455	96.96 88	98.10 130	99.26 74	81.31 366	99.51 180	96.90 156	99.04 146	99.59 89

SymmetryMVS		97.84 90	97.58 92	98.62 94	99.01 126	96.60 137	98.94 100	98.44 205	97.86 29	98.71 95	99.08 117	91.22 171	99.80 103	97.40 134	97.53 232	99.47 110

Anonymous20240529		95.10 261	94.22 282	97.75 186	99.01 126	94.26 271	98.87 125	98.83 92	85.79 430	96.64 223	98.97 132	78.73 389	99.85 78	96.27 184	94.89 293	99.12 183

Anonymous202405211		95.28 250	94.49 266	97.67 196	99.00 128	93.75 289	98.70 182	97.04 387	90.66 383	96.49 234	98.80 162	78.13 396	99.83 84	96.21 188	95.36 292	99.44 118

DELS-MVS		98.40 57	98.20 66	98.99 65	99.00 128	97.66 76	97.75 335	98.89 70	97.71 34	98.33 123	98.97 132	94.97 81	99.88 71	98.42 67	99.76 43	99.42 123
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 85	98.48 33	96.30 310	99.00 128	89.54 395	97.43 357	98.87 80	98.16 20	99.26 52	99.38 51	96.12 35	99.64 150	98.30 72	99.77 37	99.72 54

test1111		95.94 207	95.78 198	96.41 302	98.99 131	90.12 382	99.04 74	92.45 454	96.99 87	98.03 137	99.27 73	81.40 365	99.48 189	96.87 162	99.04 146	99.63 83

thres100view900		95.38 241	94.70 255	97.41 214	98.98 132	94.92 238	98.87 125	96.90 398	95.38 170	96.61 226	96.88 362	84.29 338	99.56 166	88.11 397	96.29 270	97.76 287

thres600view7		95.49 231	94.77 250	97.67 196	98.98 132	95.02 229	98.85 133	96.90 398	95.38 170	96.63 224	96.90 361	84.29 338	99.59 160	88.65 394	96.33 266	98.40 266

mamv4		97.13 147	98.11 71	94.17 394	98.97 134	83.70 438	98.66 194	98.71 131	94.63 223	97.83 157	98.90 147	96.25 29	99.55 173	99.27 26	99.76 43	99.27 151

MVSMamba_PlusPlus		98.31 68	98.19 68	98.67 90	98.96 135	97.36 92	99.24 31	98.57 173	94.81 212	98.99 69	98.90 147	95.22 72	99.59 160	99.15 28	99.84 11	99.07 199

test_cas_vis1_n_1920		97.38 129	97.36 112	97.45 210	98.95 136	93.25 313	99.00 84	98.53 182	97.70 35	99.77 16	99.35 58	84.71 331	99.85 78	98.57 50	99.66 73	99.26 158

tfpn200view9		95.32 248	94.62 259	97.43 212	98.94 137	94.98 234	98.68 187	96.93 396	95.33 173	96.55 230	96.53 381	84.23 342	99.56 166	88.11 397	96.29 270	97.76 287

thres400		95.38 241	94.62 259	97.65 200	98.94 137	94.98 234	98.68 187	96.93 396	95.33 173	96.55 230	96.53 381	84.23 342	99.56 166	88.11 397	96.29 270	98.40 266

MSDG		95.93 208	95.30 227	97.83 176	98.90 139	95.36 211	96.83 408	98.37 229	91.32 369	94.43 290	98.73 178	90.27 198	99.60 159	90.05 370	98.82 163	98.52 260

RPSCF		94.87 277	95.40 215	93.26 407	98.89 140	82.06 445	98.33 250	98.06 303	90.30 392	96.56 228	99.26 74	87.09 281	99.49 184	93.82 280	96.32 267	98.24 273

fmvsm_s_conf0.1_n_2		98.14 76	98.02 77	98.53 106	98.88 141	97.07 116	98.69 185	98.82 95	98.78 7	99.77 16	99.61 4	88.83 241	99.91 51	99.71 13	99.07 144	98.61 251

test_fmvsmconf_n		98.92 11	98.87 6	99.04 63	98.88 141	97.25 107	98.82 141	99.34 11	98.75 9	99.80 12	99.61 4	95.16 74	99.95 9	99.70 15	99.80 24	99.93 1

VNet		97.79 93	97.40 109	98.96 70	98.88 141	97.55 81	98.63 201	98.93 61	96.74 99	99.02 64	98.84 155	90.33 196	99.83 84	98.53 53	96.66 255	99.50 101

LFMVS		95.86 212	94.98 242	98.47 115	98.87 144	96.32 156	98.84 137	96.02 421	93.40 294	98.62 104	99.20 86	74.99 423	99.63 153	97.72 104	97.20 237	99.46 115

fmvsm_s_conf0.5_n_7		98.23 71	98.35 43	97.89 173	98.86 145	94.99 233	98.58 209	99.00 49	98.29 18	99.73 20	99.60 9	91.70 149	99.92 41	99.63 19	99.73 57	98.76 233

UA-Net		97.96 82	97.62 90	98.98 67	98.86 145	97.47 87	98.89 115	99.08 42	96.67 105	98.72 94	99.54 18	93.15 113	99.81 96	94.87 235	98.83 162	99.65 78

WTY-MVS		97.37 131	96.92 140	98.72 86	98.86 145	96.89 125	98.31 255	98.71 131	95.26 178	97.67 171	98.56 198	92.21 134	99.78 118	95.89 197	96.85 249	99.48 108

IS-MVSNet		97.22 139	96.88 141	98.25 136	98.85 148	96.36 154	99.19 45	97.97 308	95.39 169	97.23 192	98.99 131	91.11 178	98.93 278	94.60 250	98.59 174	99.47 110

VDD-MVS		95.82 215	95.23 229	97.61 203	98.84 149	93.98 280	98.68 187	97.40 359	95.02 199	97.95 146	99.34 62	74.37 428	99.78 118	98.64 46	96.80 250	99.08 195

test_fmvs1		96.42 183	96.67 157	95.66 339	98.82 150	88.53 415	98.80 150	98.20 267	96.39 118	99.64 28	99.20 86	80.35 380	99.67 143	99.04 31	99.57 94	98.78 229

CHOSEN 280x420		97.18 143	97.18 124	97.20 223	98.81 151	93.27 310	95.78 428	99.15 38	95.25 179	96.79 217	98.11 242	92.29 129	99.07 255	98.56 52	99.85 6	99.25 160

thres200		95.25 251	94.57 262	97.28 220	98.81 151	94.92 238	98.20 270	97.11 380	95.24 181	96.54 232	96.22 392	84.58 335	99.53 176	87.93 402	96.50 262	97.39 301

XVG-OURS-SEG-HR		96.51 180	96.34 173	97.02 240	98.77 153	93.76 287	97.79 333	98.50 193	95.45 165	96.94 206	99.09 115	87.87 267	99.55 173	96.76 170	95.83 287	97.74 289

XVG-OURS		96.55 179	96.41 169	96.99 241	98.75 154	93.76 287	97.50 354	98.52 185	95.67 154	96.83 212	99.30 68	88.95 239	99.53 176	95.88 198	96.26 275	97.69 292

test_yl		97.22 139	96.78 149	98.54 103	98.73 155	96.60 137	98.45 235	98.31 242	94.70 217	98.02 139	98.42 209	90.80 186	99.70 136	96.81 166	96.79 251	99.34 135

DCV-MVSNet		97.22 139	96.78 149	98.54 103	98.73 155	96.60 137	98.45 235	98.31 242	94.70 217	98.02 139	98.42 209	90.80 186	99.70 136	96.81 166	96.79 251	99.34 135

CANet		98.05 80	97.76 86	98.90 76	98.73 155	97.27 101	98.35 248	98.78 115	97.37 60	97.72 167	98.96 137	91.53 158	99.92 41	98.79 39	99.65 76	99.51 99

Vis-MVSNet (Re-imp)		96.87 159	96.55 163	97.83 176	98.73 155	95.46 206	99.20 43	98.30 249	94.96 203	96.60 227	98.87 152	90.05 200	98.59 317	93.67 285	98.60 173	99.46 115

PAPR		96.84 161	96.24 178	98.65 92	98.72 159	96.92 122	97.36 364	98.57 173	93.33 296	96.67 222	97.57 296	94.30 95	99.56 166	91.05 356	98.59 174	99.47 110

sasdasda		97.67 100	97.23 120	98.98 67	98.70 160	98.38 36	99.34 17	98.39 223	96.76 97	97.67 171	97.40 310	92.26 130	99.49 184	98.28 73	96.28 273	99.08 195

canonicalmvs		97.67 100	97.23 120	98.98 67	98.70 160	98.38 36	99.34 17	98.39 223	96.76 97	97.67 171	97.40 310	92.26 130	99.49 184	98.28 73	96.28 273	99.08 195

API-MVS		97.41 127	97.25 117	97.91 170	98.70 160	96.80 127	98.82 141	98.69 137	94.53 229	98.11 129	98.28 226	94.50 91	99.57 163	94.12 270	99.49 113	97.37 303

testing3-2		95.45 235	95.34 221	95.77 335	98.69 163	88.75 410	98.87 125	97.21 375	96.13 129	97.22 193	97.68 285	77.95 400	99.65 147	97.58 117	96.77 253	98.91 216

MAR-MVS		96.91 157	96.40 170	98.45 117	98.69 163	96.90 123	98.66 194	98.68 140	92.40 336	97.07 201	97.96 255	91.54 157	99.75 126	93.68 283	98.92 153	98.69 241
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 95	97.77 85	97.62 202	98.68 165	95.58 198	97.34 366	98.51 188	97.29 63	98.66 102	97.88 264	94.51 88	99.90 59	97.87 95	99.17 142	97.39 301

test_fmvs1_n		95.90 210	95.99 191	95.63 340	98.67 166	88.32 419	99.26 28	98.22 264	96.40 117	99.67 25	99.26 74	73.91 429	99.70 136	99.02 32	99.50 111	98.87 218

MGCFI-Net		97.62 106	97.19 123	98.92 73	98.66 167	98.20 54	99.32 22	98.38 227	96.69 103	97.58 182	97.42 309	92.10 138	99.50 183	98.28 73	96.25 276	99.08 195

alignmvs		97.56 114	97.07 130	99.01 64	98.66 167	98.37 43	98.83 139	98.06 303	96.74 99	98.00 143	97.65 287	90.80 186	99.48 189	98.37 69	96.56 259	99.19 171

Vis-MVSNet		97.42 126	97.11 127	98.34 128	98.66 167	96.23 159	99.22 37	99.00 49	96.63 107	98.04 136	99.21 84	88.05 262	99.35 205	96.01 195	99.21 139	99.45 117
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
balanced_conf03		98.45 51	98.35 43	98.74 84	98.65 170	97.55 81	99.19 45	98.60 159	96.72 102	99.35 44	98.77 171	95.06 79	99.55 173	98.95 33	99.87 1	99.12 183

EPP-MVSNet		97.46 120	97.28 115	97.99 166	98.64 171	95.38 210	99.33 21	98.31 242	93.61 285	97.19 194	99.07 120	94.05 100	99.23 226	96.89 157	98.43 188	99.37 129

ab-mvs		96.42 183	95.71 204	98.55 101	98.63 172	96.75 130	97.88 321	98.74 123	93.84 263	96.54 232	98.18 237	85.34 317	99.75 126	95.93 196	96.35 265	99.15 178

PCF-MVS	93.45 11	94.68 286	93.43 338	98.42 123	98.62 173	96.77 129	95.48 434	98.20 267	84.63 435	93.34 345	98.32 223	88.55 249	99.81 96	84.80 424	98.96 152	98.68 243
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
xiu_mvs_v2_base		97.66 102	97.70 88	97.56 206	98.61 174	95.46 206	97.44 355	98.46 201	97.15 78	98.65 103	98.15 239	94.33 94	99.80 103	97.84 98	98.66 171	97.41 299

sss		97.39 128	96.98 138	98.61 95	98.60 175	96.61 136	98.22 267	98.93 61	93.97 256	98.01 142	98.48 204	91.98 142	99.85 78	96.45 179	98.15 203	99.39 126

Test_1112_low_res		96.34 188	95.66 209	98.36 127	98.56 176	95.94 176	97.71 338	98.07 298	92.10 346	94.79 277	97.29 318	91.75 148	99.56 166	94.17 268	96.50 262	99.58 93

1112_ss		96.63 173	96.00 190	98.50 111	98.56 176	96.37 153	98.18 278	98.10 291	92.92 316	94.84 273	98.43 207	92.14 136	99.58 162	94.35 259	96.51 261	99.56 95

BH-untuned		95.95 204	95.72 201	96.65 269	98.55 178	92.26 333	98.23 266	97.79 319	93.73 271	94.62 280	98.01 250	88.97 238	99.00 267	93.04 302	98.51 182	98.68 243

fmvsm_s_conf0.1_n		98.18 75	98.21 64	98.11 153	98.54 179	95.24 219	98.87 125	99.24 20	97.50 48	99.70 24	99.67 1	91.33 165	99.89 62	99.47 23	99.54 105	99.21 166

LS3D		97.16 145	96.66 158	98.68 89	98.53 180	97.19 110	98.93 106	98.90 68	92.83 320	95.99 251	99.37 52	92.12 137	99.87 73	93.67 285	99.57 94	98.97 209

guyue		97.57 112	97.37 111	98.20 141	98.50 181	95.86 188	98.89 115	97.03 388	97.29 63	98.73 92	98.90 147	89.41 220	99.32 209	98.68 43	98.86 159	99.42 123

fmvsm_s_conf0.5_n_6		98.65 22	98.55 25	98.95 72	98.50 181	97.30 97	98.79 158	99.16 36	98.14 21	99.86 7	99.41 44	93.71 106	99.91 51	99.71 13	99.64 81	99.65 78

hse-mvs2		95.71 220	95.30 227	96.93 247	98.50 181	93.53 298	98.36 247	98.10 291	97.48 50	98.67 98	97.99 252	89.76 206	99.02 264	97.95 88	80.91 439	98.22 275

AUN-MVS		94.53 300	93.73 323	96.92 250	98.50 181	93.52 299	98.34 249	98.10 291	93.83 265	95.94 255	97.98 254	85.59 312	99.03 261	94.35 259	80.94 438	98.22 275

baseline1		95.84 213	95.12 235	98.01 164	98.49 185	95.98 168	98.73 173	97.03 388	95.37 172	96.22 242	98.19 236	89.96 202	99.16 235	94.60 250	87.48 401	98.90 217

SSM_0404		97.26 137	97.00 134	98.03 161	98.46 186	95.99 167	98.62 204	98.44 205	94.77 214	97.24 191	98.93 141	91.22 171	99.28 217	96.54 174	98.74 166	98.84 221

HY-MVS	93.96 8	96.82 162	96.23 179	98.57 98	98.46 186	97.00 118	98.14 283	98.21 265	93.95 257	96.72 221	97.99 252	91.58 153	99.76 124	94.51 254	96.54 260	98.95 212

ETV-MVS		97.96 82	97.81 84	98.40 125	98.42 188	97.27 101	98.73 173	98.55 178	96.84 92	98.38 119	97.44 306	95.39 58	99.35 205	97.62 114	98.89 155	98.58 257

casdiffmvs_mvg		97.72 96	97.48 103	98.44 119	98.42 188	96.59 141	98.92 108	98.44 205	96.20 126	97.76 161	99.20 86	91.66 152	99.23 226	98.27 76	98.41 193	99.49 106
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		97.47 119	97.25 117	98.14 145	98.41 190	95.84 189	98.57 216	98.43 213	95.55 160	97.97 144	99.12 104	91.26 169	99.15 238	97.42 132	98.53 180	99.43 120

tttt0517		96.07 199	95.51 213	97.78 181	98.41 190	94.84 241	99.28 25	94.33 442	94.26 242	97.64 176	98.64 188	84.05 346	99.47 193	95.34 219	97.60 224	99.03 203

reproduce_monomvs		94.77 282	94.67 257	95.08 360	98.40 192	89.48 396	98.80 150	98.64 153	97.57 44	93.21 349	97.65 287	80.57 378	98.83 294	97.72 104	89.47 379	96.93 318

EIA-MVS		97.75 94	97.58 92	98.27 132	98.38 193	96.44 148	99.01 82	98.60 159	95.88 142	97.26 190	97.53 300	94.97 81	99.33 208	97.38 137	99.20 140	99.05 200

thisisatest0530		96.01 201	95.36 220	97.97 167	98.38 193	95.52 203	98.88 122	94.19 444	94.04 248	97.64 176	98.31 224	83.82 353	99.46 194	95.29 224	97.70 221	98.93 214

KinetiMVS		97.48 118	97.05 132	98.78 81	98.37 195	97.30 97	98.99 87	98.70 135	97.18 75	99.02 64	99.01 128	87.50 275	99.67 143	95.33 220	99.33 134	99.37 129

FE-MVS		95.62 226	94.90 246	97.78 181	98.37 195	94.92 238	97.17 383	97.38 361	90.95 380	97.73 166	97.70 280	85.32 319	99.63 153	91.18 348	98.33 198	98.79 225

GeoE		96.58 177	96.07 184	98.10 154	98.35 197	95.89 186	99.34 17	98.12 285	93.12 308	96.09 247	98.87 152	89.71 209	98.97 268	92.95 305	98.08 206	99.43 120

xiu_mvs_v1_base_debu		97.60 107	97.56 95	97.72 188	98.35 197	95.98 168	97.86 324	98.51 188	97.13 80	99.01 66	98.40 211	91.56 154	99.80 103	98.53 53	98.68 167	97.37 303

xiu_mvs_v1_base		97.60 107	97.56 95	97.72 188	98.35 197	95.98 168	97.86 324	98.51 188	97.13 80	99.01 66	98.40 211	91.56 154	99.80 103	98.53 53	98.68 167	97.37 303

xiu_mvs_v1_base_debi		97.60 107	97.56 95	97.72 188	98.35 197	95.98 168	97.86 324	98.51 188	97.13 80	99.01 66	98.40 211	91.56 154	99.80 103	98.53 53	98.68 167	97.37 303

baseline		97.64 103	97.44 106	98.25 136	98.35 197	96.20 160	99.00 84	98.32 238	96.33 123	98.03 137	99.17 93	91.35 164	99.16 235	98.10 81	98.29 201	99.39 126

mvsmamba		97.25 138	96.99 136	98.02 163	98.34 202	95.54 202	99.18 49	97.47 350	95.04 195	98.15 126	98.57 197	89.46 217	99.31 212	97.68 111	99.01 149	99.22 164

BH-w/o		95.38 241	95.08 237	96.26 312	98.34 202	91.79 344	97.70 339	97.43 357	92.87 318	94.24 303	97.22 324	88.66 244	98.84 291	91.55 344	97.70 221	98.16 278

EC-MVSNet		98.21 74	98.11 71	98.49 113	98.34 202	97.26 106	99.61 5	98.43 213	96.78 95	98.87 79	98.84 155	93.72 105	99.01 266	98.91 35	99.50 111	99.19 171

test_fmvsmvis_n_1920		98.44 52	98.51 27	98.23 138	98.33 205	96.15 163	98.97 91	99.15 38	98.55 14	98.45 115	99.55 16	94.26 97	99.97 1	99.65 16	99.66 73	98.57 258

MVS_Test		97.28 135	97.00 134	98.13 149	98.33 205	95.97 173	98.74 167	98.07 298	94.27 241	98.44 117	98.07 244	92.48 122	99.26 220	96.43 180	98.19 202	99.16 177

casdiffmvs		97.63 105	97.41 108	98.28 131	98.33 205	96.14 164	98.82 141	98.32 238	96.38 119	97.95 146	99.21 84	91.23 170	99.23 226	98.12 80	98.37 195	99.48 108
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		97.58 111	97.40 109	98.13 149	98.32 208	95.81 192	98.06 295	98.37 229	96.20 126	98.74 90	98.89 150	91.31 167	99.25 223	98.16 79	98.52 181	99.34 135
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		95.92 209	95.32 225	97.69 192	98.32 208	94.64 250	98.19 273	97.45 355	94.56 227	96.03 249	98.61 189	85.02 322	99.12 246	90.68 361	99.06 145	99.30 145

viewmacassd2359aftdt		97.32 133	97.07 130	98.08 156	98.30 210	95.69 195	98.62 204	98.44 205	95.56 158	97.86 156	99.22 82	89.91 203	99.14 241	97.29 140	98.43 188	99.42 123

GDP-MVS		97.64 103	97.28 115	98.71 87	98.30 210	97.33 93	99.05 70	98.52 185	96.34 121	98.80 85	99.05 122	89.74 208	99.51 180	96.86 165	98.86 159	99.28 150

VortexMVS		95.95 204	95.79 197	96.42 301	98.29 212	93.96 281	98.68 187	98.31 242	96.02 134	94.29 299	97.57 296	89.47 215	98.37 347	97.51 128	91.93 342	96.94 317

Fast-Effi-MVS+		96.28 193	95.70 206	98.03 161	98.29 212	95.97 173	98.58 209	98.25 261	91.74 354	95.29 266	97.23 323	91.03 181	99.15 238	92.90 307	97.96 210	98.97 209

diffmvs_AUTHOR		97.59 110	97.44 106	98.01 164	98.26 214	95.47 205	98.12 286	98.36 232	96.38 119	98.84 81	99.10 107	91.13 175	99.26 220	98.24 77	98.56 177	99.30 145

BP-MVS1		97.82 91	97.51 100	98.76 83	98.25 215	97.39 91	99.15 52	97.68 323	96.69 103	98.47 111	99.10 107	90.29 197	99.51 180	98.60 48	99.35 131	99.37 129

mvsany_test1		97.69 99	97.70 88	97.66 199	98.24 216	94.18 275	97.53 351	97.53 344	95.52 162	99.66 26	99.51 24	94.30 95	99.56 166	98.38 68	98.62 172	99.23 162

UGNet		96.78 164	96.30 175	98.19 144	98.24 216	95.89 186	98.88 122	98.93 61	97.39 57	96.81 215	97.84 268	82.60 360	99.90 59	96.53 176	99.49 113	98.79 225
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		96.06 200	95.72 201	97.08 236	98.23 218	95.93 179	98.73 173	98.27 252	94.86 209	95.07 268	98.09 243	88.21 255	98.54 320	96.59 172	93.46 319	96.79 338

ET-MVSNet_ETH3D		94.13 330	92.98 348	97.58 204	98.22 219	96.20 160	97.31 369	95.37 431	94.53 229	79.56 449	97.63 292	86.51 290	97.53 409	96.91 153	90.74 359	99.02 204

FA-MVS(test-final)		96.41 186	95.94 192	97.82 178	98.21 220	95.20 221	97.80 331	97.58 334	93.21 302	97.36 186	97.70 280	89.47 215	99.56 166	94.12 270	97.99 208	98.71 239

GBi-Net		94.49 304	93.80 316	96.56 284	98.21 220	95.00 230	98.82 141	98.18 272	92.46 330	94.09 310	97.07 337	81.16 368	97.95 385	92.08 327	92.14 339	96.72 346

test1		94.49 304	93.80 316	96.56 284	98.21 220	95.00 230	98.82 141	98.18 272	92.46 330	94.09 310	97.07 337	81.16 368	97.95 385	92.08 327	92.14 339	96.72 346

FMVSNet2		94.47 307	93.61 329	97.04 239	98.21 220	96.43 149	98.79 158	98.27 252	92.46 330	93.50 338	97.09 334	81.16 368	98.00 382	91.09 351	91.93 342	96.70 350

mamba_0408		96.81 163	96.38 171	98.09 155	98.19 224	95.90 182	95.69 429	98.32 238	94.51 232	96.75 218	98.73 178	90.99 182	99.27 219	95.83 200	98.43 188	99.10 188

SSM_04072		96.71 168	96.38 171	97.68 194	98.19 224	95.90 182	95.69 429	98.32 238	94.51 232	96.75 218	98.73 178	90.99 182	98.02 379	95.83 200	98.43 188	99.10 188

SSM_0407		97.17 144	96.87 142	98.08 156	98.19 224	95.90 182	98.52 221	98.44 205	94.77 214	96.75 218	98.93 141	91.22 171	99.22 230	96.54 174	98.43 188	99.10 188

viewmambaseed2359dif		97.01 153	96.84 144	97.51 208	98.19 224	94.21 274	98.16 280	98.23 263	93.61 285	97.78 159	99.13 101	90.79 189	99.18 234	97.24 141	98.40 194	99.15 178

Effi-MVS+		97.12 148	96.69 155	98.39 126	98.19 224	96.72 132	97.37 362	98.43 213	93.71 274	97.65 175	98.02 248	92.20 135	99.25 223	96.87 162	97.79 216	99.19 171

mvs_anonymous		96.70 170	96.53 165	97.18 226	98.19 224	93.78 286	98.31 255	98.19 269	94.01 253	94.47 285	98.27 229	92.08 140	98.46 328	97.39 136	97.91 211	99.31 142

ETVMVS		94.50 303	93.44 337	97.68 194	98.18 230	95.35 213	98.19 273	97.11 380	93.73 271	96.40 238	95.39 417	74.53 425	98.84 291	91.10 350	96.31 268	98.84 221

LCM-MVSNet-Re		95.22 253	95.32 225	94.91 365	98.18 230	87.85 425	98.75 163	95.66 428	95.11 190	88.96 413	96.85 365	90.26 199	97.65 402	95.65 211	98.44 186	99.22 164

FMVSNet3		94.97 272	94.26 280	97.11 234	98.18 230	96.62 134	98.56 218	98.26 260	93.67 281	94.09 310	97.10 330	84.25 340	98.01 380	92.08 327	92.14 339	96.70 350

myMVS_eth3d28		95.12 259	94.62 259	96.64 273	98.17 233	92.17 334	98.02 300	97.32 364	95.41 168	96.22 242	96.05 398	78.01 398	99.13 243	95.22 228	97.16 238	98.60 252

CANet_DTU		96.96 155	96.55 163	98.21 139	98.17 233	96.07 166	97.98 305	98.21 265	97.24 70	97.13 196	98.93 141	86.88 286	99.91 51	95.00 233	99.37 130	98.66 247

thisisatest0515		95.61 229	94.89 247	97.76 185	98.15 235	95.15 224	96.77 409	94.41 440	92.95 315	97.18 195	97.43 307	84.78 328	99.45 195	94.63 247	97.73 220	98.68 243

AstraMVS		97.34 132	97.24 119	97.65 200	98.13 236	94.15 276	98.94 100	96.25 420	97.47 52	98.60 106	99.28 70	89.67 210	99.41 199	98.73 41	98.07 207	99.38 128

IterMVS-LS		95.46 233	95.21 230	96.22 313	98.12 237	93.72 292	98.32 254	98.13 284	93.71 274	94.26 301	97.31 317	92.24 132	98.10 370	94.63 247	90.12 367	96.84 334
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cl22		94.68 286	94.19 284	96.13 316	98.11 238	93.60 294	96.94 395	98.31 242	92.43 334	93.32 346	96.87 364	86.51 290	98.28 360	94.10 272	91.16 354	96.51 378

viewdifsd2359ckpt11		96.30 189	96.13 181	96.81 256	98.10 239	92.10 337	98.49 231	98.40 218	96.02 134	97.61 178	99.31 65	86.37 296	99.29 215	97.52 125	93.36 325	99.04 201

viewmsd2359difaftdt		96.30 189	96.13 181	96.81 256	98.10 239	92.10 337	98.49 231	98.40 218	96.02 134	97.61 178	99.31 65	86.37 296	99.30 213	97.52 125	93.37 324	99.04 201

VDDNet		95.36 244	94.53 264	97.86 174	98.10 239	95.13 225	98.85 133	97.75 321	90.46 387	98.36 120	99.39 46	73.27 431	99.64 150	97.98 87	96.58 258	98.81 224

testing3		93.19 357	92.48 361	95.30 353	98.07 242	92.27 332	98.64 198	97.17 378	93.94 259	93.98 316	97.04 345	67.97 440	96.01 437	88.40 395	97.14 239	97.63 294

MVSFormer		97.57 112	97.49 101	97.84 175	98.07 242	95.76 193	99.47 7	98.40 218	94.98 201	98.79 86	98.83 159	92.34 126	98.41 340	96.91 153	99.59 90	99.34 135

lupinMVS		97.44 124	97.22 122	98.12 152	98.07 242	95.76 193	97.68 340	97.76 320	94.50 234	98.79 86	98.61 189	92.34 126	99.30 213	97.58 117	99.59 90	99.31 142

MVS_0304		98.23 71	97.91 82	99.21 45	98.06 245	97.96 68	98.58 209	95.51 429	98.58 12	98.87 79	99.26 74	92.99 115	99.95 9	99.62 20	99.67 70	99.73 50

TAMVS		97.02 152	96.79 148	97.70 191	98.06 245	95.31 216	98.52 221	98.31 242	93.95 257	97.05 203	98.61 189	93.49 108	98.52 322	95.33 220	97.81 215	99.29 148

UBG		95.32 248	94.72 254	97.13 230	98.05 247	93.26 311	97.87 322	97.20 376	94.96 203	96.18 245	95.66 414	80.97 372	99.35 205	94.47 256	97.08 240	98.78 229

CDS-MVSNet		96.99 154	96.69 155	97.90 171	98.05 247	95.98 168	98.20 270	98.33 237	93.67 281	96.95 205	98.49 203	93.54 107	98.42 333	95.24 227	97.74 219	99.31 142
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Elysia		96.64 171	96.02 188	98.51 108	98.04 249	97.30 97	98.74 167	98.60 159	95.04 195	97.91 152	98.84 155	83.59 355	99.48 189	94.20 266	99.25 137	98.75 234

StellarMVS		96.64 171	96.02 188	98.51 108	98.04 249	97.30 97	98.74 167	98.60 159	95.04 195	97.91 152	98.84 155	83.59 355	99.48 189	94.20 266	99.25 137	98.75 234

WBMVS		94.56 296	94.04 294	96.10 318	98.03 251	93.08 321	97.82 330	98.18 272	94.02 250	93.77 327	96.82 367	81.28 367	98.34 349	95.47 218	91.00 357	96.88 328

SD_0403		94.28 320	94.46 269	93.73 398	98.02 252	85.32 434	98.31 255	98.40 218	94.75 216	93.59 330	98.16 238	89.01 233	96.54 429	82.32 433	97.58 226	99.34 135

testing222		94.12 332	93.03 347	97.37 219	98.02 252	94.66 248	97.94 310	96.65 412	94.63 223	95.78 256	95.76 406	71.49 433	98.92 279	91.17 349	95.88 285	98.52 260

ADS-MVSNet2		94.58 295	94.40 276	95.11 358	98.00 254	88.74 411	96.04 422	97.30 366	90.15 393	96.47 235	96.64 378	87.89 265	97.56 408	90.08 368	97.06 241	99.02 204

ADS-MVSNet		95.00 266	94.45 272	96.63 274	98.00 254	91.91 343	96.04 422	97.74 322	90.15 393	96.47 235	96.64 378	87.89 265	98.96 272	90.08 368	97.06 241	99.02 204

icg_test_0407_2		96.56 178	96.50 166	96.73 261	97.99 256	92.82 325	97.18 380	98.27 252	95.16 183	97.30 187	98.79 164	91.53 158	98.10 370	94.74 241	97.54 228	99.27 151

IMVS_0407		96.74 165	96.64 159	97.05 238	97.99 256	92.82 325	98.45 235	98.27 252	95.16 183	97.30 187	98.79 164	91.53 158	99.06 256	94.74 241	97.54 228	99.27 151

IMVS_0404		95.82 215	95.52 211	96.73 261	97.99 256	92.82 325	97.23 373	98.27 252	95.16 183	94.31 297	98.79 164	85.63 310	98.10 370	94.74 241	97.54 228	99.27 151

IMVS_0403		96.74 165	96.61 160	97.12 232	97.99 256	92.82 325	98.47 233	98.27 252	95.16 183	97.13 196	98.79 164	91.44 161	99.26 220	94.74 241	97.54 228	99.27 151

IterMVS		94.09 335	93.85 313	94.80 374	97.99 256	90.35 379	97.18 380	98.12 285	93.68 279	92.46 375	97.34 313	84.05 346	97.41 412	92.51 320	91.33 350	96.62 359
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PVSNet_0	88.72 19	91.28 379	90.03 386	95.00 362	97.99 256	87.29 428	94.84 440	98.50 193	92.06 347	89.86 405	95.19 420	79.81 383	99.39 203	92.27 324	69.79 456	98.33 271

tt0805		94.54 298	93.85 313	96.63 274	97.98 262	93.06 322	98.77 162	97.84 317	93.67 281	93.80 325	98.04 247	76.88 414	98.96 272	94.79 240	92.86 332	97.86 286

IterMVS-SCA-FT		94.11 333	93.87 311	94.85 370	97.98 262	90.56 374	97.18 380	98.11 288	93.75 268	92.58 369	97.48 302	83.97 348	97.41 412	92.48 322	91.30 351	96.58 363

testing11		95.00 266	94.28 279	97.16 228	97.96 264	93.36 308	98.09 292	97.06 386	94.94 207	95.33 265	96.15 394	76.89 413	99.40 200	95.77 206	96.30 269	98.72 236

testing91		94.98 270	94.25 281	97.20 223	97.94 265	93.41 303	98.00 303	97.58 334	94.99 200	95.45 261	96.04 399	77.20 408	99.42 198	94.97 234	96.02 283	98.78 229

testing99		94.83 278	94.08 292	97.07 237	97.94 265	93.13 317	98.10 291	97.17 378	94.86 209	95.34 262	96.00 403	76.31 416	99.40 200	95.08 231	95.90 284	98.68 243

EI-MVSNet		95.96 203	95.83 196	96.36 305	97.93 267	93.70 293	98.12 286	98.27 252	93.70 276	95.07 268	99.02 124	92.23 133	98.54 320	94.68 245	93.46 319	96.84 334

CVMVSNet		95.43 237	96.04 186	93.57 401	97.93 267	83.62 439	98.12 286	98.59 166	95.68 153	96.56 228	99.02 124	87.51 273	97.51 410	93.56 289	97.44 233	99.60 87

RRT-MVS		97.03 151	96.78 149	97.77 184	97.90 269	94.34 267	99.12 59	98.35 233	95.87 143	98.06 133	98.70 182	86.45 294	99.63 153	98.04 86	98.54 179	99.35 133

PMMVS		96.60 174	96.33 174	97.41 214	97.90 269	93.93 282	97.35 365	98.41 216	92.84 319	97.76 161	97.45 305	91.10 179	99.20 231	96.26 185	97.91 211	99.11 186

Effi-MVS+-dtu		96.29 191	96.56 162	95.51 344	97.89 271	90.22 381	98.80 150	98.10 291	96.57 110	96.45 237	96.66 375	90.81 185	98.91 281	95.72 207	97.99 208	97.40 300

QAPM		96.29 191	95.40 215	98.96 70	97.85 272	97.60 80	99.23 33	98.93 61	89.76 400	93.11 355	99.02 124	89.11 230	99.93 32	91.99 332	99.62 85	99.34 135

UWE-MVS		94.30 316	93.89 310	95.53 343	97.83 273	88.95 407	97.52 353	93.25 448	94.44 237	96.63 224	97.07 337	78.70 390	99.28 217	91.99 332	97.56 227	98.36 269

3Dnovator+	94.38 6	97.43 125	96.78 149	99.38 19	97.83 273	98.52 29	99.37 13	98.71 131	97.09 83	92.99 358	99.13 101	89.36 222	99.89 62	96.97 150	99.57 94	99.71 58

ACMH+	92.99 14	94.30 316	93.77 319	95.88 329	97.81 275	92.04 342	98.71 178	98.37 229	93.99 255	90.60 399	98.47 205	80.86 375	99.05 257	92.75 311	92.40 338	96.55 369

3Dnovator	94.51 5	97.46 120	96.93 139	99.07 60	97.78 276	97.64 77	99.35 16	99.06 44	97.02 85	93.75 328	99.16 96	89.25 225	99.92 41	97.22 143	99.75 50	99.64 81

test_vis1_n		95.47 232	95.13 233	96.49 292	97.77 277	90.41 377	99.27 27	98.11 288	96.58 108	99.66 26	99.18 92	67.00 443	99.62 157	99.21 27	99.40 126	99.44 118

miper_lstm_enhance		94.33 314	94.07 293	95.11 358	97.75 278	90.97 359	97.22 375	98.03 305	91.67 358	92.76 363	96.97 353	90.03 201	97.78 398	92.51 320	89.64 373	96.56 367

c3_l		94.79 280	94.43 274	95.89 328	97.75 278	93.12 319	97.16 385	98.03 305	92.23 342	93.46 341	97.05 344	91.39 162	98.01 380	93.58 288	89.21 383	96.53 372

TR-MVS		94.94 275	94.20 283	97.17 227	97.75 278	94.14 277	97.59 348	97.02 391	92.28 341	95.75 257	97.64 290	83.88 350	98.96 272	89.77 374	96.15 280	98.40 266

Fast-Effi-MVS+-dtu		95.87 211	95.85 195	95.91 326	97.74 281	91.74 347	98.69 185	98.15 281	95.56 158	94.92 271	97.68 285	88.98 237	98.79 299	93.19 297	97.78 217	97.20 307

test_fmvsmconf0.1_n		98.58 32	98.44 35	98.99 65	97.73 282	97.15 112	98.84 137	98.97 53	98.75 9	99.43 39	99.54 18	93.29 111	99.93 32	99.64 18	99.79 30	99.89 6

MIMVSNet		93.26 354	92.21 365	96.41 302	97.73 282	93.13 317	95.65 431	97.03 388	91.27 373	94.04 313	96.06 397	75.33 421	97.19 415	86.56 408	96.23 278	98.92 215

miper_ehance_all_eth		95.01 265	94.69 256	95.97 323	97.70 284	93.31 309	97.02 391	98.07 298	92.23 342	93.51 337	96.96 355	91.85 146	98.15 366	93.68 283	91.16 354	96.44 386

dmvs_re		94.48 306	94.18 286	95.37 350	97.68 285	90.11 383	98.54 220	97.08 382	94.56 227	94.42 291	97.24 322	84.25 340	97.76 399	91.02 357	92.83 333	98.24 273

SCA		95.46 233	95.13 233	96.46 298	97.67 286	91.29 355	97.33 367	97.60 333	94.68 220	96.92 209	97.10 330	83.97 348	98.89 285	92.59 315	98.32 200	99.20 167

ACMP	93.49 10	95.34 246	94.98 242	96.43 300	97.67 286	93.48 300	98.73 173	98.44 205	94.94 207	92.53 371	98.53 199	84.50 337	99.14 241	95.48 217	94.00 307	96.66 356
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
fmvsm_s_conf0.1_n_a		98.08 77	98.04 76	98.21 139	97.66 288	95.39 209	98.89 115	99.17 34	97.24 70	99.76 18	99.67 1	91.13 175	99.88 71	99.39 24	99.41 123	99.35 133

eth_miper_zixun_eth		94.68 286	94.41 275	95.47 346	97.64 289	91.71 348	96.73 412	98.07 298	92.71 323	93.64 329	97.21 325	90.54 192	98.17 365	93.38 291	89.76 371	96.54 370

ACMH	92.88 16	94.55 297	93.95 304	96.34 307	97.63 290	93.26 311	98.81 149	98.49 198	93.43 293	89.74 406	98.53 199	81.91 362	99.08 254	93.69 282	93.30 327	96.70 350
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMM	93.85 9	95.69 223	95.38 219	96.61 277	97.61 291	93.84 285	98.91 110	98.44 205	95.25 179	94.28 300	98.47 205	86.04 305	99.12 246	95.50 216	93.95 309	96.87 331
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mmtdpeth		93.12 360	92.61 356	94.63 380	97.60 292	89.68 392	99.21 40	97.32 364	94.02 250	97.72 167	94.42 428	77.01 412	99.44 196	99.05 30	77.18 450	94.78 428

Patchmatch-test		94.42 310	93.68 327	96.63 274	97.60 292	91.76 345	94.83 441	97.49 349	89.45 406	94.14 308	97.10 330	88.99 234	98.83 294	85.37 418	98.13 204	99.29 148

cl____		94.51 302	94.01 299	96.02 320	97.58 294	93.40 305	97.05 389	97.96 310	91.73 356	92.76 363	97.08 336	89.06 232	98.13 368	92.61 312	90.29 365	96.52 375

tpm cat1		93.36 349	92.80 351	95.07 361	97.58 294	87.97 423	96.76 410	97.86 316	82.17 442	93.53 334	96.04 399	86.13 301	99.13 243	89.24 386	95.87 286	98.10 280

MVS-HIRNet		89.46 401	88.40 399	92.64 412	97.58 294	82.15 444	94.16 450	93.05 452	75.73 452	90.90 395	82.52 455	79.42 386	98.33 351	83.53 429	98.68 167	97.43 298

PatchmatchNet		95.71 220	95.52 211	96.29 311	97.58 294	90.72 367	96.84 407	97.52 345	94.06 247	97.08 199	96.96 355	89.24 226	98.90 284	92.03 331	98.37 195	99.26 158
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DIV-MVS_self_test		94.52 301	94.03 296	95.99 321	97.57 298	93.38 306	97.05 389	97.94 311	91.74 354	92.81 361	97.10 330	89.12 229	98.07 376	92.60 313	90.30 364	96.53 372

tpmrst		95.63 225	95.69 207	95.44 348	97.54 299	88.54 414	96.97 393	97.56 337	93.50 289	97.52 184	96.93 359	89.49 213	99.16 235	95.25 226	96.42 264	98.64 249

FMVSNet1		93.19 357	92.07 366	96.56 284	97.54 299	95.00 230	98.82 141	98.18 272	90.38 390	92.27 378	97.07 337	73.68 430	97.95 385	89.36 384	91.30 351	96.72 346

miper_enhance_ethall		95.10 261	94.75 252	96.12 317	97.53 301	93.73 291	96.61 415	98.08 296	92.20 345	93.89 319	96.65 377	92.44 123	98.30 356	94.21 265	91.16 354	96.34 389

CLD-MVS		95.62 226	95.34 221	96.46 298	97.52 302	93.75 289	97.27 372	98.46 201	95.53 161	94.42 291	98.00 251	86.21 300	98.97 268	96.25 187	94.37 294	96.66 356
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
LuminaMVS		97.49 117	97.18 124	98.42 123	97.50 303	97.15 112	98.45 235	97.68 323	96.56 111	98.68 97	98.78 168	89.84 205	99.32 209	98.60 48	98.57 176	98.79 225

MDTV_nov1_ep13			95.40 215		97.48 304	88.34 418	96.85 406	97.29 367	93.74 270	97.48 185	97.26 319	89.18 227	99.05 257	91.92 335	97.43 234

IB-MVS	91.98 17	93.27 353	91.97 368	97.19 225	97.47 305	93.41 303	97.09 388	95.99 422	93.32 297	92.47 374	95.73 409	78.06 397	99.53 176	94.59 252	82.98 429	98.62 250
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		94.60 292	94.36 277	95.33 352	97.46 306	88.60 413	96.88 404	97.68 323	91.29 371	93.80 325	96.42 385	88.58 245	99.24 225	91.06 354	96.04 282	98.17 277

LPG-MVS_test		95.62 226	95.34 221	96.47 295	97.46 306	93.54 296	98.99 87	98.54 180	94.67 221	94.36 294	98.77 171	85.39 314	99.11 248	95.71 208	94.15 302	96.76 341

LGP-MVS_train				96.47 295	97.46 306	93.54 296		98.54 180	94.67 221	94.36 294	98.77 171	85.39 314	99.11 248	95.71 208	94.15 302	96.76 341

test_vis1_rt		91.29 378	90.65 378	93.19 409	97.45 309	86.25 432	98.57 216	90.90 459	93.30 299	86.94 427	93.59 437	62.07 451	99.11 248	97.48 130	95.58 290	94.22 432

jason		97.32 133	97.08 129	98.06 160	97.45 309	95.59 197	97.87 322	97.91 314	94.79 213	98.55 109	98.83 159	91.12 177	99.23 226	97.58 117	99.60 88	99.34 135
jason: jason.
HQP_MVS		96.14 198	95.90 194	96.85 253	97.42 311	94.60 256	98.80 150	98.56 176	97.28 65	95.34 262	98.28 226	87.09 281	99.03 261	96.07 189	94.27 296	96.92 319

plane_prior7					97.42 311	94.63 251

ITE_SJBPF				95.44 348	97.42 311	91.32 354		97.50 347	95.09 193	93.59 330	98.35 217	81.70 363	98.88 287	89.71 376	93.39 323	96.12 399

LTVRE_ROB	92.95 15	94.60 292	93.90 308	96.68 268	97.41 314	94.42 262	98.52 221	98.59 166	91.69 357	91.21 392	98.35 217	84.87 325	99.04 260	91.06 354	93.44 322	96.60 361
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		92.55 368	92.61 356	92.38 414	97.39 315	83.41 440	97.91 314	97.46 351	93.16 305	93.42 342	95.37 418	84.75 329	96.12 435	77.00 448	96.99 243	97.60 295

myMVS_eth3d		92.73 365	92.01 367	94.89 367	97.39 315	90.94 360	97.91 314	97.46 351	93.16 305	93.42 342	95.37 418	68.09 439	96.12 435	88.34 396	96.99 243	97.60 295

plane_prior1					97.37 317

plane_prior6					97.35 318	94.61 254						87.09 281

dp		94.15 329	93.90 308	94.90 366	97.31 319	86.82 430	96.97 393	97.19 377	91.22 375	96.02 250	96.61 380	85.51 313	99.02 264	90.00 372	94.30 295	98.85 219

NP-MVS					97.28 320	94.51 259					97.73 277

CostFormer		94.95 273	94.73 253	95.60 342	97.28 320	89.06 403	97.53 351	96.89 400	89.66 402	96.82 214	96.72 372	86.05 303	98.95 277	95.53 215	96.13 281	98.79 225

VPA-MVSNet		95.75 218	95.11 236	97.69 192	97.24 322	97.27 101	98.94 100	99.23 25	95.13 188	95.51 260	97.32 316	85.73 308	98.91 281	97.33 139	89.55 376	96.89 327

tpm2		94.19 325	93.76 321	95.46 347	97.23 323	89.04 404	97.31 369	96.85 404	87.08 421	96.21 244	96.79 369	83.75 354	98.74 302	92.43 323	96.23 278	98.59 255

EPMVS		94.99 268	94.48 267	96.52 290	97.22 324	91.75 346	97.23 373	91.66 456	94.11 245	97.28 189	96.81 368	85.70 309	98.84 291	93.04 302	97.28 236	98.97 209

FMVSNet5		91.81 373	90.92 376	94.49 385	97.21 325	92.09 339	98.00 303	97.55 342	89.31 409	90.86 396	95.61 415	74.48 426	95.32 443	85.57 415	89.70 372	96.07 401

HQP-NCC					97.20 326		98.05 296		96.43 114	94.45 286

ACMP_Plane					97.20 326		98.05 296		96.43 114	94.45 286

HQP-MVS		95.72 219	95.40 215	96.69 267	97.20 326	94.25 272	98.05 296	98.46 201	96.43 114	94.45 286	97.73 277	86.75 287	98.96 272	95.30 222	94.18 300	96.86 333

UniMVSNet_ETH3D		94.24 322	93.33 340	96.97 244	97.19 329	93.38 306	98.74 167	98.57 173	91.21 376	93.81 324	98.58 194	72.85 432	98.77 301	95.05 232	93.93 310	98.77 232

OpenMVS	93.04 13	95.83 214	95.00 240	98.32 129	97.18 330	97.32 94	99.21 40	98.97 53	89.96 396	91.14 393	99.05 122	86.64 289	99.92 41	93.38 291	99.47 116	97.73 290

VPNet		94.99 268	94.19 284	97.40 216	97.16 331	96.57 142	98.71 178	98.97 53	95.67 154	94.84 273	98.24 233	80.36 379	98.67 309	96.46 178	87.32 405	96.96 314

GA-MVS		94.81 279	94.03 296	97.14 229	97.15 332	93.86 284	96.76 410	97.58 334	94.00 254	94.76 279	97.04 345	80.91 373	98.48 324	91.79 337	96.25 276	99.09 191

FIs		96.51 180	96.12 183	97.67 196	97.13 333	97.54 83	99.36 14	99.22 29	95.89 141	94.03 314	98.35 217	91.98 142	98.44 331	96.40 181	92.76 334	97.01 311

1314		96.25 195	95.73 200	97.79 180	97.13 333	95.55 201	98.19 273	98.59 166	93.47 291	92.03 384	97.82 272	91.33 165	99.49 184	94.62 249	98.44 186	98.32 272

D2MVS		95.18 256	95.08 237	95.48 345	97.10 335	92.07 340	98.30 258	99.13 40	94.02 250	92.90 359	96.73 371	89.48 214	98.73 303	94.48 255	93.60 318	95.65 410

DeepMVS_CX				86.78 427	97.09 336	72.30 457		95.17 435	75.92 451	84.34 440	95.19 420	70.58 434	95.35 441	79.98 441	89.04 386	92.68 445

PAPM		94.95 273	94.00 300	97.78 181	97.04 337	95.65 196	96.03 424	98.25 261	91.23 374	94.19 306	97.80 274	91.27 168	98.86 290	82.61 432	97.61 223	98.84 221

CR-MVSNet		94.76 283	94.15 288	96.59 280	97.00 338	93.43 301	94.96 437	97.56 337	92.46 330	96.93 207	96.24 388	88.15 257	97.88 393	87.38 404	96.65 256	98.46 264

RPMNet		92.81 363	91.34 374	97.24 221	97.00 338	93.43 301	94.96 437	98.80 108	82.27 441	96.93 207	92.12 448	86.98 284	99.82 91	76.32 449	96.65 256	98.46 264

UniMVSNet (Re)		95.78 217	95.19 231	97.58 204	96.99 340	97.47 87	98.79 158	99.18 33	95.60 156	93.92 318	97.04 345	91.68 150	98.48 324	95.80 204	87.66 400	96.79 338

test_fmvs2		93.43 348	93.58 330	92.95 411	96.97 341	83.91 437	99.19 45	97.24 372	95.74 149	95.20 267	98.27 229	69.65 435	98.72 304	96.26 185	93.73 313	96.24 394

FC-MVSNet-test		96.42 183	96.05 185	97.53 207	96.95 342	97.27 101	99.36 14	99.23 25	95.83 145	93.93 317	98.37 215	92.00 141	98.32 352	96.02 194	92.72 335	97.00 312

tfpnnormal		93.66 343	92.70 354	96.55 288	96.94 343	95.94 176	98.97 91	99.19 32	91.04 378	91.38 391	97.34 313	84.94 324	98.61 313	85.45 417	89.02 387	95.11 419

TESTMET0.1,1		94.18 328	93.69 326	95.63 340	96.92 344	89.12 402	96.91 398	94.78 437	93.17 304	94.88 272	96.45 384	78.52 391	98.92 279	93.09 299	98.50 183	98.85 219

TinyColmap		92.31 371	91.53 372	94.65 379	96.92 344	89.75 387	96.92 396	96.68 409	90.45 388	89.62 408	97.85 267	76.06 419	98.81 297	86.74 407	92.51 337	95.41 412

cascas		94.63 291	93.86 312	96.93 247	96.91 346	94.27 270	96.00 425	98.51 188	85.55 431	94.54 282	96.23 390	84.20 344	98.87 288	95.80 204	96.98 246	97.66 293

nrg030		96.28 193	95.72 201	97.96 169	96.90 347	98.15 59	99.39 11	98.31 242	95.47 164	94.42 291	98.35 217	92.09 139	98.69 305	97.50 129	89.05 385	97.04 310

MVS		94.67 289	93.54 333	98.08 156	96.88 348	96.56 143	98.19 273	98.50 193	78.05 447	92.69 366	98.02 248	91.07 180	99.63 153	90.09 367	98.36 197	98.04 281

WR-MVS_H		95.05 264	94.46 269	96.81 256	96.86 349	95.82 191	99.24 31	99.24 20	93.87 262	92.53 371	96.84 366	90.37 194	98.24 362	93.24 295	87.93 397	96.38 388

UniMVSNet_NR-MVSNet		95.71 220	95.15 232	97.40 216	96.84 350	96.97 119	98.74 167	99.24 20	95.16 183	93.88 320	97.72 279	91.68 150	98.31 354	95.81 202	87.25 406	96.92 319

USDC		93.33 352	92.71 353	95.21 354	96.83 351	90.83 365	96.91 398	97.50 347	93.84 263	90.72 397	98.14 240	77.69 402	98.82 296	89.51 381	93.21 329	95.97 403

WB-MVSnew		94.19 325	94.04 294	94.66 378	96.82 352	92.14 335	97.86 324	95.96 424	93.50 289	95.64 258	96.77 370	88.06 261	97.99 383	84.87 421	96.86 247	93.85 440

SSC-MVS3.2		93.59 347	93.13 345	94.97 363	96.81 353	89.71 389	97.95 307	98.49 198	94.59 226	93.50 338	96.91 360	77.74 401	98.37 347	91.69 340	90.47 362	96.83 336

test-LLR		95.10 261	94.87 248	95.80 332	96.77 354	89.70 390	96.91 398	95.21 432	95.11 190	94.83 275	95.72 411	87.71 269	98.97 268	93.06 300	98.50 183	98.72 236

test-mter		94.08 336	93.51 334	95.80 332	96.77 354	89.70 390	96.91 398	95.21 432	92.89 317	94.83 275	95.72 411	77.69 402	98.97 268	93.06 300	98.50 183	98.72 236

Patchmtry		93.22 355	92.35 363	95.84 331	96.77 354	93.09 320	94.66 444	97.56 337	87.37 420	92.90 359	96.24 388	88.15 257	97.90 389	87.37 405	90.10 368	96.53 372

gg-mvs-nofinetune		92.21 372	90.58 380	97.13 230	96.75 357	95.09 226	95.85 426	89.40 461	85.43 432	94.50 284	81.98 456	80.80 376	98.40 346	92.16 325	98.33 198	97.88 284

XXY-MVS		95.20 255	94.45 272	97.46 209	96.75 357	96.56 143	98.86 129	98.65 152	93.30 299	93.27 347	98.27 229	84.85 326	98.87 288	94.82 238	91.26 353	96.96 314

CP-MVSNet		94.94 275	94.30 278	96.83 254	96.72 359	95.56 199	99.11 61	98.95 57	93.89 260	92.42 376	97.90 261	87.19 280	98.12 369	94.32 261	88.21 394	96.82 337

PatchT		93.06 361	91.97 368	96.35 306	96.69 360	92.67 329	94.48 447	97.08 382	86.62 422	97.08 199	92.23 447	87.94 264	97.90 389	78.89 444	96.69 254	98.49 262

PS-CasMVS		94.67 289	93.99 302	96.71 264	96.68 361	95.26 217	99.13 58	99.03 47	93.68 279	92.33 377	97.95 256	85.35 316	98.10 370	93.59 287	88.16 396	96.79 338

WR-MVS		95.15 257	94.46 269	97.22 222	96.67 362	96.45 147	98.21 268	98.81 101	94.15 244	93.16 351	97.69 282	87.51 273	98.30 356	95.29 224	88.62 391	96.90 326

baseline2		95.11 260	94.52 265	96.87 252	96.65 363	93.56 295	98.27 263	94.10 446	93.45 292	92.02 385	97.43 307	87.45 278	99.19 232	93.88 278	97.41 235	97.87 285

test_0402		91.32 377	90.27 383	94.48 386	96.60 364	91.12 357	98.50 228	97.22 373	86.10 427	88.30 420	96.98 352	77.65 404	97.99 383	78.13 446	92.94 331	94.34 429

TransMVSNet (Re)		92.67 366	91.51 373	96.15 314	96.58 365	94.65 249	98.90 111	96.73 406	90.86 381	89.46 411	97.86 265	85.62 311	98.09 374	86.45 409	81.12 436	95.71 408

XVG-ACMP-BASELINE		94.54 298	94.14 289	95.75 336	96.55 366	91.65 349	98.11 289	98.44 205	94.96 203	94.22 304	97.90 261	79.18 388	99.11 248	94.05 274	93.85 311	96.48 383

DU-MVS		95.42 238	94.76 251	97.40 216	96.53 367	96.97 119	98.66 194	98.99 52	95.43 166	93.88 320	97.69 282	88.57 246	98.31 354	95.81 202	87.25 406	96.92 319

NR-MVSNet		94.98 270	94.16 287	97.44 211	96.53 367	97.22 109	98.74 167	98.95 57	94.96 203	89.25 412	97.69 282	89.32 223	98.18 364	94.59 252	87.40 403	96.92 319

tpm		94.13 330	93.80 316	95.12 357	96.50 369	87.91 424	97.44 355	95.89 427	92.62 326	96.37 240	96.30 387	84.13 345	98.30 356	93.24 295	91.66 348	99.14 181

pm-mvs1		93.94 341	93.06 346	96.59 280	96.49 370	95.16 222	98.95 97	98.03 305	92.32 339	91.08 394	97.84 268	84.54 336	98.41 340	92.16 325	86.13 418	96.19 397

JIA-IIPM		93.35 350	92.49 360	95.92 325	96.48 371	90.65 369	95.01 436	96.96 394	85.93 428	96.08 248	87.33 453	87.70 271	98.78 300	91.35 346	95.58 290	98.34 270

UWE-MVS-28		92.79 364	92.51 359	93.62 400	96.46 372	86.28 431	97.93 311	92.71 453	94.17 243	94.78 278	97.16 327	81.05 371	96.43 432	81.45 436	96.86 247	98.14 279

TranMVSNet+NR-MVSNet		95.14 258	94.48 267	97.11 234	96.45 373	96.36 154	99.03 77	99.03 47	95.04 195	93.58 332	97.93 258	88.27 254	98.03 378	94.13 269	86.90 411	96.95 316

testgi		93.06 361	92.45 362	94.88 368	96.43 374	89.90 384	98.75 163	97.54 343	95.60 156	91.63 390	97.91 260	74.46 427	97.02 417	86.10 411	93.67 314	97.72 291

v10		94.29 318	93.55 332	96.51 291	96.39 375	94.80 245	98.99 87	98.19 269	91.35 367	93.02 357	96.99 351	88.09 259	98.41 340	90.50 363	88.41 393	96.33 391

v8		94.47 307	93.77 319	96.57 283	96.36 376	94.83 243	99.05 70	98.19 269	91.92 350	93.16 351	96.97 353	88.82 243	98.48 324	91.69 340	87.79 398	96.39 387

GG-mvs-BLEND				96.59 280	96.34 377	94.98 234	96.51 418	88.58 462		93.10 356	94.34 433	80.34 381	98.05 377	89.53 380	96.99 243	96.74 343

V42		94.78 281	94.14 289	96.70 266	96.33 378	95.22 220	98.97 91	98.09 295	92.32 339	94.31 297	97.06 341	88.39 252	98.55 319	92.90 307	88.87 389	96.34 389

PEN-MVS		94.42 310	93.73 323	96.49 292	96.28 379	94.84 241	99.17 50	99.00 49	93.51 288	92.23 379	97.83 271	86.10 302	97.90 389	92.55 318	86.92 410	96.74 343

v1144		94.59 294	93.92 305	96.60 279	96.21 380	94.78 247	98.59 207	98.14 283	91.86 353	94.21 305	97.02 348	87.97 263	98.41 340	91.72 339	89.57 374	96.61 360

Baseline_NR-MVSNet		94.35 313	93.81 315	95.96 324	96.20 381	94.05 279	98.61 206	96.67 410	91.44 363	93.85 322	97.60 293	88.57 246	98.14 367	94.39 257	86.93 409	95.68 409

tt0320-xc		89.79 395	88.11 402	94.84 372	96.19 382	90.61 372	98.16 280	97.22 373	77.35 449	88.75 418	96.70 374	65.94 446	97.63 404	89.31 385	83.39 427	96.28 393

MS-PatchMatch		93.84 342	93.63 328	94.46 388	96.18 383	89.45 397	97.76 334	98.27 252	92.23 342	92.13 382	97.49 301	79.50 385	98.69 305	89.75 375	99.38 128	95.25 415

v2v482		94.69 284	94.03 296	96.65 269	96.17 384	94.79 246	98.67 192	98.08 296	92.72 322	94.00 315	97.16 327	87.69 272	98.45 329	92.91 306	88.87 389	96.72 346

EPNet_dtu		95.21 254	94.95 244	95.99 321	96.17 384	90.45 375	98.16 280	97.27 370	96.77 96	93.14 354	98.33 222	90.34 195	98.42 333	85.57 415	98.81 164	99.09 191
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OPM-MVS		95.69 223	95.33 224	96.76 260	96.16 386	94.63 251	98.43 242	98.39 223	96.64 106	95.02 270	98.78 168	85.15 321	99.05 257	95.21 229	94.20 299	96.60 361
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tt0320		90.26 391	88.73 398	94.86 369	96.12 387	90.62 371	98.17 279	97.63 330	77.46 448	89.68 407	96.04 399	69.19 437	97.79 396	88.98 389	85.29 421	96.16 398

v1192		94.32 315	93.58 330	96.53 289	96.10 388	94.45 260	98.50 228	98.17 278	91.54 360	94.19 306	97.06 341	86.95 285	98.43 332	90.14 366	89.57 374	96.70 350

v148		94.29 318	93.76 321	95.91 326	96.10 388	92.93 323	98.58 209	97.97 308	92.59 328	93.47 340	96.95 357	88.53 250	98.32 352	92.56 317	87.06 408	96.49 381

v144192		94.39 312	93.70 325	96.48 294	96.06 390	94.35 266	98.58 209	98.16 280	91.45 362	94.33 296	97.02 348	87.50 275	98.45 329	91.08 353	89.11 384	96.63 358

DTE-MVSNet		93.98 340	93.26 343	96.14 315	96.06 390	94.39 264	99.20 43	98.86 86	93.06 310	91.78 386	97.81 273	85.87 307	97.58 407	90.53 362	86.17 415	96.46 385

v1240		94.06 338	93.29 342	96.34 307	96.03 392	93.90 283	98.44 240	98.17 278	91.18 377	94.13 309	97.01 350	86.05 303	98.42 333	89.13 388	89.50 378	96.70 350

sc_t1		91.01 384	89.39 390	95.85 330	95.99 393	90.39 378	98.43 242	97.64 329	78.79 445	92.20 380	97.94 257	66.00 445	98.60 316	91.59 343	85.94 419	98.57 258

APD_test1		88.22 405	88.01 404	88.86 424	95.98 394	74.66 456	97.21 376	96.44 416	83.96 437	86.66 430	97.90 261	60.95 452	97.84 395	82.73 430	90.23 366	94.09 435

v1921920		94.20 324	93.47 336	96.40 304	95.98 394	94.08 278	98.52 221	98.15 281	91.33 368	94.25 302	97.20 326	86.41 295	98.42 333	90.04 371	89.39 381	96.69 355

EU-MVSNet		93.66 343	94.14 289	92.25 417	95.96 396	83.38 441	98.52 221	98.12 285	94.69 219	92.61 368	98.13 241	87.36 279	96.39 433	91.82 336	90.00 369	96.98 313

v7n		94.19 325	93.43 338	96.47 295	95.90 397	94.38 265	99.26 28	98.34 236	91.99 348	92.76 363	97.13 329	88.31 253	98.52 322	89.48 382	87.70 399	96.52 375

gm-plane-assit					95.88 398	87.47 426			89.74 401		96.94 358		99.19 232	93.32 294

LF4IMVS		93.14 359	92.79 352	94.20 392	95.88 398	88.67 412	97.66 342	97.07 384	93.81 266	91.71 387	97.65 287	77.96 399	98.81 297	91.47 345	91.92 344	95.12 418

PS-MVSNAJss		96.43 182	96.26 177	96.92 250	95.84 400	95.08 227	99.16 51	98.50 193	95.87 143	93.84 323	98.34 221	94.51 88	98.61 313	96.88 159	93.45 321	97.06 309

pmmvs4		94.69 284	93.99 302	96.81 256	95.74 401	95.94 176	97.40 358	97.67 326	90.42 389	93.37 344	97.59 294	89.08 231	98.20 363	92.97 304	91.67 347	96.30 392

test_djsdf		96.00 202	95.69 207	96.93 247	95.72 402	95.49 204	99.47 7	98.40 218	94.98 201	94.58 281	97.86 265	89.16 228	98.41 340	96.91 153	94.12 304	96.88 328

SixPastTwentyTwo		93.34 351	92.86 350	94.75 375	95.67 403	89.41 399	98.75 163	96.67 410	93.89 260	90.15 404	98.25 232	80.87 374	98.27 361	90.90 358	90.64 360	96.57 365

K. test v3		92.55 368	91.91 371	94.48 386	95.64 404	89.24 400	99.07 67	94.88 436	94.04 248	86.78 428	97.59 294	77.64 405	97.64 403	92.08 327	89.43 380	96.57 365

OurMVSNet-221017-0		94.21 323	94.00 300	94.85 370	95.60 405	89.22 401	98.89 115	97.43 357	95.29 176	92.18 381	98.52 202	82.86 358	98.59 317	93.46 290	91.76 345	96.74 343

mvs_tets		95.41 240	95.00 240	96.65 269	95.58 406	94.42 262	99.00 84	98.55 178	95.73 151	93.21 349	98.38 214	83.45 357	98.63 311	97.09 146	94.00 307	96.91 324

MonoMVSNet		95.51 230	95.45 214	95.68 337	95.54 407	90.87 362	98.92 108	97.37 362	95.79 147	95.53 259	97.38 312	89.58 212	97.68 401	96.40 181	92.59 336	98.49 262

Gipuma		78.40 422	76.75 425	83.38 435	95.54 407	80.43 447	79.42 460	97.40 359	64.67 457	73.46 454	80.82 458	45.65 457	93.14 452	66.32 456	87.43 402	76.56 460
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		94.08 336	93.51 334	95.80 332	95.53 409	92.89 324	97.38 360	95.97 423	95.11 190	92.51 373	96.66 375	87.71 269	96.94 419	87.03 406	93.67 314	97.57 297

pmmvs5		93.65 345	92.97 349	95.68 337	95.49 410	92.37 331	98.20 270	97.28 369	89.66 402	92.58 369	97.26 319	82.14 361	98.09 374	93.18 298	90.95 358	96.58 363

test_fmvsmconf0.01_n		97.86 87	97.54 98	98.83 78	95.48 411	96.83 126	98.95 97	98.60 159	98.58 12	98.93 75	99.55 16	88.57 246	99.91 51	99.54 22	99.61 86	99.77 35

N_pmnet		87.12 410	87.77 408	85.17 430	95.46 412	61.92 466	97.37 362	70.66 471	85.83 429	88.73 419	96.04 399	85.33 318	97.76 399	80.02 439	90.48 361	95.84 405

our_test_3		93.65 345	93.30 341	94.69 376	95.45 413	89.68 392	96.91 398	97.65 327	91.97 349	91.66 389	96.88 362	89.67 210	97.93 388	88.02 400	91.49 349	96.48 383

ppachtmachnet_test		93.22 355	92.63 355	94.97 363	95.45 413	90.84 364	96.88 404	97.88 315	90.60 384	92.08 383	97.26 319	88.08 260	97.86 394	85.12 420	90.33 363	96.22 395

jajsoiax		95.45 235	95.03 239	96.73 261	95.42 415	94.63 251	99.14 55	98.52 185	95.74 149	93.22 348	98.36 216	83.87 351	98.65 310	96.95 152	94.04 305	96.91 324

dmvs_testset		87.64 407	88.93 397	83.79 433	95.25 416	63.36 465	97.20 377	91.17 457	93.07 309	85.64 436	95.98 404	85.30 320	91.52 455	69.42 454	87.33 404	96.49 381

MDA-MVSNet-bldmvs		89.97 394	88.35 400	94.83 373	95.21 417	91.34 353	97.64 344	97.51 346	88.36 416	71.17 457	96.13 395	79.22 387	96.63 428	83.65 428	86.27 414	96.52 375

dongtai		82.47 415	81.88 418	84.22 432	95.19 418	76.03 449	94.59 446	74.14 470	82.63 439	87.19 426	96.09 396	64.10 448	87.85 460	58.91 458	84.11 425	88.78 452

anonymousdsp		95.42 238	94.91 245	96.94 246	95.10 419	95.90 182	99.14 55	98.41 216	93.75 268	93.16 351	97.46 303	87.50 275	98.41 340	95.63 212	94.03 306	96.50 380

EPNet		97.28 135	96.87 142	98.51 108	94.98 420	96.14 164	98.90 111	97.02 391	98.28 19	95.99 251	99.11 105	91.36 163	99.89 62	96.98 149	99.19 141	99.50 101
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVP-Stereo		94.28 320	93.92 305	95.35 351	94.95 421	92.60 330	97.97 306	97.65 327	91.61 359	90.68 398	97.09 334	86.32 299	98.42 333	89.70 377	99.34 132	95.02 423
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lessismore_v0				94.45 389	94.93 422	88.44 417		91.03 458		86.77 429	97.64 290	76.23 417	98.42 333	90.31 365	85.64 420	96.51 378

MDA-MVSNet_test_wron		90.71 387	89.38 392	94.68 377	94.83 423	90.78 366	97.19 379	97.46 351	87.60 418	72.41 456	95.72 411	86.51 290	96.71 426	85.92 413	86.80 412	96.56 367

EGC-MVSNET		75.22 425	69.54 428	92.28 416	94.81 424	89.58 394	97.64 344	96.50 414	1.82 468	5.57 469	95.74 407	68.21 438	96.26 434	73.80 451	91.71 346	90.99 446

YYNet1		90.70 388	89.39 390	94.62 381	94.79 425	90.65 369	97.20 377	97.46 351	87.54 419	72.54 455	95.74 407	86.51 290	96.66 427	86.00 412	86.76 413	96.54 370

EG-PatchMatch MVS		91.13 382	90.12 385	94.17 394	94.73 426	89.00 405	98.13 285	97.81 318	89.22 410	85.32 438	96.46 383	67.71 441	98.42 333	87.89 403	93.82 312	95.08 420

pmmvs6		91.77 374	90.63 379	95.17 356	94.69 427	91.24 356	98.67 192	97.92 313	86.14 426	89.62 408	97.56 299	75.79 420	98.34 349	90.75 360	84.56 422	95.94 404

MVStest1		89.53 400	87.99 405	94.14 396	94.39 428	90.42 376	98.25 265	96.84 405	82.81 438	81.18 446	97.33 315	77.09 411	96.94 419	85.27 419	78.79 444	95.06 421

new_pmnet		90.06 393	89.00 396	93.22 408	94.18 429	88.32 419	96.42 420	96.89 400	86.19 425	85.67 435	93.62 436	77.18 409	97.10 416	81.61 435	89.29 382	94.23 431

DSMNet-mixed		92.52 370	92.58 358	92.33 415	94.15 430	82.65 443	98.30 258	94.26 443	89.08 411	92.65 367	95.73 409	85.01 323	95.76 439	86.24 410	97.76 218	98.59 255

ttmdpeth		92.61 367	91.96 370	94.55 382	94.10 431	90.60 373	98.52 221	97.29 367	92.67 324	90.18 402	97.92 259	79.75 384	97.79 396	91.09 351	86.15 417	95.26 414

UnsupCasMVSNet_eth		90.99 385	89.92 387	94.19 393	94.08 432	89.83 385	97.13 387	98.67 145	93.69 277	85.83 434	96.19 393	75.15 422	96.74 423	89.14 387	79.41 443	96.00 402

KD-MVS_2432*1600		89.61 398	87.96 406	94.54 383	94.06 433	91.59 350	95.59 432	97.63 330	89.87 398	88.95 414	94.38 431	78.28 394	96.82 421	84.83 422	68.05 457	95.21 416

miper_refine_blended		89.61 398	87.96 406	94.54 383	94.06 433	91.59 350	95.59 432	97.63 330	89.87 398	88.95 414	94.38 431	78.28 394	96.82 421	84.83 422	68.05 457	95.21 416

Anonymous20231206		91.66 375	91.10 375	93.33 405	94.02 435	87.35 427	98.58 209	97.26 371	90.48 386	90.16 403	96.31 386	83.83 352	96.53 430	79.36 442	89.90 370	96.12 399

Anonymous20240521		91.18 381	90.44 381	93.42 402	93.70 436	88.47 416	98.94 100	97.56 337	88.46 415	89.56 410	95.08 423	77.15 410	96.97 418	83.92 427	89.55 376	94.82 425

test20.03		90.89 386	90.38 382	92.43 413	93.48 437	88.14 422	98.33 250	97.56 337	93.40 294	87.96 421	96.71 373	80.69 377	94.13 448	79.15 443	86.17 415	95.01 424

CMPMVS	66.06 21	89.70 396	89.67 389	89.78 422	93.19 438	76.56 448	97.00 392	98.35 233	80.97 443	81.57 444	97.75 276	74.75 424	98.61 313	89.85 373	93.63 316	94.17 433
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
OpenMVS_ROB	86.42 20	89.00 402	87.43 410	93.69 399	93.08 439	89.42 398	97.91 314	96.89 400	78.58 446	85.86 433	94.69 425	69.48 436	98.29 359	77.13 447	93.29 328	93.36 442

KD-MVS_self_test		90.38 389	89.38 392	93.40 404	92.85 440	88.94 408	97.95 307	97.94 311	90.35 391	90.25 401	93.96 434	79.82 382	95.94 438	84.62 426	76.69 451	95.33 413

MIMVSNet1		89.67 397	88.28 401	93.82 397	92.81 441	91.08 358	98.01 301	97.45 355	87.95 417	87.90 422	95.87 405	67.63 442	94.56 447	78.73 445	88.18 395	95.83 406

kuosan		78.45 421	77.69 422	80.72 440	92.73 442	75.32 453	94.63 445	74.51 469	75.96 450	80.87 448	93.19 441	63.23 450	79.99 464	42.56 464	81.56 435	86.85 456

mvs5depth		91.23 380	90.17 384	94.41 390	92.09 443	89.79 386	95.26 435	96.50 414	90.73 382	91.69 388	97.06 341	76.12 418	98.62 312	88.02 400	84.11 425	94.82 425

UnsupCasMVSNet_bld		87.17 408	85.12 415	93.31 406	91.94 444	88.77 409	94.92 439	98.30 249	84.30 436	82.30 442	90.04 450	63.96 449	97.25 414	85.85 414	74.47 455	93.93 439

CL-MVSNet_self_test		90.11 392	89.14 394	93.02 410	91.86 445	88.23 421	96.51 418	98.07 298	90.49 385	90.49 400	94.41 429	84.75 329	95.34 442	80.79 438	74.95 453	95.50 411

Patchmatch-RL test		91.49 376	90.85 377	93.41 403	91.37 446	84.40 435	92.81 451	95.93 426	91.87 352	87.25 424	94.87 424	88.99 234	96.53 430	92.54 319	82.00 431	99.30 145

test_fmvs3		87.17 408	87.06 411	87.50 426	91.21 447	75.66 451	99.05 70	96.61 413	92.79 321	88.85 416	92.78 443	43.72 458	93.49 449	93.95 275	84.56 422	93.34 443

pmmvs-eth3d		90.36 390	89.05 395	94.32 391	91.10 448	92.12 336	97.63 347	96.95 395	88.86 413	84.91 439	93.13 442	78.32 393	96.74 423	88.70 392	81.81 433	94.09 435

PM-MVS		87.77 406	86.55 412	91.40 420	91.03 449	83.36 442	96.92 396	95.18 434	91.28 372	86.48 432	93.42 438	53.27 455	96.74 423	89.43 383	81.97 432	94.11 434

new-patchmatchnet		88.50 404	87.45 409	91.67 419	90.31 450	85.89 433	97.16 385	97.33 363	89.47 405	83.63 441	92.77 444	76.38 415	95.06 445	82.70 431	77.29 449	94.06 437

mvsany_test3		88.80 403	88.04 403	91.09 421	89.78 451	81.57 446	97.83 329	95.49 430	93.81 266	87.53 423	93.95 435	56.14 454	97.43 411	94.68 245	83.13 428	94.26 430

WB-MVS		84.86 413	85.33 414	83.46 434	89.48 452	69.56 460	98.19 273	96.42 417	89.55 404	81.79 443	94.67 426	84.80 327	90.12 456	52.44 460	80.64 440	90.69 447

test_f		86.07 412	85.39 413	88.10 425	89.28 453	75.57 452	97.73 337	96.33 418	89.41 408	85.35 437	91.56 449	43.31 460	95.53 440	91.32 347	84.23 424	93.21 444

SSC-MVS		84.27 414	84.71 417	82.96 438	89.19 454	68.83 461	98.08 293	96.30 419	89.04 412	81.37 445	94.47 427	84.60 334	89.89 457	49.80 462	79.52 442	90.15 448

pmmvs3		86.67 411	84.86 416	92.11 418	88.16 455	87.19 429	96.63 414	94.75 438	79.88 444	87.22 425	92.75 445	66.56 444	95.20 444	81.24 437	76.56 452	93.96 438

testf1		79.02 418	77.70 420	82.99 436	88.10 456	66.90 462	94.67 442	93.11 449	71.08 454	74.02 452	93.41 439	34.15 464	93.25 450	72.25 452	78.50 446	88.82 450

APD_test2		79.02 418	77.70 420	82.99 436	88.10 456	66.90 462	94.67 442	93.11 449	71.08 454	74.02 452	93.41 439	34.15 464	93.25 450	72.25 452	78.50 446	88.82 450

ambc				89.49 423	86.66 458	75.78 450	92.66 452	96.72 407		86.55 431	92.50 446	46.01 456	97.90 389	90.32 364	82.09 430	94.80 427

test_vis3_rt		79.22 416	77.40 423	84.67 431	86.44 459	74.85 455	97.66 342	81.43 466	84.98 433	67.12 459	81.91 457	28.09 468	97.60 405	88.96 390	80.04 441	81.55 457

test_method		79.03 417	78.17 419	81.63 439	86.06 460	54.40 471	82.75 459	96.89 400	39.54 463	80.98 447	95.57 416	58.37 453	94.73 446	84.74 425	78.61 445	95.75 407

TDRefinement		91.06 383	89.68 388	95.21 354	85.35 461	91.49 352	98.51 227	97.07 384	91.47 361	88.83 417	97.84 268	77.31 406	99.09 253	92.79 310	77.98 448	95.04 422

PMMVS2		77.95 423	75.44 427	85.46 429	82.54 462	74.95 454	94.23 449	93.08 451	72.80 453	74.68 451	87.38 452	36.36 463	91.56 454	73.95 450	63.94 459	89.87 449

E-PMN		64.94 429	64.25 431	67.02 446	82.28 463	59.36 469	91.83 454	85.63 463	52.69 460	60.22 461	77.28 460	41.06 461	80.12 463	46.15 463	41.14 461	61.57 462

EMVS		64.07 430	63.26 433	66.53 447	81.73 464	58.81 470	91.85 453	84.75 464	51.93 462	59.09 462	75.13 461	43.32 459	79.09 465	42.03 465	39.47 462	61.69 461

FPMVS		77.62 424	77.14 424	79.05 442	79.25 465	60.97 467	95.79 427	95.94 425	65.96 456	67.93 458	94.40 430	37.73 462	88.88 459	68.83 455	88.46 392	87.29 453

wuyk23d		30.17 432	30.18 436	30.16 448	78.61 466	43.29 473	66.79 461	14.21 472	17.31 465	14.82 468	11.93 468	11.55 471	41.43 467	37.08 466	19.30 465	5.76 465

LCM-MVSNet		78.70 420	76.24 426	86.08 428	77.26 467	71.99 458	94.34 448	96.72 407	61.62 458	76.53 450	89.33 451	33.91 466	92.78 453	81.85 434	74.60 454	93.46 441

MVE	62.14 22	63.28 431	59.38 434	74.99 443	74.33 468	65.47 464	85.55 457	80.50 467	52.02 461	51.10 463	75.00 462	10.91 472	80.50 462	51.60 461	53.40 460	78.99 458
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		69.08 426	65.37 430	80.22 441	65.99 469	71.96 459	90.91 455	90.09 460	82.62 440	49.93 464	78.39 459	29.36 467	81.75 461	62.49 457	38.52 463	86.95 455

PMVS	61.03 23	65.95 428	63.57 432	73.09 445	57.90 470	51.22 472	85.05 458	93.93 447	54.45 459	44.32 465	83.57 454	13.22 469	89.15 458	58.68 459	81.00 437	78.91 459
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		68.90 427	66.97 429	74.68 444	50.78 471	59.95 468	87.13 456	83.47 465	38.80 464	62.21 460	96.23 390	64.70 447	76.91 466	88.91 391	30.49 464	87.19 454

testmvs		21.48 434	24.95 437	11.09 450	14.89 472	6.47 475	96.56 416	9.87 473	7.55 466	17.93 466	39.02 464	9.43 473	5.90 469	16.56 468	12.72 466	20.91 464

test123		20.95 435	23.72 438	12.64 449	13.54 473	8.19 474	96.55 417	6.13 474	7.48 467	16.74 467	37.98 465	12.97 470	6.05 468	16.69 467	5.43 467	23.68 463

mmdepth		0.00 438	0.00 441	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.00 469	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

monomultidepth		0.00 438	0.00 441	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.00 469	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

test_blank		0.00 438	0.00 441	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.00 469	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

eth-test2					0.00 474

eth-test					0.00 474

uanet_test		0.00 438	0.00 441	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.00 469	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

DCPMVS		0.00 438	0.00 441	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.00 469	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

cdsmvs_eth3d_5k		23.98 433	31.98 435	0.00 451	0.00 474	0.00 476	0.00 462	98.59 166	0.00 469	0.00 470	98.61 189	90.60 191	0.00 470	0.00 469	0.00 468	0.00 466

pcd_1.5k_mvsjas		7.88 437	10.50 440	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.00 469	94.51 88	0.00 470	0.00 469	0.00 468	0.00 466

sosnet-low-res		0.00 438	0.00 441	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.00 469	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

sosnet		0.00 438	0.00 441	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.00 469	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

uncertanet		0.00 438	0.00 441	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.00 469	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

Regformer		0.00 438	0.00 441	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.00 469	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

ab-mvs-re		8.20 436	10.94 439	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	98.43 207	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

uanet		0.00 438	0.00 441	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.00 469	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

WAC-MVS						90.94 360								88.66 393

PC_three_1452									95.08 194	99.60 30	99.16 96	97.86 2	98.47 327	97.52 125	99.72 62	99.74 45

test_241102_TWO								98.87 80	97.65 37	99.53 35	99.48 31	97.34 11	99.94 13	98.43 65	99.80 24	99.83 16

test_0728_THIRD									97.32 61	99.45 37	99.46 38	97.88 1	99.94 13	98.47 61	99.86 2	99.85 13

GSMVS																99.20 167

sam_mvs1												89.45 218				99.20 167

sam_mvs												88.99 234

MTGPA								98.74 123

test_post1							96.68 413				30.43 467	87.85 268	98.69 305	92.59 315

test_post											31.83 466	88.83 241	98.91 281

patchmatchnet-post											95.10 422	89.42 219	98.89 285

MTMP							98.89 115	94.14 445

test9_res														96.39 183	99.57 94	99.69 65

agg_prior2														95.87 199	99.57 94	99.68 70

test_prior4						98.01 66	97.86 324

test_prior2							97.80 331		96.12 131	97.89 155	98.69 183	95.96 41		96.89 157	99.60 88

旧先验2							97.57 350		91.30 370	98.67 98			99.80 103	95.70 210

新几何2							97.64 344

无先验							97.58 349	98.72 128	91.38 364				99.87 73	93.36 293		99.60 87

原ACMM2							97.67 341

testdata2													99.89 62	91.65 342

segment_acmp												96.85 14

testdata1							97.32 368		96.34 121

plane_prior5								98.56 176					99.03 261	96.07 189	94.27 296	96.92 319

plane_prior4											98.28 226

plane_prior3						94.61 254			97.02 85	95.34 262

plane_prior2							98.80 150		97.28 65

plane_prior						94.60 256	98.44 240		96.74 99						94.22 298

n2								0.00 475

nn								0.00 475

door-mid								94.37 441

test11								98.66 148

door								94.64 439

HQP5-MVS						94.25 272

BP-MVS														95.30 222

HQP4-MVS										94.45 286			98.96 272			96.87 331

HQP3-MVS								98.46 201							94.18 300

HQP2-MVS												86.75 287

MDTV_nov1_ep13_2view						84.26 436	96.89 403		90.97 379	97.90 154		89.89 204		93.91 277		99.18 176

ACMMP++_ref															92.97 330

ACMMP++															93.61 317

Test By Simon												94.64 85

High-resolution multi-view benchmark