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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

LTVRE_ROB	99.39 1	99.90 1	99.87 1	99.93 1	99.97 2	99.82 8	99.91 3	99.92 37	99.75 4	99.93 5	99.89 30	100.00 1	99.87 2	99.93 3	99.82 10	99.96 3	99.90 2
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
v7n		99.89 2	99.86 3	99.93 1	99.97 2	99.83 4	99.93 1	99.96 12	99.77 3	99.89 17	99.99 1	99.86 76	99.84 5	99.89 11	99.81 11	99.97 1	99.88 6

SixPastTwentyTwo		99.89 2	99.85 5	99.93 1	99.97 2	99.88 1	99.92 2	99.97 1	99.66 12	99.94 4	99.94 11	99.74 106	99.81 7	99.97 1	99.89 1	99.96 3	99.89 4

pmmvs6		99.88 4	99.87 1	99.89 9	99.97 2	99.76 21	99.89 5	99.96 12	99.82 2	99.90 15	99.92 16	99.95 25	99.68 31	99.93 3	99.88 3	99.95 7	99.86 11

anonymousdsp		99.87 5	99.86 3	99.88 12	99.95 10	99.75 27	99.90 4	99.96 12	99.69 7	99.83 51	99.96 4	99.99 3	99.74 21	99.95 2	99.83 7	99.91 24	99.88 6

FC-MVSNet-test		99.84 6	99.80 6	99.89 9	99.96 7	99.83 4	99.84 16	99.95 23	99.37 48	99.77 68	99.95 6	99.96 14	99.85 3	99.93 3	99.83 7	99.95 7	99.72 39

UniMVSNet_ETH3D		99.81 7	99.79 7	99.85 18	99.98 1	99.76 21	99.73 47	99.96 12	99.68 9	99.87 29	99.59 84	99.91 56	99.58 51	99.90 10	99.85 6	99.96 3	99.81 19

TDRefinement		99.81 7	99.76 9	99.86 15	99.83 88	99.53 62	99.89 5	99.91 43	99.73 5	99.88 23	99.83 45	99.96 14	99.76 16	99.91 9	99.81 11	99.86 41	99.59 68

WR-MVS		99.79 9	99.68 13	99.91 5	99.95 10	99.83 4	99.87 9	99.96 12	99.39 46	99.93 5	99.87 35	99.29 149	99.77 14	99.83 22	99.72 20	99.97 1	99.82 16

MIMVSNet1		99.79 9	99.75 10	99.84 21	99.89 42	99.83 4	99.84 16	99.89 52	99.31 54	99.93 5	99.92 16	99.97 9	99.68 31	99.89 11	99.64 27	99.82 55	99.66 53

pm-mvs1		99.77 11	99.69 12	99.86 15	99.94 23	99.68 36	99.84 16	99.93 27	99.59 21	99.87 29	99.92 16	99.21 152	99.65 37	99.88 15	99.77 16	99.93 20	99.78 26

PEN-MVS		99.77 11	99.65 18	99.91 5	99.95 10	99.80 15	99.86 10	99.97 1	99.08 82	99.89 17	99.69 67	99.68 115	99.84 5	99.81 27	99.64 27	99.95 7	99.81 19

EU-MVSNet		99.76 13	99.74 11	99.78 41	99.82 93	99.81 12	99.88 7	99.87 57	99.31 54	99.75 76	99.91 23	99.76 105	99.78 12	99.84 21	99.74 19	99.56 135	99.81 19

Vis-MVSNet		99.76 13	99.78 8	99.75 51	99.92 30	99.77 20	99.83 19	99.85 68	99.43 40	99.85 42	99.84 42	100.00 1	99.13 116	99.83 22	99.66 24	99.90 28	99.90 2
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS		99.75 15	99.66 17	99.85 18	99.87 53	99.86 2	99.83 19	99.91 43	98.84 116	99.92 9	99.57 86	99.85 82	99.60 46	99.82 25	99.79 13	99.94 15	99.87 9

CS-MVS-test		99.75 15	99.67 14	99.84 21	99.91 34	99.85 3	99.85 13	99.92 37	98.75 126	99.89 17	99.64 74	99.95 25	99.55 54	99.89 11	99.79 13	99.92 21	99.83 14

DTE-MVSNet		99.75 15	99.61 24	99.92 4	99.95 10	99.81 12	99.86 10	99.96 12	99.18 71	99.92 9	99.66 70	99.45 134	99.85 3	99.80 28	99.56 33	99.96 3	99.79 25

tfpnnormal		99.74 18	99.63 21	99.86 15	99.93 27	99.75 27	99.80 28	99.89 52	99.31 54	99.88 23	99.43 107	99.66 118	99.77 14	99.80 28	99.71 21	99.92 21	99.76 30

DeepC-MVS	99.05 5	99.74 18	99.64 19	99.84 21	99.90 39	99.39 93	99.79 29	99.81 97	99.69 7	99.90 15	99.87 35	99.98 5	99.81 7	99.62 54	99.32 60	99.83 52	99.65 56
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
thisisatest0515		99.73 20	99.67 14	99.81 31	99.93 27	99.74 29	99.68 56	99.91 43	99.59 21	99.88 23	99.73 56	99.81 91	99.55 54	99.59 55	99.53 38	99.89 31	99.70 47

PS-CasMVS		99.73 20	99.59 30	99.90 8	99.95 10	99.80 15	99.85 13	99.97 1	98.95 100	99.86 35	99.73 56	99.36 141	99.81 7	99.83 22	99.67 23	99.95 7	99.83 14

WR-MVS_H		99.73 20	99.61 24	99.88 12	99.95 10	99.82 8	99.83 19	99.96 12	99.01 92	99.84 46	99.71 64	99.41 140	99.74 21	99.77 33	99.70 22	99.95 7	99.82 16

TransMVSNet (Re)		99.72 23	99.59 30	99.88 12	99.95 10	99.76 21	99.88 7	99.94 24	99.58 23	99.92 9	99.90 27	98.55 168	99.65 37	99.89 11	99.76 17	99.95 7	99.70 47

ACMH	99.11 4	99.72 23	99.63 21	99.84 21	99.87 53	99.59 49	99.83 19	99.88 56	99.46 37	99.87 29	99.66 70	99.95 25	99.76 16	99.73 38	99.47 47	99.84 47	99.52 99
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FC-MVSNet-train		99.70 25	99.67 14	99.74 57	99.94 23	99.71 32	99.82 24	99.91 43	99.14 79	99.53 133	99.70 65	99.88 68	99.33 89	99.88 15	99.61 32	99.94 15	99.77 27

DROMVSNet		99.70 25	99.57 33	99.85 18	99.95 10	99.81 12	99.85 13	99.93 27	98.39 164	99.76 71	99.48 104	99.94 35	99.70 29	99.85 19	99.66 24	99.91 24	99.87 9

COLMAP_ROB	99.18 2	99.70 25	99.60 28	99.81 31	99.84 82	99.37 99	99.76 35	99.84 77	99.54 29	99.82 54	99.64 74	99.95 25	99.75 18	99.79 30	99.56 33	99.83 52	99.37 129
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	98.94 6	99.69 28	99.59 30	99.81 31	99.88 48	99.41 90	99.75 39	99.86 61	99.43 40	99.80 58	99.54 90	99.97 9	99.73 24	99.82 25	99.52 40	99.85 44	99.43 115

test20.03		99.68 29	99.60 28	99.76 47	99.91 34	99.70 35	99.68 56	99.87 57	99.05 89	99.88 23	99.92 16	99.88 68	99.50 67	99.77 33	99.42 54	99.75 76	99.49 101

CP-MVSNet		99.68 29	99.51 42	99.89 9	99.95 10	99.76 21	99.83 19	99.96 12	98.83 120	99.84 46	99.65 73	99.09 154	99.80 10	99.78 31	99.62 31	99.95 7	99.82 16

casdiffmvs_mvg		99.67 31	99.61 24	99.74 57	99.94 23	99.60 45	99.62 70	99.77 120	99.54 29	99.67 108	99.82 47	99.80 97	99.52 61	99.40 76	99.51 41	99.91 24	99.59 68
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		99.66 32	99.64 19	99.67 69	99.91 34	99.71 32	99.61 71	99.79 108	99.41 42	99.91 13	99.85 40	99.61 121	99.00 126	99.67 45	99.42 54	99.81 58	99.81 19

v10		99.65 33	99.51 42	99.81 31	99.83 88	99.61 44	99.75 39	99.94 24	99.56 25	99.76 71	99.94 11	99.60 123	99.73 24	99.11 131	99.01 101	99.85 44	99.74 34

CHOSEN 1792x2688		99.65 33	99.55 36	99.77 46	99.93 27	99.60 45	99.79 29	99.92 37	99.73 5	99.74 82	99.93 14	99.98 5	99.80 10	98.83 171	99.01 101	99.45 153	99.76 30

UA-Net		99.64 35	99.62 23	99.66 71	99.97 2	99.82 8	99.14 158	99.96 12	98.95 100	99.52 139	99.38 116	99.86 76	99.55 54	99.72 39	99.66 24	99.80 62	99.94 1

GeoE		99.63 36	99.51 42	99.78 41	99.91 34	99.57 52	99.78 31	99.97 1	99.23 62	99.72 91	99.72 60	99.80 97	99.50 67	99.45 73	99.10 87	99.79 65	99.71 45

Baseline_NR-MVSNet		99.62 37	99.48 47	99.78 41	99.85 76	99.76 21	99.59 76	99.82 89	98.84 116	99.88 23	99.91 23	99.04 155	99.61 44	99.46 66	99.78 15	99.94 15	99.60 66

pmmvs-eth3d		99.61 38	99.48 47	99.75 51	99.87 53	99.30 115	99.75 39	99.89 52	99.23 62	99.85 42	99.88 34	99.97 9	99.49 72	99.46 66	99.01 101	99.68 95	99.52 99

v1144		99.61 38	99.43 55	99.82 26	99.88 48	99.41 90	99.76 35	99.86 61	99.64 15	99.84 46	99.95 6	99.49 132	99.74 21	99.00 141	98.93 113	99.84 47	99.58 77

v8		99.61 38	99.45 53	99.79 40	99.80 99	99.59 49	99.73 47	99.93 27	99.48 35	99.77 68	99.90 27	99.48 133	99.67 34	99.11 131	98.89 117	99.84 47	99.73 36

casdiffmvs		99.61 38	99.55 36	99.68 68	99.89 42	99.53 62	99.64 64	99.68 148	99.51 32	99.62 117	99.90 27	99.96 14	99.37 83	99.28 101	99.25 63	99.88 33	99.44 112
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CSCG		99.61 38	99.52 41	99.71 62	99.89 42	99.62 42	99.52 92	99.76 129	99.61 19	99.69 100	99.73 56	99.96 14	99.57 52	99.27 104	98.62 147	99.81 58	99.85 13

v1192		99.60 43	99.41 59	99.82 26	99.89 42	99.43 85	99.81 26	99.84 77	99.63 17	99.85 42	99.95 6	99.35 144	99.72 26	99.01 139	98.90 116	99.82 55	99.58 77

APDe-MVS		99.60 43	99.48 47	99.73 60	99.85 76	99.51 73	99.75 39	99.85 68	99.17 72	99.81 57	99.56 88	99.94 35	99.44 79	99.42 75	99.22 64	99.67 97	99.54 91

v1921920		99.59 45	99.40 62	99.82 26	99.88 48	99.45 80	99.81 26	99.83 82	99.65 13	99.86 35	99.95 6	99.29 149	99.75 18	98.98 145	98.86 121	99.78 67	99.59 68

TranMVSNet+NR-MVSNet		99.59 45	99.42 58	99.80 36	99.87 53	99.55 56	99.64 64	99.86 61	99.05 89	99.88 23	99.72 60	99.33 147	99.64 41	99.47 65	99.14 73	99.91 24	99.67 52

EG-PatchMatch MVS		99.59 45	99.49 46	99.70 65	99.82 93	99.26 122	99.39 121	99.83 82	98.99 94	99.93 5	99.54 90	99.92 50	99.51 63	99.78 31	99.50 42	99.73 85	99.41 119

pmmvs5		99.58 48	99.47 50	99.70 65	99.84 82	99.50 74	99.58 80	99.80 105	98.98 97	99.73 88	99.92 16	99.81 91	99.49 72	99.28 101	99.05 95	99.77 71	99.73 36

v144192		99.58 48	99.39 63	99.80 36	99.87 53	99.44 82	99.77 32	99.84 77	99.64 15	99.86 35	99.93 14	99.35 144	99.72 26	98.92 151	98.82 125	99.74 81	99.66 53

v148		99.58 48	99.43 55	99.76 47	99.87 53	99.40 92	99.76 35	99.85 68	99.48 35	99.83 51	99.82 47	99.83 87	99.51 63	99.20 117	98.82 125	99.75 76	99.45 109

v1240		99.58 48	99.38 66	99.82 26	99.89 42	99.49 75	99.82 24	99.83 82	99.63 17	99.86 35	99.96 4	98.92 161	99.75 18	99.15 127	98.96 110	99.76 73	99.56 84

V42		99.57 52	99.41 59	99.75 51	99.84 82	99.37 99	99.73 47	99.83 82	99.41 42	99.75 76	99.89 30	99.42 138	99.60 46	99.15 127	98.96 110	99.76 73	99.65 56

TSAR-MVS + MP.		99.56 53	99.54 39	99.58 87	99.69 143	99.14 144	99.73 47	99.45 184	99.50 33	99.35 170	99.60 82	99.93 42	99.50 67	99.56 57	99.37 58	99.77 71	99.64 59
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
v2v482		99.56 53	99.35 68	99.81 31	99.87 53	99.35 105	99.75 39	99.85 68	99.56 25	99.87 29	99.95 6	99.44 136	99.66 35	98.91 154	98.76 131	99.86 41	99.45 109

Gipuma		99.55 55	99.23 87	99.91 5	99.87 53	99.52 69	99.86 10	99.93 27	99.87 1	99.96 2	96.72 207	99.55 128	99.97 1	99.77 33	99.46 49	99.87 39	99.74 34
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DVP-MVS		99.53 56	99.51 42	99.55 95	99.82 93	99.58 51	99.54 88	99.78 113	99.28 60	99.21 180	99.70 65	99.97 9	99.32 92	99.32 89	99.14 73	99.64 109	99.58 77
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
NR-MVSNet		99.52 57	99.29 77	99.80 36	99.96 7	99.38 96	99.55 84	99.81 97	98.86 113	99.87 29	99.51 100	98.81 163	99.72 26	99.86 18	99.04 97	99.89 31	99.54 91

ACMMPR		99.51 58	99.32 72	99.72 61	99.87 53	99.33 108	99.61 71	99.85 68	99.19 69	99.73 88	98.73 165	99.95 25	99.61 44	99.35 83	99.14 73	99.66 99	99.58 77

UniMVSNet (Re)		99.50 59	99.29 77	99.75 51	99.86 68	99.47 78	99.51 95	99.82 89	98.90 108	99.89 17	99.64 74	99.00 156	99.55 54	99.32 89	99.08 90	99.90 28	99.59 68

FMVSNet1		99.50 59	99.57 33	99.42 117	99.67 150	99.65 39	99.60 75	99.91 43	99.40 44	99.39 163	99.83 45	99.27 151	98.14 165	99.68 42	99.50 42	99.81 58	99.68 49

HyFIR lowres test		99.50 59	99.26 81	99.80 36	99.95 10	99.62 42	99.76 35	99.97 1	99.67 10	99.56 129	99.94 11	98.40 171	99.78 12	98.84 170	98.59 150	99.76 73	99.72 39

PM-MVS		99.49 62	99.43 55	99.57 90	99.76 121	99.34 107	99.53 89	99.77 120	98.93 104	99.75 76	99.46 105	99.83 87	99.11 118	99.72 39	99.29 62	99.49 148	99.46 108

Anonymous20231206		99.48 63	99.31 74	99.69 67	99.79 103	99.57 52	99.63 68	99.79 108	98.88 110	99.91 13	99.72 60	99.93 42	99.59 48	99.24 107	98.63 146	99.43 157	99.18 146

DU-MVS		99.48 63	99.26 81	99.75 51	99.85 76	99.38 96	99.50 99	99.81 97	98.86 113	99.89 17	99.51 100	98.98 157	99.59 48	99.46 66	98.97 108	99.87 39	99.63 60

RPSCF		99.48 63	99.45 53	99.52 102	99.73 136	99.33 108	99.13 159	99.77 120	99.33 52	99.47 150	99.39 115	99.92 50	99.36 84	99.63 51	99.13 81	99.63 112	99.41 119

ACMMP_NAP		99.47 66	99.33 70	99.63 79	99.85 76	99.28 120	99.56 83	99.83 82	98.75 126	99.48 147	99.03 152	99.95 25	99.47 78	99.48 62	99.19 66	99.57 131	99.59 68

Anonymous20231211		99.47 66	99.39 63	99.57 90	99.89 42	99.60 45	99.50 99	99.69 142	98.91 107	99.62 117	99.17 138	99.35 144	98.86 139	99.63 51	99.46 49	99.84 47	99.62 63

SteuartSystems-ACMMP		99.47 66	99.22 90	99.76 47	99.88 48	99.36 101	99.65 63	99.84 77	98.47 151	99.80 58	98.68 168	99.96 14	99.68 31	99.37 80	99.06 92	99.72 88	99.66 53
Skip Steuart: Steuart Systems R&D Blog.
ACMM	98.37 12	99.47 66	99.23 87	99.74 57	99.86 68	99.19 138	99.68 56	99.86 61	99.16 76	99.71 97	98.52 178	99.95 25	99.62 43	99.35 83	99.02 99	99.74 81	99.42 118
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DVP-MVS++		99.46 70	99.57 33	99.33 138	99.75 125	99.57 52	99.44 112	99.81 97	99.38 47	98.56 209	99.81 51	99.99 3	98.79 143	99.33 87	99.13 81	99.62 118	99.81 19

HFP-MVS		99.46 70	99.30 75	99.65 73	99.82 93	99.25 126	99.50 99	99.82 89	99.23 62	99.58 127	98.86 156	99.94 35	99.56 53	99.14 129	99.12 85	99.63 112	99.56 84

LGP-MVS_train		99.46 70	99.18 99	99.78 41	99.87 53	99.25 126	99.71 54	99.87 57	98.02 183	99.79 62	98.90 155	99.96 14	99.66 35	99.49 61	99.17 69	99.79 65	99.49 101

SED-MVS		99.45 73	99.46 52	99.42 117	99.77 116	99.57 52	99.42 115	99.80 105	99.06 86	99.38 164	99.66 70	99.96 14	98.65 151	99.31 91	99.14 73	99.53 140	99.55 89

ETV-MVS		99.45 73	99.32 72	99.60 84	99.79 103	99.60 45	99.40 120	99.78 113	97.88 189	99.83 51	99.33 119	99.70 113	98.97 129	99.74 36	99.43 53	99.84 47	99.58 77

ACMP	98.32 13	99.44 75	99.18 99	99.75 51	99.83 88	99.18 139	99.64 64	99.83 82	98.81 122	99.79 62	98.42 185	99.96 14	99.64 41	99.46 66	98.98 107	99.74 81	99.44 112
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DCV-MVSNet		99.43 76	99.23 87	99.67 69	99.92 30	99.76 21	99.64 64	99.93 27	99.06 86	99.68 107	97.77 196	98.97 158	98.97 129	99.72 39	99.54 37	99.88 33	99.81 19

SMA-MVS		99.43 76	99.41 59	99.45 113	99.82 93	99.31 113	99.02 173	99.59 163	99.06 86	99.34 173	99.53 96	99.96 14	99.38 82	99.29 96	99.13 81	99.53 140	99.59 68
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
testgi		99.43 76	99.47 50	99.38 126	99.90 39	99.67 38	99.30 139	99.73 137	98.64 139	99.53 133	99.52 98	99.90 59	98.08 168	99.65 49	99.40 57	99.75 76	99.55 89

DELS-MVS		99.42 79	99.53 40	99.29 141	99.52 178	99.43 85	99.42 115	99.28 199	99.16 76	99.72 91	99.82 47	99.97 9	98.17 162	99.56 57	99.16 70	99.65 101	99.59 68
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
3Dnovator	99.16 3	99.42 79	99.22 90	99.65 73	99.78 108	99.13 148	99.50 99	99.85 68	99.40 44	99.80 58	98.59 174	99.79 101	99.30 96	99.20 117	99.06 92	99.71 91	99.35 132

DPE-MVS		99.41 81	99.36 67	99.47 109	99.66 151	99.48 76	99.46 110	99.75 134	98.65 135	99.41 160	99.67 68	99.95 25	98.82 140	99.21 114	99.14 73	99.72 88	99.40 124
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UniMVSNet_NR-MVSNet		99.41 81	99.12 111	99.76 47	99.86 68	99.48 76	99.50 99	99.81 97	98.84 116	99.89 17	99.45 106	98.32 174	99.59 48	99.22 111	98.89 117	99.90 28	99.63 60

CP-MVS		99.41 81	99.20 95	99.65 73	99.80 99	99.23 133	99.44 112	99.75 134	98.60 144	99.74 82	98.66 169	99.93 42	99.48 75	99.33 87	99.16 70	99.73 85	99.48 104

QAPM		99.41 81	99.21 94	99.64 78	99.78 108	99.16 141	99.51 95	99.85 68	99.20 66	99.72 91	99.43 107	99.81 91	99.25 100	98.87 160	98.71 138	99.71 91	99.30 137

UGNet		99.40 85	99.61 24	99.16 160	99.88 48	99.64 40	99.61 71	99.77 120	99.31 54	99.63 116	99.33 119	99.93 42	96.46 202	99.63 51	99.53 38	99.63 112	99.89 4
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
Vis-MVSNet (Re-imp)		99.40 85	99.28 79	99.55 95	99.92 30	99.68 36	99.31 134	99.87 57	98.69 132	99.16 182	99.08 147	98.64 167	99.20 104	99.65 49	99.46 49	99.83 52	99.72 39

OPM-MVS		99.39 87	99.22 90	99.59 85	99.76 121	98.82 172	99.51 95	99.79 108	99.17 72	99.53 133	99.31 124	99.95 25	99.35 85	99.22 111	98.79 130	99.60 123	99.27 140
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Fast-Effi-MVS+		99.39 87	99.18 99	99.63 79	99.86 68	99.28 120	99.45 111	99.91 43	98.47 151	99.61 120	99.50 102	99.57 125	99.17 105	99.24 107	98.66 143	99.78 67	99.59 68

LS3D		99.39 87	99.28 79	99.52 102	99.77 116	99.39 93	99.55 84	99.82 89	98.93 104	99.64 114	98.52 178	99.67 117	98.58 155	99.74 36	99.63 29	99.75 76	99.06 162

diffmvs		99.38 90	99.33 70	99.45 113	99.87 53	99.39 93	99.28 142	99.58 166	99.55 27	99.50 143	99.85 40	99.85 82	98.94 134	98.58 183	98.68 141	99.51 145	99.39 126
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CANet		99.36 91	99.39 63	99.34 137	99.80 99	99.35 105	99.41 119	99.47 182	99.20 66	99.74 82	99.54 90	99.68 115	98.05 170	99.23 109	98.97 108	99.57 131	99.73 36

MVS_0304		99.36 91	99.35 68	99.37 132	99.85 76	99.36 101	99.39 121	99.56 168	99.36 50	99.75 76	99.23 130	99.90 59	97.97 176	99.00 141	98.83 124	99.69 94	99.77 27

ACMMP		99.36 91	99.06 119	99.71 62	99.86 68	99.36 101	99.63 68	99.85 68	98.33 166	99.72 91	97.73 198	99.94 35	99.53 58	99.37 80	99.13 81	99.65 101	99.56 84
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
SD-MVS		99.35 94	99.26 81	99.46 111	99.66 151	99.15 143	98.92 182	99.67 151	99.55 27	99.35 170	98.83 158	99.91 56	99.35 85	99.19 120	98.53 152	99.78 67	99.68 49
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
MP-MVS		99.35 94	99.09 117	99.65 73	99.84 82	99.22 134	99.59 76	99.78 113	98.13 175	99.67 108	98.44 182	99.93 42	99.43 81	99.31 91	99.09 89	99.60 123	99.49 101
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
pmmvs4		99.34 96	99.15 106	99.57 90	99.77 116	98.90 165	99.51 95	99.77 120	99.07 84	99.73 88	99.72 60	99.84 85	99.07 120	98.85 165	98.39 161	99.55 138	99.27 140

EPP-MVSNet		99.34 96	99.10 115	99.62 83	99.94 23	99.74 29	99.66 62	99.80 105	99.07 84	98.93 192	99.61 79	96.13 189	99.49 72	99.67 45	99.63 29	99.92 21	99.86 11

TSAR-MVS + GP.		99.33 98	99.17 103	99.51 104	99.71 141	99.00 160	98.84 190	99.71 139	98.23 172	99.74 82	99.53 96	99.90 59	99.35 85	99.38 79	98.85 122	99.72 88	99.31 135

PHI-MVS		99.33 98	99.19 97	99.49 107	99.69 143	99.25 126	99.27 143	99.59 163	98.44 155	99.78 66	99.15 139	99.92 50	98.95 133	99.39 77	99.04 97	99.64 109	99.18 146

MSP-MVS		99.32 100	99.26 81	99.38 126	99.76 121	99.54 59	99.42 115	99.72 138	98.92 106	98.84 199	98.96 154	99.96 14	98.91 135	98.72 178	99.14 73	99.63 112	99.58 77
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
PGM-MVS		99.32 100	98.99 128	99.71 62	99.86 68	99.31 113	99.59 76	99.86 61	97.51 198	99.75 76	98.23 188	99.94 35	99.53 58	99.29 96	99.08 90	99.65 101	99.54 91

DeepC-MVS_fast	98.69 9	99.32 100	99.13 109	99.53 98	99.63 157	98.78 175	99.53 89	99.33 197	99.08 82	99.77 68	99.18 137	99.89 62	99.29 97	99.00 141	98.70 139	99.65 101	99.30 137
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSDG		99.32 100	99.09 117	99.58 87	99.75 125	98.74 179	99.36 126	99.54 171	99.14 79	99.72 91	99.24 128	99.89 62	99.51 63	99.30 93	98.76 131	99.62 118	98.54 180

TSAR-MVS + ACMM		99.31 104	99.26 81	99.37 132	99.66 151	98.97 163	99.20 151	99.56 168	99.33 52	99.19 181	99.54 90	99.91 56	99.32 92	99.12 130	98.34 164	99.29 171	99.65 56

3Dnovator+	98.92 7	99.31 104	99.03 123	99.63 79	99.77 116	98.90 165	99.52 92	99.81 97	99.37 48	99.72 91	98.03 193	99.73 109	99.32 92	98.99 144	98.81 128	99.67 97	99.36 130

X-MVS		99.30 106	98.99 128	99.66 71	99.85 76	99.30 115	99.49 106	99.82 89	98.32 167	99.69 100	97.31 205	99.93 42	99.50 67	99.37 80	99.16 70	99.60 123	99.53 94

MVS_111021_HR		99.30 106	99.14 107	99.48 108	99.58 174	99.25 126	99.27 143	99.61 158	98.74 128	99.66 111	99.02 153	99.84 85	99.33 89	99.20 117	98.76 131	99.44 154	99.18 146

TAPA-MVS	98.54 10	99.30 106	99.24 86	99.36 136	99.44 192	98.77 177	99.00 175	99.41 188	99.23 62	99.60 122	99.50 102	99.86 76	99.15 112	99.29 96	98.95 112	99.56 135	99.08 158
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CLD-MVS		99.30 106	99.01 127	99.63 79	99.75 125	98.89 168	99.35 129	99.60 160	98.53 149	99.86 35	99.57 86	99.94 35	99.52 61	98.96 146	98.10 177	99.70 93	99.08 158
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
USDC		99.29 110	98.98 130	99.65 73	99.72 138	98.87 170	99.47 108	99.66 154	99.35 51	99.87 29	99.58 85	99.87 75	99.51 63	98.85 165	97.93 183	99.65 101	98.38 184

PMVS	94.32 17	99.27 111	99.55 36	98.94 177	99.60 166	99.43 85	99.39 121	99.54 171	98.99 94	99.69 100	99.60 82	99.81 91	95.68 207	99.88 15	99.83 7	99.73 85	99.31 135
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FA-MVS(training)		99.26 112	99.12 111	99.44 115	99.60 166	99.26 122	99.24 148	99.97 1	98.84 116	99.76 71	99.43 107	98.74 164	98.47 158	99.39 77	99.10 87	99.57 131	99.07 161

MVS_111021_LR		99.25 113	99.13 109	99.39 122	99.50 186	99.14 144	99.23 149	99.50 179	98.67 133	99.61 120	99.12 143	99.81 91	99.16 108	99.28 101	98.67 142	99.35 167	99.21 145

ECVR-MVS		99.24 114	98.74 152	99.82 26	99.95 10	99.78 17	99.67 60	99.93 27	99.45 38	99.80 58	99.86 38	92.58 205	99.65 37	99.93 3	99.88 3	99.94 15	99.71 45

baseline		99.24 114	99.30 75	99.17 159	99.78 108	99.14 144	99.10 163	99.69 142	98.97 98	99.49 145	99.84 42	99.88 68	97.99 175	98.85 165	98.73 136	98.98 186	99.72 39

EIA-MVS		99.23 116	99.03 123	99.47 109	99.83 88	99.64 40	99.16 155	99.81 97	97.11 205	99.65 113	98.44 182	99.78 104	98.61 154	99.46 66	99.22 64	99.75 76	99.59 68

HPM-MVS++		99.23 116	98.98 130	99.53 98	99.75 125	99.02 158	99.44 112	99.77 120	98.65 135	99.52 139	98.72 166	99.92 50	99.33 89	98.77 176	98.40 160	99.40 161	99.36 130

PMMVS2		99.23 116	99.22 90	99.24 148	99.80 99	99.14 144	99.50 99	99.82 89	99.12 81	98.41 214	99.91 23	99.98 5	98.51 156	99.48 62	98.76 131	99.38 163	98.14 192

test1111		99.21 119	98.67 156	99.84 21	99.96 7	99.82 8	99.72 51	99.94 24	99.54 29	99.78 66	99.89 30	91.89 208	99.69 30	99.93 3	99.89 1	99.95 7	99.75 32

CPTT-MVS		99.21 119	98.89 140	99.58 87	99.72 138	99.12 151	99.30 139	99.76 129	98.62 140	99.66 111	97.51 201	99.89 62	99.48 75	99.01 139	98.64 145	99.58 130	99.40 124

TinyColmap		99.21 119	98.89 140	99.59 85	99.61 162	98.61 187	99.47 108	99.67 151	99.02 91	99.82 54	99.15 139	99.74 106	99.35 85	99.17 125	98.33 165	99.63 112	98.22 190

Effi-MVS+		99.20 122	98.93 135	99.50 106	99.79 103	99.26 122	98.82 193	99.96 12	98.37 165	99.60 122	99.12 143	98.36 172	99.05 123	98.93 149	98.82 125	99.78 67	99.68 49

PVSNet_BlendedMVS		99.20 122	99.17 103	99.23 149	99.69 143	99.33 108	99.04 168	99.13 202	98.41 160	99.79 62	99.33 119	99.36 141	98.10 166	99.29 96	98.87 119	99.65 101	99.56 84

PVSNet_Blended		99.20 122	99.17 103	99.23 149	99.69 143	99.33 108	99.04 168	99.13 202	98.41 160	99.79 62	99.33 119	99.36 141	98.10 166	99.29 96	98.87 119	99.65 101	99.56 84

MCST-MVS		99.17 125	98.82 148	99.57 90	99.75 125	98.70 183	99.25 147	99.69 142	98.62 140	99.59 124	98.54 176	99.79 101	99.53 58	98.48 187	98.15 173	99.64 109	99.43 115

APD-MVS		99.17 125	98.92 136	99.46 111	99.78 108	99.24 131	99.34 130	99.78 113	97.79 192	99.48 147	98.25 187	99.88 68	98.77 144	99.18 123	98.92 114	99.63 112	99.18 146
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
OpenMVS	98.82 8	99.17 125	98.85 144	99.53 98	99.75 125	99.06 156	99.36 126	99.82 89	98.28 169	99.76 71	98.47 180	99.61 121	98.91 135	98.80 173	98.70 139	99.60 123	99.04 166

IterMVS-LS		99.16 128	98.82 148	99.57 90	99.87 53	99.71 32	99.58 80	99.92 37	99.24 61	99.71 97	99.73 56	95.79 190	98.91 135	98.82 172	98.66 143	99.43 157	99.77 27
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DeepPCF-MVS	98.38 11	99.16 128	99.20 95	99.12 164	99.20 209	98.71 182	98.85 189	99.06 205	99.17 72	98.96 191	99.61 79	99.86 76	99.29 97	99.17 125	98.72 137	99.36 165	99.15 154

IterMVS-SCA-FT		99.15 130	98.96 132	99.38 126	99.87 53	99.54 59	99.53 89	99.79 108	98.94 102	99.82 54	99.92 16	97.65 181	98.82 140	98.95 148	98.26 167	98.45 195	99.47 107

CDS-MVSNet		99.15 130	99.10 115	99.21 155	99.59 171	99.22 134	99.48 107	99.47 182	98.89 109	99.41 160	99.84 42	98.11 177	97.76 179	99.26 106	99.01 101	99.57 131	99.38 127
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IS_MVSNet		99.15 130	99.12 111	99.19 157	99.92 30	99.73 31	99.55 84	99.86 61	98.45 154	96.91 220	98.74 164	98.33 173	99.02 125	99.54 59	99.47 47	99.88 33	99.61 65

MDA-MVSNet-bldmvs		99.11 133	99.11 114	99.12 164	99.91 34	99.38 96	99.77 32	98.72 209	99.31 54	99.85 42	99.43 107	98.26 175	99.48 75	99.85 19	98.47 155	96.99 206	99.08 158

OMC-MVS		99.11 133	98.95 133	99.29 141	99.37 198	98.57 189	99.19 152	99.20 201	98.87 112	99.58 127	99.13 141	99.88 68	99.00 126	99.19 120	98.46 156	99.43 157	98.57 179

MVS_Test		99.09 135	98.92 136	99.29 141	99.61 162	99.07 155	99.04 168	99.81 97	98.58 146	99.37 167	99.74 54	98.87 162	98.41 160	98.61 182	98.01 181	99.50 147	99.57 83

CNVR-MVS		99.08 136	98.83 145	99.37 132	99.61 162	98.74 179	99.15 156	99.54 171	98.59 145	99.37 167	98.15 190	99.88 68	99.08 119	98.91 154	98.46 156	99.48 149	99.06 162

IterMVS		99.08 136	98.90 139	99.29 141	99.87 53	99.53 62	99.52 92	99.77 120	98.94 102	99.75 76	99.91 23	97.52 185	98.72 148	98.86 163	98.14 174	98.09 198	99.43 115
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet2		99.07 138	99.19 97	98.93 179	99.02 214	99.53 62	99.31 134	99.84 77	98.86 113	98.88 195	99.64 74	98.44 170	96.92 196	99.35 83	99.00 105	99.61 120	99.53 94

CVMVSNet		99.06 139	98.88 143	99.28 145	99.52 178	99.53 62	99.42 115	99.69 142	98.74 128	98.27 216	99.89 30	95.48 193	99.44 79	99.46 66	99.33 59	99.32 170	99.75 32

CDPH-MVS		99.05 140	98.63 157	99.54 97	99.75 125	98.78 175	99.59 76	99.68 148	97.79 192	99.37 167	98.20 189	99.86 76	99.14 114	98.58 183	98.01 181	99.68 95	99.16 152

TAMVS		99.05 140	99.02 126	99.08 169	99.69 143	99.22 134	99.33 131	99.32 198	99.16 76	98.97 190	99.87 35	97.36 186	97.76 179	99.21 114	99.00 105	99.44 154	99.33 133

CANet_DTU		99.03 142	99.18 99	98.87 182	99.58 174	99.03 157	99.18 153	99.41 188	98.65 135	99.74 82	99.55 89	99.71 110	96.13 205	99.19 120	98.92 114	99.17 180	99.18 146

Effi-MVS+-dtu		99.01 143	99.05 120	98.98 173	99.60 166	99.13 148	99.03 172	99.61 158	98.52 150	99.01 187	98.53 177	99.83 87	96.95 195	99.48 62	98.59 150	99.66 99	99.25 144

canonicalmvs		99.00 144	98.68 155	99.37 132	99.68 149	99.42 89	98.94 181	99.89 52	99.00 93	98.99 188	98.43 184	95.69 191	98.96 132	99.18 123	99.18 67	99.74 81	99.88 6

MIMVSNet		99.00 144	99.03 123	98.97 176	99.32 204	99.32 112	99.39 121	99.91 43	98.41 160	98.76 202	99.24 128	99.17 153	97.13 189	99.30 93	98.80 129	99.29 171	99.01 167

CHOSEN 280x420		98.99 146	98.91 138	99.07 170	99.77 116	99.26 122	99.55 84	99.92 37	98.62 140	98.67 206	99.62 78	97.20 187	98.44 159	99.50 60	99.18 67	98.08 199	98.99 170

SF-MVS		98.96 147	98.95 133	98.98 173	99.64 156	98.89 168	98.00 219	99.58 166	98.42 158	99.08 186	98.63 171	99.83 87	98.04 172	99.02 138	98.76 131	99.52 142	99.13 155

GBi-Net		98.96 147	99.05 120	98.85 183	99.02 214	99.53 62	99.31 134	99.78 113	98.13 175	98.48 210	99.43 107	97.58 182	96.92 196	99.68 42	99.50 42	99.61 120	99.53 94

test1		98.96 147	99.05 120	98.85 183	99.02 214	99.53 62	99.31 134	99.78 113	98.13 175	98.48 210	99.43 107	97.58 182	96.92 196	99.68 42	99.50 42	99.61 120	99.53 94

PCF-MVS	97.86 15	98.95 150	98.53 162	99.44 115	99.70 142	98.80 174	98.96 177	99.69 142	98.65 135	99.59 124	99.33 119	99.94 35	99.12 117	98.01 197	97.11 194	99.59 129	97.83 196
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MS-PatchMatch		98.94 151	98.71 154	99.21 155	99.52 178	98.22 205	98.97 176	99.53 176	98.76 124	99.50 143	98.59 174	99.56 127	98.68 149	98.63 181	98.45 158	99.05 183	98.73 176

AdaColmap		98.93 152	98.53 162	99.39 122	99.52 178	98.65 186	99.11 162	99.59 163	98.08 179	99.44 153	97.46 203	99.45 134	99.24 101	98.92 151	98.44 159	99.44 154	98.73 176

MSLP-MVS++		98.92 153	98.73 153	99.14 161	99.44 192	99.00 160	98.36 209	99.35 194	98.82 121	99.38 164	96.06 209	99.79 101	99.07 120	98.88 159	99.05 95	99.27 173	99.53 94

new_pmnet		98.91 154	98.89 140	98.94 177	99.51 184	98.27 201	99.15 156	98.66 210	99.17 72	99.48 147	99.79 52	99.80 97	98.49 157	99.23 109	98.20 171	98.34 196	97.74 200

train_agg		98.89 155	98.48 167	99.38 126	99.69 143	98.76 178	99.31 134	99.60 160	97.71 194	98.98 189	97.89 194	99.89 62	99.29 97	98.32 188	97.59 190	99.42 160	99.16 152

NCCC		98.88 156	98.42 168	99.42 117	99.62 158	98.81 173	99.10 163	99.54 171	98.76 124	99.53 133	95.97 210	99.80 97	99.16 108	98.49 186	98.06 180	99.55 138	99.05 164

PLC	97.83 16	98.88 156	98.52 164	99.30 140	99.45 190	98.60 188	98.65 199	99.49 180	98.66 134	99.59 124	96.33 208	99.59 124	99.17 105	98.87 160	98.53 152	99.46 151	99.05 164
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
pmmvs3		98.85 158	98.60 158	99.13 162	99.66 151	98.72 181	99.37 125	99.06 205	98.44 155	99.76 71	99.74 54	99.55 128	99.15 112	99.04 136	96.00 202	97.80 200	98.72 178

Fast-Effi-MVS+-dtu		98.82 159	98.80 150	98.84 185	99.51 184	98.90 165	98.96 177	99.91 43	98.29 168	99.11 185	98.47 180	99.63 120	96.03 206	99.21 114	98.12 175	99.52 142	99.01 167

CNLPA		98.82 159	98.52 164	99.18 158	99.21 208	98.50 193	98.73 197	99.34 196	98.73 130	99.56 129	97.55 200	99.42 138	99.06 122	98.93 149	98.10 177	99.21 179	98.38 184

PatchMatch-RL		98.80 161	98.52 164	99.12 164	99.38 197	98.70 183	98.56 202	99.55 170	97.81 191	99.34 173	97.57 199	99.31 148	98.67 150	99.27 104	98.62 147	99.22 178	98.35 186

thisisatest0530		98.78 162	98.26 171	99.39 122	99.78 108	99.43 85	99.07 165	99.64 156	98.44 155	99.42 158	99.22 131	92.68 204	98.63 152	99.30 93	99.14 73	99.80 62	99.60 66

tttt0517		98.77 163	98.25 173	99.38 126	99.79 103	99.46 79	99.07 165	99.64 156	98.40 163	99.38 164	99.21 133	92.54 206	98.63 152	99.34 86	99.14 73	99.80 62	99.62 63

DI_MVS_plusplus_trai		98.74 164	98.08 181	99.51 104	99.79 103	99.29 119	99.61 71	99.60 160	99.20 66	99.46 151	99.09 146	92.93 198	98.97 129	98.27 191	98.35 163	99.65 101	99.45 109

TSAR-MVS + COLMAP		98.74 164	98.58 160	98.93 179	99.29 205	98.23 202	99.04 168	99.24 200	98.79 123	98.80 201	99.37 117	99.71 110	98.06 169	98.02 196	97.46 192	99.16 181	98.48 182

MDTV_nov1_ep13_2view		98.73 166	98.31 170	99.22 152	99.75 125	99.24 131	99.75 39	99.93 27	99.31 54	99.84 46	99.86 38	99.81 91	99.31 95	97.40 205	94.77 204	96.73 208	97.81 197

PMMVS		98.71 167	98.55 161	98.90 181	99.28 206	98.45 195	98.53 205	99.45 184	97.67 196	99.15 184	98.76 162	99.54 130	97.79 178	98.77 176	98.23 169	99.16 181	98.46 183

HQP-MVS		98.70 168	98.19 177	99.28 145	99.61 162	98.52 191	98.71 198	99.35 194	97.97 186	99.53 133	97.38 204	99.85 82	99.14 114	97.53 201	96.85 198	99.36 165	99.26 143

N_pmnet		98.64 169	98.23 176	99.11 167	99.78 108	99.25 126	99.75 39	99.39 192	99.65 13	99.70 99	99.78 53	99.89 62	98.81 142	97.60 200	94.28 205	97.24 205	97.15 204

CMPMVS	76.62 19	98.64 169	98.60 158	98.68 190	99.33 202	97.07 217	98.11 217	98.50 211	97.69 195	99.26 176	98.35 186	99.66 118	97.62 182	99.43 74	99.02 99	99.24 176	99.01 167
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet3		98.63 171	98.75 151	98.49 196	98.10 220	99.44 82	99.02 173	99.78 113	98.13 175	98.48 210	99.43 107	97.58 182	96.16 204	98.85 165	98.39 161	99.40 161	99.41 119

GA-MVS		98.59 172	98.15 178	99.09 168	99.59 171	99.13 148	98.84 190	99.52 178	98.61 143	99.35 170	99.67 68	93.03 197	97.73 181	98.90 158	98.26 167	99.51 145	99.48 104

MAR-MVS		98.54 173	98.15 178	98.98 173	99.37 198	98.09 208	98.56 202	99.65 155	96.11 219	99.27 175	97.16 206	99.50 131	98.03 173	98.87 160	98.23 169	99.01 184	99.13 155
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
new-patchmatchnet		98.49 174	97.60 183	99.53 98	99.90 39	99.55 56	99.77 32	99.48 181	99.67 10	99.86 35	99.98 3	99.98 5	99.50 67	96.90 207	91.52 211	98.67 192	95.62 210

FPMVS		98.48 175	98.83 145	98.07 206	99.09 212	97.98 211	99.07 165	98.04 217	98.99 94	99.22 179	98.85 157	99.43 137	93.79 214	99.66 47	99.11 86	99.24 176	97.76 198

MVS-HIRNet		98.45 176	98.25 173	98.69 189	99.12 210	97.81 216	98.55 204	99.85 68	98.58 146	99.67 108	99.61 79	99.86 76	97.46 185	97.95 198	96.37 200	97.49 202	97.56 201

test0.0.03 1		98.41 177	98.41 169	98.40 200	99.62 158	99.16 141	98.87 187	99.41 188	97.15 203	96.60 222	99.31 124	97.00 188	96.55 201	98.91 154	98.51 154	99.37 164	98.82 174

gg-mvs-nofinetune		98.40 178	98.26 171	98.57 194	99.83 88	98.86 171	98.77 196	99.97 1	99.57 24	99.99 1	99.99 1	93.81 195	93.50 215	98.91 154	98.20 171	99.33 169	98.52 181

baseline1		98.39 179	97.59 184	99.31 139	99.78 108	99.45 80	99.13 159	99.53 176	98.06 181	98.87 196	98.63 171	90.04 212	98.76 145	98.85 165	98.84 123	99.81 58	99.28 139

pmnet_mix02		98.28 180	97.48 186	99.22 152	99.78 108	99.12 151	99.68 56	99.39 192	99.49 34	99.86 35	99.82 47	99.89 62	99.23 102	95.54 210	92.36 208	97.38 203	96.14 208

PatchT		98.11 181	97.12 192	99.26 147	99.65 155	98.34 199	99.57 82	99.97 1	97.48 199	99.43 155	99.04 151	90.84 210	98.15 163	98.04 194	97.78 184	98.82 189	98.30 187

DPM-MVS		98.10 182	97.32 190	99.01 172	99.52 178	97.92 212	98.47 207	99.45 184	98.25 170	98.91 193	93.99 214	99.69 114	98.73 147	96.29 209	96.32 201	99.00 185	98.77 175

EPNet_dtu		98.09 183	98.25 173	97.91 208	99.58 174	98.02 210	98.19 214	99.67 151	97.94 187	99.74 82	99.07 149	98.71 166	93.40 216	97.50 202	97.09 195	96.89 207	99.44 112
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPNet		98.06 184	98.11 180	98.00 207	99.60 166	98.99 162	98.38 208	99.68 148	98.18 174	98.85 198	97.89 194	95.60 192	92.72 217	98.30 189	98.10 177	98.76 190	99.72 39
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		97.91 185	96.80 195	99.22 152	99.60 166	98.23 202	98.91 183	99.97 1	96.89 212	99.43 155	99.10 145	89.24 215	98.15 163	98.04 194	97.78 184	99.26 174	98.30 187

thres200		97.87 186	96.56 197	99.39 122	99.76 121	99.52 69	99.13 159	99.76 129	96.88 214	98.66 207	92.87 218	88.77 218	99.16 108	99.11 131	99.42 54	99.88 33	99.33 133

baseline2		97.87 186	97.18 191	98.67 191	99.34 201	99.17 140	98.48 206	98.82 208	97.08 206	98.83 200	98.75 163	89.47 214	97.03 194	98.67 180	98.27 166	99.52 142	98.83 173

thres600view7		97.86 188	96.53 200	99.41 120	99.84 82	99.52 69	99.36 126	99.76 129	97.32 201	98.38 215	93.24 215	87.25 220	99.23 102	99.11 131	99.75 18	99.88 33	99.48 104

tfpn200view9		97.85 189	96.54 198	99.38 126	99.74 134	99.52 69	99.17 154	99.76 129	96.10 220	98.70 204	92.99 216	89.10 216	99.00 126	99.11 131	99.56 33	99.88 33	99.41 119

thres400		97.82 190	96.47 201	99.40 121	99.81 98	99.44 82	99.29 141	99.69 142	97.15 203	98.57 208	92.82 219	87.96 219	99.16 108	98.96 146	99.55 36	99.86 41	99.41 119

IB-MVS	98.10 14	97.76 191	97.40 189	98.18 202	99.62 158	99.11 153	98.24 212	98.35 213	96.56 216	99.44 153	91.28 220	98.96 160	93.84 213	98.09 193	98.62 147	99.56 135	99.18 146
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
test-LLR		97.74 192	97.46 187	98.08 204	99.62 158	98.37 197	98.26 210	99.41 188	97.03 207	97.38 218	99.54 90	92.89 199	95.12 210	98.78 174	97.68 188	98.65 193	97.90 194

RPMNet		97.70 193	96.54 198	99.06 171	99.57 177	98.23 202	98.95 180	99.97 1	96.89 212	99.49 145	99.13 141	89.63 213	97.09 191	96.68 208	97.02 196	99.26 174	98.19 191

thres100view900		97.69 194	96.37 202	99.23 149	99.74 134	99.21 137	98.81 194	99.43 187	96.10 220	98.70 204	92.99 216	89.10 216	98.88 138	98.58 183	99.31 61	99.82 55	99.27 140

FMVSNet5		97.69 194	96.98 193	98.53 195	98.53 218	99.36 101	98.90 186	99.54 171	96.38 217	98.44 213	95.38 212	90.08 211	97.05 193	99.46 66	99.06 92	98.73 191	99.12 157

MVE	91.08 18	97.68 196	97.65 182	97.71 214	98.46 219	91.62 223	97.92 220	98.86 207	98.73 130	97.99 217	98.64 170	99.96 14	99.17 105	99.59 55	97.75 186	93.87 222	97.27 202
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test-mter		97.65 197	97.57 185	97.75 212	98.90 217	98.56 190	98.15 215	98.45 212	96.92 211	96.84 221	99.52 98	92.53 207	95.24 209	99.04 136	98.12 175	98.90 188	98.29 189

TESTMET0.1,1		97.62 198	97.46 187	97.81 210	99.07 213	98.37 197	98.26 210	98.35 213	97.03 207	97.38 218	99.54 90	92.89 199	95.12 210	98.78 174	97.68 188	98.65 193	97.90 194

test2506		97.57 199	95.67 208	99.78 41	99.95 10	99.78 17	99.67 60	99.93 27	99.45 38	99.55 132	99.20 134	71.73 227	99.65 37	99.93 3	99.88 3	99.94 15	99.72 39

MVSTER		97.55 200	96.75 196	98.48 197	99.46 189	99.54 59	98.24 212	99.77 120	97.56 197	99.41 160	99.31 124	84.86 222	94.66 212	98.86 163	97.75 186	99.34 168	99.38 127

ET-MVSNet_ETH3D		97.44 201	96.29 203	98.78 186	97.93 221	98.95 164	98.91 183	99.09 204	98.00 184	99.24 177	98.83 158	84.62 223	98.02 174	97.43 204	97.38 193	99.48 149	98.84 172

MDTV_nov1_ep13		97.41 202	96.26 204	98.76 187	99.47 188	98.43 196	99.26 146	99.82 89	98.06 181	99.23 178	99.22 131	92.86 201	98.05 170	95.33 212	93.66 207	96.73 208	96.26 207

ADS-MVSNet		97.29 203	96.17 205	98.59 193	99.59 171	98.70 183	99.32 132	99.86 61	98.47 151	99.56 129	99.08 147	98.16 176	97.34 187	92.92 214	91.17 212	95.91 211	94.72 213

SCA		97.25 204	96.05 206	98.64 192	99.36 200	99.02 158	99.27 143	99.96 12	98.25 170	99.69 100	98.71 167	94.66 194	97.95 177	93.95 213	92.35 209	95.64 212	95.40 212

gm-plane-assit		96.82 205	94.84 213	99.13 162	99.95 10	99.78 17	99.69 55	99.92 37	99.19 69	99.84 46	99.92 16	72.93 226	96.44 203	98.21 192	97.01 197	98.92 187	96.87 206

PatchmatchNet		96.81 206	95.41 210	98.43 199	99.43 194	98.30 200	99.23 149	99.93 27	98.19 173	99.64 114	98.81 161	93.50 196	97.43 186	92.89 215	90.78 214	94.94 217	95.41 211
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		96.76 207	95.30 212	98.46 198	99.42 195	98.47 194	99.32 132	99.91 43	98.42 158	99.51 141	99.07 149	92.81 202	97.12 190	92.39 216	91.71 210	95.51 213	94.20 215

E-PMN		96.72 208	95.78 207	97.81 210	99.45 190	95.46 220	98.14 216	98.33 215	97.99 185	98.73 203	98.09 191	98.97 158	97.54 184	97.45 203	91.09 213	94.70 219	91.40 218

tpm		96.56 209	94.68 214	98.74 188	99.12 210	97.90 213	98.79 195	99.93 27	96.79 215	99.69 100	99.19 136	81.48 225	97.56 183	95.46 211	93.97 206	97.37 204	97.99 193

EMVS		96.47 210	95.38 211	97.74 213	99.42 195	95.37 221	98.07 218	98.27 216	97.85 190	98.90 194	97.48 202	98.73 165	97.20 188	97.21 206	90.39 215	94.59 221	90.65 219

tpmrst		96.18 211	94.47 215	98.18 202	99.52 178	97.89 214	98.96 177	99.79 108	98.07 180	99.16 182	99.30 127	92.69 203	96.69 199	90.76 218	88.85 218	94.96 216	93.69 216

CostFormer		95.61 212	93.35 218	98.24 201	99.48 187	98.03 209	98.65 199	99.83 82	96.93 210	99.42 158	98.83 158	83.65 224	97.08 192	90.39 219	89.54 217	94.94 217	96.11 209

dps		95.59 213	93.46 217	98.08 204	99.33 202	98.22 205	98.87 187	99.70 140	96.17 218	98.87 196	97.75 197	86.85 221	96.60 200	91.24 217	89.62 216	95.10 215	94.34 214

tpm cat1		95.52 214	93.49 216	97.88 209	99.28 206	97.87 215	98.65 199	99.77 120	97.27 202	99.46 151	98.04 192	90.99 209	95.46 208	88.57 220	88.14 219	94.64 220	93.54 217

test_method		91.96 215	95.51 209	87.82 216	70.84 223	82.79 224	92.13 223	87.74 219	98.88 110	95.40 223	99.20 134	98.04 178	85.65 219	97.71 199	94.95 203	95.13 214	97.00 205

GG-mvs-BLEND		70.44 216	96.91 194	39.57 217	3.32 226	96.51 218	91.01 224	4.05 223	97.03 207	33.20 225	94.67 213	97.75 180	7.59 222	98.28 190	96.85 198	98.24 197	97.26 203

testmvs		22.33 217	29.66 219	13.79 218	8.97 224	10.35 225	15.53 227	8.09 222	32.51 222	19.87 226	45.18 221	30.56 229	17.05 221	29.96 221	24.74 220	13.21 223	34.30 220

test123		21.52 218	28.47 220	13.42 219	7.29 225	10.12 226	15.70 226	8.31 221	31.54 223	19.34 227	36.33 222	37.40 228	17.14 220	27.45 222	23.17 221	12.73 224	33.30 221

uanet_test		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 230	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

sosnet-low-res		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 230	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

sosnet		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 230	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

RE-MVS-def										99.96 2

9.14												99.57 125

SR-MVS					99.73 136			99.74 136				99.88 68

Anonymous202405211			99.14 107		99.87 53	99.55 56	99.50 99	99.70 140	98.55 148		98.61 173	98.46 169	98.76 145	99.66 47	99.50 42	99.85 44	99.63 60

our_test_3					99.75 125	99.11 153	99.74 46

ambc			98.83 145		99.72 138	98.52 191	98.84 190		98.96 99	99.92 9	99.34 118	99.74 106	99.04 124	98.68 179	97.57 191	99.46 151	98.99 170

MTAPA										99.62 117		99.95 25

MTMP										99.53 133		99.92 50

Patchmatch-RL test							65.75 225

tmp_tt				88.14 215	96.68 222	91.91 222	93.70 222	61.38 220	99.61 19	90.51 224	99.40 114	99.71 110	90.32 218	99.22 111	99.44 52	96.25 210

XVS					99.86 68	99.30 115	99.72 51			99.69 100		99.93 42				99.60 123

X-MVStestdata					99.86 68	99.30 115	99.72 51			99.69 100		99.93 42				99.60 123

mPP-MVS					99.84 82							99.92 50

NP-MVS									97.37 200

Patchmtry						98.19 207	98.91 183	99.97 1		99.43 155

DeepMVS_CX						96.39 219	97.15 221	88.89 218	97.94 187	99.51 141	95.71 211	97.88 179	98.19 161	98.92 151		97.73 201	97.75 199

High-resolution multi-view benchmark