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 38	99.75 4	99.93 6	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 18	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 13	99.94 5	99.94 11	99.74 108	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 22	99.89 5	99.96 12	99.82 2	99.90 16	99.92 16	99.95 25	99.68 32	99.93 3	99.88 3	99.95 7	99.86 11

anonymousdsp		99.87 5	99.86 3	99.88 13	99.95 10	99.75 28	99.90 4	99.96 12	99.69 7	99.83 52	99.96 4	99.99 3	99.74 22	99.95 2	99.83 7	99.91 25	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 49	99.77 69	99.95 6	99.96 14	99.85 3	99.93 3	99.83 7	99.95 7	99.72 40

WB-MVS		99.82 7	99.76 9	99.89 9	99.94 23	99.82 8	99.79 29	99.93 27	99.67 10	99.97 2	99.83 45	99.78 105	99.79 12	99.72 39	99.70 22	99.95 7	99.78 26

UniMVSNet_ETH3D		99.81 8	99.79 7	99.85 19	99.98 1	99.76 22	99.73 48	99.96 12	99.68 9	99.87 30	99.59 85	99.91 56	99.58 52	99.90 10	99.85 6	99.96 3	99.81 19

TDRefinement		99.81 8	99.76 9	99.86 16	99.83 89	99.53 63	99.89 5	99.91 44	99.73 5	99.88 24	99.83 45	99.96 14	99.76 17	99.91 9	99.81 11	99.86 42	99.59 69

WR-MVS		99.79 10	99.68 14	99.91 5	99.95 10	99.83 4	99.87 9	99.96 12	99.39 47	99.93 6	99.87 35	99.29 151	99.77 15	99.83 22	99.72 20	99.97 1	99.82 16

MIMVSNet1		99.79 10	99.75 11	99.84 22	99.89 43	99.83 4	99.84 16	99.89 53	99.31 55	99.93 6	99.92 16	99.97 9	99.68 32	99.89 11	99.64 28	99.82 56	99.66 54

pm-mvs1		99.77 12	99.69 13	99.86 16	99.94 23	99.68 37	99.84 16	99.93 27	99.59 22	99.87 30	99.92 16	99.21 154	99.65 38	99.88 15	99.77 16	99.93 21	99.78 26

PEN-MVS		99.77 12	99.65 19	99.91 5	99.95 10	99.80 16	99.86 10	99.97 1	99.08 83	99.89 18	99.69 68	99.68 117	99.84 5	99.81 27	99.64 28	99.95 7	99.81 19

EU-MVSNet		99.76 14	99.74 12	99.78 42	99.82 94	99.81 13	99.88 7	99.87 58	99.31 55	99.75 77	99.91 23	99.76 107	99.78 13	99.84 21	99.74 19	99.56 137	99.81 19

Vis-MVSNet		99.76 14	99.78 8	99.75 52	99.92 31	99.77 21	99.83 19	99.85 69	99.43 41	99.85 43	99.84 42	100.00 1	99.13 118	99.83 22	99.66 25	99.90 29	99.90 2
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS		99.75 16	99.66 18	99.85 19	99.87 54	99.86 2	99.83 19	99.91 44	98.84 117	99.92 10	99.57 87	99.85 82	99.60 47	99.82 25	99.79 13	99.94 16	99.87 9

CS-MVS-test		99.75 16	99.67 15	99.84 22	99.91 35	99.85 3	99.85 13	99.92 38	98.75 127	99.89 18	99.64 75	99.95 25	99.55 55	99.89 11	99.79 13	99.92 22	99.83 14

DTE-MVSNet		99.75 16	99.61 25	99.92 4	99.95 10	99.81 13	99.86 10	99.96 12	99.18 72	99.92 10	99.66 71	99.45 136	99.85 3	99.80 28	99.56 34	99.96 3	99.79 25

tfpnnormal		99.74 19	99.63 22	99.86 16	99.93 28	99.75 28	99.80 28	99.89 53	99.31 55	99.88 24	99.43 108	99.66 120	99.77 15	99.80 28	99.71 21	99.92 22	99.76 31

DeepC-MVS	99.05 5	99.74 19	99.64 20	99.84 22	99.90 40	99.39 94	99.79 29	99.81 98	99.69 7	99.90 16	99.87 35	99.98 5	99.81 7	99.62 55	99.32 62	99.83 53	99.65 57
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 21	99.67 15	99.81 32	99.93 28	99.74 30	99.68 57	99.91 44	99.59 22	99.88 24	99.73 57	99.81 92	99.55 55	99.59 56	99.53 39	99.89 32	99.70 48

PS-CasMVS		99.73 21	99.59 31	99.90 8	99.95 10	99.80 16	99.85 13	99.97 1	98.95 101	99.86 36	99.73 57	99.36 143	99.81 7	99.83 22	99.67 24	99.95 7	99.83 14

WR-MVS_H		99.73 21	99.61 25	99.88 13	99.95 10	99.82 8	99.83 19	99.96 12	99.01 93	99.84 47	99.71 65	99.41 142	99.74 22	99.77 33	99.70 22	99.95 7	99.82 16

TransMVSNet (Re)		99.72 24	99.59 31	99.88 13	99.95 10	99.76 22	99.88 7	99.94 24	99.58 24	99.92 10	99.90 27	98.55 171	99.65 38	99.89 11	99.76 17	99.95 7	99.70 48

ACMH	99.11 4	99.72 24	99.63 22	99.84 22	99.87 54	99.59 50	99.83 19	99.88 57	99.46 38	99.87 30	99.66 71	99.95 25	99.76 17	99.73 38	99.47 48	99.84 48	99.52 101
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FC-MVSNet-train		99.70 26	99.67 15	99.74 58	99.94 23	99.71 33	99.82 24	99.91 44	99.14 80	99.53 135	99.70 66	99.88 68	99.33 90	99.88 15	99.61 33	99.94 16	99.77 28

EC-MVSNet		99.70 26	99.57 34	99.85 19	99.95 10	99.81 13	99.85 13	99.93 27	98.39 165	99.76 72	99.48 105	99.94 35	99.70 30	99.85 19	99.66 25	99.91 25	99.87 9

COLMAP_ROB	99.18 2	99.70 26	99.60 29	99.81 32	99.84 83	99.37 101	99.76 36	99.84 78	99.54 30	99.82 55	99.64 75	99.95 25	99.75 19	99.79 30	99.56 34	99.83 53	99.37 131
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 29	99.59 31	99.81 32	99.88 49	99.41 91	99.75 40	99.86 62	99.43 41	99.80 59	99.54 91	99.97 9	99.73 25	99.82 25	99.52 41	99.85 45	99.43 117

test20.03		99.68 30	99.60 29	99.76 48	99.91 35	99.70 36	99.68 57	99.87 58	99.05 90	99.88 24	99.92 16	99.88 68	99.50 68	99.77 33	99.42 55	99.75 77	99.49 103

CP-MVSNet		99.68 30	99.51 43	99.89 9	99.95 10	99.76 22	99.83 19	99.96 12	98.83 121	99.84 47	99.65 74	99.09 157	99.80 10	99.78 31	99.62 32	99.95 7	99.82 16

casdiffmvs_mvg		99.67 32	99.61 25	99.74 58	99.94 23	99.60 46	99.62 71	99.77 121	99.54 30	99.67 110	99.82 48	99.80 98	99.52 62	99.40 77	99.51 42	99.91 25	99.59 69
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 33	99.64 20	99.67 70	99.91 35	99.71 33	99.61 72	99.79 109	99.41 43	99.91 14	99.85 40	99.61 123	99.00 128	99.67 46	99.42 55	99.81 59	99.81 19

v10		99.65 34	99.51 43	99.81 32	99.83 89	99.61 45	99.75 40	99.94 24	99.56 26	99.76 72	99.94 11	99.60 125	99.73 25	99.11 133	99.01 103	99.85 45	99.74 35

CHOSEN 1792x2688		99.65 34	99.55 37	99.77 47	99.93 28	99.60 46	99.79 29	99.92 38	99.73 5	99.74 83	99.93 14	99.98 5	99.80 10	98.83 173	99.01 103	99.45 155	99.76 31

UA-Net		99.64 36	99.62 24	99.66 72	99.97 2	99.82 8	99.14 160	99.96 12	98.95 101	99.52 141	99.38 117	99.86 76	99.55 55	99.72 39	99.66 25	99.80 63	99.94 1

GeoE		99.63 37	99.51 43	99.78 42	99.91 35	99.57 53	99.78 32	99.97 1	99.23 63	99.72 93	99.72 61	99.80 98	99.50 68	99.45 74	99.10 89	99.79 66	99.71 46

Baseline_NR-MVSNet		99.62 38	99.48 48	99.78 42	99.85 77	99.76 22	99.59 77	99.82 90	98.84 117	99.88 24	99.91 23	99.04 158	99.61 45	99.46 67	99.78 15	99.94 16	99.60 67

pmmvs-eth3d		99.61 39	99.48 48	99.75 52	99.87 54	99.30 117	99.75 40	99.89 53	99.23 63	99.85 43	99.88 34	99.97 9	99.49 73	99.46 67	99.01 103	99.68 97	99.52 101

v1144		99.61 39	99.43 56	99.82 27	99.88 49	99.41 91	99.76 36	99.86 62	99.64 16	99.84 47	99.95 6	99.49 134	99.74 22	99.00 143	98.93 115	99.84 48	99.58 78

v8		99.61 39	99.45 54	99.79 41	99.80 100	99.59 50	99.73 48	99.93 27	99.48 36	99.77 69	99.90 27	99.48 135	99.67 35	99.11 133	98.89 119	99.84 48	99.73 37

casdiffmvs		99.61 39	99.55 37	99.68 69	99.89 43	99.53 63	99.64 65	99.68 149	99.51 33	99.62 119	99.90 27	99.96 14	99.37 84	99.28 102	99.25 65	99.88 34	99.44 114
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CSCG		99.61 39	99.52 42	99.71 63	99.89 43	99.62 43	99.52 93	99.76 130	99.61 20	99.69 102	99.73 57	99.96 14	99.57 53	99.27 105	98.62 149	99.81 59	99.85 13

v1192		99.60 44	99.41 60	99.82 27	99.89 43	99.43 86	99.81 26	99.84 78	99.63 18	99.85 43	99.95 6	99.35 146	99.72 27	99.01 141	98.90 118	99.82 56	99.58 78

APDe-MVS		99.60 44	99.48 48	99.73 61	99.85 77	99.51 74	99.75 40	99.85 69	99.17 73	99.81 58	99.56 89	99.94 35	99.44 80	99.42 76	99.22 66	99.67 99	99.54 93
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
v1921920		99.59 46	99.40 63	99.82 27	99.88 49	99.45 81	99.81 26	99.83 83	99.65 14	99.86 36	99.95 6	99.29 151	99.75 19	98.98 147	98.86 123	99.78 68	99.59 69

TranMVSNet+NR-MVSNet		99.59 46	99.42 59	99.80 37	99.87 54	99.55 57	99.64 65	99.86 62	99.05 90	99.88 24	99.72 61	99.33 149	99.64 42	99.47 66	99.14 75	99.91 25	99.67 53

EG-PatchMatch MVS		99.59 46	99.49 47	99.70 66	99.82 94	99.26 124	99.39 122	99.83 83	98.99 95	99.93 6	99.54 91	99.92 50	99.51 64	99.78 31	99.50 43	99.73 86	99.41 121

pmmvs5		99.58 49	99.47 51	99.70 66	99.84 83	99.50 75	99.58 81	99.80 106	98.98 98	99.73 90	99.92 16	99.81 92	99.49 73	99.28 102	99.05 97	99.77 72	99.73 37

v144192		99.58 49	99.39 64	99.80 37	99.87 54	99.44 83	99.77 33	99.84 78	99.64 16	99.86 36	99.93 14	99.35 146	99.72 27	98.92 153	98.82 127	99.74 82	99.66 54

v148		99.58 49	99.43 56	99.76 48	99.87 54	99.40 93	99.76 36	99.85 69	99.48 36	99.83 52	99.82 48	99.83 87	99.51 64	99.20 119	98.82 127	99.75 77	99.45 111

v1240		99.58 49	99.38 67	99.82 27	99.89 43	99.49 76	99.82 24	99.83 83	99.63 18	99.86 36	99.96 4	98.92 164	99.75 19	99.15 129	98.96 112	99.76 74	99.56 85

V42		99.57 53	99.41 60	99.75 52	99.84 83	99.37 101	99.73 48	99.83 83	99.41 43	99.75 77	99.89 30	99.42 140	99.60 47	99.15 129	98.96 112	99.76 74	99.65 57

TSAR-MVS + MP.		99.56 54	99.54 40	99.58 88	99.69 145	99.14 146	99.73 48	99.45 186	99.50 34	99.35 172	99.60 83	99.93 42	99.50 68	99.56 58	99.37 59	99.77 72	99.64 60
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 54	99.35 69	99.81 32	99.87 54	99.35 107	99.75 40	99.85 69	99.56 26	99.87 30	99.95 6	99.44 138	99.66 36	98.91 156	98.76 133	99.86 42	99.45 111

Gipuma		99.55 56	99.23 88	99.91 5	99.87 54	99.52 70	99.86 10	99.93 27	99.87 1	99.96 3	96.72 210	99.55 130	99.97 1	99.77 33	99.46 50	99.87 40	99.74 35
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DVP-MVS		99.53 57	99.51 43	99.55 97	99.82 94	99.58 52	99.54 89	99.78 114	99.28 61	99.21 182	99.70 66	99.97 9	99.32 93	99.32 90	99.14 75	99.64 111	99.58 78
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 58	99.29 78	99.80 37	99.96 7	99.38 97	99.55 85	99.81 98	98.86 114	99.87 30	99.51 101	98.81 166	99.72 27	99.86 18	99.04 99	99.89 32	99.54 93

ACMMPR		99.51 59	99.32 73	99.72 62	99.87 54	99.33 110	99.61 72	99.85 69	99.19 70	99.73 90	98.73 166	99.95 25	99.61 45	99.35 84	99.14 75	99.66 101	99.58 78

UniMVSNet (Re)		99.50 60	99.29 78	99.75 52	99.86 69	99.47 79	99.51 96	99.82 90	98.90 109	99.89 18	99.64 75	99.00 159	99.55 55	99.32 90	99.08 92	99.90 29	99.59 69

FMVSNet1		99.50 60	99.57 34	99.42 119	99.67 152	99.65 40	99.60 76	99.91 44	99.40 45	99.39 165	99.83 45	99.27 153	98.14 167	99.68 43	99.50 43	99.81 59	99.68 50

HyFIR lowres test		99.50 60	99.26 82	99.80 37	99.95 10	99.62 43	99.76 36	99.97 1	99.67 10	99.56 131	99.94 11	98.40 174	99.78 13	98.84 172	98.59 152	99.76 74	99.72 40

PM-MVS		99.49 63	99.43 56	99.57 92	99.76 122	99.34 109	99.53 90	99.77 121	98.93 105	99.75 77	99.46 106	99.83 87	99.11 120	99.72 39	99.29 64	99.49 150	99.46 110

Anonymous20231206		99.48 64	99.31 75	99.69 68	99.79 104	99.57 53	99.63 69	99.79 109	98.88 111	99.91 14	99.72 61	99.93 42	99.59 49	99.24 108	98.63 148	99.43 159	99.18 148

DU-MVS		99.48 64	99.26 82	99.75 52	99.85 77	99.38 97	99.50 100	99.81 98	98.86 114	99.89 18	99.51 101	98.98 160	99.59 49	99.46 67	98.97 110	99.87 40	99.63 61

RPSCF		99.48 64	99.45 54	99.52 104	99.73 138	99.33 110	99.13 161	99.77 121	99.33 53	99.47 152	99.39 116	99.92 50	99.36 85	99.63 52	99.13 83	99.63 114	99.41 121

ACMMP_NAP		99.47 67	99.33 71	99.63 80	99.85 77	99.28 122	99.56 84	99.83 83	98.75 127	99.48 149	99.03 153	99.95 25	99.47 79	99.48 63	99.19 68	99.57 133	99.59 69

Anonymous20231211		99.47 67	99.39 64	99.57 92	99.89 43	99.60 46	99.50 100	99.69 143	98.91 108	99.62 119	99.17 139	99.35 146	98.86 141	99.63 52	99.46 50	99.84 48	99.62 64

SteuartSystems-ACMMP		99.47 67	99.22 91	99.76 48	99.88 49	99.36 103	99.65 64	99.84 78	98.47 152	99.80 59	98.68 169	99.96 14	99.68 32	99.37 81	99.06 94	99.72 90	99.66 54
Skip Steuart: Steuart Systems R&D Blog.
ACMM	98.37 12	99.47 67	99.23 88	99.74 58	99.86 69	99.19 140	99.68 57	99.86 62	99.16 77	99.71 99	98.52 179	99.95 25	99.62 44	99.35 84	99.02 101	99.74 82	99.42 120
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DVP-MVS++		99.46 71	99.57 34	99.33 140	99.75 126	99.57 53	99.44 113	99.81 98	99.38 48	98.56 211	99.81 52	99.99 3	98.79 145	99.33 88	99.13 83	99.62 120	99.81 19

HFP-MVS		99.46 71	99.30 76	99.65 74	99.82 94	99.25 128	99.50 100	99.82 90	99.23 63	99.58 129	98.86 157	99.94 35	99.56 54	99.14 131	99.12 87	99.63 114	99.56 85

LGP-MVS_train		99.46 71	99.18 100	99.78 42	99.87 54	99.25 128	99.71 55	99.87 58	98.02 184	99.79 63	98.90 156	99.96 14	99.66 36	99.49 62	99.17 71	99.79 66	99.49 103

SED-MVS		99.45 74	99.46 53	99.42 119	99.77 117	99.57 53	99.42 116	99.80 106	99.06 87	99.38 166	99.66 71	99.96 14	98.65 153	99.31 92	99.14 75	99.53 142	99.55 90

ETV-MVS		99.45 74	99.32 73	99.60 85	99.79 104	99.60 46	99.40 121	99.78 114	97.88 190	99.83 52	99.33 120	99.70 115	98.97 131	99.74 36	99.43 54	99.84 48	99.58 78

ACMP	98.32 13	99.44 76	99.18 100	99.75 52	99.83 89	99.18 141	99.64 65	99.83 83	98.81 123	99.79 63	98.42 186	99.96 14	99.64 42	99.46 67	98.98 109	99.74 82	99.44 114
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DCV-MVSNet		99.43 77	99.23 88	99.67 70	99.92 31	99.76 22	99.64 65	99.93 27	99.06 87	99.68 109	97.77 197	98.97 161	98.97 131	99.72 39	99.54 38	99.88 34	99.81 19

SMA-MVS		99.43 77	99.41 60	99.45 115	99.82 94	99.31 115	99.02 175	99.59 165	99.06 87	99.34 175	99.53 97	99.96 14	99.38 83	99.29 97	99.13 83	99.53 142	99.59 69
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 77	99.47 51	99.38 128	99.90 40	99.67 39	99.30 140	99.73 138	98.64 140	99.53 135	99.52 99	99.90 59	98.08 170	99.65 50	99.40 58	99.75 77	99.55 90

DELS-MVS		99.42 80	99.53 41	99.29 143	99.52 180	99.43 86	99.42 116	99.28 201	99.16 77	99.72 93	99.82 48	99.97 9	98.17 164	99.56 58	99.16 72	99.65 103	99.59 69
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 80	99.22 91	99.65 74	99.78 109	99.13 150	99.50 100	99.85 69	99.40 45	99.80 59	98.59 175	99.79 102	99.30 97	99.20 119	99.06 94	99.71 93	99.35 134

DPE-MVS		99.41 82	99.36 68	99.47 111	99.66 153	99.48 77	99.46 111	99.75 135	98.65 136	99.41 162	99.67 69	99.95 25	98.82 142	99.21 116	99.14 75	99.72 90	99.40 126
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 82	99.12 112	99.76 48	99.86 69	99.48 77	99.50 100	99.81 98	98.84 117	99.89 18	99.45 107	98.32 177	99.59 49	99.22 112	98.89 119	99.90 29	99.63 61

CP-MVS		99.41 82	99.20 96	99.65 74	99.80 100	99.23 135	99.44 113	99.75 135	98.60 145	99.74 83	98.66 170	99.93 42	99.48 76	99.33 88	99.16 72	99.73 86	99.48 106

QAPM		99.41 82	99.21 95	99.64 79	99.78 109	99.16 143	99.51 96	99.85 69	99.20 67	99.72 93	99.43 108	99.81 92	99.25 102	98.87 162	98.71 140	99.71 93	99.30 139

UGNet		99.40 86	99.61 25	99.16 162	99.88 49	99.64 41	99.61 72	99.77 121	99.31 55	99.63 118	99.33 120	99.93 42	96.46 204	99.63 52	99.53 39	99.63 114	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 86	99.28 80	99.55 97	99.92 31	99.68 37	99.31 135	99.87 58	98.69 133	99.16 184	99.08 148	98.64 170	99.20 106	99.65 50	99.46 50	99.83 53	99.72 40

OPM-MVS		99.39 88	99.22 91	99.59 86	99.76 122	98.82 174	99.51 96	99.79 109	99.17 73	99.53 135	99.31 125	99.95 25	99.35 86	99.22 112	98.79 132	99.60 125	99.27 142
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Fast-Effi-MVS+		99.39 88	99.18 100	99.63 80	99.86 69	99.28 122	99.45 112	99.91 44	98.47 152	99.61 122	99.50 103	99.57 127	99.17 107	99.24 108	98.66 145	99.78 68	99.59 69

LS3D		99.39 88	99.28 80	99.52 104	99.77 117	99.39 94	99.55 85	99.82 90	98.93 105	99.64 116	98.52 179	99.67 119	98.58 157	99.74 36	99.63 30	99.75 77	99.06 164

diffmvs		99.38 91	99.33 71	99.45 115	99.87 54	99.39 94	99.28 144	99.58 168	99.55 28	99.50 145	99.85 40	99.85 82	98.94 136	98.58 185	98.68 143	99.51 147	99.39 128
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 92	99.39 64	99.34 139	99.80 100	99.35 107	99.41 120	99.47 184	99.20 67	99.74 83	99.54 91	99.68 117	98.05 172	99.23 110	98.97 110	99.57 133	99.73 37

MVS_0304		99.36 92	99.35 69	99.37 134	99.85 77	99.36 103	99.39 122	99.56 170	99.36 51	99.75 77	99.23 131	99.90 59	97.97 178	99.00 143	98.83 126	99.69 96	99.77 28

ACMMP		99.36 92	99.06 120	99.71 63	99.86 69	99.36 103	99.63 69	99.85 69	98.33 167	99.72 93	97.73 199	99.94 35	99.53 59	99.37 81	99.13 83	99.65 103	99.56 85
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 95	99.26 82	99.46 113	99.66 153	99.15 145	98.92 184	99.67 153	99.55 28	99.35 172	98.83 159	99.91 56	99.35 86	99.19 122	98.53 154	99.78 68	99.68 50
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 95	99.09 118	99.65 74	99.84 83	99.22 136	99.59 77	99.78 114	98.13 176	99.67 110	98.44 183	99.93 42	99.43 82	99.31 92	99.09 91	99.60 125	99.49 103
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
pmmvs4		99.34 97	99.15 107	99.57 92	99.77 117	98.90 167	99.51 96	99.77 121	99.07 85	99.73 90	99.72 61	99.84 85	99.07 122	98.85 167	98.39 163	99.55 140	99.27 142

EPP-MVSNet		99.34 97	99.10 116	99.62 84	99.94 23	99.74 30	99.66 63	99.80 106	99.07 85	98.93 194	99.61 80	96.13 192	99.49 73	99.67 46	99.63 30	99.92 22	99.86 11

TSAR-MVS + GP.		99.33 99	99.17 104	99.51 106	99.71 143	99.00 162	98.84 192	99.71 140	98.23 173	99.74 83	99.53 97	99.90 59	99.35 86	99.38 80	98.85 124	99.72 90	99.31 137

PHI-MVS		99.33 99	99.19 98	99.49 109	99.69 145	99.25 128	99.27 145	99.59 165	98.44 156	99.78 67	99.15 140	99.92 50	98.95 135	99.39 78	99.04 99	99.64 111	99.18 148

MSP-MVS		99.32 101	99.26 82	99.38 128	99.76 122	99.54 60	99.42 116	99.72 139	98.92 107	98.84 201	98.96 155	99.96 14	98.91 137	98.72 180	99.14 75	99.63 114	99.58 78
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		99.32 101	98.99 129	99.71 63	99.86 69	99.31 115	99.59 77	99.86 62	97.51 199	99.75 77	98.23 189	99.94 35	99.53 59	99.29 97	99.08 92	99.65 103	99.54 93

DeepC-MVS_fast	98.69 9	99.32 101	99.13 110	99.53 100	99.63 159	98.78 177	99.53 90	99.33 199	99.08 83	99.77 69	99.18 138	99.89 62	99.29 98	99.00 143	98.70 141	99.65 103	99.30 139
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSDG		99.32 101	99.09 118	99.58 88	99.75 126	98.74 181	99.36 127	99.54 173	99.14 80	99.72 93	99.24 129	99.89 62	99.51 64	99.30 94	98.76 133	99.62 120	98.54 183

TSAR-MVS + ACMM		99.31 105	99.26 82	99.37 134	99.66 153	98.97 165	99.20 153	99.56 170	99.33 53	99.19 183	99.54 91	99.91 56	99.32 93	99.12 132	98.34 166	99.29 173	99.65 57

3Dnovator+	98.92 7	99.31 105	99.03 124	99.63 80	99.77 117	98.90 167	99.52 93	99.81 98	99.37 49	99.72 93	98.03 194	99.73 111	99.32 93	98.99 146	98.81 130	99.67 99	99.36 132

X-MVS		99.30 107	98.99 129	99.66 72	99.85 77	99.30 117	99.49 107	99.82 90	98.32 168	99.69 102	97.31 208	99.93 42	99.50 68	99.37 81	99.16 72	99.60 125	99.53 96

MVS_111021_HR		99.30 107	99.14 108	99.48 110	99.58 176	99.25 128	99.27 145	99.61 160	98.74 129	99.66 113	99.02 154	99.84 85	99.33 90	99.20 119	98.76 133	99.44 156	99.18 148

TAPA-MVS	98.54 10	99.30 107	99.24 87	99.36 138	99.44 195	98.77 179	99.00 177	99.41 190	99.23 63	99.60 124	99.50 103	99.86 76	99.15 114	99.29 97	98.95 114	99.56 137	99.08 160
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CLD-MVS		99.30 107	99.01 128	99.63 80	99.75 126	98.89 170	99.35 130	99.60 162	98.53 150	99.86 36	99.57 87	99.94 35	99.52 62	98.96 148	98.10 179	99.70 95	99.08 160
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
USDC		99.29 111	98.98 131	99.65 74	99.72 140	98.87 172	99.47 109	99.66 156	99.35 52	99.87 30	99.58 86	99.87 75	99.51 64	98.85 167	97.93 185	99.65 103	98.38 187

PMVS	94.32 17	99.27 112	99.55 37	98.94 179	99.60 168	99.43 86	99.39 122	99.54 173	98.99 95	99.69 102	99.60 83	99.81 92	95.68 209	99.88 15	99.83 7	99.73 86	99.31 137
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FA-MVS(training)		99.26 113	99.12 112	99.44 117	99.60 168	99.26 124	99.24 150	99.97 1	98.84 117	99.76 72	99.43 108	98.74 167	98.47 160	99.39 78	99.10 89	99.57 133	99.07 163

MVS_111021_LR		99.25 114	99.13 110	99.39 124	99.50 188	99.14 146	99.23 151	99.50 181	98.67 134	99.61 122	99.12 144	99.81 92	99.16 110	99.28 102	98.67 144	99.35 169	99.21 147

ECVR-MVS		99.24 115	98.74 154	99.82 27	99.95 10	99.78 18	99.67 61	99.93 27	99.45 39	99.80 59	99.86 38	92.58 208	99.65 38	99.93 3	99.88 3	99.94 16	99.71 46

baseline		99.24 115	99.30 76	99.17 161	99.78 109	99.14 146	99.10 165	99.69 143	98.97 99	99.49 147	99.84 42	99.88 68	97.99 177	98.85 167	98.73 138	98.98 188	99.72 40

EIA-MVS		99.23 117	99.03 124	99.47 111	99.83 89	99.64 41	99.16 157	99.81 98	97.11 206	99.65 115	98.44 183	99.78 105	98.61 156	99.46 67	99.22 66	99.75 77	99.59 69

HPM-MVS++		99.23 117	98.98 131	99.53 100	99.75 126	99.02 160	99.44 113	99.77 121	98.65 136	99.52 141	98.72 167	99.92 50	99.33 90	98.77 178	98.40 162	99.40 163	99.36 132

PMMVS2		99.23 117	99.22 91	99.24 150	99.80 100	99.14 146	99.50 100	99.82 90	99.12 82	98.41 217	99.91 23	99.98 5	98.51 158	99.48 63	98.76 133	99.38 165	98.14 195

test1111		99.21 120	98.67 158	99.84 22	99.96 7	99.82 8	99.72 52	99.94 24	99.54 30	99.78 67	99.89 30	91.89 211	99.69 31	99.93 3	99.89 1	99.95 7	99.75 33

CPTT-MVS		99.21 120	98.89 141	99.58 88	99.72 140	99.12 153	99.30 140	99.76 130	98.62 141	99.66 113	97.51 204	99.89 62	99.48 76	99.01 141	98.64 147	99.58 132	99.40 126

TinyColmap		99.21 120	98.89 141	99.59 86	99.61 164	98.61 189	99.47 109	99.67 153	99.02 92	99.82 55	99.15 140	99.74 108	99.35 86	99.17 127	98.33 167	99.63 114	98.22 193

Effi-MVS+		99.20 123	98.93 136	99.50 108	99.79 104	99.26 124	98.82 195	99.96 12	98.37 166	99.60 124	99.12 144	98.36 175	99.05 125	98.93 151	98.82 127	99.78 68	99.68 50

PVSNet_BlendedMVS		99.20 123	99.17 104	99.23 151	99.69 145	99.33 110	99.04 170	99.13 204	98.41 161	99.79 63	99.33 120	99.36 143	98.10 168	99.29 97	98.87 121	99.65 103	99.56 85

PVSNet_Blended		99.20 123	99.17 104	99.23 151	99.69 145	99.33 110	99.04 170	99.13 204	98.41 161	99.79 63	99.33 120	99.36 143	98.10 168	99.29 97	98.87 121	99.65 103	99.56 85

MCST-MVS		99.17 126	98.82 149	99.57 92	99.75 126	98.70 185	99.25 149	99.69 143	98.62 141	99.59 126	98.54 177	99.79 102	99.53 59	98.48 189	98.15 175	99.64 111	99.43 117

APD-MVS		99.17 126	98.92 137	99.46 113	99.78 109	99.24 133	99.34 131	99.78 114	97.79 193	99.48 149	98.25 188	99.88 68	98.77 146	99.18 125	98.92 116	99.63 114	99.18 148
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
OpenMVS	98.82 8	99.17 126	98.85 145	99.53 100	99.75 126	99.06 158	99.36 127	99.82 90	98.28 170	99.76 72	98.47 181	99.61 123	98.91 137	98.80 175	98.70 141	99.60 125	99.04 168

IterMVS-LS		99.16 129	98.82 149	99.57 92	99.87 54	99.71 33	99.58 81	99.92 38	99.24 62	99.71 99	99.73 57	95.79 193	98.91 137	98.82 174	98.66 145	99.43 159	99.77 28
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DeepPCF-MVS	98.38 11	99.16 129	99.20 96	99.12 166	99.20 212	98.71 184	98.85 191	99.06 207	99.17 73	98.96 193	99.61 80	99.86 76	99.29 98	99.17 127	98.72 139	99.36 167	99.15 156

IterMVS-SCA-FT		99.15 131	98.96 133	99.38 128	99.87 54	99.54 60	99.53 90	99.79 109	98.94 103	99.82 55	99.92 16	97.65 184	98.82 142	98.95 150	98.26 169	98.45 198	99.47 109

CDS-MVSNet		99.15 131	99.10 116	99.21 157	99.59 173	99.22 136	99.48 108	99.47 184	98.89 110	99.41 162	99.84 42	98.11 180	97.76 181	99.26 107	99.01 103	99.57 133	99.38 129
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IS_MVSNet		99.15 131	99.12 112	99.19 159	99.92 31	99.73 32	99.55 85	99.86 62	98.45 155	96.91 223	98.74 165	98.33 176	99.02 127	99.54 60	99.47 48	99.88 34	99.61 66

dmvs_re		99.14 134	98.76 152	99.58 88	99.75 126	99.38 97	99.30 140	99.68 149	96.94 211	99.74 83	97.70 200	99.20 155	99.29 98	99.22 112	99.35 60	99.73 86	99.55 90

MDA-MVSNet-bldmvs		99.11 135	99.11 115	99.12 166	99.91 35	99.38 97	99.77 33	98.72 211	99.31 55	99.85 43	99.43 108	98.26 178	99.48 76	99.85 19	98.47 157	96.99 209	99.08 160

OMC-MVS		99.11 135	98.95 134	99.29 143	99.37 201	98.57 191	99.19 154	99.20 203	98.87 113	99.58 129	99.13 142	99.88 68	99.00 128	99.19 122	98.46 158	99.43 159	98.57 182

MVS_Test		99.09 137	98.92 137	99.29 143	99.61 164	99.07 157	99.04 170	99.81 98	98.58 147	99.37 169	99.74 55	98.87 165	98.41 162	98.61 184	98.01 183	99.50 149	99.57 84

CNVR-MVS		99.08 138	98.83 146	99.37 134	99.61 164	98.74 181	99.15 158	99.54 173	98.59 146	99.37 169	98.15 191	99.88 68	99.08 121	98.91 156	98.46 158	99.48 151	99.06 164

IterMVS		99.08 138	98.90 140	99.29 143	99.87 54	99.53 63	99.52 93	99.77 121	98.94 103	99.75 77	99.91 23	97.52 188	98.72 150	98.86 165	98.14 176	98.09 201	99.43 117
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet2		99.07 140	99.19 98	98.93 181	99.02 217	99.53 63	99.31 135	99.84 78	98.86 114	98.88 197	99.64 75	98.44 173	96.92 198	99.35 84	99.00 107	99.61 122	99.53 96

CVMVSNet		99.06 141	98.88 144	99.28 147	99.52 180	99.53 63	99.42 116	99.69 143	98.74 129	98.27 219	99.89 30	95.48 196	99.44 80	99.46 67	99.33 61	99.32 172	99.75 33

CDPH-MVS		99.05 142	98.63 159	99.54 99	99.75 126	98.78 177	99.59 77	99.68 149	97.79 193	99.37 169	98.20 190	99.86 76	99.14 116	98.58 185	98.01 183	99.68 97	99.16 154

TAMVS		99.05 142	99.02 127	99.08 171	99.69 145	99.22 136	99.33 132	99.32 200	99.16 77	98.97 192	99.87 35	97.36 189	97.76 181	99.21 116	99.00 107	99.44 156	99.33 135

CANet_DTU		99.03 144	99.18 100	98.87 184	99.58 176	99.03 159	99.18 155	99.41 190	98.65 136	99.74 83	99.55 90	99.71 112	96.13 207	99.19 122	98.92 116	99.17 182	99.18 148

Effi-MVS+-dtu		99.01 145	99.05 121	98.98 175	99.60 168	99.13 150	99.03 174	99.61 160	98.52 151	99.01 189	98.53 178	99.83 87	96.95 197	99.48 63	98.59 152	99.66 101	99.25 146

canonicalmvs		99.00 146	98.68 157	99.37 134	99.68 151	99.42 90	98.94 183	99.89 53	99.00 94	98.99 190	98.43 185	95.69 194	98.96 134	99.18 125	99.18 69	99.74 82	99.88 6

MIMVSNet		99.00 146	99.03 124	98.97 178	99.32 207	99.32 114	99.39 122	99.91 44	98.41 161	98.76 204	99.24 129	99.17 156	97.13 191	99.30 94	98.80 131	99.29 173	99.01 169

CHOSEN 280x420		98.99 148	98.91 139	99.07 172	99.77 117	99.26 124	99.55 85	99.92 38	98.62 141	98.67 208	99.62 79	97.20 190	98.44 161	99.50 61	99.18 69	98.08 202	98.99 172

SF-MVS		98.96 149	98.95 134	98.98 175	99.64 158	98.89 170	98.00 221	99.58 168	98.42 159	99.08 188	98.63 172	99.83 87	98.04 174	99.02 140	98.76 133	99.52 144	99.13 157

GBi-Net		98.96 149	99.05 121	98.85 185	99.02 217	99.53 63	99.31 135	99.78 114	98.13 176	98.48 213	99.43 108	97.58 185	96.92 198	99.68 43	99.50 43	99.61 122	99.53 96

test1		98.96 149	99.05 121	98.85 185	99.02 217	99.53 63	99.31 135	99.78 114	98.13 176	98.48 213	99.43 108	97.58 185	96.92 198	99.68 43	99.50 43	99.61 122	99.53 96

PCF-MVS	97.86 15	98.95 152	98.53 164	99.44 117	99.70 144	98.80 176	98.96 179	99.69 143	98.65 136	99.59 126	99.33 120	99.94 35	99.12 119	98.01 199	97.11 196	99.59 131	97.83 199
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MS-PatchMatch		98.94 153	98.71 156	99.21 157	99.52 180	98.22 207	98.97 178	99.53 178	98.76 125	99.50 145	98.59 175	99.56 129	98.68 151	98.63 183	98.45 160	99.05 185	98.73 179

AdaColmap		98.93 154	98.53 164	99.39 124	99.52 180	98.65 188	99.11 164	99.59 165	98.08 180	99.44 155	97.46 206	99.45 136	99.24 103	98.92 153	98.44 161	99.44 156	98.73 179

MSLP-MVS++		98.92 155	98.73 155	99.14 163	99.44 195	99.00 162	98.36 211	99.35 196	98.82 122	99.38 166	96.06 212	99.79 102	99.07 122	98.88 161	99.05 97	99.27 175	99.53 96

new_pmnet		98.91 156	98.89 141	98.94 179	99.51 186	98.27 203	99.15 158	98.66 212	99.17 73	99.48 149	99.79 53	99.80 98	98.49 159	99.23 110	98.20 173	98.34 199	97.74 203

train_agg		98.89 157	98.48 169	99.38 128	99.69 145	98.76 180	99.31 135	99.60 162	97.71 195	98.98 191	97.89 195	99.89 62	99.29 98	98.32 190	97.59 192	99.42 162	99.16 154

NCCC		98.88 158	98.42 170	99.42 119	99.62 160	98.81 175	99.10 165	99.54 173	98.76 125	99.53 135	95.97 213	99.80 98	99.16 110	98.49 188	98.06 182	99.55 140	99.05 166

PLC	97.83 16	98.88 158	98.52 166	99.30 142	99.45 193	98.60 190	98.65 201	99.49 182	98.66 135	99.59 126	96.33 211	99.59 126	99.17 107	98.87 162	98.53 154	99.46 153	99.05 166
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
pmmvs3		98.85 160	98.60 160	99.13 164	99.66 153	98.72 183	99.37 126	99.06 207	98.44 156	99.76 72	99.74 55	99.55 130	99.15 114	99.04 138	96.00 204	97.80 203	98.72 181

Fast-Effi-MVS+-dtu		98.82 161	98.80 151	98.84 187	99.51 186	98.90 167	98.96 179	99.91 44	98.29 169	99.11 187	98.47 181	99.63 122	96.03 208	99.21 116	98.12 177	99.52 144	99.01 169

CNLPA		98.82 161	98.52 166	99.18 160	99.21 211	98.50 195	98.73 199	99.34 198	98.73 131	99.56 131	97.55 203	99.42 140	99.06 124	98.93 151	98.10 179	99.21 181	98.38 187

PatchMatch-RL		98.80 163	98.52 166	99.12 166	99.38 200	98.70 185	98.56 204	99.55 172	97.81 192	99.34 175	97.57 202	99.31 150	98.67 152	99.27 105	98.62 149	99.22 180	98.35 189

thisisatest0530		98.78 164	98.26 173	99.39 124	99.78 109	99.43 86	99.07 167	99.64 158	98.44 156	99.42 160	99.22 132	92.68 207	98.63 154	99.30 94	99.14 75	99.80 63	99.60 67

tttt0517		98.77 165	98.25 175	99.38 128	99.79 104	99.46 80	99.07 167	99.64 158	98.40 164	99.38 166	99.21 134	92.54 209	98.63 154	99.34 87	99.14 75	99.80 63	99.62 64

DI_MVS_plusplus_trai		98.74 166	98.08 183	99.51 106	99.79 104	99.29 121	99.61 72	99.60 162	99.20 67	99.46 153	99.09 147	92.93 201	98.97 131	98.27 193	98.35 165	99.65 103	99.45 111

TSAR-MVS + COLMAP		98.74 166	98.58 162	98.93 181	99.29 208	98.23 204	99.04 170	99.24 202	98.79 124	98.80 203	99.37 118	99.71 112	98.06 171	98.02 198	97.46 194	99.16 183	98.48 185

MDTV_nov1_ep13_2view		98.73 168	98.31 172	99.22 154	99.75 126	99.24 133	99.75 40	99.93 27	99.31 55	99.84 47	99.86 38	99.81 92	99.31 96	97.40 207	94.77 206	96.73 211	97.81 200

PMMVS		98.71 169	98.55 163	98.90 183	99.28 209	98.45 197	98.53 207	99.45 186	97.67 197	99.15 186	98.76 163	99.54 132	97.79 180	98.77 178	98.23 171	99.16 183	98.46 186

HQP-MVS		98.70 170	98.19 179	99.28 147	99.61 164	98.52 193	98.71 200	99.35 196	97.97 187	99.53 135	97.38 207	99.85 82	99.14 116	97.53 203	96.85 200	99.36 167	99.26 145

N_pmnet		98.64 171	98.23 178	99.11 169	99.78 109	99.25 128	99.75 40	99.39 194	99.65 14	99.70 101	99.78 54	99.89 62	98.81 144	97.60 202	94.28 207	97.24 208	97.15 207

CMPMVS	76.62 19	98.64 171	98.60 160	98.68 192	99.33 205	97.07 220	98.11 219	98.50 213	97.69 196	99.26 178	98.35 187	99.66 120	97.62 184	99.43 75	99.02 101	99.24 178	99.01 169
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet3		98.63 173	98.75 153	98.49 198	98.10 223	99.44 83	99.02 175	99.78 114	98.13 176	98.48 213	99.43 108	97.58 185	96.16 206	98.85 167	98.39 163	99.40 163	99.41 121

GA-MVS		98.59 174	98.15 180	99.09 170	99.59 173	99.13 150	98.84 192	99.52 180	98.61 144	99.35 172	99.67 69	93.03 200	97.73 183	98.90 160	98.26 169	99.51 147	99.48 106

MAR-MVS		98.54 175	98.15 180	98.98 175	99.37 201	98.09 210	98.56 204	99.65 157	96.11 221	99.27 177	97.16 209	99.50 133	98.03 175	98.87 162	98.23 171	99.01 186	99.13 157
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		98.49 176	97.60 185	99.53 100	99.90 40	99.55 57	99.77 33	99.48 183	99.67 10	99.86 36	99.98 3	99.98 5	99.50 68	96.90 209	91.52 213	98.67 195	95.62 213

FPMVS		98.48 177	98.83 146	98.07 208	99.09 215	97.98 213	99.07 167	98.04 219	98.99 95	99.22 181	98.85 158	99.43 139	93.79 217	99.66 48	99.11 88	99.24 178	97.76 201

MVS-HIRNet		98.45 178	98.25 175	98.69 191	99.12 213	97.81 219	98.55 206	99.85 69	98.58 147	99.67 110	99.61 80	99.86 76	97.46 187	97.95 200	96.37 202	97.49 205	97.56 204

test0.0.03 1		98.41 179	98.41 171	98.40 202	99.62 160	99.16 143	98.87 189	99.41 190	97.15 204	96.60 225	99.31 125	97.00 191	96.55 203	98.91 156	98.51 156	99.37 166	98.82 176

gg-mvs-nofinetune		98.40 180	98.26 173	98.57 196	99.83 89	98.86 173	98.77 198	99.97 1	99.57 25	99.99 1	99.99 1	93.81 198	93.50 218	98.91 156	98.20 173	99.33 171	98.52 184

baseline1		98.39 181	97.59 186	99.31 141	99.78 109	99.45 81	99.13 161	99.53 178	98.06 182	98.87 198	98.63 172	90.04 215	98.76 147	98.85 167	98.84 125	99.81 59	99.28 141

pmnet_mix02		98.28 182	97.48 188	99.22 154	99.78 109	99.12 153	99.68 57	99.39 194	99.49 35	99.86 36	99.82 48	99.89 62	99.23 104	95.54 212	92.36 210	97.38 206	96.14 211

PatchT		98.11 183	97.12 194	99.26 149	99.65 157	98.34 201	99.57 83	99.97 1	97.48 200	99.43 157	99.04 152	90.84 213	98.15 165	98.04 196	97.78 186	98.82 192	98.30 190

DPM-MVS		98.10 184	97.32 192	99.01 174	99.52 180	97.92 214	98.47 209	99.45 186	98.25 171	98.91 195	93.99 217	99.69 116	98.73 149	96.29 211	96.32 203	99.00 187	98.77 177

EPNet_dtu		98.09 185	98.25 175	97.91 210	99.58 176	98.02 212	98.19 216	99.67 153	97.94 188	99.74 83	99.07 150	98.71 169	93.40 219	97.50 204	97.09 197	96.89 210	99.44 114
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPNet		98.06 186	98.11 182	98.00 209	99.60 168	98.99 164	98.38 210	99.68 149	98.18 175	98.85 200	97.89 195	95.60 195	92.72 220	98.30 191	98.10 179	98.76 193	99.72 40
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		97.91 187	96.80 197	99.22 154	99.60 168	98.23 204	98.91 185	99.97 1	96.89 214	99.43 157	99.10 146	89.24 218	98.15 165	98.04 196	97.78 186	99.26 176	98.30 190

thres200		97.87 188	96.56 199	99.39 124	99.76 122	99.52 70	99.13 161	99.76 130	96.88 216	98.66 209	92.87 221	88.77 221	99.16 110	99.11 133	99.42 55	99.88 34	99.33 135

baseline2		97.87 188	97.18 193	98.67 193	99.34 204	99.17 142	98.48 208	98.82 210	97.08 207	98.83 202	98.75 164	89.47 217	97.03 196	98.67 182	98.27 168	99.52 144	98.83 175

thres600view7		97.86 190	96.53 202	99.41 122	99.84 83	99.52 70	99.36 127	99.76 130	97.32 202	98.38 218	93.24 218	87.25 223	99.23 104	99.11 133	99.75 18	99.88 34	99.48 106

tfpn200view9		97.85 191	96.54 200	99.38 128	99.74 136	99.52 70	99.17 156	99.76 130	96.10 222	98.70 206	92.99 219	89.10 219	99.00 128	99.11 133	99.56 34	99.88 34	99.41 121

thres400		97.82 192	96.47 203	99.40 123	99.81 99	99.44 83	99.29 143	99.69 143	97.15 204	98.57 210	92.82 222	87.96 222	99.16 110	98.96 148	99.55 37	99.86 42	99.41 121

IB-MVS	98.10 14	97.76 193	97.40 191	98.18 204	99.62 160	99.11 155	98.24 214	98.35 215	96.56 218	99.44 155	91.28 223	98.96 163	93.84 216	98.09 195	98.62 149	99.56 137	99.18 148
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		97.74 194	97.46 189	98.08 206	99.62 160	98.37 199	98.26 212	99.41 190	97.03 208	97.38 221	99.54 91	92.89 202	95.12 213	98.78 176	97.68 190	98.65 196	97.90 197

RPMNet		97.70 195	96.54 200	99.06 173	99.57 179	98.23 204	98.95 182	99.97 1	96.89 214	99.49 147	99.13 142	89.63 216	97.09 193	96.68 210	97.02 198	99.26 176	98.19 194

thres100view900		97.69 196	96.37 204	99.23 151	99.74 136	99.21 139	98.81 196	99.43 189	96.10 222	98.70 206	92.99 219	89.10 219	98.88 140	98.58 185	99.31 63	99.82 56	99.27 142

FMVSNet5		97.69 196	96.98 195	98.53 197	98.53 221	99.36 103	98.90 188	99.54 173	96.38 219	98.44 216	95.38 215	90.08 214	97.05 195	99.46 67	99.06 94	98.73 194	99.12 159

MVE	91.08 18	97.68 198	97.65 184	97.71 216	98.46 222	91.62 226	97.92 222	98.86 209	98.73 131	97.99 220	98.64 171	99.96 14	99.17 107	99.59 56	97.75 188	93.87 225	97.27 205
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test-mter		97.65 199	97.57 187	97.75 214	98.90 220	98.56 192	98.15 217	98.45 214	96.92 213	96.84 224	99.52 99	92.53 210	95.24 212	99.04 138	98.12 177	98.90 190	98.29 192

TESTMET0.1,1		97.62 200	97.46 189	97.81 212	99.07 216	98.37 199	98.26 212	98.35 215	97.03 208	97.38 221	99.54 91	92.89 202	95.12 213	98.78 176	97.68 190	98.65 196	97.90 197

test2506		97.57 201	95.67 210	99.78 42	99.95 10	99.78 18	99.67 61	99.93 27	99.45 39	99.55 134	99.20 135	71.73 230	99.65 38	99.93 3	99.88 3	99.94 16	99.72 40

MVSTER		97.55 202	96.75 198	98.48 199	99.46 192	99.54 60	98.24 214	99.77 121	97.56 198	99.41 162	99.31 125	84.86 225	94.66 215	98.86 165	97.75 188	99.34 170	99.38 129

ET-MVSNet_ETH3D		97.44 203	96.29 205	98.78 188	97.93 224	98.95 166	98.91 185	99.09 206	98.00 185	99.24 179	98.83 159	84.62 226	98.02 176	97.43 206	97.38 195	99.48 151	98.84 174

MDTV_nov1_ep13		97.41 204	96.26 206	98.76 189	99.47 190	98.43 198	99.26 148	99.82 90	98.06 182	99.23 180	99.22 132	92.86 204	98.05 172	95.33 214	93.66 209	96.73 211	96.26 210

ADS-MVSNet		97.29 205	96.17 207	98.59 195	99.59 173	98.70 185	99.32 133	99.86 62	98.47 152	99.56 131	99.08 148	98.16 179	97.34 189	92.92 216	91.17 214	95.91 214	94.72 216

SCA		97.25 206	96.05 208	98.64 194	99.36 203	99.02 160	99.27 145	99.96 12	98.25 171	99.69 102	98.71 168	94.66 197	97.95 179	93.95 215	92.35 211	95.64 215	95.40 215

gm-plane-assit		96.82 207	94.84 215	99.13 164	99.95 10	99.78 18	99.69 56	99.92 38	99.19 70	99.84 47	99.92 16	72.93 229	96.44 205	98.21 194	97.01 199	98.92 189	96.87 209

PatchmatchNet		96.81 208	95.41 212	98.43 201	99.43 197	98.30 202	99.23 151	99.93 27	98.19 174	99.64 116	98.81 162	93.50 199	97.43 188	92.89 217	90.78 216	94.94 220	95.41 214
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		96.76 209	95.30 214	98.46 200	99.42 198	98.47 196	99.32 133	99.91 44	98.42 159	99.51 143	99.07 150	92.81 205	97.12 192	92.39 218	91.71 212	95.51 216	94.20 218

E-PMN		96.72 210	95.78 209	97.81 212	99.45 193	95.46 223	98.14 218	98.33 217	97.99 186	98.73 205	98.09 192	98.97 161	97.54 186	97.45 205	91.09 215	94.70 222	91.40 221

tpm		96.56 211	94.68 216	98.74 190	99.12 213	97.90 215	98.79 197	99.93 27	96.79 217	99.69 102	99.19 137	81.48 228	97.56 185	95.46 213	93.97 208	97.37 207	97.99 196

EMVS		96.47 212	95.38 213	97.74 215	99.42 198	95.37 224	98.07 220	98.27 218	97.85 191	98.90 196	97.48 205	98.73 168	97.20 190	97.21 208	90.39 217	94.59 224	90.65 222

tpmrst		96.18 213	94.47 217	98.18 204	99.52 180	97.89 216	98.96 179	99.79 109	98.07 181	99.16 184	99.30 128	92.69 206	96.69 201	90.76 220	88.85 220	94.96 219	93.69 219

CostFormer		95.61 214	93.35 220	98.24 203	99.48 189	98.03 211	98.65 201	99.83 83	96.93 212	99.42 160	98.83 159	83.65 227	97.08 194	90.39 221	89.54 219	94.94 220	96.11 212

dps		95.59 215	93.46 219	98.08 206	99.33 205	98.22 207	98.87 189	99.70 141	96.17 220	98.87 198	97.75 198	86.85 224	96.60 202	91.24 219	89.62 218	95.10 218	94.34 217

tpm cat1		95.52 216	93.49 218	97.88 211	99.28 209	97.87 217	98.65 201	99.77 121	97.27 203	99.46 153	98.04 193	90.99 212	95.46 210	88.57 222	88.14 221	94.64 223	93.54 220

test_method		91.96 217	95.51 211	87.82 218	70.84 226	82.79 227	92.13 226	87.74 221	98.88 111	95.40 226	99.20 135	98.04 181	85.65 222	97.71 201	94.95 205	95.13 217	97.00 208

GG-mvs-BLEND		70.44 218	96.91 196	39.57 219	3.32 229	96.51 221	91.01 227	4.05 225	97.03 208	33.20 228	94.67 216	97.75 183	7.59 225	98.28 192	96.85 200	98.24 200	97.26 206

testmvs		22.33 219	29.66 221	13.79 220	8.97 227	10.35 228	15.53 230	8.09 224	32.51 224	19.87 229	45.18 224	30.56 232	17.05 224	29.96 223	24.74 222	13.21 226	34.30 223

test123		21.52 220	28.47 222	13.42 221	7.29 228	10.12 229	15.70 229	8.31 223	31.54 225	19.34 230	36.33 225	37.40 231	17.14 223	27.45 224	23.17 223	12.73 227	33.30 224

uanet_test		0.00 221	0.00 223	0.00 222	0.00 230	0.00 230	0.00 231	0.00 226	0.00 226	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet-low-res		0.00 221	0.00 223	0.00 222	0.00 230	0.00 230	0.00 231	0.00 226	0.00 226	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet		0.00 221	0.00 223	0.00 222	0.00 230	0.00 230	0.00 231	0.00 226	0.00 226	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

TPM-MVS					99.47 190	97.86 218	97.79 223			98.49 212	97.62 201	99.83 87	95.33 211			98.90 190	98.77 177
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										99.96 3

9.14												99.57 127

SR-MVS					99.73 138			99.74 137				99.88 68

Anonymous202405211			99.14 108		99.87 54	99.55 57	99.50 100	99.70 141	98.55 149		98.61 174	98.46 172	98.76 147	99.66 48	99.50 43	99.85 45	99.63 61

our_test_3					99.75 126	99.11 155	99.74 47

ambc			98.83 146		99.72 140	98.52 193	98.84 192		98.96 100	99.92 10	99.34 119	99.74 108	99.04 126	98.68 181	97.57 193	99.46 153	98.99 172

MTAPA										99.62 119		99.95 25

MTMP										99.53 135		99.92 50

Patchmatch-RL test							65.75 228

tmp_tt				88.14 217	96.68 225	91.91 225	93.70 225	61.38 222	99.61 20	90.51 227	99.40 115	99.71 112	90.32 221	99.22 112	99.44 53	96.25 213

XVS					99.86 69	99.30 117	99.72 52			99.69 102		99.93 42				99.60 125

X-MVStestdata					99.86 69	99.30 117	99.72 52			99.69 102		99.93 42				99.60 125

mPP-MVS					99.84 83							99.92 50

NP-MVS									97.37 201

Patchmtry						98.19 209	98.91 185	99.97 1		99.43 157

DeepMVS_CX						96.39 222	97.15 224	88.89 220	97.94 188	99.51 143	95.71 214	97.88 182	98.19 163	98.92 153		97.73 204	97.75 202

High-resolution multi-view benchmark