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	98.82 1	99.76 1	99.75 1	99.77 7	99.87 16	99.71 10	99.77 8	99.76 19	99.52 2	99.80 3	99.79 21	99.91 1	99.56 13	99.83 3	99.75 4	99.86 9	99.75 1
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
pmmvs6		99.74 2	99.75 1	99.73 11	99.92 5	99.67 15	99.76 10	99.84 11	99.59 1	99.52 24	99.87 11	99.91 1	99.43 27	99.87 1	99.81 2	99.89 6	99.52 12

SixPastTwentyTwo		99.70 3	99.59 4	99.82 2	99.93 3	99.80 1	99.86 2	99.87 6	98.87 12	99.79 5	99.85 14	99.33 73	99.74 5	99.85 2	99.82 1	99.74 24	99.63 5

v7n		99.68 4	99.61 3	99.76 8	99.89 12	99.74 7	99.87 1	99.82 13	99.20 6	99.71 6	99.96 1	99.73 16	99.76 3	99.58 20	99.59 16	99.52 47	99.46 17

anonymousdsp		99.64 5	99.55 6	99.74 10	99.87 16	99.56 26	99.82 3	99.73 23	98.54 20	99.71 6	99.92 4	99.84 7	99.61 9	99.70 9	99.63 9	99.69 33	99.64 3

UniMVSNet_ETH3D		99.61 6	99.59 4	99.63 13	99.96 1	99.70 11	99.53 36	99.86 8	99.28 5	99.48 30	99.44 58	99.86 5	99.01 70	99.78 4	99.76 3	99.90 2	99.33 23

WR-MVS		99.61 6	99.44 8	99.82 2	99.92 5	99.80 1	99.80 4	99.89 1	98.54 20	99.66 13	99.78 22	99.16 95	99.68 7	99.70 9	99.63 9	99.94 1	99.49 15

PEN-MVS		99.54 8	99.30 16	99.83 1	99.92 5	99.76 4	99.80 4	99.88 3	97.60 71	99.71 6	99.59 40	99.52 50	99.75 4	99.64 15	99.51 19	99.90 2	99.46 17

TDRefinement		99.54 8	99.50 7	99.60 17	99.70 71	99.35 46	99.77 8	99.58 51	99.40 4	99.28 48	99.66 29	99.41 62	99.55 15	99.74 8	99.65 8	99.70 30	99.25 28

DTE-MVSNet		99.52 10	99.27 17	99.82 2	99.93 3	99.77 3	99.79 6	99.87 6	97.89 51	99.70 11	99.55 49	99.21 85	99.77 2	99.65 13	99.43 23	99.90 2	99.36 21

PS-CasMVS		99.50 11	99.23 20	99.82 2	99.92 5	99.75 6	99.78 7	99.89 1	97.30 82	99.71 6	99.60 38	99.23 81	99.71 6	99.65 13	99.55 18	99.90 2	99.56 8

WR-MVS_H		99.48 12	99.23 20	99.76 8	99.91 9	99.76 4	99.75 11	99.88 3	97.27 85	99.58 17	99.56 45	99.24 80	99.56 13	99.60 18	99.60 15	99.88 8	99.58 7

pm-mvs1		99.47 13	99.38 9	99.57 21	99.82 28	99.49 30	99.63 23	99.65 39	98.88 11	99.31 42	99.85 14	99.02 114	99.23 46	99.60 18	99.58 17	99.80 15	99.22 35

MIMVSNet1		99.46 14	99.34 10	99.60 17	99.83 23	99.68 14	99.74 14	99.71 27	98.20 33	99.41 35	99.86 13	99.66 29	99.41 30	99.50 24	99.39 26	99.50 54	99.10 47

TransMVSNet (Re)		99.45 15	99.32 13	99.61 15	99.88 14	99.60 21	99.75 11	99.63 43	99.11 7	99.28 48	99.83 18	98.35 149	99.27 43	99.70 9	99.62 13	99.84 10	99.03 55

ACMH	97.81 6	99.44 16	99.33 11	99.56 22	99.81 32	99.42 37	99.73 15	99.58 51	99.02 8	99.10 72	99.41 63	99.69 21	99.60 10	99.45 28	99.26 37	99.55 43	99.05 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CP-MVSNet		99.39 17	99.04 29	99.80 6	99.91 9	99.70 11	99.75 11	99.88 3	96.82 110	99.68 12	99.32 70	98.86 123	99.68 7	99.57 21	99.47 20	99.89 6	99.52 12

COLMAP_ROB	98.29 2	99.37 18	99.25 18	99.51 30	99.74 61	99.12 82	99.56 33	99.39 91	98.96 10	99.17 60	99.44 58	99.63 36	99.58 11	99.48 26	99.27 36	99.60 40	98.81 81
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
DeepC-MVS	97.88 4	99.33 19	99.15 24	99.53 29	99.73 66	99.05 91	99.49 41	99.40 89	98.42 23	99.55 21	99.71 24	99.89 3	99.49 19	99.14 44	98.81 71	99.54 44	99.02 57
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
FC-MVSNet-test		99.32 20	99.33 11	99.31 57	99.87 16	99.65 18	99.63 23	99.75 21	97.76 55	97.29 206	99.87 11	99.63 36	99.52 16	99.66 12	99.63 9	99.77 20	99.12 43

UA-Net		99.30 21	99.22 22	99.39 44	99.94 2	99.66 17	98.91 119	99.86 8	97.74 61	98.74 114	99.00 99	99.60 42	99.17 55	99.50 24	99.39 26	99.70 30	99.64 3

ACMH+	97.53 7	99.29 22	99.20 23	99.40 43	99.81 32	99.22 65	99.59 30	99.50 71	98.64 19	98.29 152	99.21 83	99.69 21	99.57 12	99.53 23	99.33 31	99.66 34	98.81 81

Vis-MVSNet		99.25 23	99.32 13	99.17 68	99.65 86	99.55 28	99.63 23	99.33 107	98.16 34	99.29 45	99.65 33	99.77 13	97.56 156	99.44 30	99.14 42	99.58 41	99.51 14
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TranMVSNet+NR-MVSNet		99.23 24	98.91 38	99.61 15	99.81 32	99.45 34	99.47 43	99.68 30	97.28 84	99.39 36	99.54 50	99.08 110	99.45 22	99.09 50	98.84 67	99.83 11	99.04 53

CSCG		99.23 24	99.15 24	99.32 56	99.83 23	99.45 34	98.97 111	99.21 130	98.83 13	99.04 82	99.43 60	99.64 34	99.26 44	98.85 77	98.20 109	99.62 38	99.62 6

Gipuma		99.22 26	98.86 43	99.64 12	99.70 71	99.24 59	99.17 88	99.63 43	99.52 2	99.89 1	96.54 187	99.14 99	99.93 1	99.42 32	99.15 41	99.52 47	99.04 53
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tfpnnormal		99.19 27	98.90 39	99.54 26	99.81 32	99.55 28	99.60 28	99.54 59	98.53 22	99.23 52	98.40 121	98.23 152	99.40 31	99.29 37	99.36 29	99.63 37	98.95 67

Baseline_NR-MVSNet		99.18 28	98.87 41	99.54 26	99.74 61	99.56 26	99.36 59	99.62 48	96.53 130	99.29 45	99.85 14	98.64 141	99.40 31	99.03 61	99.63 9	99.83 11	98.86 76

thisisatest0515		99.16 29	98.94 34	99.41 38	99.75 55	99.43 36	99.36 59	99.63 43	97.68 67	99.35 38	99.31 71	98.90 120	99.09 64	98.95 66	99.20 38	99.27 86	99.11 44

SPE-MVS-test		99.16 29	98.78 48	99.60 17	99.80 38	99.72 9	99.69 16	99.73 23	95.88 152	99.51 26	98.53 117	99.54 47	99.21 49	99.24 40	99.43 23	99.66 34	99.15 42

CS-MVS		99.15 31	98.75 50	99.62 14	99.76 50	99.73 8	99.60 28	99.75 21	95.67 159	99.50 27	98.53 117	99.39 67	99.29 40	99.21 42	99.46 22	99.79 18	99.29 26

APDe-MVS		99.15 31	98.95 31	99.39 44	99.77 45	99.28 55	99.52 37	99.54 59	97.22 89	99.06 76	99.20 84	99.64 34	99.05 68	99.14 44	99.02 52	99.39 68	99.17 39
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
WB-MVS		99.14 33	99.31 15	98.95 98	99.81 32	99.61 20	98.85 126	99.51 68	99.01 9	97.37 200	99.33 68	99.56 45	98.70 89	99.44 30	99.29 33	99.45 59	98.96 66

FC-MVSNet-train		99.13 34	99.05 28	99.21 63	99.87 16	99.57 25	99.67 18	99.60 50	96.75 115	98.28 153	99.48 54	99.52 50	98.10 131	99.47 27	99.37 28	99.76 22	99.21 36

NR-MVSNet		99.10 35	98.68 60	99.58 20	99.89 12	99.23 62	99.35 63	99.63 43	96.58 123	99.36 37	99.05 93	98.67 139	99.46 20	99.63 16	98.73 81	99.80 15	98.88 75

DVP-MVS++		99.09 36	99.25 18	98.90 106	99.53 117	99.37 44	99.17 88	99.48 76	98.28 31	97.95 177	99.54 50	99.88 4	98.13 130	99.08 51	98.94 56	99.15 101	99.65 2

DVP-MVS		99.09 36	99.07 27	99.12 75	99.55 108	99.40 39	99.36 59	99.44 88	97.75 58	98.23 156	99.23 80	99.80 9	98.97 72	99.08 51	98.96 53	99.19 95	99.25 28
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
UniMVSNet (Re)		99.08 38	98.69 58	99.54 26	99.75 55	99.33 49	99.29 71	99.64 42	96.75 115	99.48 30	99.30 73	98.69 134	99.26 44	98.94 68	98.76 77	99.78 19	99.02 57

ACMMPR		99.05 39	98.72 54	99.44 32	99.79 39	99.12 82	99.35 63	99.56 54	97.74 61	99.21 54	97.72 147	99.55 46	99.29 40	98.90 75	98.81 71	99.41 67	99.19 37

DU-MVS		99.04 40	98.59 65	99.56 22	99.74 61	99.23 62	99.29 71	99.63 43	96.58 123	99.55 21	99.05 93	98.68 136	99.36 35	99.03 61	98.60 88	99.77 20	98.97 62

TSAR-MVS + MP.		99.02 41	98.95 31	99.11 79	99.23 169	98.79 128	99.51 38	98.73 177	97.50 75	98.56 126	99.03 96	99.59 43	99.16 57	99.29 37	99.17 40	99.50 54	99.24 32
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
v10		99.01 42	98.66 61	99.41 38	99.52 122	99.39 40	99.57 32	99.66 37	97.59 72	99.32 41	99.88 9	99.23 81	99.50 18	97.77 148	97.98 122	98.92 136	98.78 86

EG-PatchMatch MVS		99.01 42	98.77 49	99.28 61	99.64 89	98.90 120	98.81 132	99.27 118	96.55 127	99.71 6	99.31 71	99.66 29	99.17 55	99.28 39	99.11 44	99.10 103	98.57 102

viewmacassd2359aftdt		98.99 44	98.89 40	99.12 75	99.78 42	99.27 56	99.21 83	99.26 119	98.73 17	98.30 150	99.61 37	99.82 8	98.94 75	98.26 123	98.29 105	99.20 94	98.24 134

PVSNet_Blended_VisFu		98.98 45	98.79 46	99.21 63	99.76 50	99.34 47	99.35 63	99.35 103	97.12 97	99.46 32	99.56 45	98.89 121	98.08 135	99.05 55	98.58 90	99.27 86	98.98 61

HFP-MVS		98.97 46	98.70 56	99.29 59	99.67 79	98.98 104	99.13 96	99.53 63	97.76 55	98.90 97	98.07 135	99.50 57	99.14 60	98.64 93	98.78 75	99.37 70	99.18 38

UniMVSNet_NR-MVSNet		98.97 46	98.46 77	99.56 22	99.76 50	99.34 47	99.29 71	99.61 49	96.55 127	99.55 21	99.05 93	97.96 160	99.36 35	98.84 78	98.50 96	99.81 14	98.97 62

casdiffmvs_mvg		98.96 48	98.87 41	99.07 82	99.82 28	99.36 45	99.36 59	99.22 127	98.13 36	97.74 184	99.42 61	99.46 60	98.59 98	98.39 105	98.95 55	99.71 29	98.39 120
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EC-MVSNet		98.96 48	98.45 80	99.56 22	99.88 14	99.70 11	99.68 17	99.78 16	94.15 193	98.97 86	98.26 127	99.21 85	99.35 37	99.30 36	99.14 42	99.73 25	99.40 20

SED-MVS		98.94 50	98.95 31	98.91 105	99.43 140	99.38 42	99.12 98	99.46 81	97.05 102	98.43 142	99.23 80	99.79 10	97.99 139	99.05 55	98.94 56	99.05 118	99.23 33

ACMMP_NAP		98.94 50	98.72 54	99.21 63	99.67 79	99.08 86	99.26 76	99.39 91	96.84 107	98.88 101	98.22 128	99.68 24	98.82 82	99.06 54	98.90 59	99.25 89	99.25 28

v1144		98.94 50	98.53 71	99.42 36	99.62 93	99.03 98	99.58 31	99.36 100	97.99 42	99.49 29	99.91 8	99.20 88	99.51 17	97.61 154	97.85 130	98.95 131	98.10 147

v8		98.94 50	98.60 63	99.35 53	99.54 114	99.39 40	99.55 34	99.67 34	97.48 76	99.13 68	99.81 19	99.10 106	99.39 33	97.86 143	97.89 128	98.81 146	98.66 95

SteuartSystems-ACMMP		98.94 50	98.52 73	99.43 35	99.79 39	99.13 81	99.33 67	99.55 56	96.17 145	99.04 82	97.53 153	99.65 33	99.46 20	99.04 60	98.76 77	99.44 62	99.35 22
Skip Steuart: Steuart Systems R&D Blog.
viewdifsd2359ckpt11		98.92 55	98.94 34	98.90 106	99.71 69	99.16 76	99.16 91	98.82 169	98.78 15	98.12 166	99.68 26	99.78 11	98.52 107	98.80 83	98.11 113	99.05 118	98.25 132

viewmsd2359difaftdt		98.92 55	98.94 34	98.90 106	99.71 69	99.16 76	99.16 91	98.82 169	98.78 15	98.12 166	99.68 26	99.78 11	98.52 107	98.80 83	98.11 113	99.05 118	98.25 132

v1192		98.91 57	98.48 76	99.41 38	99.61 97	99.03 98	99.64 20	99.25 123	97.91 48	99.58 17	99.92 4	99.07 112	99.45 22	97.55 159	97.68 144	98.93 133	98.23 136

FMVSNet1		98.90 58	99.10 26	98.67 135	99.54 114	99.48 31	99.22 81	99.66 37	98.39 26	97.50 192	99.66 29	99.04 113	96.58 176	99.05 55	99.03 49	99.52 47	99.08 49

ACMM	96.66 11	98.90 58	98.44 82	99.44 32	99.74 61	98.95 110	99.47 43	99.55 56	97.66 69	99.09 73	96.43 189	99.41 62	99.35 37	98.95 66	98.67 84	99.45 59	99.03 55
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20231211		98.89 60	98.79 46	98.99 95	99.82 28	99.41 38	99.18 87	99.31 113	96.92 104	98.54 128	98.58 115	98.84 126	97.46 158	99.45 28	99.29 33	99.65 36	99.08 49

v1921920		98.89 60	98.46 77	99.39 44	99.58 101	99.04 96	99.64 20	99.17 136	97.91 48	99.64 15	99.92 4	98.99 118	99.44 25	97.44 167	97.57 153	98.84 144	98.35 123

GeoE		98.88 62	98.43 86	99.41 38	99.83 23	99.24 59	99.51 38	99.82 13	96.55 127	99.22 53	98.76 107	99.22 84	98.96 73	98.55 96	98.15 111	99.10 103	98.56 105

v144192		98.88 62	98.46 77	99.37 51	99.56 107	99.03 98	99.61 26	99.26 119	97.79 53	99.58 17	99.88 9	99.11 104	99.43 27	97.38 172	97.61 149	98.80 147	98.43 117

SMA-MVS		98.87 64	98.73 53	99.04 88	99.72 67	99.05 91	98.64 144	99.17 136	96.31 140	98.80 108	99.07 91	99.70 20	98.67 91	98.93 71	98.82 68	99.23 92	99.23 33
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
ACMP	96.54 13	98.87 64	98.40 90	99.41 38	99.74 61	98.88 122	99.29 71	99.50 71	96.85 106	98.96 89	97.05 169	99.66 29	99.43 27	98.98 65	98.60 88	99.52 47	98.81 81
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DCV-MVSNet		98.86 66	98.57 69	99.19 66	99.86 20	99.67 15	99.39 53	99.71 27	97.53 74	98.69 118	95.85 200	98.48 144	97.75 150	99.57 21	99.41 25	99.72 26	99.48 16

v1240		98.86 66	98.41 88	99.38 49	99.59 99	99.05 91	99.65 19	99.14 141	97.68 67	99.66 13	99.93 3	98.72 133	99.45 22	97.38 172	97.72 142	98.79 148	98.35 123

CP-MVS		98.86 66	98.43 86	99.36 52	99.68 77	98.97 108	99.19 85	99.46 81	96.60 121	99.20 55	97.11 168	99.51 55	99.15 59	98.92 72	98.82 68	99.45 59	99.08 49

v2v482		98.85 69	98.40 90	99.38 49	99.65 86	98.98 104	99.55 34	99.39 91	97.92 47	99.35 38	99.85 14	99.14 99	99.39 33	97.50 162	97.78 132	98.98 128	97.60 168

DPE-MVS		98.84 70	98.69 58	99.00 92	99.05 188	99.26 57	99.19 85	99.35 103	95.85 154	98.74 114	99.27 75	99.66 29	98.30 123	98.90 75	98.93 58	99.37 70	99.00 59
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
OPM-MVS		98.84 70	98.59 65	99.12 75	99.52 122	98.50 154	99.13 96	99.22 127	97.76 55	98.76 110	98.70 109	99.61 39	98.90 77	98.67 91	98.37 102	99.19 95	98.57 102
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test20.03		98.84 70	98.74 52	98.95 98	99.77 45	99.33 49	99.21 83	99.46 81	97.29 83	98.88 101	99.65 33	99.10 106	97.07 168	99.11 47	98.76 77	99.32 79	97.98 154

casdiffmvs		98.84 70	98.75 50	98.94 102	99.75 55	99.21 66	99.33 67	99.04 153	98.04 38	97.46 195	99.72 23	99.72 17	98.60 96	98.30 117	98.37 102	99.48 56	97.92 157
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LGP-MVS_train		98.84 70	98.33 96	99.44 32	99.78 42	98.98 104	99.39 53	99.55 56	95.41 164	98.90 97	97.51 154	99.68 24	99.44 25	99.03 61	98.81 71	99.57 42	98.91 71

RPSCF		98.84 70	98.81 45	98.89 110	99.37 148	98.95 110	98.51 156	98.85 167	97.73 63	98.33 148	98.97 101	99.14 99	98.95 74	99.18 43	98.68 83	99.31 80	98.99 60

ACMMP		98.82 76	98.33 96	99.39 44	99.77 45	99.14 80	99.37 56	99.54 59	96.47 134	99.03 84	96.26 193	99.52 50	99.28 42	98.92 72	98.80 74	99.37 70	99.16 40
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
FE-MVSNET		98.81 77	98.41 88	99.27 62	99.55 108	99.09 84	99.61 26	99.46 81	97.15 94	98.70 117	99.18 86	99.17 92	99.23 46	97.94 137	98.48 97	99.10 103	97.88 159

V42		98.81 77	98.49 75	99.18 67	99.52 122	98.92 115	99.50 40	99.29 115	97.43 79	98.97 86	99.81 19	99.00 117	99.30 39	97.93 138	98.01 120	98.51 173	98.34 127

LS3D		98.79 79	98.52 73	99.12 75	99.64 89	99.09 84	99.24 79	99.46 81	97.75 58	98.93 95	97.47 156	98.23 152	97.98 141	99.36 33	99.30 32	99.46 57	98.42 118

MP-MVS		98.78 80	98.30 98	99.34 55	99.75 55	98.95 110	99.26 76	99.46 81	95.78 158	99.17 60	96.98 173	99.72 17	99.06 67	98.84 78	98.74 80	99.33 76	99.11 44
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
viewmanbaseed2359cas		98.77 81	98.64 62	98.93 103	99.70 71	99.16 76	98.95 114	99.09 149	98.35 29	98.14 163	99.33 68	99.69 21	98.63 94	97.91 140	97.90 125	99.08 110	98.15 145

v148		98.77 81	98.45 80	99.15 71	99.68 77	98.94 114	99.49 41	99.31 113	97.95 44	98.91 96	99.65 33	99.62 38	99.18 52	97.99 135	97.64 148	98.33 178	97.38 173

test1111		98.75 83	98.14 111	99.46 31	99.86 20	99.63 19	99.47 43	99.68 30	98.34 30	98.76 110	99.66 29	90.92 207	99.23 46	99.77 5	99.71 5	99.75 23	98.95 67

viewcassd2359sk11		98.74 84	98.58 67	98.93 103	99.69 74	99.16 76	98.98 109	99.10 147	98.36 27	98.45 140	99.39 65	99.61 39	98.38 115	97.68 152	97.77 137	98.99 127	98.08 149

ECVR-MVS		98.74 84	98.15 109	99.42 36	99.83 23	99.58 23	99.37 56	99.67 34	98.02 40	98.85 105	99.59 40	91.66 205	99.10 62	99.77 5	99.70 6	99.72 26	98.73 88

SD-MVS		98.73 86	98.54 70	98.95 98	99.14 178	98.76 131	98.46 160	99.14 141	97.71 65	98.56 126	98.06 137	99.61 39	98.85 81	98.56 95	97.74 139	99.54 44	99.32 24
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
MSP-MVS		98.72 87	98.60 63	98.87 112	99.67 79	99.33 49	99.15 93	99.26 119	96.99 103	97.90 180	98.19 130	99.74 15	98.29 124	97.69 151	98.96 53	98.96 129	99.27 27
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		98.69 88	98.09 116	99.39 44	99.76 50	99.07 87	99.30 70	99.51 68	94.76 175	99.18 59	96.70 182	99.51 55	99.20 50	98.79 85	98.71 82	99.39 68	99.11 44

pmmvs-eth3d		98.68 89	98.14 111	99.29 59	99.49 127	98.45 157	99.45 48	99.38 96	97.21 90	99.50 27	99.65 33	99.21 85	99.16 57	97.11 180	97.56 154	98.79 148	97.82 162

EU-MVSNet		98.68 89	98.94 34	98.37 158	99.14 178	98.74 133	99.64 20	98.20 202	98.21 32	99.17 60	99.66 29	99.18 91	99.08 65	99.11 47	98.86 62	95.00 215	98.83 78

PMVS	92.51 17	98.66 91	98.86 43	98.43 154	99.26 164	98.98 104	98.60 150	98.59 186	97.73 63	99.45 33	99.38 66	98.54 143	95.24 195	99.62 17	99.61 14	99.42 64	98.17 143
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DeepC-MVS_fast	97.38 8	98.65 92	98.34 95	99.02 91	99.33 152	98.29 164	98.99 107	98.71 179	97.40 80	99.31 42	98.20 129	99.40 65	98.54 105	98.33 114	98.18 110	99.23 92	98.58 100
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator	98.16 3	98.65 92	98.35 94	99.00 92	99.59 99	98.70 136	98.90 123	99.36 100	97.97 43	99.09 73	96.55 186	99.09 108	97.97 142	98.70 90	98.65 86	99.12 102	98.81 81

TSAR-MVS + ACMM		98.64 94	98.58 67	98.72 128	99.17 176	98.63 143	98.69 139	99.10 147	97.69 66	98.30 150	99.12 89	99.38 68	98.70 89	98.45 100	97.51 156	98.35 177	99.25 28

DELS-MVS		98.63 95	98.70 56	98.55 150	99.24 168	99.04 96	98.96 112	98.52 189	96.83 109	98.38 144	99.58 43	99.68 24	97.06 169	98.74 89	98.44 99	99.10 103	98.59 99
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
QAPM		98.62 96	98.40 90	98.89 110	99.57 106	98.80 127	98.63 145	99.35 103	96.82 110	98.60 122	98.85 106	99.08 110	98.09 133	98.31 115	98.21 107	99.08 110	98.72 89

EPP-MVSNet		98.61 97	98.19 106	99.11 79	99.86 20	99.60 21	99.44 49	99.53 63	97.37 81	96.85 212	98.69 110	93.75 198	99.18 52	99.22 41	99.35 30	99.82 13	99.32 24

3Dnovator+	97.85 5	98.61 97	98.14 111	99.15 71	99.62 93	98.37 161	99.10 99	99.51 68	98.04 38	98.98 85	96.07 197	98.75 132	98.55 103	98.51 98	98.40 100	99.17 98	98.82 79

viewdifsd2359ckpt13		98.60 99	98.39 93	98.85 117	99.67 79	99.05 91	98.77 136	99.05 152	97.89 51	98.19 158	99.25 77	99.54 47	98.37 116	97.55 159	97.45 159	99.04 122	97.99 151

X-MVS		98.59 100	97.99 123	99.30 58	99.75 55	99.07 87	99.17 88	99.50 71	96.62 119	98.95 91	93.95 216	99.37 69	99.11 61	98.94 68	98.86 62	99.35 74	99.09 48

MVS_111021_HR		98.58 101	98.26 101	98.96 97	99.32 155	98.81 125	98.48 158	98.99 158	96.81 112	99.16 63	98.07 135	99.23 81	98.89 79	98.43 102	98.27 106	98.90 138	98.24 134

MVS_0304		98.57 102	98.44 82	98.71 130	99.76 50	99.31 53	99.43 50	99.24 125	97.79 53	98.35 146	98.48 119	96.64 180	96.30 184	98.91 74	98.82 68	99.18 97	99.16 40

PM-MVS		98.57 102	98.24 103	98.95 98	99.26 164	98.59 146	99.03 103	98.74 176	96.84 107	99.44 34	99.13 88	98.31 151	98.75 87	98.03 133	98.21 107	98.48 174	98.58 100

PHI-MVS		98.57 102	98.20 105	99.00 92	99.48 129	98.91 117	98.68 140	99.17 136	94.97 171	99.27 50	98.33 123	99.33 73	98.05 137	98.82 81	98.62 87	99.34 75	98.38 121

diffmvs_AUTHOR		98.56 105	98.53 71	98.60 142	99.69 74	98.90 120	99.01 106	98.86 166	98.36 27	97.21 208	99.70 25	99.67 28	98.08 135	97.61 154	97.45 159	98.77 150	98.00 150

HPM-MVS++		98.56 105	98.08 117	99.11 79	99.53 117	98.61 145	99.02 105	99.32 111	96.29 142	99.06 76	97.23 163	99.50 57	98.77 85	98.15 129	97.90 125	98.96 129	98.90 72

TSAR-MVS + GP.		98.54 107	98.29 100	98.82 121	99.28 162	98.59 146	97.73 201	99.24 125	95.93 151	98.59 123	99.07 91	99.17 92	98.86 80	98.44 101	98.10 115	99.26 88	98.72 89

UGNet		98.52 108	99.00 30	97.96 179	99.58 101	99.26 57	99.27 75	99.40 89	98.07 37	98.28 153	98.76 107	99.71 19	92.24 223	98.94 68	98.85 64	99.00 126	99.43 19
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
Anonymous20231206		98.50 109	98.03 120	99.05 86	99.50 125	99.01 101	99.15 93	99.26 119	96.38 138	99.12 70	99.50 53	99.12 102	98.60 96	97.68 152	97.24 169	98.66 157	97.30 177

CLD-MVS		98.48 110	98.15 109	98.86 115	99.53 117	98.35 162	98.55 153	97.83 211	96.02 150	98.97 86	99.08 90	99.75 14	99.03 69	98.10 132	97.33 165	99.28 84	98.44 116
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CANet		98.47 111	98.30 98	98.67 135	99.65 86	98.87 123	98.82 131	99.01 156	96.14 146	99.29 45	98.86 104	99.01 115	96.54 177	98.36 109	98.08 117	98.72 153	98.80 85

APD-MVS		98.47 111	97.97 124	99.05 86	99.64 89	98.91 117	98.94 115	99.45 87	94.40 186	98.77 109	97.26 162	99.41 62	98.21 127	98.67 91	98.57 93	99.31 80	98.57 102
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Vis-MVSNet (Re-imp)		98.46 113	98.23 104	98.73 127	99.81 32	99.29 54	98.79 133	99.50 71	96.20 144	96.03 219	98.29 125	96.98 175	98.54 105	99.11 47	99.08 45	99.70 30	98.62 97

Fast-Effi-MVS+		98.42 114	97.79 132	99.15 71	99.69 74	98.66 141	98.94 115	99.68 30	94.49 180	99.05 78	98.06 137	98.86 123	98.48 110	98.18 126	97.78 132	99.05 118	98.54 108

ETV-MVS		98.41 115	97.76 133	99.17 68	99.58 101	99.01 101	98.91 119	99.50 71	93.33 206	99.31 42	96.82 179	98.42 147	98.17 129	99.13 46	99.08 45	99.54 44	98.56 105

MVS_111021_LR		98.39 116	98.11 114	98.71 130	99.08 185	98.54 152	98.23 183	98.56 188	96.57 125	99.13 68	98.41 120	98.86 123	98.65 93	98.23 124	97.87 129	98.65 159	98.28 129

pmmvs5		98.37 117	97.81 131	99.03 89	99.46 131	98.97 108	99.03 103	98.96 160	95.85 154	99.05 78	99.45 57	98.66 140	98.79 84	96.02 197	97.52 155	98.87 140	98.21 139

OMC-MVS		98.35 118	98.10 115	98.64 141	98.85 195	97.99 183	98.56 152	98.21 200	97.26 87	98.87 103	98.54 116	99.27 79	98.43 112	98.34 112	97.66 145	98.92 136	97.65 167

sasdasda		98.34 119	97.92 127	98.83 118	99.45 133	99.21 66	98.37 168	99.53 63	97.06 99	97.74 184	96.95 176	95.05 193	98.36 117	98.77 86	98.85 64	99.51 52	99.53 10

canonicalmvs		98.34 119	97.92 127	98.83 118	99.45 133	99.21 66	98.37 168	99.53 63	97.06 99	97.74 184	96.95 176	95.05 193	98.36 117	98.77 86	98.85 64	99.51 52	99.53 10

CHOSEN 1792x2688		98.31 121	98.02 121	98.66 137	99.55 108	98.57 149	99.38 55	99.25 123	98.42 23	98.48 136	99.58 43	99.85 6	98.31 122	95.75 200	95.71 195	96.96 202	98.27 131

viewmambaseed2359dif		98.30 122	98.05 119	98.58 144	99.55 108	98.69 137	98.99 107	98.76 175	97.06 99	97.32 203	99.40 64	99.52 50	97.99 139	97.22 178	96.54 183	98.85 143	97.95 155

CPTT-MVS		98.28 123	97.51 146	99.16 70	99.54 114	98.78 129	98.96 112	99.36 100	96.30 141	98.89 100	93.10 220	99.30 76	99.20 50	98.35 111	97.96 123	99.03 124	98.82 79

TinyColmap		98.27 124	97.62 143	99.03 89	99.29 160	97.79 192	98.92 118	98.95 161	97.48 76	99.52 24	98.65 112	97.86 162	98.90 77	98.34 112	97.27 167	98.64 160	95.97 197

diffmvs		98.26 125	98.16 107	98.39 156	99.61 97	98.78 129	98.79 133	98.61 184	97.94 45	97.11 211	99.51 52	99.52 50	97.61 154	96.55 189	96.93 175	98.61 162	97.87 160
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
USDC		98.26 125	97.57 144	99.06 83	99.42 143	97.98 185	98.83 128	98.85 167	97.57 73	99.59 16	99.15 87	98.59 142	98.99 71	97.42 168	96.08 194	98.69 156	96.23 195

SF-MVS		98.25 127	98.16 107	98.35 159	99.43 140	98.42 160	97.05 223	99.09 149	96.42 136	98.13 164	97.73 146	99.20 88	97.22 164	98.36 109	98.38 101	99.16 100	98.62 97

MCST-MVS		98.25 127	97.57 144	99.06 83	99.53 117	98.24 170	98.63 145	99.17 136	95.88 152	98.58 124	96.11 195	99.09 108	99.18 52	97.58 158	97.31 166	99.25 89	98.75 87

MGCFI-Net		98.23 129	97.93 126	98.58 144	99.44 137	99.20 72	98.37 168	99.54 59	97.14 95	96.70 216	96.98 173	95.04 195	97.92 146	98.75 88	98.89 60	99.52 47	99.55 9

IterMVS-LS		98.23 129	97.66 139	98.90 106	99.63 92	99.38 42	99.07 100	99.48 76	97.75 58	98.81 107	99.37 67	94.57 197	97.88 147	96.54 190	97.04 172	98.53 170	98.97 62
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TAPA-MVS	96.65 12	98.23 129	97.96 125	98.55 150	98.81 197	98.16 174	98.40 165	97.94 209	96.68 117	98.49 134	98.61 113	98.89 121	98.57 101	97.45 165	97.59 151	99.09 109	98.35 123
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CNVR-MVS		98.22 132	97.76 133	98.76 125	99.33 152	98.26 168	98.48 158	98.88 164	96.22 143	98.47 138	95.79 201	99.33 73	98.35 119	98.37 108	97.99 121	99.03 124	98.38 121

IS_MVSNet		98.20 133	98.00 122	98.44 153	99.82 28	99.48 31	99.25 78	99.56 54	95.58 161	93.93 231	97.56 152	96.52 181	98.27 125	99.08 51	99.20 38	99.80 15	98.56 105

DeepPCF-MVS	96.68 10	98.20 133	98.26 101	98.12 172	97.03 234	98.11 177	98.44 162	97.70 213	96.77 114	98.52 130	98.91 102	99.17 92	98.58 100	98.41 104	98.02 119	98.46 175	98.46 113

MSDG		98.20 133	97.88 130	98.56 148	99.33 152	97.74 193	98.27 180	98.10 203	97.20 92	98.06 170	98.59 114	99.16 95	98.76 86	98.39 105	97.71 143	98.86 142	96.38 192

testgi		98.18 136	98.44 82	97.89 181	99.78 42	99.23 62	98.78 135	99.21 130	97.26 87	97.41 197	97.39 159	99.36 72	92.85 219	98.82 81	98.66 85	99.31 80	98.35 123

Effi-MVS+		98.11 137	97.29 152	99.06 83	99.62 93	98.55 150	98.16 186	99.80 15	94.64 176	99.15 66	96.59 184	97.43 168	98.44 111	97.46 164	97.90 125	99.17 98	98.45 115

FA-MVS(training)		98.08 138	97.68 137	98.56 148	99.14 178	98.69 137	98.41 163	99.83 12	95.85 154	98.57 125	97.95 142	96.92 177	96.85 171	98.51 98	98.09 116	98.54 168	97.74 163

HyFIR lowres test		98.08 138	97.16 161	99.14 74	99.72 67	98.91 117	99.41 51	99.58 51	97.93 46	98.82 106	99.24 78	95.81 187	98.73 88	95.16 211	95.13 204	98.60 164	97.94 156

EIA-MVS		98.03 140	97.20 158	98.99 95	99.66 83	99.24 59	98.53 155	99.52 67	91.56 222	99.25 51	95.34 205	98.78 129	97.72 151	98.38 107	98.58 90	99.28 84	98.54 108

train_agg		97.99 141	97.26 153	98.83 118	99.43 140	98.22 172	98.91 119	99.07 151	94.43 184	97.96 176	96.42 190	99.30 76	98.81 83	97.39 170	96.62 181	98.82 145	98.47 111

MSLP-MVS++		97.99 141	97.64 142	98.40 155	98.91 193	98.47 156	97.12 221	98.78 173	96.49 132	98.48 136	93.57 218	99.12 102	98.51 109	98.31 115	98.58 90	98.58 166	98.95 67

CDPH-MVS		97.99 141	97.23 156	98.87 112	99.58 101	98.29 164	98.83 128	99.20 132	93.76 200	98.11 168	96.11 195	99.16 95	98.23 126	97.80 146	97.22 170	99.29 83	98.28 129

FMVSNet2		97.94 144	98.08 117	97.77 187	98.71 201	99.21 66	98.62 147	99.47 78	96.62 119	96.37 218	99.20 84	97.70 164	94.39 206	97.39 170	97.75 138	99.08 110	98.70 92

PVSNet_BlendedMVS		97.93 145	97.66 139	98.25 165	99.30 157	98.67 139	98.31 175	97.95 207	94.30 190	98.75 112	97.63 149	98.76 130	96.30 184	98.29 118	97.78 132	98.93 133	98.18 141

PVSNet_Blended		97.93 145	97.66 139	98.25 165	99.30 157	98.67 139	98.31 175	97.95 207	94.30 190	98.75 112	97.63 149	98.76 130	96.30 184	98.29 118	97.78 132	98.93 133	98.18 141

OpenMVS	97.26 9	97.88 147	97.17 160	98.70 132	99.50 125	98.55 150	98.34 173	99.11 145	93.92 198	98.90 97	95.04 210	98.23 152	97.38 161	98.11 131	98.12 112	98.95 131	98.23 136

pmmvs4		97.87 148	97.02 165	98.86 115	99.20 170	97.68 196	98.89 124	99.03 154	96.57 125	99.12 70	99.03 96	97.26 172	98.42 113	95.16 211	96.34 186	98.53 170	97.10 184

NCCC		97.84 149	96.96 167	98.87 112	99.39 146	98.27 167	98.46 160	99.02 155	96.78 113	98.73 116	91.12 224	98.91 119	98.57 101	97.83 145	97.49 157	99.04 122	98.33 128

Effi-MVS+-dtu		97.78 150	97.37 150	98.26 163	99.25 166	98.50 154	97.89 195	99.19 135	94.51 178	98.16 161	95.93 198	98.80 128	95.97 188	98.27 122	97.38 162	99.10 103	98.23 136

MDA-MVSNet-bldmvs		97.75 151	97.26 153	98.33 160	99.35 151	98.45 157	99.32 69	97.21 218	97.90 50	99.05 78	99.01 98	96.86 178	99.08 65	99.36 33	92.97 214	95.97 211	96.25 194

CDS-MVSNet		97.75 151	97.68 137	97.83 185	99.08 185	98.20 173	98.68 140	98.61 184	95.63 160	97.80 182	99.24 78	96.93 176	94.09 211	97.96 136	97.82 131	98.71 154	97.99 151
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CNLPA		97.75 151	97.26 153	98.32 162	98.58 209	97.86 188	97.80 197	98.09 204	96.49 132	98.49 134	96.15 194	98.08 155	98.35 119	98.00 134	97.03 173	98.61 162	97.21 181

PLC	95.63 15	97.73 154	97.01 166	98.57 147	99.10 182	97.80 191	97.72 202	98.77 174	96.34 139	98.38 144	93.46 219	98.06 156	98.66 92	97.90 141	97.65 147	98.77 150	97.90 158
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVS_Test		97.69 155	97.15 162	98.33 160	99.27 163	98.43 159	98.25 181	99.29 115	95.00 170	97.39 199	98.86 104	98.00 159	97.14 166	95.38 206	96.22 188	98.62 161	98.15 145

GBi-Net		97.69 155	97.75 135	97.62 188	98.71 201	99.21 66	98.62 147	99.33 107	94.09 194	95.60 221	98.17 132	95.97 184	94.39 206	99.05 55	99.03 49	99.08 110	98.70 92

test1		97.69 155	97.75 135	97.62 188	98.71 201	99.21 66	98.62 147	99.33 107	94.09 194	95.60 221	98.17 132	95.97 184	94.39 206	99.05 55	99.03 49	99.08 110	98.70 92

CANet_DTU		97.65 158	97.50 148	97.82 186	99.19 173	98.08 179	98.41 163	98.67 181	94.40 186	99.16 63	98.32 124	98.69 134	93.96 213	97.87 142	97.61 149	97.51 198	97.56 170

IterMVS-SCA-FT		97.63 159	96.86 169	98.52 152	99.48 129	98.71 135	98.84 127	98.91 162	96.44 135	99.16 63	99.56 45	95.54 189	97.95 143	95.68 203	95.07 207	96.76 203	97.03 187

TSAR-MVS + COLMAP		97.62 160	97.31 151	97.98 177	98.47 215	97.39 200	98.29 177	98.25 199	96.68 117	97.54 191	98.87 103	98.04 158	97.08 167	96.78 184	96.26 187	98.26 181	97.12 183

MS-PatchMatch		97.60 161	97.22 157	98.04 176	98.67 205	97.18 205	97.91 193	98.28 198	95.82 157	98.34 147	97.66 148	98.38 148	97.77 149	97.10 181	97.25 168	97.27 200	97.18 182

PCF-MVS	95.58 16	97.60 161	96.67 170	98.69 133	99.44 137	98.23 171	98.37 168	98.81 171	93.01 210	98.22 157	97.97 141	99.59 43	98.20 128	95.72 202	95.08 205	99.08 110	97.09 186
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HQP-MVS		97.58 163	96.65 173	98.66 137	99.30 157	97.99 183	97.88 196	98.65 182	94.58 177	98.66 119	94.65 214	99.15 98	98.59 98	96.10 195	95.59 196	98.90 138	98.50 110

DI_MVS_pp		97.57 164	96.55 175	98.77 124	99.55 108	98.76 131	99.22 81	99.00 157	97.08 98	97.95 177	97.78 145	91.35 206	98.02 138	96.20 193	96.81 177	98.87 140	97.87 160

AdaColmap		97.57 164	96.57 174	98.74 126	99.25 166	98.01 181	98.36 172	98.98 159	94.44 183	98.47 138	92.44 221	97.91 161	98.62 95	98.19 125	97.74 139	98.73 152	97.28 178

baseline		97.50 166	97.51 146	97.50 192	99.18 174	97.38 201	98.00 189	98.00 206	96.52 131	97.49 193	99.28 74	99.43 61	95.31 194	95.27 208	96.22 188	96.99 201	98.47 111

IterMVS		97.40 167	96.67 170	98.25 165	99.45 133	98.66 141	98.87 125	98.73 177	96.40 137	98.94 94	99.56 45	95.26 191	97.58 155	95.38 206	94.70 209	95.90 212	96.72 190
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		97.38 168	96.15 183	98.82 121	99.39 146	98.34 163	98.65 143	98.88 164	90.80 229	98.86 104	92.35 222	95.13 192	98.09 133	98.84 78	98.88 61	99.06 117	98.71 91

CVMVSNet		97.38 168	97.39 149	97.37 195	98.58 209	97.72 194	98.70 138	97.42 216	97.21 90	95.95 220	99.46 56	93.31 201	97.38 161	97.60 156	97.78 132	96.18 208	98.66 95

new-patchmatchnet		97.26 170	96.12 184	98.58 144	99.55 108	98.63 143	99.14 95	97.04 220	98.80 14	99.19 57	99.92 4	99.19 90	98.92 76	95.51 205	87.04 223	97.66 195	93.73 213

MIMVSNet		97.24 171	97.15 162	97.36 196	99.03 189	98.52 153	98.55 153	99.73 23	94.94 174	94.94 228	97.98 140	97.37 170	93.66 214	97.60 156	97.34 164	98.23 184	96.29 193

PatchMatch-RL		97.24 171	96.45 178	98.17 169	98.70 204	97.57 199	97.31 216	98.48 192	94.42 185	98.39 143	95.74 202	96.35 183	97.88 147	97.75 149	97.48 158	98.24 183	95.87 198

thisisatest0530		97.20 173	95.95 188	98.66 137	99.46 131	98.84 124	98.29 177	99.20 132	94.51 178	98.25 155	97.42 157	85.03 222	97.68 152	98.43 102	98.56 94	99.08 110	98.89 74

tttt0517		97.18 174	95.92 189	98.65 140	99.49 127	98.92 115	98.29 177	99.20 132	94.37 188	98.17 159	97.37 160	84.72 225	97.68 152	98.55 96	98.56 94	99.10 103	98.95 67

MDTV_nov1_ep13_2view		97.12 175	96.19 182	98.22 168	99.13 181	98.05 180	99.24 79	99.47 78	97.61 70	99.15 66	99.59 40	99.01 115	98.40 114	94.87 214	90.14 217	93.91 218	94.04 212

MAR-MVS		97.12 175	96.28 181	98.11 173	98.94 191	97.22 203	97.65 206	99.38 96	90.93 228	98.15 162	95.17 207	97.13 173	96.48 180	97.71 150	97.40 161	98.06 188	98.40 119
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
Fast-Effi-MVS+-dtu		96.99 177	96.46 177	97.61 190	98.98 190	97.89 186	97.54 210	99.76 19	93.43 204	96.55 217	94.93 211	98.06 156	94.32 209	96.93 182	96.50 184	98.53 170	97.47 171

FPMVS		96.97 178	97.20 158	96.70 212	97.75 226	96.11 217	97.72 202	95.47 224	97.13 96	98.02 172	97.57 151	96.67 179	92.97 218	99.00 64	98.34 104	98.28 180	95.58 200

TAMVS		96.95 179	96.94 168	96.97 207	99.07 187	97.67 198	97.98 191	97.12 219	95.04 169	95.41 224	99.27 75	95.57 188	94.09 211	97.32 174	97.11 171	98.16 186	96.59 191

FMVSNet3		96.85 180	96.67 170	97.06 201	97.56 229	99.01 101	97.99 190	99.33 107	94.09 194	95.60 221	98.17 132	95.97 184	93.26 217	94.76 216	96.22 188	98.59 165	98.46 113

GA-MVS		96.84 181	95.86 191	97.98 177	99.16 177	98.29 164	97.91 193	98.64 183	95.14 167	97.71 187	98.04 139	88.90 210	96.50 179	96.41 192	96.61 182	97.97 192	97.60 168

CHOSEN 280x420		96.80 182	96.30 180	97.39 193	99.09 183	96.52 209	98.76 137	99.29 115	93.88 199	97.65 188	98.34 122	93.66 199	96.29 187	98.28 120	97.73 141	93.27 221	95.70 199

gg-mvs-nofinetune		96.77 183	96.52 176	97.06 201	99.66 83	97.82 190	97.54 210	99.86 8	98.69 18	98.61 121	99.94 2	89.62 208	88.37 231	97.55 159	96.67 179	98.30 179	95.35 201

DPM-MVS		96.73 184	95.70 194	97.95 180	98.93 192	97.26 202	97.39 215	98.44 194	95.47 163	97.62 189	90.71 225	98.47 146	97.03 170	95.02 213	95.27 201	98.26 181	97.67 165

baseline1		96.72 185	95.40 196	98.26 163	99.53 117	98.81 125	98.32 174	98.80 172	94.96 172	96.78 215	96.50 188	84.87 224	96.68 175	97.42 168	97.91 124	99.46 57	97.33 176

N_pmnet		96.68 186	95.70 194	97.84 184	99.42 143	98.00 182	99.35 63	98.21 200	98.40 25	98.13 164	99.42 61	99.30 76	97.44 160	94.00 220	88.79 218	94.47 217	91.96 219

pmnet_mix02		96.61 187	95.32 197	98.11 173	99.41 145	97.68 196	99.05 101	97.59 214	98.16 34	99.05 78	99.48 54	99.11 104	98.32 121	92.36 224	87.67 220	95.26 214	92.80 217

new_pmnet		96.59 188	96.40 179	96.81 209	98.24 222	95.46 226	97.71 204	94.75 227	96.92 104	96.80 214	99.23 80	97.81 163	96.69 173	96.58 188	95.16 203	96.69 204	93.64 214

PMMVS		96.47 189	95.81 192	97.23 197	97.38 231	95.96 221	97.31 216	96.91 221	93.21 207	97.93 179	97.14 166	97.64 166	95.70 190	95.24 209	96.18 191	98.17 185	95.33 202

EPNet		96.44 190	96.08 185	96.86 208	99.32 155	97.15 206	97.69 205	99.32 111	93.67 201	98.11 168	95.64 203	93.44 200	89.07 229	96.86 183	96.83 176	97.67 194	98.97 62
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thres600view7		96.35 191	94.27 199	98.79 123	99.66 83	99.18 73	98.94 115	99.38 96	94.37 188	97.21 208	87.19 227	84.10 226	98.10 131	98.16 127	99.47 20	99.42 64	97.43 172

EPNet_dtu		96.31 192	95.96 187	96.72 211	99.18 174	95.39 227	97.03 224	99.13 144	93.02 209	99.35 38	97.23 163	97.07 174	90.70 228	95.74 201	95.08 205	94.94 216	98.16 144
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs3		96.30 193	95.87 190	96.80 210	97.66 228	96.48 210	97.93 192	93.80 228	93.40 205	98.54 128	98.27 126	97.50 167	97.37 163	97.49 163	93.11 213	95.52 213	94.85 206

PMMVS2		96.29 194	97.05 164	95.40 222	98.32 221	96.16 214	98.18 185	97.46 215	97.20 92	84.51 237	99.60 38	98.68 136	96.37 181	98.59 94	97.38 162	97.58 197	91.76 220

thres200		96.23 195	94.13 200	98.69 133	99.44 137	99.18 73	98.58 151	99.38 96	93.52 203	97.35 201	86.33 232	85.83 220	97.93 144	98.16 127	98.78 75	99.42 64	97.10 184

thres400		96.22 196	94.08 202	98.72 128	99.58 101	99.05 91	98.83 128	99.22 127	94.01 197	97.40 198	86.34 231	84.91 223	97.93 144	97.85 144	99.08 45	99.37 70	97.28 178

tfpn200view9		96.17 197	94.08 202	98.60 142	99.37 148	99.18 73	98.68 140	99.39 91	92.02 216	97.30 204	86.53 229	86.34 217	97.45 159	98.15 129	99.08 45	99.43 63	97.28 178

CMPMVS	74.71 19	96.17 197	96.06 186	96.30 216	97.41 230	94.52 230	94.83 232	95.46 225	91.57 221	97.26 207	94.45 215	98.33 150	94.98 197	98.28 120	97.59 151	97.86 193	97.68 164
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test2506		96.12 199	93.35 212	99.35 53	99.83 23	99.58 23	99.37 56	99.67 34	98.02 40	98.44 141	97.51 154	60.03 240	99.10 62	99.77 5	99.70 6	99.72 26	98.86 76

IB-MVS	95.85 14	95.87 200	94.88 198	97.02 204	99.09 183	98.25 169	97.16 218	97.38 217	91.97 219	97.77 183	83.61 234	97.29 171	92.03 226	97.16 179	97.66 145	98.66 157	98.20 140
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
test0.0.03 1		95.81 201	95.77 193	95.85 221	99.20 170	98.15 176	97.49 214	98.50 190	92.24 212	92.74 234	96.82 179	92.70 202	88.60 230	97.31 176	97.01 174	98.57 167	96.19 196

thres100view900		95.74 202	93.66 211	98.17 169	99.37 148	98.59 146	98.10 187	98.33 197	92.02 216	97.30 204	86.53 229	86.34 217	96.69 173	96.77 185	98.47 98	99.24 91	96.89 188

ET-MVSNet_ETH3D		95.72 203	93.85 207	97.89 181	97.30 232	98.09 178	98.19 184	98.40 195	94.46 182	98.01 175	96.71 181	77.85 236	96.76 172	96.08 196	96.39 185	98.70 155	97.36 174

baseline2		95.58 204	94.04 204	97.38 194	98.80 198	98.16 174	97.14 219	97.80 212	91.45 223	97.49 193	95.22 206	83.63 227	94.98 197	96.42 191	96.66 180	98.06 188	96.76 189

PatchT		95.49 205	93.29 213	98.06 175	98.65 206	96.20 213	98.91 119	99.73 23	92.00 218	98.50 131	96.67 183	83.25 228	96.34 182	94.40 217	95.50 197	96.21 207	95.04 204

CR-MVSNet		95.38 206	93.01 214	98.16 171	98.63 207	95.85 223	97.64 207	99.78 16	91.27 225	98.50 131	96.84 178	82.16 229	96.34 182	94.40 217	95.50 197	98.05 190	95.04 204

MVSTER		95.38 206	93.99 206	97.01 205	98.83 196	98.95 110	96.62 225	99.14 141	92.17 214	97.44 196	97.29 161	77.88 235	91.63 227	97.45 165	96.18 191	98.41 176	97.99 151

MVS-HIRNet		94.86 208	93.83 208	96.07 217	97.07 233	94.00 231	94.31 233	99.17 136	91.23 227	98.17 159	98.69 110	97.43 168	95.66 191	94.05 219	91.92 215	92.04 228	89.46 228

test-LLR		94.79 209	93.71 209	96.06 218	99.20 170	96.16 214	96.31 227	98.50 190	89.98 230	94.08 229	97.01 170	86.43 215	92.20 224	96.76 186	95.31 199	96.05 209	94.31 209

RPMNet		94.72 210	92.01 219	97.88 183	98.56 212	95.85 223	97.78 198	99.70 29	91.27 225	98.33 148	93.69 217	81.88 230	94.91 200	92.60 222	94.34 211	98.01 191	94.46 208

gm-plane-assit		94.62 211	91.39 221	98.39 156	99.90 11	99.47 33	99.40 52	99.65 39	97.44 78	99.56 20	99.68 26	59.40 241	94.23 210	96.17 194	94.77 208	97.61 196	92.79 218

test-mter		94.62 211	94.02 205	95.32 223	97.72 227	96.75 207	96.23 229	95.67 223	89.83 233	93.23 233	96.99 172	85.94 219	92.66 222	97.32 174	96.11 193	96.44 205	95.22 203

FMVSNet5		94.57 213	92.77 215	96.67 213	97.88 224	98.72 134	97.54 210	98.70 180	88.64 234	95.11 226	86.90 228	81.77 231	93.27 216	97.92 139	98.07 118	97.50 199	97.34 175

SCA		94.53 214	91.95 220	97.55 191	98.58 209	97.86 188	98.49 157	99.68 30	95.11 168	99.07 75	95.87 199	87.24 213	96.53 178	89.77 227	87.08 222	92.96 223	90.69 223

MDTV_nov1_ep13		94.47 215	92.15 217	97.17 198	98.54 214	96.42 211	98.10 187	98.89 163	94.49 180	98.02 172	97.41 158	86.49 214	95.56 192	90.85 225	87.95 219	93.91 218	91.45 222

TESTMET0.1,1		94.44 216	93.71 209	95.30 224	97.84 225	96.16 214	96.31 227	95.32 226	89.98 230	94.08 229	97.01 170	86.43 215	92.20 224	96.76 186	95.31 199	96.05 209	94.31 209

ADS-MVSNet		94.41 217	92.13 218	97.07 200	98.86 194	96.60 208	98.38 167	98.47 193	96.13 148	98.02 172	96.98 173	87.50 212	95.87 189	89.89 226	87.58 221	92.79 225	90.27 225

tpm		93.89 218	91.21 222	97.03 203	98.36 219	96.07 218	97.53 213	99.65 39	92.24 212	98.64 120	97.23 163	74.67 239	94.64 204	92.68 221	90.73 216	93.37 220	94.82 207

PatchmatchNet		93.88 219	91.08 223	97.14 199	98.75 200	96.01 220	98.25 181	99.39 91	94.95 173	98.96 89	96.32 191	85.35 221	95.50 193	88.89 228	85.89 226	91.99 229	90.15 226
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		93.67 220	90.82 224	96.99 206	98.62 208	96.39 212	98.40 165	99.11 145	95.54 162	97.87 181	97.14 166	81.27 233	94.97 199	88.54 230	86.80 224	92.95 224	90.06 227

MVE	82.47 18	93.12 221	94.09 201	91.99 227	90.79 235	82.50 236	93.93 234	96.30 222	96.06 149	88.81 235	98.19 130	96.38 182	97.56 156	97.24 177	95.18 202	84.58 235	93.07 215
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CostFormer		92.75 222	89.49 226	96.55 214	98.78 199	95.83 225	97.55 209	98.59 186	91.83 220	97.34 202	96.31 192	78.53 234	94.50 205	86.14 231	84.92 227	92.54 226	92.84 216

tpmrst		92.45 223	89.48 227	95.92 220	98.43 217	95.03 228	97.14 219	97.92 210	94.16 192	97.56 190	97.86 144	81.63 232	93.56 215	85.89 232	82.86 228	90.91 233	88.95 230

dps		92.35 224	88.78 229	96.52 215	98.21 223	95.94 222	97.78 198	98.38 196	89.88 232	96.81 213	95.07 209	75.31 238	94.70 203	88.62 229	86.21 225	93.21 222	90.41 224

E-PMN		92.28 225	90.12 225	94.79 225	98.56 212	90.90 233	95.16 231	93.68 229	95.36 165	95.10 227	96.56 185	89.05 209	95.24 195	95.21 210	81.84 230	90.98 231	81.94 232

EMVS		91.84 226	89.39 228	94.70 226	98.44 216	90.84 234	95.27 230	93.53 230	95.18 166	95.26 225	95.62 204	87.59 211	94.77 202	94.87 214	80.72 231	90.95 232	80.88 233

tpm cat1		91.52 227	87.70 230	95.97 219	98.33 220	94.98 229	97.06 222	98.03 205	92.11 215	98.03 171	94.77 213	77.19 237	92.71 220	83.56 233	82.24 229	91.67 230	89.04 229

test_method		77.69 228	85.40 231	68.69 228	42.66 237	55.39 238	82.17 237	52.05 232	92.83 211	84.52 236	94.88 212	95.41 190	65.37 232	92.49 223	79.32 232	85.36 234	87.50 231

GG-mvs-BLEND		65.66 229	92.62 216	34.20 230	1.45 240	93.75 232	85.40 236	1.64 236	91.37 224	17.21 239	87.25 226	94.78 196	3.25 236	95.64 204	93.80 212	96.27 206	91.74 221

testmvs		9.73 230	13.38 232	5.48 232	3.62 238	4.12 239	6.40 240	3.19 235	14.92 235	7.68 241	22.10 235	13.89 243	6.83 234	13.47 234	10.38 234	5.14 238	14.81 234

test123		9.37 231	12.26 233	6.00 231	3.32 239	4.06 240	6.39 241	3.41 234	13.20 236	10.48 240	16.43 236	16.22 242	6.76 235	11.37 235	10.40 233	5.62 237	14.10 235

uanet_test		0.00 232	0.00 234	0.00 233	0.00 241	0.00 241	0.00 242	0.00 237	0.00 237	0.00 242	0.00 237	0.00 244	0.00 237	0.00 236	0.00 235	0.00 239	0.00 236

sosnet-low-res		0.00 232	0.00 234	0.00 233	0.00 241	0.00 241	0.00 242	0.00 237	0.00 237	0.00 242	0.00 237	0.00 244	0.00 237	0.00 236	0.00 235	0.00 239	0.00 236

sosnet		0.00 232	0.00 234	0.00 233	0.00 241	0.00 241	0.00 242	0.00 237	0.00 237	0.00 242	0.00 237	0.00 244	0.00 237	0.00 236	0.00 235	0.00 239	0.00 236

TPM-MVS					98.38 218	97.20 204	96.44 226			97.17 210	95.17 207	98.68 136	92.69 221			98.11 187	97.67 165
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										99.88 2

9.14												98.83 127

SR-MVS					99.62 93			99.47 78				99.40 65

Anonymous202405211			98.44 82		99.79 39	99.32 52	99.05 101	99.34 106	96.59 122		97.95 142	97.68 165	97.16 165	99.36 33	99.28 35	99.61 39	98.90 72

our_test_3					99.29 160	97.72 194	98.98 109

ambc			97.89 129		99.45 133	97.88 187	97.78 198		97.27 85	99.80 3	98.99 100	98.48 144	98.55 103	97.80 146	96.68 178	98.54 168	98.10 147

MTAPA										99.19 57		99.68 24

MTMP										99.20 55		99.54 47

Patchmatch-RL test							32.47 239

tmp_tt				65.28 229	82.24 236	71.50 237	70.81 238	23.21 233	96.14 146	81.70 238	85.98 233	92.44 203	49.84 233	95.81 199	94.36 210	83.86 236

XVS					99.77 45	99.07 87	99.46 46			98.95 91		99.37 69				99.33 76

X-MVStestdata					99.77 45	99.07 87	99.46 46			98.95 91		99.37 69				99.33 76

mPP-MVS					99.75 55							99.49 59

NP-MVS									93.07 208

Patchmtry						96.05 219	97.64 207	99.78 16		98.50 131

DeepMVS_CX						87.86 235	92.27 235	61.98 231	93.64 202	93.62 232	91.17 223	91.67 204	94.90 201	95.99 198		92.48 227	94.18 211

High-resolution multi-view benchmark