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 10

SixPastTwentyTwo		99.70 3	99.59 4	99.82 2	99.93 3	99.80 1	99.86 2	99.87 6	98.87 11	99.79 5	99.85 14	99.33 65	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 13	99.76 3	99.58 20	99.59 16	99.52 47	99.46 15

anonymousdsp		99.64 5	99.55 6	99.74 10	99.87 16	99.56 25	99.82 3	99.73 23	98.54 16	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 35	99.86 8	99.28 5	99.48 30	99.44 54	99.86 5	99.01 69	99.78 4	99.76 3	99.90 2	99.33 21

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 16	99.66 13	99.78 22	99.16 86	99.68 7	99.70 9	99.63 9	99.94 1	99.49 13

PEN-MVS		99.54 8	99.30 15	99.83 1	99.92 5	99.76 4	99.80 4	99.88 3	97.60 62	99.71 6	99.59 36	99.52 43	99.75 4	99.64 15	99.51 19	99.90 2	99.46 15

TDRefinement		99.54 8	99.50 7	99.60 17	99.70 67	99.35 45	99.77 8	99.58 51	99.40 4	99.28 49	99.66 26	99.41 54	99.55 15	99.74 8	99.65 8	99.70 30	99.25 26

DTE-MVSNet		99.52 10	99.27 16	99.82 2	99.93 3	99.77 3	99.79 6	99.87 6	97.89 44	99.70 11	99.55 45	99.21 77	99.77 2	99.65 13	99.43 23	99.90 2	99.36 19

PS-CasMVS		99.50 11	99.23 19	99.82 2	99.92 5	99.75 6	99.78 7	99.89 1	97.30 73	99.71 6	99.60 34	99.23 73	99.71 6	99.65 13	99.55 18	99.90 2	99.56 8

WR-MVS_H		99.48 12	99.23 19	99.76 8	99.91 9	99.76 4	99.75 11	99.88 3	97.27 76	99.58 17	99.56 41	99.24 72	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 29	99.63 23	99.65 39	98.88 10	99.31 43	99.85 14	99.02 105	99.23 46	99.60 18	99.58 17	99.80 15	99.22 33

MIMVSNet1		99.46 14	99.34 10	99.60 17	99.83 23	99.68 14	99.74 14	99.71 27	98.20 26	99.41 35	99.86 13	99.66 25	99.41 30	99.50 24	99.39 26	99.50 52	99.10 44

TransMVSNet (Re)		99.45 15	99.32 13	99.61 15	99.88 14	99.60 20	99.75 11	99.63 43	99.11 7	99.28 49	99.83 18	98.35 139	99.27 43	99.70 9	99.62 13	99.84 10	99.03 52

ACMH	97.81 6	99.44 16	99.33 11	99.56 22	99.81 32	99.42 36	99.73 15	99.58 51	99.02 8	99.10 73	99.41 59	99.69 19	99.60 10	99.45 28	99.26 36	99.55 43	99.05 49
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CP-MVSNet		99.39 17	99.04 28	99.80 6	99.91 9	99.70 11	99.75 11	99.88 3	96.82 97	99.68 12	99.32 62	98.86 114	99.68 7	99.57 21	99.47 20	99.89 6	99.52 10

COLMAP_ROB	98.29 2	99.37 18	99.25 17	99.51 30	99.74 58	99.12 73	99.56 32	99.39 87	98.96 9	99.17 61	99.44 54	99.63 32	99.58 11	99.48 26	99.27 35	99.60 40	98.81 78
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 23	99.53 29	99.73 63	99.05 81	99.49 40	99.40 85	98.42 19	99.55 21	99.71 24	99.89 3	99.49 19	99.14 43	98.81 66	99.54 44	99.02 54
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 46	97.29 195	99.87 11	99.63 32	99.52 16	99.66 12	99.63 9	99.77 20	99.12 40

UA-Net		99.30 21	99.22 21	99.39 44	99.94 2	99.66 17	98.91 111	99.86 8	97.74 52	98.74 114	99.00 89	99.60 37	99.17 54	99.50 24	99.39 26	99.70 30	99.64 3

ACMH+	97.53 7	99.29 22	99.20 22	99.40 43	99.81 32	99.22 62	99.59 29	99.50 68	98.64 15	98.29 148	99.21 74	99.69 19	99.57 12	99.53 23	99.33 31	99.66 34	98.81 78

Vis-MVSNet		99.25 23	99.32 13	99.17 67	99.65 78	99.55 27	99.63 23	99.33 103	98.16 27	99.29 46	99.65 30	99.77 10	97.56 143	99.44 30	99.14 41	99.58 41	99.51 12
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 35	99.61 15	99.81 32	99.45 33	99.47 42	99.68 30	97.28 75	99.39 36	99.54 46	99.08 101	99.45 22	99.09 49	98.84 63	99.83 11	99.04 50

CSCG		99.23 24	99.15 23	99.32 56	99.83 23	99.45 33	98.97 103	99.21 124	98.83 12	99.04 83	99.43 56	99.64 30	99.26 44	98.85 75	98.20 102	99.62 38	99.62 6

Gipuma		99.22 26	98.86 39	99.64 12	99.70 67	99.24 56	99.17 85	99.63 43	99.52 2	99.89 1	96.54 175	99.14 90	99.93 1	99.42 31	99.15 40	99.52 47	99.04 50
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tfpnnormal		99.19 27	98.90 36	99.54 26	99.81 32	99.55 27	99.60 27	99.54 59	98.53 18	99.23 53	98.40 110	98.23 142	99.40 31	99.29 36	99.36 29	99.63 37	98.95 64

Baseline_NR-MVSNet		99.18 28	98.87 37	99.54 26	99.74 58	99.56 25	99.36 57	99.62 48	96.53 118	99.29 46	99.85 14	98.64 131	99.40 31	99.03 60	99.63 9	99.83 11	98.86 73

thisisatest0515		99.16 29	98.94 33	99.41 38	99.75 52	99.43 35	99.36 57	99.63 43	97.68 58	99.35 38	99.31 63	98.90 111	99.09 63	98.95 65	99.20 37	99.27 83	99.11 41

CS-MVS-test		99.16 29	98.78 44	99.60 17	99.80 37	99.72 9	99.69 16	99.73 23	95.88 140	99.51 26	98.53 107	99.54 41	99.21 48	99.24 39	99.43 23	99.66 34	99.15 39

CS-MVS		99.15 31	98.75 46	99.62 14	99.76 48	99.73 8	99.60 27	99.75 21	95.67 147	99.50 27	98.53 107	99.39 59	99.29 40	99.21 41	99.46 22	99.79 18	99.29 24

APDe-MVS		99.15 31	98.95 30	99.39 44	99.77 43	99.28 53	99.52 36	99.54 59	97.22 80	99.06 77	99.20 75	99.64 30	99.05 67	99.14 43	99.02 51	99.39 65	99.17 37

FC-MVSNet-train		99.13 33	99.05 27	99.21 62	99.87 16	99.57 24	99.67 18	99.60 50	96.75 103	98.28 149	99.48 50	99.52 43	98.10 122	99.47 27	99.37 28	99.76 22	99.21 34

NR-MVSNet		99.10 34	98.68 56	99.58 20	99.89 12	99.23 59	99.35 61	99.63 43	96.58 111	99.36 37	99.05 83	98.67 129	99.46 20	99.63 16	98.73 76	99.80 15	98.88 72

DVP-MVS++		99.09 35	99.25 17	98.90 101	99.53 107	99.37 43	99.17 85	99.48 73	98.28 24	97.95 169	99.54 46	99.88 4	98.13 121	99.08 50	98.94 55	99.15 96	99.65 2

DVP-MVS		99.09 35	99.07 26	99.12 74	99.55 100	99.40 38	99.36 57	99.44 84	97.75 49	98.23 152	99.23 71	99.80 8	98.97 71	99.08 50	98.96 52	99.19 91	99.25 26
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 37	98.69 54	99.54 26	99.75 52	99.33 48	99.29 69	99.64 42	96.75 103	99.48 30	99.30 65	98.69 125	99.26 44	98.94 67	98.76 72	99.78 19	99.02 54

ACMMPR		99.05 38	98.72 50	99.44 32	99.79 38	99.12 73	99.35 61	99.56 54	97.74 52	99.21 55	97.72 137	99.55 40	99.29 40	98.90 73	98.81 66	99.41 64	99.19 35

DU-MVS		99.04 39	98.59 60	99.56 22	99.74 58	99.23 59	99.29 69	99.63 43	96.58 111	99.55 21	99.05 83	98.68 127	99.36 35	99.03 60	98.60 83	99.77 20	98.97 59

TSAR-MVS + MP.		99.02 40	98.95 30	99.11 77	99.23 156	98.79 117	99.51 37	98.73 164	97.50 66	98.56 125	99.03 86	99.59 38	99.16 56	99.29 36	99.17 39	99.50 52	99.24 30
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 41	98.66 57	99.41 38	99.52 112	99.39 39	99.57 31	99.66 37	97.59 63	99.32 42	99.88 9	99.23 73	99.50 18	97.77 139	97.98 113	98.92 125	98.78 83

EG-PatchMatch MVS		99.01 41	98.77 45	99.28 61	99.64 81	98.90 110	98.81 123	99.27 114	96.55 115	99.71 6	99.31 63	99.66 25	99.17 54	99.28 38	99.11 43	99.10 98	98.57 98

PVSNet_Blended_VisFu		98.98 43	98.79 42	99.21 62	99.76 48	99.34 46	99.35 61	99.35 99	97.12 86	99.46 32	99.56 41	98.89 112	98.08 125	99.05 54	98.58 85	99.27 83	98.98 58

HFP-MVS		98.97 44	98.70 52	99.29 59	99.67 72	98.98 93	99.13 91	99.53 62	97.76 46	98.90 98	98.07 125	99.50 49	99.14 59	98.64 86	98.78 70	99.37 67	99.18 36

UniMVSNet_NR-MVSNet		98.97 44	98.46 70	99.56 22	99.76 48	99.34 46	99.29 69	99.61 49	96.55 115	99.55 21	99.05 83	97.96 150	99.36 35	98.84 76	98.50 91	99.81 14	98.97 59

casdiffmvs_mvg		98.96 46	98.87 37	99.07 80	99.82 28	99.36 44	99.36 57	99.22 121	98.13 29	97.74 176	99.42 57	99.46 52	98.59 94	98.39 98	98.95 54	99.71 29	98.39 116
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DROMVSNet		98.96 46	98.45 73	99.56 22	99.88 14	99.70 11	99.68 17	99.78 16	94.15 181	98.97 87	98.26 117	99.21 77	99.35 37	99.30 35	99.14 41	99.73 25	99.40 18

SED-MVS		98.94 48	98.95 30	98.91 100	99.43 128	99.38 41	99.12 93	99.46 78	97.05 89	98.43 140	99.23 71	99.79 9	97.99 128	99.05 54	98.94 55	99.05 111	99.23 31

ACMMP_NAP		98.94 48	98.72 50	99.21 62	99.67 72	99.08 76	99.26 74	99.39 87	96.84 94	98.88 102	98.22 118	99.68 21	98.82 80	99.06 53	98.90 58	99.25 86	99.25 26

v1144		98.94 48	98.53 65	99.42 36	99.62 85	99.03 87	99.58 30	99.36 96	97.99 35	99.49 29	99.91 8	99.20 80	99.51 17	97.61 144	97.85 120	98.95 120	98.10 139

v8		98.94 48	98.60 58	99.35 53	99.54 104	99.39 39	99.55 33	99.67 34	97.48 67	99.13 69	99.81 19	99.10 97	99.39 33	97.86 134	97.89 118	98.81 134	98.66 91

SteuartSystems-ACMMP		98.94 48	98.52 66	99.43 35	99.79 38	99.13 72	99.33 65	99.55 56	96.17 133	99.04 83	97.53 143	99.65 29	99.46 20	99.04 59	98.76 72	99.44 59	99.35 20
Skip Steuart: Steuart Systems R&D Blog.
v1192		98.91 53	98.48 69	99.41 38	99.61 89	99.03 87	99.64 20	99.25 118	97.91 41	99.58 17	99.92 4	99.07 103	99.45 22	97.55 148	97.68 134	98.93 122	98.23 129

FMVSNet1		98.90 54	99.10 25	98.67 125	99.54 104	99.48 30	99.22 79	99.66 37	98.39 22	97.50 183	99.66 26	99.04 104	96.58 164	99.05 54	99.03 48	99.52 47	99.08 46

ACMM	96.66 11	98.90 54	98.44 75	99.44 32	99.74 58	98.95 99	99.47 42	99.55 56	97.66 60	99.09 74	96.43 177	99.41 54	99.35 37	98.95 65	98.67 79	99.45 57	99.03 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20231211		98.89 56	98.79 42	98.99 93	99.82 28	99.41 37	99.18 84	99.31 109	96.92 91	98.54 127	98.58 105	98.84 117	97.46 145	99.45 28	99.29 33	99.65 36	99.08 46

v1921920		98.89 56	98.46 70	99.39 44	99.58 93	99.04 85	99.64 20	99.17 130	97.91 41	99.64 15	99.92 4	98.99 109	99.44 25	97.44 155	97.57 143	98.84 132	98.35 119

GeoE		98.88 58	98.43 78	99.41 38	99.83 23	99.24 56	99.51 37	99.82 13	96.55 115	99.22 54	98.76 97	99.22 76	98.96 72	98.55 89	98.15 104	99.10 98	98.56 101

v144192		98.88 58	98.46 70	99.37 51	99.56 99	99.03 87	99.61 26	99.26 115	97.79 45	99.58 17	99.88 9	99.11 95	99.43 27	97.38 160	97.61 139	98.80 135	98.43 113

SMA-MVS		98.87 60	98.73 49	99.04 86	99.72 64	99.05 81	98.64 133	99.17 130	96.31 128	98.80 108	99.07 81	99.70 18	98.67 88	98.93 70	98.82 64	99.23 89	99.23 31
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 60	98.40 81	99.41 38	99.74 58	98.88 111	99.29 69	99.50 68	96.85 93	98.96 90	97.05 159	99.66 25	99.43 27	98.98 64	98.60 83	99.52 47	98.81 78
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DCV-MVSNet		98.86 62	98.57 63	99.19 65	99.86 20	99.67 15	99.39 51	99.71 27	97.53 65	98.69 117	95.85 188	98.48 134	97.75 137	99.57 21	99.41 25	99.72 26	99.48 14

v1240		98.86 62	98.41 80	99.38 49	99.59 91	99.05 81	99.65 19	99.14 135	97.68 58	99.66 13	99.93 3	98.72 124	99.45 22	97.38 160	97.72 132	98.79 136	98.35 119

CP-MVS		98.86 62	98.43 78	99.36 52	99.68 70	98.97 97	99.19 82	99.46 78	96.60 109	99.20 56	97.11 158	99.51 47	99.15 58	98.92 71	98.82 64	99.45 57	99.08 46

v2v482		98.85 65	98.40 81	99.38 49	99.65 78	98.98 93	99.55 33	99.39 87	97.92 40	99.35 38	99.85 14	99.14 90	99.39 33	97.50 150	97.78 123	98.98 117	97.60 154

DPE-MVS		98.84 66	98.69 54	99.00 90	99.05 175	99.26 54	99.19 82	99.35 99	95.85 142	98.74 114	99.27 67	99.66 25	98.30 114	98.90 73	98.93 57	99.37 67	99.00 56
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
OPM-MVS		98.84 66	98.59 60	99.12 74	99.52 112	98.50 142	99.13 91	99.22 121	97.76 46	98.76 110	98.70 99	99.61 35	98.90 75	98.67 84	98.37 96	99.19 91	98.57 98
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test20.03		98.84 66	98.74 48	98.95 96	99.77 43	99.33 48	99.21 81	99.46 78	97.29 74	98.88 102	99.65 30	99.10 97	97.07 155	99.11 46	98.76 72	99.32 76	97.98 143

casdiffmvs		98.84 66	98.75 46	98.94 99	99.75 52	99.21 63	99.33 65	99.04 145	98.04 31	97.46 186	99.72 23	99.72 15	98.60 92	98.30 110	98.37 96	99.48 54	97.92 145
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 66	98.33 87	99.44 32	99.78 41	98.98 93	99.39 51	99.55 56	95.41 152	98.90 98	97.51 144	99.68 21	99.44 25	99.03 60	98.81 66	99.57 42	98.91 68

RPSCF		98.84 66	98.81 41	98.89 103	99.37 135	98.95 99	98.51 145	98.85 157	97.73 54	98.33 145	98.97 91	99.14 90	98.95 73	99.18 42	98.68 78	99.31 77	98.99 57

ACMMP		98.82 72	98.33 87	99.39 44	99.77 43	99.14 71	99.37 54	99.54 59	96.47 122	99.03 85	96.26 181	99.52 43	99.28 42	98.92 71	98.80 69	99.37 67	99.16 38
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
V42		98.81 73	98.49 68	99.18 66	99.52 112	98.92 105	99.50 39	99.29 111	97.43 70	98.97 87	99.81 19	99.00 108	99.30 39	97.93 130	98.01 111	98.51 160	98.34 123

LS3D		98.79 74	98.52 66	99.12 74	99.64 81	99.09 75	99.24 77	99.46 78	97.75 49	98.93 96	97.47 146	98.23 142	97.98 129	99.36 32	99.30 32	99.46 55	98.42 114

MP-MVS		98.78 75	98.30 89	99.34 55	99.75 52	98.95 99	99.26 74	99.46 78	95.78 146	99.17 61	96.98 163	99.72 15	99.06 66	98.84 76	98.74 75	99.33 73	99.11 41
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
v148		98.77 76	98.45 73	99.15 70	99.68 70	98.94 103	99.49 40	99.31 109	97.95 37	98.91 97	99.65 30	99.62 34	99.18 51	97.99 128	97.64 138	98.33 165	97.38 159

test1111		98.75 77	98.14 102	99.46 31	99.86 20	99.63 19	99.47 42	99.68 30	98.34 23	98.76 110	99.66 26	90.92 193	99.23 46	99.77 5	99.71 5	99.75 23	98.95 64

ECVR-MVS		98.74 78	98.15 100	99.42 36	99.83 23	99.58 22	99.37 54	99.67 34	98.02 33	98.85 105	99.59 36	91.66 191	99.10 61	99.77 5	99.70 6	99.72 26	98.73 85

SD-MVS		98.73 79	98.54 64	98.95 96	99.14 165	98.76 120	98.46 149	99.14 135	97.71 56	98.56 125	98.06 127	99.61 35	98.85 79	98.56 88	97.74 129	99.54 44	99.32 22
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 80	98.60 58	98.87 105	99.67 72	99.33 48	99.15 88	99.26 115	96.99 90	97.90 172	98.19 120	99.74 12	98.29 115	97.69 142	98.96 52	98.96 118	99.27 25
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 81	98.09 107	99.39 44	99.76 48	99.07 77	99.30 68	99.51 66	94.76 163	99.18 60	96.70 170	99.51 47	99.20 49	98.79 80	98.71 77	99.39 65	99.11 41

pmmvs-eth3d		98.68 82	98.14 102	99.29 59	99.49 117	98.45 145	99.45 47	99.38 92	97.21 81	99.50 27	99.65 30	99.21 77	99.16 56	97.11 167	97.56 144	98.79 136	97.82 149

EU-MVSNet		98.68 82	98.94 33	98.37 145	99.14 165	98.74 122	99.64 20	98.20 189	98.21 25	99.17 61	99.66 26	99.18 83	99.08 64	99.11 46	98.86 59	95.00 201	98.83 75

PMVS	92.51 17	98.66 84	98.86 39	98.43 141	99.26 151	98.98 93	98.60 139	98.59 173	97.73 54	99.45 33	99.38 60	98.54 133	95.24 182	99.62 17	99.61 14	99.42 61	98.17 136
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DeepC-MVS_fast	97.38 8	98.65 85	98.34 86	99.02 89	99.33 139	98.29 151	98.99 101	98.71 166	97.40 71	99.31 43	98.20 119	99.40 57	98.54 101	98.33 107	98.18 103	99.23 89	98.58 96
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 85	98.35 85	99.00 90	99.59 91	98.70 125	98.90 115	99.36 96	97.97 36	99.09 74	96.55 174	99.09 99	97.97 130	98.70 83	98.65 81	99.12 97	98.81 78

TSAR-MVS + ACMM		98.64 87	98.58 62	98.72 119	99.17 163	98.63 131	98.69 129	99.10 142	97.69 57	98.30 147	99.12 79	99.38 60	98.70 87	98.45 93	97.51 146	98.35 164	99.25 26

DELS-MVS		98.63 88	98.70 52	98.55 137	99.24 155	99.04 85	98.96 104	98.52 176	96.83 96	98.38 142	99.58 39	99.68 21	97.06 156	98.74 82	98.44 93	99.10 98	98.59 95
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 89	98.40 81	98.89 103	99.57 98	98.80 116	98.63 134	99.35 99	96.82 97	98.60 121	98.85 96	99.08 101	98.09 124	98.31 108	98.21 100	99.08 104	98.72 86

EPP-MVSNet		98.61 90	98.19 97	99.11 77	99.86 20	99.60 20	99.44 48	99.53 62	97.37 72	96.85 199	98.69 100	93.75 184	99.18 51	99.22 40	99.35 30	99.82 13	99.32 22

3Dnovator+	97.85 5	98.61 90	98.14 102	99.15 70	99.62 85	98.37 149	99.10 94	99.51 66	98.04 31	98.98 86	96.07 185	98.75 123	98.55 99	98.51 91	98.40 94	99.17 93	98.82 76

X-MVS		98.59 92	97.99 113	99.30 58	99.75 52	99.07 77	99.17 85	99.50 68	96.62 107	98.95 92	93.95 203	99.37 61	99.11 60	98.94 67	98.86 59	99.35 71	99.09 45

MVS_111021_HR		98.58 93	98.26 92	98.96 95	99.32 142	98.81 114	98.48 147	98.99 150	96.81 99	99.16 64	98.07 125	99.23 73	98.89 77	98.43 95	98.27 99	98.90 127	98.24 128

MVS_0304		98.57 94	98.36 84	98.82 112	99.72 64	98.94 103	98.92 109	99.14 135	96.76 102	99.33 41	98.30 114	99.73 13	96.74 160	98.05 125	97.79 122	99.08 104	98.97 59

PM-MVS		98.57 94	98.24 94	98.95 96	99.26 151	98.59 134	99.03 98	98.74 163	96.84 94	99.44 34	99.13 78	98.31 141	98.75 85	98.03 126	98.21 100	98.48 161	98.58 96

PHI-MVS		98.57 94	98.20 96	99.00 90	99.48 119	98.91 107	98.68 130	99.17 130	94.97 159	99.27 51	98.33 112	99.33 65	98.05 126	98.82 78	98.62 82	99.34 72	98.38 117

HPM-MVS++		98.56 97	98.08 108	99.11 77	99.53 107	98.61 133	99.02 100	99.32 107	96.29 130	99.06 77	97.23 153	99.50 49	98.77 83	98.15 121	97.90 116	98.96 118	98.90 69

TSAR-MVS + GP.		98.54 98	98.29 91	98.82 112	99.28 149	98.59 134	97.73 188	99.24 120	95.93 139	98.59 122	99.07 81	99.17 84	98.86 78	98.44 94	98.10 106	99.26 85	98.72 86

UGNet		98.52 99	99.00 29	97.96 166	99.58 93	99.26 54	99.27 73	99.40 85	98.07 30	98.28 149	98.76 97	99.71 17	92.24 209	98.94 67	98.85 61	99.00 116	99.43 17
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		98.50 100	98.03 110	99.05 84	99.50 115	99.01 90	99.15 88	99.26 115	96.38 126	99.12 71	99.50 49	99.12 93	98.60 92	97.68 143	97.24 157	98.66 144	97.30 163

CLD-MVS		98.48 101	98.15 100	98.86 108	99.53 107	98.35 150	98.55 142	97.83 198	96.02 138	98.97 87	99.08 80	99.75 11	99.03 68	98.10 124	97.33 153	99.28 81	98.44 112
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CANet		98.47 102	98.30 89	98.67 125	99.65 78	98.87 112	98.82 122	99.01 148	96.14 134	99.29 46	98.86 94	99.01 106	96.54 165	98.36 102	98.08 108	98.72 140	98.80 82

APD-MVS		98.47 102	97.97 114	99.05 84	99.64 81	98.91 107	98.94 106	99.45 83	94.40 174	98.77 109	97.26 152	99.41 54	98.21 118	98.67 84	98.57 88	99.31 77	98.57 98
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Vis-MVSNet (Re-imp)		98.46 104	98.23 95	98.73 118	99.81 32	99.29 52	98.79 124	99.50 68	96.20 132	96.03 205	98.29 115	96.98 165	98.54 101	99.11 46	99.08 44	99.70 30	98.62 93

Fast-Effi-MVS+		98.42 105	97.79 120	99.15 70	99.69 69	98.66 129	98.94 106	99.68 30	94.49 168	99.05 79	98.06 127	98.86 114	98.48 104	98.18 118	97.78 123	99.05 111	98.54 104

ETV-MVS		98.41 106	97.76 121	99.17 67	99.58 93	99.01 90	98.91 111	99.50 68	93.33 194	99.31 43	96.82 167	98.42 137	98.17 120	99.13 45	99.08 44	99.54 44	98.56 101

MVS_111021_LR		98.39 107	98.11 105	98.71 121	99.08 172	98.54 140	98.23 170	98.56 175	96.57 113	99.13 69	98.41 109	98.86 114	98.65 90	98.23 116	97.87 119	98.65 146	98.28 125

pmmvs5		98.37 108	97.81 119	99.03 87	99.46 121	98.97 97	99.03 98	98.96 152	95.85 142	99.05 79	99.45 53	98.66 130	98.79 82	96.02 184	97.52 145	98.87 129	98.21 132

OMC-MVS		98.35 109	98.10 106	98.64 131	98.85 182	97.99 170	98.56 141	98.21 187	97.26 78	98.87 104	98.54 106	99.27 71	98.43 106	98.34 105	97.66 135	98.92 125	97.65 153

canonicalmvs		98.34 110	97.92 116	98.83 110	99.45 123	99.21 63	98.37 157	99.53 62	97.06 88	97.74 176	96.95 165	95.05 181	98.36 109	98.77 81	98.85 61	99.51 51	99.53 9

CHOSEN 1792x2688		98.31 111	98.02 111	98.66 127	99.55 100	98.57 137	99.38 53	99.25 118	98.42 19	98.48 135	99.58 39	99.85 6	98.31 113	95.75 187	95.71 182	96.96 188	98.27 127

CPTT-MVS		98.28 112	97.51 134	99.16 69	99.54 104	98.78 118	98.96 104	99.36 96	96.30 129	98.89 101	93.10 207	99.30 68	99.20 49	98.35 104	97.96 114	99.03 114	98.82 76

TinyColmap		98.27 113	97.62 131	99.03 87	99.29 147	97.79 179	98.92 109	98.95 153	97.48 67	99.52 24	98.65 102	97.86 152	98.90 75	98.34 105	97.27 155	98.64 147	95.97 183

diffmvs		98.26 114	98.16 98	98.39 143	99.61 89	98.78 118	98.79 124	98.61 171	97.94 38	97.11 198	99.51 48	99.52 43	97.61 141	96.55 176	96.93 163	98.61 149	97.87 147
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		98.26 114	97.57 132	99.06 81	99.42 131	97.98 172	98.83 119	98.85 157	97.57 64	99.59 16	99.15 77	98.59 132	98.99 70	97.42 156	96.08 181	98.69 143	96.23 181

SF-MVS		98.25 116	98.16 98	98.35 146	99.43 128	98.42 148	97.05 210	99.09 143	96.42 124	98.13 158	97.73 136	99.20 80	97.22 151	98.36 102	98.38 95	99.16 95	98.62 93

MCST-MVS		98.25 116	97.57 132	99.06 81	99.53 107	98.24 157	98.63 134	99.17 130	95.88 140	98.58 123	96.11 183	99.09 99	99.18 51	97.58 147	97.31 154	99.25 86	98.75 84

IterMVS-LS		98.23 118	97.66 127	98.90 101	99.63 84	99.38 41	99.07 95	99.48 73	97.75 49	98.81 107	99.37 61	94.57 183	97.88 134	96.54 177	97.04 160	98.53 157	98.97 59
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TAPA-MVS	96.65 12	98.23 118	97.96 115	98.55 137	98.81 184	98.16 161	98.40 154	97.94 196	96.68 105	98.49 133	98.61 103	98.89 112	98.57 97	97.45 153	97.59 141	99.09 103	98.35 119
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CNVR-MVS		98.22 120	97.76 121	98.76 116	99.33 139	98.26 155	98.48 147	98.88 156	96.22 131	98.47 137	95.79 189	99.33 65	98.35 110	98.37 101	97.99 112	99.03 114	98.38 117

IS_MVSNet		98.20 121	98.00 112	98.44 140	99.82 28	99.48 30	99.25 76	99.56 54	95.58 149	93.93 217	97.56 142	96.52 170	98.27 116	99.08 50	99.20 37	99.80 15	98.56 101

DeepPCF-MVS	96.68 10	98.20 121	98.26 92	98.12 159	97.03 220	98.11 164	98.44 151	97.70 200	96.77 101	98.52 129	98.91 92	99.17 84	98.58 96	98.41 97	98.02 110	98.46 162	98.46 109

MSDG		98.20 121	97.88 118	98.56 135	99.33 139	97.74 180	98.27 167	98.10 190	97.20 83	98.06 162	98.59 104	99.16 86	98.76 84	98.39 98	97.71 133	98.86 131	96.38 178

testgi		98.18 124	98.44 75	97.89 168	99.78 41	99.23 59	98.78 126	99.21 124	97.26 78	97.41 188	97.39 149	99.36 64	92.85 206	98.82 78	98.66 80	99.31 77	98.35 119

Effi-MVS+		98.11 125	97.29 140	99.06 81	99.62 85	98.55 138	98.16 173	99.80 15	94.64 164	99.15 67	96.59 172	97.43 158	98.44 105	97.46 152	97.90 116	99.17 93	98.45 111

FA-MVS(training)		98.08 126	97.68 125	98.56 135	99.14 165	98.69 126	98.41 152	99.83 12	95.85 142	98.57 124	97.95 132	96.92 167	96.85 158	98.51 91	98.09 107	98.54 155	97.74 150

HyFIR lowres test		98.08 126	97.16 149	99.14 73	99.72 64	98.91 107	99.41 49	99.58 51	97.93 39	98.82 106	99.24 69	95.81 176	98.73 86	95.16 198	95.13 191	98.60 151	97.94 144

EIA-MVS		98.03 128	97.20 146	98.99 93	99.66 75	99.24 56	98.53 144	99.52 65	91.56 210	99.25 52	95.34 193	98.78 120	97.72 138	98.38 100	98.58 85	99.28 81	98.54 104

train_agg		97.99 129	97.26 141	98.83 110	99.43 128	98.22 159	98.91 111	99.07 144	94.43 172	97.96 168	96.42 178	99.30 68	98.81 81	97.39 158	96.62 169	98.82 133	98.47 107

MSLP-MVS++		97.99 129	97.64 130	98.40 142	98.91 180	98.47 144	97.12 208	98.78 161	96.49 120	98.48 135	93.57 205	99.12 93	98.51 103	98.31 108	98.58 85	98.58 153	98.95 64

CDPH-MVS		97.99 129	97.23 144	98.87 105	99.58 93	98.29 151	98.83 119	99.20 126	93.76 188	98.11 160	96.11 183	99.16 86	98.23 117	97.80 137	97.22 158	99.29 80	98.28 125

FMVSNet2		97.94 132	98.08 108	97.77 174	98.71 188	99.21 63	98.62 136	99.47 75	96.62 107	96.37 204	99.20 75	97.70 154	94.39 193	97.39 158	97.75 128	99.08 104	98.70 88

PVSNet_BlendedMVS		97.93 133	97.66 127	98.25 152	99.30 144	98.67 127	98.31 162	97.95 194	94.30 178	98.75 112	97.63 139	98.76 121	96.30 172	98.29 111	97.78 123	98.93 122	98.18 134

PVSNet_Blended		97.93 133	97.66 127	98.25 152	99.30 144	98.67 127	98.31 162	97.95 194	94.30 178	98.75 112	97.63 139	98.76 121	96.30 172	98.29 111	97.78 123	98.93 122	98.18 134

OpenMVS	97.26 9	97.88 135	97.17 148	98.70 122	99.50 115	98.55 138	98.34 160	99.11 140	93.92 186	98.90 98	95.04 197	98.23 142	97.38 148	98.11 123	98.12 105	98.95 120	98.23 129

pmmvs4		97.87 136	97.02 153	98.86 108	99.20 157	97.68 183	98.89 116	99.03 146	96.57 113	99.12 71	99.03 86	97.26 162	98.42 107	95.16 198	96.34 173	98.53 157	97.10 170

NCCC		97.84 137	96.96 155	98.87 105	99.39 134	98.27 154	98.46 149	99.02 147	96.78 100	98.73 116	91.12 210	98.91 110	98.57 97	97.83 136	97.49 147	99.04 113	98.33 124

Effi-MVS+-dtu		97.78 138	97.37 138	98.26 150	99.25 153	98.50 142	97.89 182	99.19 129	94.51 166	98.16 156	95.93 186	98.80 119	95.97 175	98.27 115	97.38 150	99.10 98	98.23 129

MDA-MVSNet-bldmvs		97.75 139	97.26 141	98.33 147	99.35 138	98.45 145	99.32 67	97.21 205	97.90 43	99.05 79	99.01 88	96.86 168	99.08 64	99.36 32	92.97 201	95.97 197	96.25 180

CDS-MVSNet		97.75 139	97.68 125	97.83 172	99.08 172	98.20 160	98.68 130	98.61 171	95.63 148	97.80 174	99.24 69	96.93 166	94.09 198	97.96 129	97.82 121	98.71 141	97.99 141
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CNLPA		97.75 139	97.26 141	98.32 149	98.58 196	97.86 175	97.80 184	98.09 191	96.49 120	98.49 133	96.15 182	98.08 145	98.35 110	98.00 127	97.03 161	98.61 149	97.21 167

PLC	95.63 15	97.73 142	97.01 154	98.57 134	99.10 169	97.80 178	97.72 189	98.77 162	96.34 127	98.38 142	93.46 206	98.06 146	98.66 89	97.90 132	97.65 137	98.77 138	97.90 146
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVS_Test		97.69 143	97.15 150	98.33 147	99.27 150	98.43 147	98.25 168	99.29 111	95.00 158	97.39 190	98.86 94	98.00 149	97.14 153	95.38 193	96.22 175	98.62 148	98.15 138

GBi-Net		97.69 143	97.75 123	97.62 175	98.71 188	99.21 63	98.62 136	99.33 103	94.09 182	95.60 207	98.17 122	95.97 173	94.39 193	99.05 54	99.03 48	99.08 104	98.70 88

test1		97.69 143	97.75 123	97.62 175	98.71 188	99.21 63	98.62 136	99.33 103	94.09 182	95.60 207	98.17 122	95.97 173	94.39 193	99.05 54	99.03 48	99.08 104	98.70 88

CANet_DTU		97.65 146	97.50 136	97.82 173	99.19 160	98.08 166	98.41 152	98.67 168	94.40 174	99.16 64	98.32 113	98.69 125	93.96 200	97.87 133	97.61 139	97.51 184	97.56 156

IterMVS-SCA-FT		97.63 147	96.86 157	98.52 139	99.48 119	98.71 124	98.84 118	98.91 154	96.44 123	99.16 64	99.56 41	95.54 178	97.95 131	95.68 190	95.07 194	96.76 189	97.03 173

TSAR-MVS + COLMAP		97.62 148	97.31 139	97.98 164	98.47 202	97.39 187	98.29 164	98.25 186	96.68 105	97.54 182	98.87 93	98.04 148	97.08 154	96.78 171	96.26 174	98.26 168	97.12 169

MS-PatchMatch		97.60 149	97.22 145	98.04 163	98.67 192	97.18 191	97.91 180	98.28 185	95.82 145	98.34 144	97.66 138	98.38 138	97.77 136	97.10 168	97.25 156	97.27 186	97.18 168

PCF-MVS	95.58 16	97.60 149	96.67 158	98.69 123	99.44 126	98.23 158	98.37 157	98.81 159	93.01 198	98.22 153	97.97 131	99.59 38	98.20 119	95.72 189	95.08 192	99.08 104	97.09 172
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HQP-MVS		97.58 151	96.65 161	98.66 127	99.30 144	97.99 170	97.88 183	98.65 169	94.58 165	98.66 118	94.65 201	99.15 89	98.59 94	96.10 182	95.59 183	98.90 127	98.50 106

DI_MVS_plusplus_trai		97.57 152	96.55 163	98.77 115	99.55 100	98.76 120	99.22 79	99.00 149	97.08 87	97.95 169	97.78 135	91.35 192	98.02 127	96.20 180	96.81 165	98.87 129	97.87 147

AdaColmap		97.57 152	96.57 162	98.74 117	99.25 153	98.01 168	98.36 159	98.98 151	94.44 171	98.47 137	92.44 208	97.91 151	98.62 91	98.19 117	97.74 129	98.73 139	97.28 164

baseline		97.50 154	97.51 134	97.50 179	99.18 161	97.38 188	98.00 176	98.00 193	96.52 119	97.49 184	99.28 66	99.43 53	95.31 181	95.27 195	96.22 175	96.99 187	98.47 107

IterMVS		97.40 155	96.67 158	98.25 152	99.45 123	98.66 129	98.87 117	98.73 164	96.40 125	98.94 95	99.56 41	95.26 180	97.58 142	95.38 193	94.70 196	95.90 198	96.72 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CVMVSNet		97.38 156	97.39 137	97.37 182	98.58 196	97.72 181	98.70 128	97.42 203	97.21 81	95.95 206	99.46 52	93.31 187	97.38 148	97.60 145	97.78 123	96.18 194	98.66 91

new-patchmatchnet		97.26 157	96.12 171	98.58 133	99.55 100	98.63 131	99.14 90	97.04 207	98.80 13	99.19 58	99.92 4	99.19 82	98.92 74	95.51 192	87.04 210	97.66 181	93.73 199

MIMVSNet		97.24 158	97.15 150	97.36 183	99.03 176	98.52 141	98.55 142	99.73 23	94.94 162	94.94 214	97.98 130	97.37 160	93.66 201	97.60 145	97.34 152	98.23 171	96.29 179

PatchMatch-RL		97.24 158	96.45 166	98.17 156	98.70 191	97.57 186	97.31 203	98.48 179	94.42 173	98.39 141	95.74 190	96.35 172	97.88 134	97.75 140	97.48 148	98.24 170	95.87 184

thisisatest0530		97.20 160	95.95 175	98.66 127	99.46 121	98.84 113	98.29 164	99.20 126	94.51 166	98.25 151	97.42 147	85.03 208	97.68 139	98.43 95	98.56 89	99.08 104	98.89 71

tttt0517		97.18 161	95.92 176	98.65 130	99.49 117	98.92 105	98.29 164	99.20 126	94.37 176	98.17 154	97.37 150	84.72 211	97.68 139	98.55 89	98.56 89	99.10 98	98.95 64

MDTV_nov1_ep13_2view		97.12 162	96.19 170	98.22 155	99.13 168	98.05 167	99.24 77	99.47 75	97.61 61	99.15 67	99.59 36	99.01 106	98.40 108	94.87 201	90.14 204	93.91 204	94.04 198

MAR-MVS		97.12 162	96.28 169	98.11 160	98.94 178	97.22 190	97.65 193	99.38 92	90.93 216	98.15 157	95.17 195	97.13 163	96.48 168	97.71 141	97.40 149	98.06 174	98.40 115
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		96.99 164	96.46 165	97.61 177	98.98 177	97.89 173	97.54 197	99.76 19	93.43 192	96.55 203	94.93 198	98.06 146	94.32 196	96.93 169	96.50 171	98.53 157	97.47 157

FPMVS		96.97 165	97.20 146	96.70 199	97.75 212	96.11 203	97.72 189	95.47 211	97.13 85	98.02 164	97.57 141	96.67 169	92.97 205	99.00 63	98.34 98	98.28 167	95.58 186

TAMVS		96.95 166	96.94 156	96.97 194	99.07 174	97.67 185	97.98 178	97.12 206	95.04 157	95.41 210	99.27 67	95.57 177	94.09 198	97.32 162	97.11 159	98.16 173	96.59 177

FMVSNet3		96.85 167	96.67 158	97.06 188	97.56 215	99.01 90	97.99 177	99.33 103	94.09 182	95.60 207	98.17 122	95.97 173	93.26 204	94.76 203	96.22 175	98.59 152	98.46 109

GA-MVS		96.84 168	95.86 178	97.98 164	99.16 164	98.29 151	97.91 180	98.64 170	95.14 155	97.71 178	98.04 129	88.90 196	96.50 167	96.41 179	96.61 170	97.97 178	97.60 154

CHOSEN 280x420		96.80 169	96.30 168	97.39 180	99.09 170	96.52 195	98.76 127	99.29 111	93.88 187	97.65 179	98.34 111	93.66 185	96.29 174	98.28 113	97.73 131	93.27 207	95.70 185

gg-mvs-nofinetune		96.77 170	96.52 164	97.06 188	99.66 75	97.82 177	97.54 197	99.86 8	98.69 14	98.61 120	99.94 2	89.62 194	88.37 217	97.55 148	96.67 167	98.30 166	95.35 187

DPM-MVS		96.73 171	95.70 181	97.95 167	98.93 179	97.26 189	97.39 202	98.44 181	95.47 151	97.62 180	90.71 211	98.47 136	97.03 157	95.02 200	95.27 188	98.26 168	97.67 152

baseline1		96.72 172	95.40 183	98.26 150	99.53 107	98.81 114	98.32 161	98.80 160	94.96 160	96.78 202	96.50 176	84.87 210	96.68 163	97.42 156	97.91 115	99.46 55	97.33 162

N_pmnet		96.68 173	95.70 181	97.84 171	99.42 131	98.00 169	99.35 61	98.21 187	98.40 21	98.13 158	99.42 57	99.30 68	97.44 147	94.00 207	88.79 205	94.47 203	91.96 205

pmnet_mix02		96.61 174	95.32 184	98.11 160	99.41 133	97.68 183	99.05 96	97.59 201	98.16 27	99.05 79	99.48 50	99.11 95	98.32 112	92.36 211	87.67 207	95.26 200	92.80 203

new_pmnet		96.59 175	96.40 167	96.81 196	98.24 208	95.46 212	97.71 191	94.75 214	96.92 91	96.80 201	99.23 71	97.81 153	96.69 161	96.58 175	95.16 190	96.69 190	93.64 200

PMMVS		96.47 176	95.81 179	97.23 184	97.38 217	95.96 207	97.31 203	96.91 208	93.21 195	97.93 171	97.14 156	97.64 156	95.70 177	95.24 196	96.18 178	98.17 172	95.33 188

EPNet		96.44 177	96.08 172	96.86 195	99.32 142	97.15 192	97.69 192	99.32 107	93.67 189	98.11 160	95.64 191	93.44 186	89.07 215	96.86 170	96.83 164	97.67 180	98.97 59
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thres600view7		96.35 178	94.27 186	98.79 114	99.66 75	99.18 68	98.94 106	99.38 92	94.37 176	97.21 197	87.19 213	84.10 212	98.10 122	98.16 119	99.47 20	99.42 61	97.43 158

EPNet_dtu		96.31 179	95.96 174	96.72 198	99.18 161	95.39 213	97.03 211	99.13 139	93.02 197	99.35 38	97.23 153	97.07 164	90.70 214	95.74 188	95.08 192	94.94 202	98.16 137
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs3		96.30 180	95.87 177	96.80 197	97.66 214	96.48 196	97.93 179	93.80 215	93.40 193	98.54 127	98.27 116	97.50 157	97.37 150	97.49 151	93.11 200	95.52 199	94.85 192

PMMVS2		96.29 181	97.05 152	95.40 209	98.32 207	96.16 200	98.18 172	97.46 202	97.20 83	84.51 223	99.60 34	98.68 127	96.37 169	98.59 87	97.38 150	97.58 183	91.76 206

thres200		96.23 182	94.13 187	98.69 123	99.44 126	99.18 68	98.58 140	99.38 92	93.52 191	97.35 191	86.33 218	85.83 206	97.93 132	98.16 119	98.78 70	99.42 61	97.10 170

thres400		96.22 183	94.08 189	98.72 119	99.58 93	99.05 81	98.83 119	99.22 121	94.01 185	97.40 189	86.34 217	84.91 209	97.93 132	97.85 135	99.08 44	99.37 67	97.28 164

tfpn200view9		96.17 184	94.08 189	98.60 132	99.37 135	99.18 68	98.68 130	99.39 87	92.02 204	97.30 193	86.53 215	86.34 203	97.45 146	98.15 121	99.08 44	99.43 60	97.28 164

CMPMVS	74.71 19	96.17 184	96.06 173	96.30 203	97.41 216	94.52 216	94.83 218	95.46 212	91.57 209	97.26 196	94.45 202	98.33 140	94.98 184	98.28 113	97.59 141	97.86 179	97.68 151
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test2506		96.12 186	93.35 199	99.35 53	99.83 23	99.58 22	99.37 54	99.67 34	98.02 33	98.44 139	97.51 144	60.03 226	99.10 61	99.77 5	99.70 6	99.72 26	98.86 73

IB-MVS	95.85 14	95.87 187	94.88 185	97.02 191	99.09 170	98.25 156	97.16 205	97.38 204	91.97 207	97.77 175	83.61 220	97.29 161	92.03 212	97.16 166	97.66 135	98.66 144	98.20 133
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		95.81 188	95.77 180	95.85 208	99.20 157	98.15 163	97.49 201	98.50 177	92.24 200	92.74 220	96.82 167	92.70 188	88.60 216	97.31 164	97.01 162	98.57 154	96.19 182

thres100view900		95.74 189	93.66 198	98.17 156	99.37 135	98.59 134	98.10 174	98.33 184	92.02 204	97.30 193	86.53 215	86.34 203	96.69 161	96.77 172	98.47 92	99.24 88	96.89 174

ET-MVSNet_ETH3D		95.72 190	93.85 194	97.89 168	97.30 218	98.09 165	98.19 171	98.40 182	94.46 170	98.01 167	96.71 169	77.85 222	96.76 159	96.08 183	96.39 172	98.70 142	97.36 160

baseline2		95.58 191	94.04 191	97.38 181	98.80 185	98.16 161	97.14 206	97.80 199	91.45 211	97.49 184	95.22 194	83.63 213	94.98 184	96.42 178	96.66 168	98.06 174	96.76 175

PatchT		95.49 192	93.29 200	98.06 162	98.65 193	96.20 199	98.91 111	99.73 23	92.00 206	98.50 130	96.67 171	83.25 214	96.34 170	94.40 204	95.50 184	96.21 193	95.04 190

CR-MVSNet		95.38 193	93.01 201	98.16 158	98.63 194	95.85 209	97.64 194	99.78 16	91.27 213	98.50 130	96.84 166	82.16 215	96.34 170	94.40 204	95.50 184	98.05 176	95.04 190

MVSTER		95.38 193	93.99 193	97.01 192	98.83 183	98.95 99	96.62 212	99.14 135	92.17 202	97.44 187	97.29 151	77.88 221	91.63 213	97.45 153	96.18 178	98.41 163	97.99 141

MVS-HIRNet		94.86 195	93.83 195	96.07 204	97.07 219	94.00 217	94.31 219	99.17 130	91.23 215	98.17 154	98.69 100	97.43 158	95.66 178	94.05 206	91.92 202	92.04 214	89.46 214

test-LLR		94.79 196	93.71 196	96.06 205	99.20 157	96.16 200	96.31 213	98.50 177	89.98 217	94.08 215	97.01 160	86.43 201	92.20 210	96.76 173	95.31 186	96.05 195	94.31 195

RPMNet		94.72 197	92.01 206	97.88 170	98.56 199	95.85 209	97.78 185	99.70 29	91.27 213	98.33 145	93.69 204	81.88 216	94.91 187	92.60 209	94.34 198	98.01 177	94.46 194

gm-plane-assit		94.62 198	91.39 208	98.39 143	99.90 11	99.47 32	99.40 50	99.65 39	97.44 69	99.56 20	99.68 25	59.40 227	94.23 197	96.17 181	94.77 195	97.61 182	92.79 204

test-mter		94.62 198	94.02 192	95.32 210	97.72 213	96.75 193	96.23 215	95.67 210	89.83 220	93.23 219	96.99 162	85.94 205	92.66 208	97.32 162	96.11 180	96.44 191	95.22 189

FMVSNet5		94.57 200	92.77 202	96.67 200	97.88 210	98.72 123	97.54 197	98.70 167	88.64 221	95.11 212	86.90 214	81.77 217	93.27 203	97.92 131	98.07 109	97.50 185	97.34 161

SCA		94.53 201	91.95 207	97.55 178	98.58 196	97.86 175	98.49 146	99.68 30	95.11 156	99.07 76	95.87 187	87.24 199	96.53 166	89.77 214	87.08 209	92.96 209	90.69 209

MDTV_nov1_ep13		94.47 202	92.15 204	97.17 185	98.54 201	96.42 197	98.10 174	98.89 155	94.49 168	98.02 164	97.41 148	86.49 200	95.56 179	90.85 212	87.95 206	93.91 204	91.45 208

TESTMET0.1,1		94.44 203	93.71 196	95.30 211	97.84 211	96.16 200	96.31 213	95.32 213	89.98 217	94.08 215	97.01 160	86.43 201	92.20 210	96.76 173	95.31 186	96.05 195	94.31 195

ADS-MVSNet		94.41 204	92.13 205	97.07 187	98.86 181	96.60 194	98.38 156	98.47 180	96.13 136	98.02 164	96.98 163	87.50 198	95.87 176	89.89 213	87.58 208	92.79 211	90.27 211

tpm		93.89 205	91.21 209	97.03 190	98.36 205	96.07 204	97.53 200	99.65 39	92.24 200	98.64 119	97.23 153	74.67 225	94.64 191	92.68 208	90.73 203	93.37 206	94.82 193

PatchmatchNet		93.88 206	91.08 210	97.14 186	98.75 187	96.01 206	98.25 168	99.39 87	94.95 161	98.96 90	96.32 179	85.35 207	95.50 180	88.89 215	85.89 213	91.99 215	90.15 212
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		93.67 207	90.82 211	96.99 193	98.62 195	96.39 198	98.40 154	99.11 140	95.54 150	97.87 173	97.14 156	81.27 219	94.97 186	88.54 217	86.80 211	92.95 210	90.06 213

MVE	82.47 18	93.12 208	94.09 188	91.99 214	90.79 221	82.50 222	93.93 220	96.30 209	96.06 137	88.81 221	98.19 120	96.38 171	97.56 143	97.24 165	95.18 189	84.58 221	93.07 201
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CostFormer		92.75 209	89.49 213	96.55 201	98.78 186	95.83 211	97.55 196	98.59 173	91.83 208	97.34 192	96.31 180	78.53 220	94.50 192	86.14 218	84.92 214	92.54 212	92.84 202

tpmrst		92.45 210	89.48 214	95.92 207	98.43 204	95.03 214	97.14 206	97.92 197	94.16 180	97.56 181	97.86 134	81.63 218	93.56 202	85.89 219	82.86 215	90.91 219	88.95 216

dps		92.35 211	88.78 216	96.52 202	98.21 209	95.94 208	97.78 185	98.38 183	89.88 219	96.81 200	95.07 196	75.31 224	94.70 190	88.62 216	86.21 212	93.21 208	90.41 210

E-PMN		92.28 212	90.12 212	94.79 212	98.56 199	90.90 219	95.16 217	93.68 216	95.36 153	95.10 213	96.56 173	89.05 195	95.24 182	95.21 197	81.84 217	90.98 217	81.94 218

EMVS		91.84 213	89.39 215	94.70 213	98.44 203	90.84 220	95.27 216	93.53 217	95.18 154	95.26 211	95.62 192	87.59 197	94.77 189	94.87 201	80.72 218	90.95 218	80.88 219

tpm cat1		91.52 214	87.70 217	95.97 206	98.33 206	94.98 215	97.06 209	98.03 192	92.11 203	98.03 163	94.77 200	77.19 223	92.71 207	83.56 220	82.24 216	91.67 216	89.04 215

test_method		77.69 215	85.40 218	68.69 215	42.66 223	55.39 224	82.17 223	52.05 219	92.83 199	84.52 222	94.88 199	95.41 179	65.37 218	92.49 210	79.32 219	85.36 220	87.50 217

GG-mvs-BLEND		65.66 216	92.62 203	34.20 217	1.45 226	93.75 218	85.40 222	1.64 223	91.37 212	17.21 225	87.25 212	94.78 182	3.25 222	95.64 191	93.80 199	96.27 192	91.74 207

testmvs		9.73 217	13.38 219	5.48 219	3.62 224	4.12 225	6.40 226	3.19 222	14.92 222	7.68 227	22.10 221	13.89 229	6.83 220	13.47 221	10.38 221	5.14 224	14.81 220

test123		9.37 218	12.26 220	6.00 218	3.32 225	4.06 226	6.39 227	3.41 221	13.20 223	10.48 226	16.43 222	16.22 228	6.76 221	11.37 222	10.40 220	5.62 223	14.10 221

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

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

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

RE-MVS-def										99.88 2

9.14												98.83 118

SR-MVS					99.62 85			99.47 75				99.40 57

Anonymous202405211			98.44 75		99.79 38	99.32 51	99.05 96	99.34 102	96.59 110		97.95 132	97.68 155	97.16 152	99.36 32	99.28 34	99.61 39	98.90 69

our_test_3					99.29 147	97.72 181	98.98 102

ambc			97.89 117		99.45 123	97.88 174	97.78 185		97.27 76	99.80 3	98.99 90	98.48 134	98.55 99	97.80 137	96.68 166	98.54 155	98.10 139

MTAPA										99.19 58		99.68 21

MTMP										99.20 56		99.54 41

Patchmatch-RL test							32.47 225

tmp_tt				65.28 216	82.24 222	71.50 223	70.81 224	23.21 220	96.14 134	81.70 224	85.98 219	92.44 189	49.84 219	95.81 186	94.36 197	83.86 222

XVS					99.77 43	99.07 77	99.46 45			98.95 92		99.37 61				99.33 73

X-MVStestdata					99.77 43	99.07 77	99.46 45			98.95 92		99.37 61				99.33 73

mPP-MVS					99.75 52							99.49 51

NP-MVS									93.07 196

Patchmtry						96.05 205	97.64 194	99.78 16		98.50 130

DeepMVS_CX						87.86 221	92.27 221	61.98 218	93.64 190	93.62 218	91.17 209	91.67 190	94.90 188	95.99 185		92.48 213	94.18 197

High-resolution multi-view benchmark