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 66	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 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 17	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 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 17	99.66 13	99.78 22	99.16 87	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 63	99.71 6	99.59 36	99.52 44	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 68	99.35 46	99.77 8	99.58 51	99.40 4	99.28 49	99.66 26	99.41 55	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 45	99.70 11	99.55 45	99.21 78	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 74	99.71 6	99.60 34	99.23 74	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 77	99.58 17	99.56 41	99.24 73	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 43	99.85 14	99.02 106	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 27	99.41 35	99.86 13	99.66 25	99.41 30	99.50 24	99.39 26	99.50 54	99.10 46

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 49	99.83 18	98.35 141	99.27 43	99.70 9	99.62 13	99.84 10	99.03 54

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 73	99.41 59	99.69 19	99.60 10	99.45 28	99.26 37	99.55 43	99.05 51
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	96.82 100	99.68 12	99.32 63	98.86 115	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 59	99.12 76	99.56 32	99.39 90	98.96 10	99.17 61	99.44 54	99.63 32	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 64	99.05 84	99.49 40	99.40 88	98.42 20	99.55 21	99.71 24	99.89 3	99.49 19	99.14 44	98.81 70	99.54 44	99.02 56
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 47	97.29 198	99.87 11	99.63 32	99.52 16	99.66 12	99.63 9	99.77 20	99.12 42

UA-Net		99.30 21	99.22 22	99.39 44	99.94 2	99.66 17	98.91 111	99.86 8	97.74 53	98.74 115	99.00 90	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 23	99.40 43	99.81 32	99.22 63	99.59 29	99.50 71	98.64 16	98.29 149	99.21 75	99.69 19	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 67	99.65 79	99.55 28	99.63 23	99.33 106	98.16 28	99.29 46	99.65 30	99.77 10	97.56 147	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 36	99.61 15	99.81 32	99.45 34	99.47 42	99.68 30	97.28 76	99.39 36	99.54 46	99.08 102	99.45 22	99.09 50	98.84 67	99.83 11	99.04 52

CSCG		99.23 24	99.15 24	99.32 56	99.83 23	99.45 34	98.97 103	99.21 127	98.83 13	99.04 83	99.43 56	99.64 30	99.26 44	98.85 76	98.20 106	99.62 38	99.62 6

Gipuma		99.22 26	98.86 40	99.64 12	99.70 68	99.24 57	99.17 85	99.63 43	99.52 2	99.89 1	96.54 178	99.14 91	99.93 1	99.42 32	99.15 41	99.52 47	99.04 52
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tfpnnormal		99.19 27	98.90 37	99.54 26	99.81 32	99.55 28	99.60 27	99.54 59	98.53 19	99.23 53	98.40 111	98.23 144	99.40 31	99.29 37	99.36 29	99.63 37	98.95 67

Baseline_NR-MVSNet		99.18 28	98.87 38	99.54 26	99.74 59	99.56 26	99.36 57	99.62 48	96.53 121	99.29 46	99.85 14	98.64 133	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 53	99.43 36	99.36 57	99.63 43	97.68 59	99.35 38	99.31 64	98.90 112	99.09 63	98.95 66	99.20 38	99.27 86	99.11 43

CS-MVS-test		99.16 29	98.78 45	99.60 17	99.80 38	99.72 9	99.69 16	99.73 23	95.88 143	99.51 26	98.53 108	99.54 42	99.21 48	99.24 40	99.43 23	99.66 34	99.15 41

CS-MVS		99.15 31	98.75 47	99.62 14	99.76 49	99.73 8	99.60 27	99.75 21	95.67 150	99.50 27	98.53 108	99.39 60	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 44	99.28 54	99.52 36	99.54 59	97.22 81	99.06 77	99.20 76	99.64 30	99.05 67	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 96	99.81 32	99.61 20	98.85 118	99.51 68	99.01 9	97.37 193	99.33 62	99.56 40	98.70 87	99.44 30	99.29 33	99.45 59	98.96 66

FC-MVSNet-train		99.13 34	99.05 28	99.21 62	99.87 16	99.57 25	99.67 18	99.60 50	96.75 106	98.28 150	99.48 50	99.52 44	98.10 124	99.47 27	99.37 28	99.76 22	99.21 36

NR-MVSNet		99.10 35	98.68 57	99.58 20	99.89 12	99.23 60	99.35 61	99.63 43	96.58 114	99.36 37	99.05 84	98.67 131	99.46 20	99.63 16	98.73 80	99.80 15	98.88 75

DVP-MVS++		99.09 36	99.25 18	98.90 102	99.53 108	99.37 44	99.17 85	99.48 76	98.28 25	97.95 170	99.54 46	99.88 4	98.13 123	99.08 51	98.94 56	99.15 99	99.65 2

DVP-MVS		99.09 36	99.07 27	99.12 74	99.55 101	99.40 39	99.36 57	99.44 87	97.75 50	98.23 153	99.23 72	99.80 8	98.97 71	99.08 51	98.96 53	99.19 94	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 55	99.54 26	99.75 53	99.33 49	99.29 69	99.64 42	96.75 106	99.48 30	99.30 66	98.69 126	99.26 44	98.94 68	98.76 76	99.78 19	99.02 56

ACMMPR		99.05 39	98.72 51	99.44 32	99.79 39	99.12 76	99.35 61	99.56 54	97.74 53	99.21 55	97.72 138	99.55 41	99.29 40	98.90 74	98.81 70	99.41 67	99.19 37

DU-MVS		99.04 40	98.59 61	99.56 22	99.74 59	99.23 60	99.29 69	99.63 43	96.58 114	99.55 21	99.05 84	98.68 128	99.36 35	99.03 61	98.60 87	99.77 20	98.97 61

TSAR-MVS + MP.		99.02 41	98.95 31	99.11 77	99.23 160	98.79 120	99.51 37	98.73 168	97.50 67	98.56 126	99.03 87	99.59 38	99.16 56	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 58	99.41 38	99.52 113	99.39 40	99.57 31	99.66 37	97.59 64	99.32 42	99.88 9	99.23 74	99.50 18	97.77 143	97.98 117	98.92 129	98.78 86

EG-PatchMatch MVS		99.01 42	98.77 46	99.28 61	99.64 82	98.90 113	98.81 124	99.27 117	96.55 118	99.71 6	99.31 64	99.66 25	99.17 54	99.28 39	99.11 44	99.10 101	98.57 102

PVSNet_Blended_VisFu		98.98 44	98.79 43	99.21 62	99.76 49	99.34 47	99.35 61	99.35 102	97.12 88	99.46 32	99.56 41	98.89 113	98.08 128	99.05 55	98.58 89	99.27 86	98.98 60

HFP-MVS		98.97 45	98.70 53	99.29 59	99.67 73	98.98 96	99.13 91	99.53 63	97.76 47	98.90 98	98.07 126	99.50 50	99.14 59	98.64 90	98.78 74	99.37 70	99.18 38

UniMVSNet_NR-MVSNet		98.97 45	98.46 71	99.56 22	99.76 49	99.34 47	99.29 69	99.61 49	96.55 118	99.55 21	99.05 84	97.96 152	99.36 35	98.84 77	98.50 95	99.81 14	98.97 61

casdiffmvs_mvg		98.96 47	98.87 38	99.07 80	99.82 28	99.36 45	99.36 57	99.22 124	98.13 30	97.74 177	99.42 57	99.46 53	98.59 95	98.39 102	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 47	98.45 74	99.56 22	99.88 14	99.70 11	99.68 17	99.78 16	94.15 184	98.97 87	98.26 118	99.21 78	99.35 37	99.30 36	99.14 42	99.73 25	99.40 20

SED-MVS		98.94 49	98.95 31	98.91 101	99.43 131	99.38 42	99.12 93	99.46 81	97.05 92	98.43 141	99.23 72	99.79 9	97.99 131	99.05 55	98.94 56	99.05 115	99.23 33

ACMMP_NAP		98.94 49	98.72 51	99.21 62	99.67 73	99.08 79	99.26 74	99.39 90	96.84 97	98.88 102	98.22 119	99.68 21	98.82 80	99.06 54	98.90 59	99.25 89	99.25 28

v1144		98.94 49	98.53 66	99.42 36	99.62 86	99.03 90	99.58 30	99.36 99	97.99 36	99.49 29	99.91 8	99.20 81	99.51 17	97.61 148	97.85 124	98.95 124	98.10 143

v8		98.94 49	98.60 59	99.35 53	99.54 105	99.39 40	99.55 33	99.67 34	97.48 68	99.13 69	99.81 19	99.10 98	99.39 33	97.86 138	97.89 122	98.81 138	98.66 95

SteuartSystems-ACMMP		98.94 49	98.52 67	99.43 35	99.79 39	99.13 75	99.33 65	99.55 56	96.17 136	99.04 83	97.53 144	99.65 29	99.46 20	99.04 60	98.76 76	99.44 62	99.35 22
Skip Steuart: Steuart Systems R&D Blog.
v1192		98.91 54	98.48 70	99.41 38	99.61 90	99.03 90	99.64 20	99.25 121	97.91 42	99.58 17	99.92 4	99.07 104	99.45 22	97.55 152	97.68 138	98.93 126	98.23 133

FMVSNet1		98.90 55	99.10 26	98.67 128	99.54 105	99.48 31	99.22 79	99.66 37	98.39 23	97.50 185	99.66 26	99.04 105	96.58 168	99.05 55	99.03 49	99.52 47	99.08 48

ACMM	96.66 11	98.90 55	98.44 76	99.44 32	99.74 59	98.95 102	99.47 42	99.55 56	97.66 61	99.09 74	96.43 180	99.41 55	99.35 37	98.95 66	98.67 83	99.45 59	99.03 54
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20231211		98.89 57	98.79 43	98.99 93	99.82 28	99.41 38	99.18 84	99.31 112	96.92 94	98.54 128	98.58 106	98.84 118	97.46 149	99.45 28	99.29 33	99.65 36	99.08 48

v1921920		98.89 57	98.46 71	99.39 44	99.58 94	99.04 88	99.64 20	99.17 133	97.91 42	99.64 15	99.92 4	98.99 110	99.44 25	97.44 159	97.57 147	98.84 136	98.35 123

GeoE		98.88 59	98.43 79	99.41 38	99.83 23	99.24 57	99.51 37	99.82 13	96.55 118	99.22 54	98.76 98	99.22 77	98.96 72	98.55 93	98.15 108	99.10 101	98.56 105

v144192		98.88 59	98.46 71	99.37 51	99.56 100	99.03 90	99.61 26	99.26 118	97.79 46	99.58 17	99.88 9	99.11 96	99.43 27	97.38 164	97.61 143	98.80 139	98.43 117

SMA-MVS		98.87 61	98.73 50	99.04 86	99.72 65	99.05 84	98.64 135	99.17 133	96.31 131	98.80 109	99.07 82	99.70 18	98.67 89	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 61	98.40 82	99.41 38	99.74 59	98.88 114	99.29 69	99.50 71	96.85 96	98.96 90	97.05 160	99.66 25	99.43 27	98.98 65	98.60 87	99.52 47	98.81 81
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DCV-MVSNet		98.86 63	98.57 64	99.19 65	99.86 20	99.67 15	99.39 51	99.71 27	97.53 66	98.69 118	95.85 191	98.48 136	97.75 141	99.57 21	99.41 25	99.72 26	99.48 16

v1240		98.86 63	98.41 81	99.38 49	99.59 92	99.05 84	99.65 19	99.14 138	97.68 59	99.66 13	99.93 3	98.72 125	99.45 22	97.38 164	97.72 136	98.79 140	98.35 123

CP-MVS		98.86 63	98.43 79	99.36 52	99.68 71	98.97 100	99.19 82	99.46 81	96.60 112	99.20 56	97.11 159	99.51 48	99.15 58	98.92 72	98.82 68	99.45 59	99.08 48

v2v482		98.85 66	98.40 82	99.38 49	99.65 79	98.98 96	99.55 33	99.39 90	97.92 41	99.35 38	99.85 14	99.14 91	99.39 33	97.50 154	97.78 127	98.98 121	97.60 159

DPE-MVS		98.84 67	98.69 55	99.00 90	99.05 179	99.26 55	99.19 82	99.35 102	95.85 145	98.74 115	99.27 68	99.66 25	98.30 116	98.90 74	98.93 58	99.37 70	99.00 58
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
OPM-MVS		98.84 67	98.59 61	99.12 74	99.52 113	98.50 145	99.13 91	99.22 124	97.76 47	98.76 111	98.70 100	99.61 35	98.90 75	98.67 88	98.37 100	99.19 94	98.57 102
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test20.03		98.84 67	98.74 49	98.95 96	99.77 44	99.33 49	99.21 81	99.46 81	97.29 75	98.88 102	99.65 30	99.10 98	97.07 159	99.11 47	98.76 76	99.32 79	97.98 147

casdiffmvs		98.84 67	98.75 47	98.94 100	99.75 53	99.21 64	99.33 65	99.04 148	98.04 32	97.46 188	99.72 23	99.72 15	98.60 93	98.30 114	98.37 100	99.48 56	97.92 149
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 67	98.33 88	99.44 32	99.78 42	98.98 96	99.39 51	99.55 56	95.41 155	98.90 98	97.51 145	99.68 21	99.44 25	99.03 61	98.81 70	99.57 42	98.91 71

RPSCF		98.84 67	98.81 42	98.89 104	99.37 139	98.95 102	98.51 147	98.85 161	97.73 55	98.33 146	98.97 92	99.14 91	98.95 73	99.18 43	98.68 82	99.31 80	98.99 59

ACMMP		98.82 73	98.33 88	99.39 44	99.77 44	99.14 74	99.37 54	99.54 59	96.47 125	99.03 85	96.26 184	99.52 44	99.28 42	98.92 72	98.80 73	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
V42		98.81 74	98.49 69	99.18 66	99.52 113	98.92 108	99.50 39	99.29 114	97.43 71	98.97 87	99.81 19	99.00 109	99.30 39	97.93 134	98.01 115	98.51 164	98.34 127

LS3D		98.79 75	98.52 67	99.12 74	99.64 82	99.09 78	99.24 77	99.46 81	97.75 50	98.93 96	97.47 147	98.23 144	97.98 132	99.36 33	99.30 32	99.46 57	98.42 118

MP-MVS		98.78 76	98.30 90	99.34 55	99.75 53	98.95 102	99.26 74	99.46 81	95.78 149	99.17 61	96.98 164	99.72 15	99.06 66	98.84 77	98.74 79	99.33 76	99.11 43
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
v148		98.77 77	98.45 74	99.15 70	99.68 71	98.94 106	99.49 40	99.31 112	97.95 38	98.91 97	99.65 30	99.62 34	99.18 51	97.99 132	97.64 142	98.33 169	97.38 164

test1111		98.75 78	98.14 103	99.46 31	99.86 20	99.63 19	99.47 42	99.68 30	98.34 24	98.76 111	99.66 26	90.92 198	99.23 46	99.77 5	99.71 5	99.75 23	98.95 67

ECVR-MVS		98.74 79	98.15 101	99.42 36	99.83 23	99.58 23	99.37 54	99.67 34	98.02 34	98.85 106	99.59 36	91.66 196	99.10 61	99.77 5	99.70 6	99.72 26	98.73 88

SD-MVS		98.73 80	98.54 65	98.95 96	99.14 169	98.76 123	98.46 151	99.14 138	97.71 57	98.56 126	98.06 128	99.61 35	98.85 79	98.56 92	97.74 133	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 81	98.60 59	98.87 106	99.67 73	99.33 49	99.15 88	99.26 118	96.99 93	97.90 173	98.19 121	99.74 12	98.29 117	97.69 146	98.96 53	98.96 122	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 82	98.09 108	99.39 44	99.76 49	99.07 80	99.30 68	99.51 68	94.76 166	99.18 60	96.70 173	99.51 48	99.20 49	98.79 82	98.71 81	99.39 68	99.11 43

pmmvs-eth3d		98.68 83	98.14 103	99.29 59	99.49 118	98.45 148	99.45 47	99.38 95	97.21 82	99.50 27	99.65 30	99.21 78	99.16 56	97.11 171	97.56 148	98.79 140	97.82 153

EU-MVSNet		98.68 83	98.94 34	98.37 149	99.14 169	98.74 125	99.64 20	98.20 193	98.21 26	99.17 61	99.66 26	99.18 84	99.08 64	99.11 47	98.86 62	95.00 206	98.83 78

PMVS	92.51 17	98.66 85	98.86 40	98.43 145	99.26 155	98.98 96	98.60 141	98.59 177	97.73 55	99.45 33	99.38 60	98.54 135	95.24 186	99.62 17	99.61 14	99.42 64	98.17 140
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DeepC-MVS_fast	97.38 8	98.65 86	98.34 87	99.02 89	99.33 143	98.29 155	98.99 101	98.71 170	97.40 72	99.31 43	98.20 120	99.40 58	98.54 102	98.33 111	98.18 107	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 86	98.35 86	99.00 90	99.59 92	98.70 128	98.90 115	99.36 99	97.97 37	99.09 74	96.55 177	99.09 100	97.97 133	98.70 87	98.65 85	99.12 100	98.81 81

TSAR-MVS + ACMM		98.64 88	98.58 63	98.72 122	99.17 167	98.63 134	98.69 130	99.10 145	97.69 58	98.30 148	99.12 80	99.38 61	98.70 87	98.45 97	97.51 150	98.35 168	99.25 28

DELS-MVS		98.63 89	98.70 53	98.55 141	99.24 159	99.04 88	98.96 104	98.52 180	96.83 99	98.38 143	99.58 39	99.68 21	97.06 160	98.74 86	98.44 97	99.10 101	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 90	98.40 82	98.89 104	99.57 99	98.80 119	98.63 136	99.35 102	96.82 100	98.60 122	98.85 97	99.08 102	98.09 126	98.31 112	98.21 104	99.08 107	98.72 89

EPP-MVSNet		98.61 91	98.19 98	99.11 77	99.86 20	99.60 21	99.44 48	99.53 63	97.37 73	96.85 203	98.69 101	93.75 189	99.18 51	99.22 41	99.35 30	99.82 13	99.32 24

3Dnovator+	97.85 5	98.61 91	98.14 103	99.15 70	99.62 86	98.37 152	99.10 94	99.51 68	98.04 32	98.98 86	96.07 188	98.75 124	98.55 100	98.51 95	98.40 98	99.17 96	98.82 79

X-MVS		98.59 93	97.99 114	99.30 58	99.75 53	99.07 80	99.17 85	99.50 71	96.62 110	98.95 92	93.95 207	99.37 62	99.11 60	98.94 68	98.86 62	99.35 74	99.09 47

MVS_111021_HR		98.58 94	98.26 93	98.96 95	99.32 146	98.81 117	98.48 149	98.99 153	96.81 102	99.16 64	98.07 126	99.23 74	98.89 77	98.43 99	98.27 103	98.90 131	98.24 132

MVS_0304		98.57 95	98.36 85	98.82 114	99.72 65	98.94 106	98.92 109	99.14 138	96.76 105	99.33 41	98.30 115	99.73 13	96.74 164	98.05 129	97.79 126	99.08 107	98.97 61

PM-MVS		98.57 95	98.24 95	98.95 96	99.26 155	98.59 137	99.03 98	98.74 167	96.84 97	99.44 34	99.13 79	98.31 143	98.75 85	98.03 130	98.21 104	98.48 165	98.58 100

PHI-MVS		98.57 95	98.20 97	99.00 90	99.48 120	98.91 110	98.68 131	99.17 133	94.97 162	99.27 51	98.33 113	99.33 66	98.05 129	98.82 80	98.62 86	99.34 75	98.38 121

HPM-MVS++		98.56 98	98.08 109	99.11 77	99.53 108	98.61 136	99.02 100	99.32 110	96.29 133	99.06 77	97.23 154	99.50 50	98.77 83	98.15 125	97.90 120	98.96 122	98.90 72

TSAR-MVS + GP.		98.54 99	98.29 92	98.82 114	99.28 153	98.59 137	97.73 192	99.24 123	95.93 142	98.59 123	99.07 82	99.17 85	98.86 78	98.44 98	98.10 110	99.26 88	98.72 89

UGNet		98.52 100	99.00 30	97.96 170	99.58 94	99.26 55	99.27 73	99.40 88	98.07 31	98.28 150	98.76 98	99.71 17	92.24 214	98.94 68	98.85 64	99.00 120	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		98.50 101	98.03 111	99.05 84	99.50 116	99.01 93	99.15 88	99.26 118	96.38 129	99.12 71	99.50 49	99.12 94	98.60 93	97.68 147	97.24 161	98.66 148	97.30 168

CLD-MVS		98.48 102	98.15 101	98.86 109	99.53 108	98.35 153	98.55 144	97.83 202	96.02 141	98.97 87	99.08 81	99.75 11	99.03 68	98.10 128	97.33 157	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		98.47 103	98.30 90	98.67 128	99.65 79	98.87 115	98.82 123	99.01 151	96.14 137	99.29 46	98.86 95	99.01 107	96.54 169	98.36 106	98.08 112	98.72 144	98.80 85

APD-MVS		98.47 103	97.97 115	99.05 84	99.64 82	98.91 110	98.94 106	99.45 86	94.40 177	98.77 110	97.26 153	99.41 55	98.21 120	98.67 88	98.57 92	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)		98.46 105	98.23 96	98.73 121	99.81 32	99.29 53	98.79 125	99.50 71	96.20 135	96.03 210	98.29 116	96.98 167	98.54 102	99.11 47	99.08 45	99.70 30	98.62 97

Fast-Effi-MVS+		98.42 106	97.79 123	99.15 70	99.69 70	98.66 132	98.94 106	99.68 30	94.49 171	99.05 79	98.06 128	98.86 115	98.48 105	98.18 122	97.78 127	99.05 115	98.54 108

ETV-MVS		98.41 107	97.76 124	99.17 67	99.58 94	99.01 93	98.91 111	99.50 71	93.33 197	99.31 43	96.82 170	98.42 139	98.17 122	99.13 46	99.08 45	99.54 44	98.56 105

MVS_111021_LR		98.39 108	98.11 106	98.71 124	99.08 176	98.54 143	98.23 174	98.56 179	96.57 116	99.13 69	98.41 110	98.86 115	98.65 91	98.23 120	97.87 123	98.65 150	98.28 129

pmmvs5		98.37 109	97.81 122	99.03 87	99.46 122	98.97 100	99.03 98	98.96 155	95.85 145	99.05 79	99.45 53	98.66 132	98.79 82	96.02 188	97.52 149	98.87 133	98.21 136

OMC-MVS		98.35 110	98.10 107	98.64 134	98.85 186	97.99 174	98.56 143	98.21 191	97.26 79	98.87 104	98.54 107	99.27 72	98.43 107	98.34 109	97.66 139	98.92 129	97.65 158

sasdasda		98.34 111	97.92 118	98.83 111	99.45 124	99.21 64	98.37 159	99.53 63	97.06 90	97.74 177	96.95 167	95.05 184	98.36 110	98.77 83	98.85 64	99.51 52	99.53 10

canonicalmvs		98.34 111	97.92 118	98.83 111	99.45 124	99.21 64	98.37 159	99.53 63	97.06 90	97.74 177	96.95 167	95.05 184	98.36 110	98.77 83	98.85 64	99.51 52	99.53 10

CHOSEN 1792x2688		98.31 113	98.02 112	98.66 130	99.55 101	98.57 140	99.38 53	99.25 121	98.42 20	98.48 136	99.58 39	99.85 6	98.31 115	95.75 191	95.71 186	96.96 193	98.27 131

CPTT-MVS		98.28 114	97.51 137	99.16 69	99.54 105	98.78 121	98.96 104	99.36 99	96.30 132	98.89 101	93.10 211	99.30 69	99.20 49	98.35 108	97.96 118	99.03 118	98.82 79

TinyColmap		98.27 115	97.62 134	99.03 87	99.29 151	97.79 183	98.92 109	98.95 156	97.48 68	99.52 24	98.65 103	97.86 154	98.90 75	98.34 109	97.27 159	98.64 151	95.97 188

diffmvs		98.26 116	98.16 99	98.39 147	99.61 90	98.78 121	98.79 125	98.61 175	97.94 39	97.11 202	99.51 48	99.52 44	97.61 145	96.55 180	96.93 167	98.61 153	97.87 151
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		98.26 116	97.57 135	99.06 81	99.42 134	97.98 176	98.83 120	98.85 161	97.57 65	99.59 16	99.15 78	98.59 134	98.99 70	97.42 160	96.08 185	98.69 147	96.23 186

SF-MVS		98.25 118	98.16 99	98.35 150	99.43 131	98.42 151	97.05 214	99.09 146	96.42 127	98.13 159	97.73 137	99.20 81	97.22 155	98.36 106	98.38 99	99.16 98	98.62 97

MCST-MVS		98.25 118	97.57 135	99.06 81	99.53 108	98.24 161	98.63 136	99.17 133	95.88 143	98.58 124	96.11 186	99.09 100	99.18 51	97.58 151	97.31 158	99.25 89	98.75 87

MGCFI-Net		98.23 120	97.93 117	98.58 136	99.44 128	99.20 70	98.37 159	99.54 59	97.14 86	96.70 207	96.98 164	95.04 186	97.92 137	98.75 85	98.89 60	99.52 47	99.55 9

IterMVS-LS		98.23 120	97.66 130	98.90 102	99.63 85	99.38 42	99.07 95	99.48 76	97.75 50	98.81 108	99.37 61	94.57 188	97.88 138	96.54 181	97.04 164	98.53 161	98.97 61
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TAPA-MVS	96.65 12	98.23 120	97.96 116	98.55 141	98.81 188	98.16 165	98.40 156	97.94 200	96.68 108	98.49 134	98.61 104	98.89 113	98.57 98	97.45 157	97.59 145	99.09 106	98.35 123
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CNVR-MVS		98.22 123	97.76 124	98.76 119	99.33 143	98.26 159	98.48 149	98.88 159	96.22 134	98.47 138	95.79 192	99.33 66	98.35 112	98.37 105	97.99 116	99.03 118	98.38 121

IS_MVSNet		98.20 124	98.00 113	98.44 144	99.82 28	99.48 31	99.25 76	99.56 54	95.58 152	93.93 222	97.56 143	96.52 172	98.27 118	99.08 51	99.20 38	99.80 15	98.56 105

DeepPCF-MVS	96.68 10	98.20 124	98.26 93	98.12 163	97.03 225	98.11 168	98.44 153	97.70 204	96.77 104	98.52 130	98.91 93	99.17 85	98.58 97	98.41 101	98.02 114	98.46 166	98.46 113

MSDG		98.20 124	97.88 121	98.56 139	99.33 143	97.74 184	98.27 171	98.10 194	97.20 84	98.06 163	98.59 105	99.16 87	98.76 84	98.39 102	97.71 137	98.86 135	96.38 183

testgi		98.18 127	98.44 76	97.89 172	99.78 42	99.23 60	98.78 127	99.21 127	97.26 79	97.41 190	97.39 150	99.36 65	92.85 210	98.82 80	98.66 84	99.31 80	98.35 123

Effi-MVS+		98.11 128	97.29 143	99.06 81	99.62 86	98.55 141	98.16 177	99.80 15	94.64 167	99.15 67	96.59 175	97.43 160	98.44 106	97.46 156	97.90 120	99.17 96	98.45 115

FA-MVS(training)		98.08 129	97.68 128	98.56 139	99.14 169	98.69 129	98.41 154	99.83 12	95.85 145	98.57 125	97.95 133	96.92 169	96.85 162	98.51 95	98.09 111	98.54 159	97.74 154

HyFIR lowres test		98.08 129	97.16 152	99.14 73	99.72 65	98.91 110	99.41 49	99.58 51	97.93 40	98.82 107	99.24 70	95.81 178	98.73 86	95.16 202	95.13 195	98.60 155	97.94 148

EIA-MVS		98.03 131	97.20 149	98.99 93	99.66 76	99.24 57	98.53 146	99.52 67	91.56 213	99.25 52	95.34 196	98.78 121	97.72 142	98.38 104	98.58 89	99.28 84	98.54 108

train_agg		97.99 132	97.26 144	98.83 111	99.43 131	98.22 163	98.91 111	99.07 147	94.43 175	97.96 169	96.42 181	99.30 69	98.81 81	97.39 162	96.62 173	98.82 137	98.47 111

MSLP-MVS++		97.99 132	97.64 133	98.40 146	98.91 184	98.47 147	97.12 212	98.78 165	96.49 123	98.48 136	93.57 209	99.12 94	98.51 104	98.31 112	98.58 89	98.58 157	98.95 67

CDPH-MVS		97.99 132	97.23 147	98.87 106	99.58 94	98.29 155	98.83 120	99.20 129	93.76 191	98.11 161	96.11 186	99.16 87	98.23 119	97.80 141	97.22 162	99.29 83	98.28 129

FMVSNet2		97.94 135	98.08 109	97.77 178	98.71 192	99.21 64	98.62 138	99.47 78	96.62 110	96.37 209	99.20 76	97.70 156	94.39 197	97.39 162	97.75 132	99.08 107	98.70 92

PVSNet_BlendedMVS		97.93 136	97.66 130	98.25 156	99.30 148	98.67 130	98.31 166	97.95 198	94.30 181	98.75 113	97.63 140	98.76 122	96.30 176	98.29 115	97.78 127	98.93 126	98.18 138

PVSNet_Blended		97.93 136	97.66 130	98.25 156	99.30 148	98.67 130	98.31 166	97.95 198	94.30 181	98.75 113	97.63 140	98.76 122	96.30 176	98.29 115	97.78 127	98.93 126	98.18 138

OpenMVS	97.26 9	97.88 138	97.17 151	98.70 125	99.50 116	98.55 141	98.34 164	99.11 143	93.92 189	98.90 98	95.04 201	98.23 144	97.38 152	98.11 127	98.12 109	98.95 124	98.23 133

pmmvs4		97.87 139	97.02 156	98.86 109	99.20 161	97.68 187	98.89 116	99.03 149	96.57 116	99.12 71	99.03 87	97.26 164	98.42 108	95.16 202	96.34 177	98.53 161	97.10 175

NCCC		97.84 140	96.96 158	98.87 106	99.39 137	98.27 158	98.46 151	99.02 150	96.78 103	98.73 117	91.12 215	98.91 111	98.57 98	97.83 140	97.49 151	99.04 117	98.33 128

Effi-MVS+-dtu		97.78 141	97.37 141	98.26 154	99.25 157	98.50 145	97.89 186	99.19 132	94.51 169	98.16 157	95.93 189	98.80 120	95.97 179	98.27 119	97.38 154	99.10 101	98.23 133

MDA-MVSNet-bldmvs		97.75 142	97.26 144	98.33 151	99.35 142	98.45 148	99.32 67	97.21 209	97.90 44	99.05 79	99.01 89	96.86 170	99.08 64	99.36 33	92.97 205	95.97 202	96.25 185

CDS-MVSNet		97.75 142	97.68 128	97.83 176	99.08 176	98.20 164	98.68 131	98.61 175	95.63 151	97.80 175	99.24 70	96.93 168	94.09 202	97.96 133	97.82 125	98.71 145	97.99 145
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CNLPA		97.75 142	97.26 144	98.32 153	98.58 200	97.86 179	97.80 188	98.09 195	96.49 123	98.49 134	96.15 185	98.08 147	98.35 112	98.00 131	97.03 165	98.61 153	97.21 172

PLC	95.63 15	97.73 145	97.01 157	98.57 138	99.10 173	97.80 182	97.72 193	98.77 166	96.34 130	98.38 143	93.46 210	98.06 148	98.66 90	97.90 136	97.65 141	98.77 142	97.90 150
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVS_Test		97.69 146	97.15 153	98.33 151	99.27 154	98.43 150	98.25 172	99.29 114	95.00 161	97.39 192	98.86 95	98.00 151	97.14 157	95.38 197	96.22 179	98.62 152	98.15 142

GBi-Net		97.69 146	97.75 126	97.62 179	98.71 192	99.21 64	98.62 138	99.33 106	94.09 185	95.60 212	98.17 123	95.97 175	94.39 197	99.05 55	99.03 49	99.08 107	98.70 92

test1		97.69 146	97.75 126	97.62 179	98.71 192	99.21 64	98.62 138	99.33 106	94.09 185	95.60 212	98.17 123	95.97 175	94.39 197	99.05 55	99.03 49	99.08 107	98.70 92

CANet_DTU		97.65 149	97.50 139	97.82 177	99.19 164	98.08 170	98.41 154	98.67 172	94.40 177	99.16 64	98.32 114	98.69 126	93.96 204	97.87 137	97.61 143	97.51 189	97.56 161

IterMVS-SCA-FT		97.63 150	96.86 160	98.52 143	99.48 120	98.71 127	98.84 119	98.91 157	96.44 126	99.16 64	99.56 41	95.54 180	97.95 134	95.68 194	95.07 198	96.76 194	97.03 178

TSAR-MVS + COLMAP		97.62 151	97.31 142	97.98 168	98.47 206	97.39 191	98.29 168	98.25 190	96.68 108	97.54 184	98.87 94	98.04 150	97.08 158	96.78 175	96.26 178	98.26 172	97.12 174

MS-PatchMatch		97.60 152	97.22 148	98.04 167	98.67 196	97.18 196	97.91 184	98.28 189	95.82 148	98.34 145	97.66 139	98.38 140	97.77 140	97.10 172	97.25 160	97.27 191	97.18 173

PCF-MVS	95.58 16	97.60 152	96.67 161	98.69 126	99.44 128	98.23 162	98.37 159	98.81 163	93.01 201	98.22 154	97.97 132	99.59 38	98.20 121	95.72 193	95.08 196	99.08 107	97.09 177
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HQP-MVS		97.58 154	96.65 164	98.66 130	99.30 148	97.99 174	97.88 187	98.65 173	94.58 168	98.66 119	94.65 205	99.15 90	98.59 95	96.10 186	95.59 187	98.90 131	98.50 110

DI_MVS_plusplus_trai		97.57 155	96.55 166	98.77 118	99.55 101	98.76 123	99.22 79	99.00 152	97.08 89	97.95 170	97.78 136	91.35 197	98.02 130	96.20 184	96.81 169	98.87 133	97.87 151

AdaColmap		97.57 155	96.57 165	98.74 120	99.25 157	98.01 172	98.36 163	98.98 154	94.44 174	98.47 138	92.44 212	97.91 153	98.62 92	98.19 121	97.74 133	98.73 143	97.28 169

baseline		97.50 157	97.51 137	97.50 183	99.18 165	97.38 192	98.00 180	98.00 197	96.52 122	97.49 186	99.28 67	99.43 54	95.31 185	95.27 199	96.22 179	96.99 192	98.47 111

IterMVS		97.40 158	96.67 161	98.25 156	99.45 124	98.66 132	98.87 117	98.73 168	96.40 128	98.94 95	99.56 41	95.26 182	97.58 146	95.38 197	94.70 200	95.90 203	96.72 181
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		97.38 159	96.15 174	98.82 114	99.39 137	98.34 154	98.65 134	98.88 159	90.80 220	98.86 105	92.35 213	95.13 183	98.09 126	98.84 77	98.88 61	99.06 114	98.71 91

CVMVSNet		97.38 159	97.39 140	97.37 186	98.58 200	97.72 185	98.70 129	97.42 207	97.21 82	95.95 211	99.46 52	93.31 192	97.38 152	97.60 149	97.78 127	96.18 199	98.66 95

new-patchmatchnet		97.26 161	96.12 175	98.58 136	99.55 101	98.63 134	99.14 90	97.04 211	98.80 14	99.19 58	99.92 4	99.19 83	98.92 74	95.51 196	87.04 214	97.66 186	93.73 204

MIMVSNet		97.24 162	97.15 153	97.36 187	99.03 180	98.52 144	98.55 144	99.73 23	94.94 165	94.94 219	97.98 131	97.37 162	93.66 205	97.60 149	97.34 156	98.23 175	96.29 184

PatchMatch-RL		97.24 162	96.45 169	98.17 160	98.70 195	97.57 190	97.31 207	98.48 183	94.42 176	98.39 142	95.74 193	96.35 174	97.88 138	97.75 144	97.48 152	98.24 174	95.87 189

thisisatest0530		97.20 164	95.95 179	98.66 130	99.46 122	98.84 116	98.29 168	99.20 129	94.51 169	98.25 152	97.42 148	85.03 213	97.68 143	98.43 99	98.56 93	99.08 107	98.89 74

tttt0517		97.18 165	95.92 180	98.65 133	99.49 118	98.92 108	98.29 168	99.20 129	94.37 179	98.17 155	97.37 151	84.72 216	97.68 143	98.55 93	98.56 93	99.10 101	98.95 67

MDTV_nov1_ep13_2view		97.12 166	96.19 173	98.22 159	99.13 172	98.05 171	99.24 77	99.47 78	97.61 62	99.15 67	99.59 36	99.01 107	98.40 109	94.87 205	90.14 208	93.91 209	94.04 203

MAR-MVS		97.12 166	96.28 172	98.11 164	98.94 182	97.22 194	97.65 197	99.38 95	90.93 219	98.15 158	95.17 198	97.13 165	96.48 172	97.71 145	97.40 153	98.06 179	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		96.99 168	96.46 168	97.61 181	98.98 181	97.89 177	97.54 201	99.76 19	93.43 195	96.55 208	94.93 202	98.06 148	94.32 200	96.93 173	96.50 175	98.53 161	97.47 162

FPMVS		96.97 169	97.20 149	96.70 203	97.75 217	96.11 208	97.72 193	95.47 215	97.13 87	98.02 165	97.57 142	96.67 171	92.97 209	99.00 64	98.34 102	98.28 171	95.58 191

TAMVS		96.95 170	96.94 159	96.97 198	99.07 178	97.67 189	97.98 182	97.12 210	95.04 160	95.41 215	99.27 68	95.57 179	94.09 202	97.32 166	97.11 163	98.16 177	96.59 182

FMVSNet3		96.85 171	96.67 161	97.06 192	97.56 220	99.01 93	97.99 181	99.33 106	94.09 185	95.60 212	98.17 123	95.97 175	93.26 208	94.76 207	96.22 179	98.59 156	98.46 113

GA-MVS		96.84 172	95.86 182	97.98 168	99.16 168	98.29 155	97.91 184	98.64 174	95.14 158	97.71 180	98.04 130	88.90 201	96.50 171	96.41 183	96.61 174	97.97 183	97.60 159

CHOSEN 280x420		96.80 173	96.30 171	97.39 184	99.09 174	96.52 200	98.76 128	99.29 114	93.88 190	97.65 181	98.34 112	93.66 190	96.29 178	98.28 117	97.73 135	93.27 212	95.70 190

gg-mvs-nofinetune		96.77 174	96.52 167	97.06 192	99.66 76	97.82 181	97.54 201	99.86 8	98.69 15	98.61 121	99.94 2	89.62 199	88.37 222	97.55 152	96.67 171	98.30 170	95.35 192

DPM-MVS		96.73 175	95.70 185	97.95 171	98.93 183	97.26 193	97.39 206	98.44 185	95.47 154	97.62 182	90.71 216	98.47 138	97.03 161	95.02 204	95.27 192	98.26 172	97.67 156

baseline1		96.72 176	95.40 187	98.26 154	99.53 108	98.81 117	98.32 165	98.80 164	94.96 163	96.78 206	96.50 179	84.87 215	96.68 167	97.42 160	97.91 119	99.46 57	97.33 167

N_pmnet		96.68 177	95.70 185	97.84 175	99.42 134	98.00 173	99.35 61	98.21 191	98.40 22	98.13 159	99.42 57	99.30 69	97.44 151	94.00 211	88.79 209	94.47 208	91.96 210

pmnet_mix02		96.61 178	95.32 188	98.11 164	99.41 136	97.68 187	99.05 96	97.59 205	98.16 28	99.05 79	99.48 50	99.11 96	98.32 114	92.36 215	87.67 211	95.26 205	92.80 208

new_pmnet		96.59 179	96.40 170	96.81 200	98.24 213	95.46 217	97.71 195	94.75 218	96.92 94	96.80 205	99.23 72	97.81 155	96.69 165	96.58 179	95.16 194	96.69 195	93.64 205

PMMVS		96.47 180	95.81 183	97.23 188	97.38 222	95.96 212	97.31 207	96.91 212	93.21 198	97.93 172	97.14 157	97.64 158	95.70 181	95.24 200	96.18 182	98.17 176	95.33 193

EPNet		96.44 181	96.08 176	96.86 199	99.32 146	97.15 197	97.69 196	99.32 110	93.67 192	98.11 161	95.64 194	93.44 191	89.07 220	96.86 174	96.83 168	97.67 185	98.97 61
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thres600view7		96.35 182	94.27 190	98.79 117	99.66 76	99.18 71	98.94 106	99.38 95	94.37 179	97.21 200	87.19 218	84.10 217	98.10 124	98.16 123	99.47 20	99.42 64	97.43 163

EPNet_dtu		96.31 183	95.96 178	96.72 202	99.18 165	95.39 218	97.03 215	99.13 142	93.02 200	99.35 38	97.23 154	97.07 166	90.70 219	95.74 192	95.08 196	94.94 207	98.16 141
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs3		96.30 184	95.87 181	96.80 201	97.66 219	96.48 201	97.93 183	93.80 219	93.40 196	98.54 128	98.27 117	97.50 159	97.37 154	97.49 155	93.11 204	95.52 204	94.85 197

PMMVS2		96.29 185	97.05 155	95.40 213	98.32 212	96.16 205	98.18 176	97.46 206	97.20 84	84.51 228	99.60 34	98.68 128	96.37 173	98.59 91	97.38 154	97.58 188	91.76 211

thres200		96.23 186	94.13 191	98.69 126	99.44 128	99.18 71	98.58 142	99.38 95	93.52 194	97.35 194	86.33 223	85.83 211	97.93 135	98.16 123	98.78 74	99.42 64	97.10 175

thres400		96.22 187	94.08 193	98.72 122	99.58 94	99.05 84	98.83 120	99.22 124	94.01 188	97.40 191	86.34 222	84.91 214	97.93 135	97.85 139	99.08 45	99.37 70	97.28 169

tfpn200view9		96.17 188	94.08 193	98.60 135	99.37 139	99.18 71	98.68 131	99.39 90	92.02 207	97.30 196	86.53 220	86.34 208	97.45 150	98.15 125	99.08 45	99.43 63	97.28 169

CMPMVS	74.71 19	96.17 188	96.06 177	96.30 207	97.41 221	94.52 221	94.83 223	95.46 216	91.57 212	97.26 199	94.45 206	98.33 142	94.98 188	98.28 117	97.59 145	97.86 184	97.68 155
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test2506		96.12 190	93.35 203	99.35 53	99.83 23	99.58 23	99.37 54	99.67 34	98.02 34	98.44 140	97.51 145	60.03 231	99.10 61	99.77 5	99.70 6	99.72 26	98.86 76

IB-MVS	95.85 14	95.87 191	94.88 189	97.02 195	99.09 174	98.25 160	97.16 209	97.38 208	91.97 210	97.77 176	83.61 225	97.29 163	92.03 217	97.16 170	97.66 139	98.66 148	98.20 137
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		95.81 192	95.77 184	95.85 212	99.20 161	98.15 167	97.49 205	98.50 181	92.24 203	92.74 225	96.82 170	92.70 193	88.60 221	97.31 168	97.01 166	98.57 158	96.19 187

thres100view900		95.74 193	93.66 202	98.17 160	99.37 139	98.59 137	98.10 178	98.33 188	92.02 207	97.30 196	86.53 220	86.34 208	96.69 165	96.77 176	98.47 96	99.24 91	96.89 179

ET-MVSNet_ETH3D		95.72 194	93.85 198	97.89 172	97.30 223	98.09 169	98.19 175	98.40 186	94.46 173	98.01 168	96.71 172	77.85 227	96.76 163	96.08 187	96.39 176	98.70 146	97.36 165

baseline2		95.58 195	94.04 195	97.38 185	98.80 189	98.16 165	97.14 210	97.80 203	91.45 214	97.49 186	95.22 197	83.63 218	94.98 188	96.42 182	96.66 172	98.06 179	96.76 180

PatchT		95.49 196	93.29 204	98.06 166	98.65 197	96.20 204	98.91 111	99.73 23	92.00 209	98.50 131	96.67 174	83.25 219	96.34 174	94.40 208	95.50 188	96.21 198	95.04 195

CR-MVSNet		95.38 197	93.01 205	98.16 162	98.63 198	95.85 214	97.64 198	99.78 16	91.27 216	98.50 131	96.84 169	82.16 220	96.34 174	94.40 208	95.50 188	98.05 181	95.04 195

MVSTER		95.38 197	93.99 197	97.01 196	98.83 187	98.95 102	96.62 216	99.14 138	92.17 205	97.44 189	97.29 152	77.88 226	91.63 218	97.45 157	96.18 182	98.41 167	97.99 145

MVS-HIRNet		94.86 199	93.83 199	96.07 208	97.07 224	94.00 222	94.31 224	99.17 133	91.23 218	98.17 155	98.69 101	97.43 160	95.66 182	94.05 210	91.92 206	92.04 219	89.46 219

test-LLR		94.79 200	93.71 200	96.06 209	99.20 161	96.16 205	96.31 218	98.50 181	89.98 221	94.08 220	97.01 161	86.43 206	92.20 215	96.76 177	95.31 190	96.05 200	94.31 200

RPMNet		94.72 201	92.01 210	97.88 174	98.56 203	95.85 214	97.78 189	99.70 29	91.27 216	98.33 146	93.69 208	81.88 221	94.91 191	92.60 213	94.34 202	98.01 182	94.46 199

gm-plane-assit		94.62 202	91.39 212	98.39 147	99.90 11	99.47 33	99.40 50	99.65 39	97.44 70	99.56 20	99.68 25	59.40 232	94.23 201	96.17 185	94.77 199	97.61 187	92.79 209

test-mter		94.62 202	94.02 196	95.32 214	97.72 218	96.75 198	96.23 220	95.67 214	89.83 224	93.23 224	96.99 163	85.94 210	92.66 213	97.32 166	96.11 184	96.44 196	95.22 194

FMVSNet5		94.57 204	92.77 206	96.67 204	97.88 215	98.72 126	97.54 201	98.70 171	88.64 225	95.11 217	86.90 219	81.77 222	93.27 207	97.92 135	98.07 113	97.50 190	97.34 166

SCA		94.53 205	91.95 211	97.55 182	98.58 200	97.86 179	98.49 148	99.68 30	95.11 159	99.07 76	95.87 190	87.24 204	96.53 170	89.77 218	87.08 213	92.96 214	90.69 214

MDTV_nov1_ep13		94.47 206	92.15 208	97.17 189	98.54 205	96.42 202	98.10 178	98.89 158	94.49 171	98.02 165	97.41 149	86.49 205	95.56 183	90.85 216	87.95 210	93.91 209	91.45 213

TESTMET0.1,1		94.44 207	93.71 200	95.30 215	97.84 216	96.16 205	96.31 218	95.32 217	89.98 221	94.08 220	97.01 161	86.43 206	92.20 215	96.76 177	95.31 190	96.05 200	94.31 200

ADS-MVSNet		94.41 208	92.13 209	97.07 191	98.86 185	96.60 199	98.38 158	98.47 184	96.13 139	98.02 165	96.98 164	87.50 203	95.87 180	89.89 217	87.58 212	92.79 216	90.27 216

tpm		93.89 209	91.21 213	97.03 194	98.36 210	96.07 209	97.53 204	99.65 39	92.24 203	98.64 120	97.23 154	74.67 230	94.64 195	92.68 212	90.73 207	93.37 211	94.82 198

PatchmatchNet		93.88 210	91.08 214	97.14 190	98.75 191	96.01 211	98.25 172	99.39 90	94.95 164	98.96 90	96.32 182	85.35 212	95.50 184	88.89 219	85.89 217	91.99 220	90.15 217
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		93.67 211	90.82 215	96.99 197	98.62 199	96.39 203	98.40 156	99.11 143	95.54 153	97.87 174	97.14 157	81.27 224	94.97 190	88.54 221	86.80 215	92.95 215	90.06 218

MVE	82.47 18	93.12 212	94.09 192	91.99 218	90.79 226	82.50 227	93.93 225	96.30 213	96.06 140	88.81 226	98.19 121	96.38 173	97.56 147	97.24 169	95.18 193	84.58 226	93.07 206
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CostFormer		92.75 213	89.49 217	96.55 205	98.78 190	95.83 216	97.55 200	98.59 177	91.83 211	97.34 195	96.31 183	78.53 225	94.50 196	86.14 222	84.92 218	92.54 217	92.84 207

tpmrst		92.45 214	89.48 218	95.92 211	98.43 208	95.03 219	97.14 210	97.92 201	94.16 183	97.56 183	97.86 135	81.63 223	93.56 206	85.89 223	82.86 219	90.91 224	88.95 221

dps		92.35 215	88.78 220	96.52 206	98.21 214	95.94 213	97.78 189	98.38 187	89.88 223	96.81 204	95.07 200	75.31 229	94.70 194	88.62 220	86.21 216	93.21 213	90.41 215

E-PMN		92.28 216	90.12 216	94.79 216	98.56 203	90.90 224	95.16 222	93.68 220	95.36 156	95.10 218	96.56 176	89.05 200	95.24 186	95.21 201	81.84 221	90.98 222	81.94 223

EMVS		91.84 217	89.39 219	94.70 217	98.44 207	90.84 225	95.27 221	93.53 221	95.18 157	95.26 216	95.62 195	87.59 202	94.77 193	94.87 205	80.72 222	90.95 223	80.88 224

tpm cat1		91.52 218	87.70 221	95.97 210	98.33 211	94.98 220	97.06 213	98.03 196	92.11 206	98.03 164	94.77 204	77.19 228	92.71 211	83.56 224	82.24 220	91.67 221	89.04 220

test_method		77.69 219	85.40 222	68.69 219	42.66 228	55.39 229	82.17 228	52.05 223	92.83 202	84.52 227	94.88 203	95.41 181	65.37 223	92.49 214	79.32 223	85.36 225	87.50 222

GG-mvs-BLEND		65.66 220	92.62 207	34.20 221	1.45 231	93.75 223	85.40 227	1.64 227	91.37 215	17.21 230	87.25 217	94.78 187	3.25 227	95.64 195	93.80 203	96.27 197	91.74 212

testmvs		9.73 221	13.38 223	5.48 223	3.62 229	4.12 230	6.40 231	3.19 226	14.92 226	7.68 232	22.10 226	13.89 234	6.83 225	13.47 225	10.38 225	5.14 229	14.81 225

test123		9.37 222	12.26 224	6.00 222	3.32 230	4.06 231	6.39 232	3.41 225	13.20 227	10.48 231	16.43 227	16.22 233	6.76 226	11.37 226	10.40 224	5.62 228	14.10 226

uanet_test		0.00 223	0.00 225	0.00 224	0.00 232	0.00 232	0.00 233	0.00 228	0.00 228	0.00 233	0.00 228	0.00 235	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

sosnet-low-res		0.00 223	0.00 225	0.00 224	0.00 232	0.00 232	0.00 233	0.00 228	0.00 228	0.00 233	0.00 228	0.00 235	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

sosnet		0.00 223	0.00 225	0.00 224	0.00 232	0.00 232	0.00 233	0.00 228	0.00 228	0.00 233	0.00 228	0.00 235	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

TPM-MVS					98.38 209	97.20 195	96.44 217			97.17 201	95.17 198	98.68 128	92.69 212			98.11 178	97.67 156
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												98.83 119

SR-MVS					99.62 86			99.47 78				99.40 58

Anonymous202405211			98.44 76		99.79 39	99.32 52	99.05 96	99.34 105	96.59 113		97.95 133	97.68 157	97.16 156	99.36 33	99.28 35	99.61 39	98.90 72

our_test_3					99.29 151	97.72 185	98.98 102

ambc			97.89 120		99.45 124	97.88 178	97.78 189		97.27 77	99.80 3	98.99 91	98.48 136	98.55 100	97.80 141	96.68 170	98.54 159	98.10 143

MTAPA										99.19 58		99.68 21

MTMP										99.20 56		99.54 42

Patchmatch-RL test							32.47 230

tmp_tt				65.28 220	82.24 227	71.50 228	70.81 229	23.21 224	96.14 137	81.70 229	85.98 224	92.44 194	49.84 224	95.81 190	94.36 201	83.86 227

XVS					99.77 44	99.07 80	99.46 45			98.95 92		99.37 62				99.33 76

X-MVStestdata					99.77 44	99.07 80	99.46 45			98.95 92		99.37 62				99.33 76

mPP-MVS					99.75 53							99.49 52

NP-MVS									93.07 199

Patchmtry						96.05 210	97.64 198	99.78 16		98.50 131

DeepMVS_CX						87.86 226	92.27 226	61.98 222	93.64 193	93.62 223	91.17 214	91.67 195	94.90 192	95.99 189		92.48 218	94.18 202

High-resolution multi-view benchmark