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 22	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 95	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 23	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 30	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 37	99.86 8	99.28 5	99.48 32	99.44 79	99.86 5	99.01 71	99.78 4	99.76 3	99.90 2	99.33 24

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 30	99.66 13	99.78 23	99.16 120	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 89	99.71 6	99.59 48	99.52 67	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 84	99.35 48	99.77 8	99.58 51	99.40 4	99.28 50	99.66 35	99.41 82	99.55 15	99.74 8	99.65 8	99.70 30	99.25 29

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 67	99.70 11	99.55 62	99.21 110	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	97.30 104	99.71 6	99.60 46	99.23 105	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 12	99.88 3	97.27 107	99.58 17	99.56 58	99.24 104	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 29	99.49 30	99.63 24	99.65 39	98.88 11	99.31 44	99.85 14	99.02 141	99.23 47	99.60 18	99.58 17	99.80 15	99.22 36

MIMVSNet1		99.46 14	99.34 10	99.60 17	99.83 24	99.68 14	99.74 15	99.71 27	98.20 46	99.41 37	99.86 13	99.66 41	99.41 30	99.50 24	99.39 26	99.50 55	99.10 48

TransMVSNet (Re)		99.45 15	99.32 13	99.61 15	99.88 14	99.60 21	99.75 12	99.63 43	99.11 7	99.28 50	99.83 19	98.35 177	99.27 44	99.70 9	99.62 13	99.84 10	99.03 56

ACMH	97.81 6	99.44 16	99.33 11	99.56 22	99.81 33	99.42 37	99.73 16	99.58 51	99.02 8	99.10 78	99.41 84	99.69 32	99.60 10	99.45 28	99.26 37	99.55 43	99.05 53
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CP-MVSNet		99.39 17	99.04 31	99.80 6	99.91 9	99.70 11	99.75 12	99.88 3	96.82 133	99.68 12	99.32 92	98.86 150	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 31	99.74 71	99.12 98	99.56 34	99.39 92	98.96 10	99.17 66	99.44 79	99.63 49	99.58 11	99.48 26	99.27 36	99.60 40	98.81 82
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 30	99.73 77	99.05 109	99.49 43	99.40 90	98.42 34	99.55 21	99.71 27	99.89 3	99.49 19	99.14 44	98.81 72	99.54 44	99.02 58
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 58	99.87 16	99.65 18	99.63 24	99.75 21	97.76 72	97.29 236	99.87 11	99.63 49	99.52 16	99.66 12	99.63 9	99.77 20	99.12 44

UA-Net		99.30 21	99.22 22	99.39 45	99.94 2	99.66 17	98.91 142	99.86 8	97.74 78	98.74 122	99.00 124	99.60 56	99.17 56	99.50 24	99.39 26	99.70 30	99.64 3

ACMH+	97.53 7	99.29 22	99.20 23	99.40 44	99.81 33	99.22 74	99.59 31	99.50 72	98.64 26	98.29 173	99.21 106	99.69 32	99.57 12	99.53 23	99.33 31	99.66 34	98.81 82

FE-MVSNET2		99.25 23	99.00 33	99.55 26	99.77 50	99.40 39	99.76 10	99.54 59	98.10 51	99.50 28	99.71 27	99.81 12	99.39 33	98.44 110	99.00 53	99.36 77	98.50 114

Vis-MVSNet		99.25 23	99.32 13	99.17 73	99.65 102	99.55 28	99.63 24	99.33 112	98.16 48	99.29 47	99.65 39	99.77 20	97.56 186	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 25	98.91 45	99.61 15	99.81 33	99.45 34	99.47 46	99.68 30	97.28 106	99.39 38	99.54 64	99.08 135	99.45 22	99.09 50	98.84 68	99.83 11	99.04 54

CSCG		99.23 25	99.15 24	99.32 57	99.83 24	99.45 34	98.97 133	99.21 138	98.83 16	99.04 89	99.43 81	99.64 47	99.26 45	98.85 77	98.20 119	99.62 38	99.62 6

Gipuma		99.22 27	98.86 51	99.64 12	99.70 84	99.24 68	99.17 99	99.63 43	99.52 2	99.89 1	96.54 219	99.14 124	99.93 1	99.42 32	99.15 41	99.52 47	99.04 54
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tfpnnormal		99.19 28	98.90 46	99.54 27	99.81 33	99.55 28	99.60 29	99.54 59	98.53 32	99.23 54	98.40 148	98.23 180	99.40 31	99.29 37	99.36 29	99.63 37	98.95 68

Baseline_NR-MVSNet		99.18 29	98.87 48	99.54 27	99.74 71	99.56 26	99.36 62	99.62 48	96.53 153	99.29 47	99.85 14	98.64 169	99.40 31	99.03 61	99.63 9	99.83 11	98.86 77

thisisatest0515		99.16 30	98.94 40	99.41 39	99.75 65	99.43 36	99.36 62	99.63 43	97.68 84	99.35 40	99.31 93	98.90 147	99.09 65	98.95 66	99.20 38	99.27 91	99.11 45

SPE-MVS-test		99.16 30	98.78 58	99.60 17	99.80 39	99.72 9	99.69 17	99.73 23	95.88 177	99.51 27	98.53 143	99.54 63	99.21 50	99.24 40	99.43 23	99.66 34	99.15 43

CS-MVS		99.15 32	98.75 63	99.62 14	99.76 60	99.73 8	99.60 29	99.75 21	95.67 185	99.50 28	98.53 143	99.39 87	99.29 41	99.21 42	99.46 22	99.79 18	99.29 27

APDe-MVS		99.15 32	98.95 37	99.39 45	99.77 50	99.28 60	99.52 38	99.54 59	97.22 111	99.06 83	99.20 107	99.64 47	99.05 69	99.14 44	99.02 52	99.39 70	99.17 40
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
WB-MVS		99.14 34	99.31 15	98.95 112	99.81 33	99.61 20	98.85 151	99.51 69	99.01 9	97.37 230	99.33 90	99.56 61	98.70 97	99.44 30	99.29 33	99.45 60	98.96 67

FC-MVSNet-train		99.13 35	99.05 28	99.21 65	99.87 16	99.57 25	99.67 19	99.60 50	96.75 138	98.28 174	99.48 70	99.52 67	98.10 157	99.47 27	99.37 28	99.76 22	99.21 37

E6new		99.12 36	99.05 28	99.20 69	99.78 44	99.33 52	99.32 74	99.34 109	98.86 13	98.62 129	99.74 24	99.83 8	98.98 73	98.53 104	98.64 92	99.16 108	98.46 118

E6		99.12 36	99.05 28	99.20 69	99.78 44	99.33 52	99.32 74	99.34 109	98.86 13	98.62 129	99.74 24	99.83 8	98.98 73	98.53 104	98.64 92	99.16 108	98.46 118

NR-MVSNet		99.10 38	98.68 75	99.58 20	99.89 12	99.23 71	99.35 66	99.63 43	96.58 146	99.36 39	99.05 118	98.67 167	99.46 20	99.63 16	98.73 86	99.80 15	98.88 76

DVP-MVS++		99.09 39	99.25 18	98.90 120	99.53 140	99.37 46	99.17 99	99.48 77	98.28 44	97.95 201	99.54 64	99.88 4	98.13 156	99.08 51	98.94 57	99.15 111	99.65 2

DVP-MVS		99.09 39	99.07 27	99.12 80	99.55 131	99.40 39	99.36 62	99.44 89	97.75 75	98.23 177	99.23 103	99.80 16	98.97 75	99.08 51	98.96 54	99.19 100	99.25 29
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 41	98.69 73	99.54 27	99.75 65	99.33 52	99.29 79	99.64 42	96.75 138	99.48 32	99.30 95	98.69 162	99.26 45	98.94 68	98.76 82	99.78 19	99.02 58

casdiffseed414692147		99.06 42	98.93 44	99.21 65	99.79 40	99.26 62	99.49 43	99.35 105	98.20 46	98.46 157	99.68 30	99.82 10	98.84 86	98.72 94	98.36 112	99.34 79	98.45 123

Casviewmamba		99.05 43	99.04 31	99.07 88	99.77 50	99.38 43	99.29 79	99.21 138	98.63 27	97.91 204	99.46 73	99.69 32	98.73 94	98.76 90	98.77 79	99.52 47	98.57 105

ACMMPR		99.05 43	98.72 67	99.44 33	99.79 40	99.12 98	99.35 66	99.56 54	97.74 78	99.21 57	97.72 179	99.55 62	99.29 41	98.90 75	98.80 74	99.41 68	99.19 38

DU-MVS		99.04 45	98.59 80	99.56 22	99.74 71	99.23 71	99.29 79	99.63 43	96.58 146	99.55 21	99.05 118	98.68 164	99.36 36	99.03 61	98.60 95	99.77 20	98.97 63

usedtu_dtu_shiyan2		99.03 46	98.84 54	99.27 63	99.87 16	99.20 81	99.52 38	98.77 193	98.46 33	99.52 24	99.84 18	99.65 45	98.85 84	98.75 91	97.80 147	99.05 131	98.15 159

MED-MVS		99.02 47	98.99 35	99.06 92	99.68 90	99.17 88	99.02 124	99.37 101	98.30 43	98.53 143	99.59 48	99.49 76	98.38 138	98.84 78	98.77 79	99.38 72	98.74 89

TSAR-MVS + MP.		99.02 47	98.95 37	99.11 84	99.23 195	98.79 147	99.51 40	98.73 197	97.50 95	98.56 139	99.03 121	99.59 57	99.16 58	99.29 37	99.17 40	99.50 55	99.24 33
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 49	98.66 76	99.41 39	99.52 145	99.39 41	99.57 33	99.66 37	97.59 90	99.32 43	99.88 9	99.23 105	99.50 18	97.77 165	97.98 135	98.92 155	98.78 87

EG-PatchMatch MVS		99.01 49	98.77 62	99.28 62	99.64 107	98.90 138	98.81 161	99.27 123	96.55 150	99.71 6	99.31 93	99.66 41	99.17 56	99.28 39	99.11 44	99.10 114	98.57 105

hybridcas		98.99 51	98.99 35	98.98 109	99.77 50	99.34 49	99.30 77	99.15 152	98.66 25	97.64 215	99.45 76	99.70 30	98.61 105	98.61 99	98.79 76	99.41 68	98.40 128

viewmacassd2359aftdt		98.99 51	98.89 47	99.12 80	99.78 44	99.27 61	99.21 93	99.26 125	98.73 23	98.30 171	99.61 43	99.82 10	98.94 78	98.26 134	98.29 114	99.20 99	98.24 145

E4		98.98 53	98.87 48	99.11 84	99.78 44	99.26 62	99.20 95	99.27 123	98.81 17	98.57 137	99.68 30	99.81 12	98.69 99	98.08 144	98.23 116	99.15 111	98.24 145

PVSNet_Blended_VisFu		98.98 53	98.79 56	99.21 65	99.76 60	99.34 49	99.35 66	99.35 105	97.12 120	99.46 34	99.56 58	98.89 148	98.08 161	99.05 55	98.58 97	99.27 91	98.98 62

HFP-MVS		98.97 55	98.70 71	99.29 60	99.67 94	98.98 122	99.13 110	99.53 64	97.76 72	98.90 104	98.07 163	99.50 74	99.14 61	98.64 98	98.78 77	99.37 73	99.18 39

UniMVSNet_NR-MVSNet		98.97 55	98.46 93	99.56 22	99.76 60	99.34 49	99.29 79	99.61 49	96.55 150	99.55 21	99.05 118	97.96 188	99.36 36	98.84 78	98.50 104	99.81 14	98.97 63

casdiffmvs_mvg		98.96 57	98.87 48	99.07 88	99.82 29	99.36 47	99.36 62	99.22 135	98.13 50	97.74 209	99.42 82	99.46 80	98.59 108	98.39 115	98.95 56	99.71 29	98.39 130
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 57	98.45 96	99.56 22	99.88 14	99.70 11	99.68 18	99.78 16	94.15 226	98.97 93	98.26 155	99.21 110	99.35 38	99.30 36	99.14 42	99.73 25	99.40 20

SED-MVS		98.94 59	98.95 37	98.91 119	99.43 164	99.38 43	99.12 113	99.46 82	97.05 125	98.43 160	99.23 103	99.79 17	97.99 167	99.05 55	98.94 57	99.05 131	99.23 34

ACMMP_NAP		98.94 59	98.72 67	99.21 65	99.67 94	99.08 104	99.26 86	99.39 92	96.84 130	98.88 109	98.22 156	99.68 36	98.82 87	99.06 54	98.90 60	99.25 94	99.25 29

v1144		98.94 59	98.53 87	99.42 37	99.62 111	99.03 116	99.58 32	99.36 102	97.99 58	99.49 31	99.91 8	99.20 113	99.51 17	97.61 173	97.85 145	98.95 148	98.10 164

v8		98.94 59	98.60 78	99.35 54	99.54 137	99.39 41	99.55 35	99.67 34	97.48 96	99.13 74	99.81 20	99.10 131	99.39 33	97.86 156	97.89 143	98.81 166	98.66 98

SteuartSystems-ACMMP		98.94 59	98.52 89	99.43 36	99.79 40	99.13 96	99.33 72	99.55 56	96.17 170	99.04 89	97.53 185	99.65 45	99.46 20	99.04 60	98.76 82	99.44 63	99.35 22
Skip Steuart: Steuart Systems R&D Blog.
E5new		98.92 64	98.78 58	99.07 88	99.77 50	99.25 66	99.16 103	99.23 133	98.80 18	98.58 134	99.61 43	99.81 12	98.50 128	97.83 159	98.01 131	99.17 103	98.17 155

E5		98.92 64	98.78 58	99.07 88	99.77 50	99.25 66	99.16 103	99.23 133	98.80 18	98.58 134	99.61 43	99.81 12	98.50 128	97.83 159	98.01 131	99.17 103	98.17 155

viewdifsd2359ckpt11		98.92 64	98.94 40	98.90 120	99.71 82	99.16 90	99.16 103	98.82 188	98.78 21	98.12 187	99.68 30	99.78 18	98.52 123	98.80 85	98.11 124	99.05 131	98.25 143

viewmsd2359difaftdt		98.92 64	98.94 40	98.90 120	99.71 82	99.16 90	99.16 103	98.82 188	98.78 21	98.12 187	99.68 30	99.78 18	98.52 123	98.80 85	98.11 124	99.05 131	98.25 143

v1192		98.91 68	98.48 92	99.41 39	99.61 115	99.03 116	99.64 21	99.25 129	97.91 64	99.58 17	99.92 4	99.07 137	99.45 22	97.55 178	97.68 160	98.93 151	98.23 148

FMVSNet1		98.90 69	99.10 26	98.67 153	99.54 137	99.48 31	99.22 91	99.66 37	98.39 37	97.50 222	99.66 35	99.04 140	96.58 210	99.05 55	99.03 49	99.52 47	99.08 50

ACMM	96.66 11	98.90 69	98.44 98	99.44 33	99.74 71	98.95 128	99.47 46	99.55 56	97.66 87	99.09 79	96.43 221	99.41 82	99.35 38	98.95 66	98.67 89	99.45 60	99.03 56
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20231211		98.89 71	98.79 56	98.99 107	99.82 29	99.41 38	99.18 98	99.31 118	96.92 127	98.54 141	98.58 141	98.84 153	97.46 189	99.45 28	99.29 33	99.65 36	99.08 50

v1921920		98.89 71	98.46 93	99.39 45	99.58 123	99.04 114	99.64 21	99.17 147	97.91 64	99.64 15	99.92 4	98.99 145	99.44 25	97.44 189	97.57 169	98.84 164	98.35 133

GeoE		98.88 73	98.43 103	99.41 39	99.83 24	99.24 68	99.51 40	99.82 13	96.55 150	99.22 56	98.76 132	99.22 109	98.96 76	98.55 102	98.15 121	99.10 114	98.56 109

v144192		98.88 73	98.46 93	99.37 52	99.56 130	99.03 116	99.61 27	99.26 125	97.79 70	99.58 17	99.88 9	99.11 129	99.43 27	97.38 194	97.61 165	98.80 167	98.43 126

aaEdge-Enhanced		98.87 75	98.78 58	98.98 109	99.67 94	99.13 96	99.34 70	98.89 179	97.44 98	98.49 150	99.59 48	99.54 63	98.49 130	98.48 108	98.52 103	99.01 140	98.74 89

SMA-MVS		98.87 75	98.73 66	99.04 98	99.72 80	99.05 109	98.64 176	99.17 147	96.31 165	98.80 116	99.07 114	99.70 30	98.67 100	98.93 71	98.82 69	99.23 97	99.23 34
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 75	98.40 107	99.41 39	99.74 71	98.88 140	99.29 79	99.50 72	96.85 129	98.96 96	97.05 201	99.66 41	99.43 27	98.98 65	98.60 95	99.52 47	98.81 82
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DCV-MVSNet		98.86 78	98.57 85	99.19 71	99.86 21	99.67 15	99.39 56	99.71 27	97.53 94	98.69 126	95.85 233	98.48 172	97.75 180	99.57 21	99.41 25	99.72 26	99.48 16

v1240		98.86 78	98.41 105	99.38 50	99.59 120	99.05 109	99.65 20	99.14 153	97.68 84	99.66 13	99.93 3	98.72 161	99.45 22	97.38 194	97.72 158	98.79 168	98.35 133

CP-MVS		98.86 78	98.43 103	99.36 53	99.68 90	98.97 126	99.19 96	99.46 82	96.60 144	99.20 59	97.11 200	99.51 72	99.15 60	98.92 72	98.82 69	99.45 60	99.08 50

E3new		98.85 81	98.72 67	99.01 102	99.73 77	99.20 81	99.08 115	99.18 145	98.57 28	98.50 146	99.54 64	99.73 23	98.52 123	97.87 154	97.97 136	99.06 128	98.14 162

E3		98.85 81	98.72 67	99.01 102	99.73 77	99.20 81	99.08 115	99.18 145	98.57 28	98.51 145	99.54 64	99.73 23	98.52 123	97.86 156	97.97 136	99.06 128	98.14 162

v2v482		98.85 81	98.40 107	99.38 50	99.65 102	98.98 122	99.55 35	99.39 92	97.92 63	99.35 40	99.85 14	99.14 124	99.39 33	97.50 182	97.78 148	98.98 145	97.60 192

DPE-MVS		98.84 84	98.69 73	99.00 104	99.05 214	99.26 62	99.19 96	99.35 105	95.85 179	98.74 122	99.27 97	99.66 41	98.30 147	98.90 75	98.93 59	99.37 73	99.00 60
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
OPM-MVS		98.84 84	98.59 80	99.12 80	99.52 145	98.50 179	99.13 110	99.22 135	97.76 72	98.76 118	98.70 134	99.61 52	98.90 80	98.67 96	98.37 110	99.19 100	98.57 105
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test20.03		98.84 84	98.74 65	98.95 112	99.77 50	99.33 52	99.21 93	99.46 82	97.29 105	98.88 109	99.65 39	99.10 131	97.07 202	99.11 47	98.76 82	99.32 84	97.98 173

casdiffmvs		98.84 84	98.75 63	98.94 116	99.75 65	99.21 75	99.33 72	99.04 166	98.04 54	97.46 225	99.72 26	99.72 27	98.60 106	98.30 127	98.37 110	99.48 57	97.92 177
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 84	98.33 114	99.44 33	99.78 44	98.98 122	99.39 56	99.55 56	95.41 190	98.90 104	97.51 186	99.68 36	99.44 25	99.03 61	98.81 72	99.57 42	98.91 72

RPSCF		98.84 84	98.81 55	98.89 125	99.37 173	98.95 128	98.51 188	98.85 185	97.73 80	98.33 168	98.97 126	99.14 124	98.95 77	99.18 43	98.68 88	99.31 85	98.99 61

ACMMP		98.82 90	98.33 114	99.39 45	99.77 50	99.14 94	99.37 59	99.54 59	96.47 157	99.03 91	96.26 225	99.52 67	99.28 43	98.92 72	98.80 74	99.37 73	99.16 41
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 91	98.41 105	99.27 63	99.55 131	99.09 101	99.61 27	99.46 82	97.15 117	98.70 125	99.18 109	99.17 117	99.23 47	97.94 149	98.48 105	99.10 114	97.88 179

V42		98.81 91	98.49 91	99.18 72	99.52 145	98.92 133	99.50 42	99.29 120	97.43 100	98.97 93	99.81 20	99.00 144	99.30 40	97.93 150	98.01 131	98.51 197	98.34 137

viewdifsd2359ckpt07		98.79 93	98.85 53	98.72 145	99.74 71	99.14 94	98.97 133	98.91 177	98.84 15	98.32 170	99.48 70	99.73 23	98.40 135	98.29 128	98.12 122	97.96 218	98.31 139

LS3D		98.79 93	98.52 89	99.12 80	99.64 107	99.09 101	99.24 89	99.46 82	97.75 75	98.93 102	97.47 188	98.23 180	97.98 169	99.36 33	99.30 32	99.46 58	98.42 127

MP-MVS		98.78 95	98.30 116	99.34 56	99.75 65	98.95 128	99.26 86	99.46 82	95.78 183	99.17 66	96.98 205	99.72 27	99.06 68	98.84 78	98.74 85	99.33 81	99.11 45
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
viewmanbaseed2359cas		98.77 96	98.64 77	98.93 117	99.70 84	99.16 90	98.95 137	99.09 162	98.35 40	98.14 184	99.33 90	99.69 32	98.63 103	97.91 152	97.90 140	99.08 121	98.15 159

v148		98.77 96	98.45 96	99.15 76	99.68 90	98.94 132	99.49 43	99.31 118	97.95 60	98.91 103	99.65 39	99.62 51	99.18 53	97.99 147	97.64 164	98.33 202	97.38 198

test1111		98.75 98	98.14 134	99.46 32	99.86 21	99.63 19	99.47 46	99.68 30	98.34 41	98.76 118	99.66 35	90.92 240	99.23 47	99.77 5	99.71 5	99.75 23	98.95 68

viewcassd2359sk11		98.74 99	98.58 82	98.93 117	99.69 87	99.16 90	98.98 130	99.10 160	98.36 38	98.45 158	99.39 86	99.61 52	98.38 138	97.68 170	97.77 153	98.99 143	98.08 166

ECVR-MVS		98.74 99	98.15 131	99.42 37	99.83 24	99.58 23	99.37 59	99.67 34	98.02 56	98.85 113	99.59 48	91.66 238	99.10 63	99.77 5	99.70 6	99.72 26	98.73 91

SD-MVS		98.73 101	98.54 86	98.95 112	99.14 204	98.76 151	98.46 192	99.14 153	97.71 82	98.56 139	98.06 165	99.61 52	98.85 84	98.56 101	97.74 155	99.54 44	99.32 25
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		98.72 102	98.60 78	98.87 127	99.67 94	99.33 52	99.15 107	99.26 125	96.99 126	97.90 205	98.19 158	99.74 22	98.29 148	97.69 169	98.96 54	98.96 146	99.27 28
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		98.69 103	98.09 139	99.39 45	99.76 60	99.07 105	99.30 77	99.51 69	94.76 204	99.18 63	96.70 214	99.51 72	99.20 51	98.79 87	98.71 87	99.39 70	99.11 45

pmmvs-eth3d		98.68 104	98.14 134	99.29 60	99.49 150	98.45 182	99.45 51	99.38 97	97.21 112	99.50 28	99.65 39	99.21 110	99.16 58	97.11 202	97.56 170	98.79 168	97.82 182

EU-MVSNet		98.68 104	98.94 40	98.37 181	99.14 204	98.74 155	99.64 21	98.20 227	98.21 45	99.17 66	99.66 35	99.18 116	99.08 66	99.11 47	98.86 63	95.00 250	98.83 79

PMVS	92.51 17	98.66 106	98.86 51	98.43 176	99.26 190	98.98 122	98.60 182	98.59 210	97.73 80	99.45 35	99.38 87	98.54 171	95.24 230	99.62 17	99.61 14	99.42 65	98.17 155
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DeepC-MVS_fast	97.38 8	98.65 107	98.34 113	99.02 101	99.33 177	98.29 189	98.99 127	98.71 200	97.40 101	99.31 44	98.20 157	99.40 85	98.54 121	98.33 124	98.18 120	99.23 97	98.58 103
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	98.65 107	98.35 112	99.00 104	99.59 120	98.70 159	98.90 146	99.36 102	97.97 59	99.09 79	96.55 218	99.09 133	97.97 170	98.70 95	98.65 91	99.12 113	98.81 82

TSAR-MVS + ACMM		98.64 109	98.58 82	98.72 145	99.17 202	98.63 168	98.69 171	99.10 160	97.69 83	98.30 171	99.12 112	99.38 89	98.70 97	98.45 109	97.51 173	98.35 201	99.25 29

E2		98.63 110	98.44 98	98.86 130	99.65 102	99.12 98	98.88 148	99.03 167	98.10 51	98.40 161	99.27 97	99.48 78	98.24 151	97.51 181	97.56 170	98.93 151	98.05 167

DELS-MVS		98.63 110	98.70 71	98.55 171	99.24 194	99.04 114	98.96 135	98.52 214	96.83 132	98.38 163	99.58 53	99.68 36	97.06 203	98.74 93	98.44 107	99.10 114	98.59 102
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		98.62 112	98.40 107	98.89 125	99.57 129	98.80 145	98.63 177	99.35 105	96.82 133	98.60 132	98.85 131	99.08 135	98.09 159	98.31 125	98.21 117	99.08 121	98.72 92

EPP-MVSNet		98.61 113	98.19 128	99.11 84	99.86 21	99.60 21	99.44 52	99.53 64	97.37 102	96.85 251	98.69 135	93.75 231	99.18 53	99.22 41	99.35 30	99.82 13	99.32 25

3Dnovator+	97.85 5	98.61 113	98.14 134	99.15 76	99.62 111	98.37 186	99.10 114	99.51 69	98.04 54	98.98 92	96.07 230	98.75 160	98.55 118	98.51 106	98.40 108	99.17 103	98.82 80

viewdifsd2359ckpt13		98.60 115	98.39 110	98.85 134	99.67 94	99.05 109	98.77 166	99.05 165	97.89 67	98.19 179	99.25 100	99.54 63	98.37 140	97.55 178	97.45 176	99.04 136	97.99 170

X-MVS		98.59 116	97.99 146	99.30 59	99.75 65	99.07 105	99.17 99	99.50 72	96.62 142	98.95 98	93.95 249	99.37 90	99.11 62	98.94 68	98.86 63	99.35 78	99.09 49

MVSMamba_PlusPlus		98.58 117	98.58 82	98.57 167	99.48 152	99.17 88	98.03 222	98.59 210	96.47 157	97.74 209	98.40 148	99.07 137	98.40 135	98.84 78	98.77 79	99.17 103	99.35 22

MVS_111021_HR		98.58 117	98.26 119	98.96 111	99.32 180	98.81 143	98.48 190	98.99 172	96.81 135	99.16 69	98.07 163	99.23 105	98.89 82	98.43 112	98.27 115	98.90 157	98.24 145

MGCNet		98.57 119	98.44 98	98.71 148	99.76 60	99.31 58	99.43 53	99.24 131	97.79 70	98.35 166	98.48 145	96.64 208	96.30 219	98.91 74	98.82 69	99.18 102	99.16 41

PM-MVS		98.57 119	98.24 124	98.95 112	99.26 190	98.59 171	99.03 122	98.74 196	96.84 130	99.44 36	99.13 111	98.31 179	98.75 92	98.03 145	98.21 117	98.48 198	98.58 103

PHI-MVS		98.57 119	98.20 127	99.00 104	99.48 152	98.91 135	98.68 172	99.17 147	94.97 199	99.27 52	98.33 151	99.33 95	98.05 164	98.82 83	98.62 94	99.34 79	98.38 131

diffmvs_AUTHOR		98.56 122	98.53 87	98.60 160	99.69 87	98.90 138	99.01 126	98.86 184	98.36 38	97.21 238	99.70 29	99.67 40	98.08 161	97.61 173	97.45 176	98.77 170	98.00 169

HPM-MVS++		98.56 122	98.08 140	99.11 84	99.53 140	98.61 170	99.02 124	99.32 116	96.29 167	99.06 83	97.23 195	99.50 74	98.77 90	98.15 140	97.90 140	98.96 146	98.90 73

TSAR-MVS + GP.		98.54 124	98.29 118	98.82 138	99.28 188	98.59 171	97.73 235	99.24 131	95.93 176	98.59 133	99.07 114	99.17 117	98.86 83	98.44 110	98.10 126	99.26 93	98.72 92

viewdifsd2359ckpt09		98.53 125	98.25 121	98.86 130	99.68 90	99.09 101	98.73 169	99.12 157	97.85 69	98.38 163	99.07 114	99.28 101	98.25 150	97.06 204	97.39 179	98.99 143	98.02 168

UGNet		98.52 126	99.00 33	97.96 206	99.58 123	99.26 62	99.27 85	99.40 90	98.07 53	98.28 174	98.76 132	99.71 29	92.24 262	98.94 68	98.85 65	99.00 142	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		98.50 127	98.03 143	99.05 96	99.50 148	99.01 119	99.15 107	99.26 125	96.38 162	99.12 76	99.50 69	99.12 127	98.60 106	97.68 170	97.24 188	98.66 180	97.30 202

CLD-MVS		98.48 128	98.15 131	98.86 130	99.53 140	98.35 187	98.55 185	97.83 236	96.02 175	98.97 93	99.08 113	99.75 21	99.03 70	98.10 143	97.33 184	99.28 89	98.44 125
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CANet		98.47 129	98.30 116	98.67 153	99.65 102	98.87 141	98.82 156	99.01 170	96.14 171	99.29 47	98.86 129	99.01 142	96.54 211	98.36 119	98.08 128	98.72 175	98.80 86

APD-MVS		98.47 129	97.97 147	99.05 96	99.64 107	98.91 135	98.94 138	99.45 88	94.40 219	98.77 117	97.26 194	99.41 82	98.21 153	98.67 96	98.57 100	99.31 85	98.57 105
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
viewmamba		98.46 131	98.36 111	98.58 162	99.65 102	98.80 145	98.82 156	98.72 199	98.33 42	97.54 220	99.58 53	99.61 52	97.96 171	97.71 167	96.86 197	98.76 173	97.65 190

Vis-MVSNet (Re-imp)		98.46 131	98.23 125	98.73 144	99.81 33	99.29 59	98.79 163	99.50 72	96.20 169	96.03 258	98.29 153	96.98 203	98.54 121	99.11 47	99.08 45	99.70 30	98.62 100

Fast-Effi-MVS+		98.42 133	97.79 155	99.15 76	99.69 87	98.66 166	98.94 138	99.68 30	94.49 213	99.05 85	98.06 165	98.86 150	98.48 131	98.18 137	97.78 148	99.05 131	98.54 112

ETV-MVS		98.41 134	97.76 156	99.17 73	99.58 123	99.01 119	98.91 142	99.50 72	93.33 239	99.31 44	96.82 211	98.42 175	98.17 155	99.13 46	99.08 45	99.54 44	98.56 109

dtuplus		98.39 135	98.22 126	98.58 162	99.58 123	98.69 160	99.05 118	98.83 187	97.68 84	97.19 240	99.46 73	99.59 57	97.89 176	97.47 185	96.69 201	98.95 148	97.97 174

MVS_111021_LR		98.39 135	98.11 137	98.71 148	99.08 211	98.54 177	98.23 215	98.56 213	96.57 148	99.13 74	98.41 147	98.86 150	98.65 102	98.23 135	97.87 144	98.65 182	98.28 140

onestephybrid01		98.38 137	98.25 121	98.53 173	99.61 115	98.79 147	99.04 121	98.68 202	97.17 116	97.58 217	99.58 53	99.57 60	97.51 188	97.79 164	97.14 190	98.77 170	97.71 185

pmmvs5		98.37 138	97.81 154	99.03 99	99.46 155	98.97 126	99.03 122	98.96 174	95.85 179	99.05 85	99.45 76	98.66 168	98.79 89	96.02 221	97.52 172	98.87 159	98.21 151

OMC-MVS		98.35 139	98.10 138	98.64 159	98.85 222	97.99 208	98.56 184	98.21 225	97.26 109	98.87 111	98.54 142	99.27 102	98.43 133	98.34 122	97.66 161	98.92 155	97.65 190

sasdasda		98.34 140	97.92 150	98.83 135	99.45 157	99.21 75	98.37 200	99.53 64	97.06 122	97.74 209	96.95 208	95.05 221	98.36 141	98.77 88	98.85 65	99.51 53	99.53 10

canonicalmvs		98.34 140	97.92 150	98.83 135	99.45 157	99.21 75	98.37 200	99.53 64	97.06 122	97.74 209	96.95 208	95.05 221	98.36 141	98.77 88	98.85 65	99.51 53	99.53 10

hybridnocas07		98.31 142	98.25 121	98.38 180	99.61 115	98.75 153	98.81 161	98.68 202	97.57 91	97.09 244	99.58 53	99.47 79	97.38 194	97.67 172	96.91 196	98.71 176	97.82 182

CHOSEN 1792x2688		98.31 142	98.02 144	98.66 155	99.55 131	98.57 174	99.38 58	99.25 129	98.42 34	98.48 153	99.58 53	99.85 6	98.31 146	95.75 225	95.71 219	96.96 231	98.27 142

viewmambaseed2359dif		98.30 144	98.05 142	98.58 162	99.55 131	98.69 160	98.99 127	98.76 195	97.06 122	97.32 233	99.40 85	99.52 67	97.99 167	97.22 200	96.54 207	98.85 163	97.95 175

CPTT-MVS		98.28 145	97.51 170	99.16 75	99.54 137	98.78 149	98.96 135	99.36 102	96.30 166	98.89 108	93.10 253	99.30 98	99.20 51	98.35 121	97.96 138	99.03 138	98.82 80

usedtu_dtu_shiyan1		98.27 146	97.72 160	98.90 120	98.96 217	98.75 153	99.17 99	98.96 174	96.35 163	98.90 104	98.69 135	99.05 139	98.55 118	96.31 216	97.36 182	98.86 161	97.55 195

TinyColmap		98.27 146	97.62 167	99.03 99	99.29 186	97.79 217	98.92 141	98.95 176	97.48 96	99.52 24	98.65 138	97.86 190	98.90 80	98.34 122	97.27 186	98.64 183	95.97 228

diffmvs		98.26 148	98.16 129	98.39 178	99.61 115	98.78 149	98.79 163	98.61 208	97.94 61	97.11 243	99.51 68	99.52 67	97.61 184	96.55 212	96.93 195	98.61 185	97.87 180
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		98.26 148	97.57 168	99.06 92	99.42 167	97.98 210	98.83 153	98.85 185	97.57 91	99.59 16	99.15 110	98.59 170	98.99 72	97.42 190	96.08 218	98.69 179	96.23 225

SF-MVS		98.25 150	98.16 129	98.35 182	99.43 164	98.42 185	97.05 258	99.09 162	96.42 160	98.13 185	97.73 178	99.20 113	97.22 198	98.36 119	98.38 109	99.16 108	98.62 100

MCST-MVS		98.25 150	97.57 168	99.06 92	99.53 140	98.24 195	98.63 177	99.17 147	95.88 177	98.58 134	96.11 228	99.09 133	99.18 53	97.58 177	97.31 185	99.25 94	98.75 88

hybrid		98.24 152	98.15 131	98.34 183	99.60 119	98.74 155	98.76 167	98.62 207	97.54 93	97.16 242	99.55 62	99.35 94	97.39 193	97.49 183	96.72 200	98.53 193	97.66 189

MGCFI-Net		98.23 153	97.93 149	98.58 162	99.44 161	99.20 81	98.37 200	99.54 59	97.14 118	96.70 255	96.98 205	95.04 223	97.92 175	98.75 91	98.89 61	99.52 47	99.55 9

IterMVS-LS		98.23 153	97.66 163	98.90 120	99.63 110	99.38 43	99.07 117	99.48 77	97.75 75	98.81 115	99.37 88	94.57 225	97.88 177	96.54 213	97.04 192	98.53 193	98.97 63
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TAPA-MVS	96.65 12	98.23 153	97.96 148	98.55 171	98.81 224	98.16 199	98.40 197	97.94 234	96.68 140	98.49 150	98.61 139	98.89 148	98.57 116	97.45 187	97.59 167	99.09 120	98.35 133
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CNVR-MVS		98.22 156	97.76 156	98.76 142	99.33 177	98.26 193	98.48 190	98.88 182	96.22 168	98.47 155	95.79 234	99.33 95	98.35 143	98.37 118	97.99 134	99.02 139	98.38 131

IS_MVSNet		98.20 157	98.00 145	98.44 175	99.82 29	99.48 31	99.25 88	99.56 54	95.58 187	93.93 270	97.56 184	96.52 209	98.27 149	99.08 51	99.20 38	99.80 15	98.56 109

DeepPCF-MVS	96.68 10	98.20 157	98.26 119	98.12 196	97.03 269	98.11 202	98.44 194	97.70 239	96.77 137	98.52 144	98.91 127	99.17 117	98.58 115	98.41 114	98.02 130	98.46 199	98.46 118

MSDG		98.20 157	97.88 153	98.56 169	99.33 177	97.74 218	98.27 212	98.10 228	97.20 114	98.06 194	98.59 140	99.16 120	98.76 91	98.39 115	97.71 159	98.86 161	96.38 222

testgi		98.18 160	98.44 98	97.89 208	99.78 44	99.23 71	98.78 165	99.21 138	97.26 109	97.41 227	97.39 191	99.36 93	92.85 257	98.82 83	98.66 90	99.31 85	98.35 133

Effi-MVS+		98.11 161	97.29 177	99.06 92	99.62 111	98.55 175	98.16 218	99.80 15	94.64 209	99.15 72	96.59 216	97.43 196	98.44 132	97.46 186	97.90 140	99.17 103	98.45 123

FA-MVS(training)		98.08 162	97.68 161	98.56 169	99.14 204	98.69 160	98.41 195	99.83 12	95.85 179	98.57 137	97.95 172	96.92 205	96.85 205	98.51 106	98.09 127	98.54 191	97.74 184

HyFIR lowres test		98.08 162	97.16 186	99.14 79	99.72 80	98.91 135	99.41 54	99.58 51	97.93 62	98.82 114	99.24 101	95.81 215	98.73 94	95.16 236	95.13 228	98.60 187	97.94 176

EIA-MVS		98.03 164	97.20 183	98.99 107	99.66 99	99.24 68	98.53 187	99.52 68	91.56 256	99.25 53	95.34 238	98.78 157	97.72 181	98.38 117	98.58 97	99.28 89	98.54 112

train_agg		97.99 165	97.26 178	98.83 135	99.43 164	98.22 197	98.91 142	99.07 164	94.43 217	97.96 200	96.42 222	99.30 98	98.81 88	97.39 192	96.62 205	98.82 165	98.47 116

MSLP-MVS++		97.99 165	97.64 166	98.40 177	98.91 220	98.47 181	97.12 255	98.78 192	96.49 155	98.48 153	93.57 251	99.12 127	98.51 127	98.31 125	98.58 97	98.58 189	98.95 68

CDPH-MVS		97.99 165	97.23 181	98.87 127	99.58 123	98.29 189	98.83 153	99.20 141	93.76 233	98.11 189	96.11 228	99.16 120	98.23 152	97.80 162	97.22 189	99.29 88	98.28 140

FMVSNet2		97.94 168	98.08 140	97.77 216	98.71 229	99.21 75	98.62 179	99.47 79	96.62 142	96.37 257	99.20 107	97.70 192	94.39 242	97.39 192	97.75 154	99.08 121	98.70 95

PVSNet_BlendedMVS		97.93 169	97.66 163	98.25 189	99.30 183	98.67 163	98.31 207	97.95 232	94.30 223	98.75 120	97.63 181	98.76 158	96.30 219	98.29 128	97.78 148	98.93 151	98.18 153

PVSNet_Blended		97.93 169	97.66 163	98.25 189	99.30 183	98.67 163	98.31 207	97.95 232	94.30 223	98.75 120	97.63 181	98.76 158	96.30 219	98.29 128	97.78 148	98.93 151	98.18 153

OpenMVS	97.26 9	97.88 171	97.17 185	98.70 150	99.50 148	98.55 175	98.34 205	99.11 158	93.92 231	98.90 104	95.04 243	98.23 180	97.38 194	98.11 142	98.12 122	98.95 148	98.23 148

pmmvs4		97.87 172	97.02 190	98.86 130	99.20 196	97.68 221	98.89 147	99.03 167	96.57 148	99.12 76	99.03 121	97.26 200	98.42 134	95.16 236	96.34 210	98.53 193	97.10 209

NCCC		97.84 173	96.96 192	98.87 127	99.39 171	98.27 192	98.46 192	99.02 169	96.78 136	98.73 124	91.12 257	98.91 146	98.57 116	97.83 159	97.49 174	99.04 136	98.33 138

Effi-MVS+-dtu		97.78 174	97.37 174	98.26 187	99.25 192	98.50 179	97.89 229	99.19 144	94.51 211	98.16 182	95.93 231	98.80 155	95.97 223	98.27 133	97.38 180	99.10 114	98.23 148

MDA-MVSNet-bldmvs		97.75 175	97.26 178	98.33 184	99.35 176	98.45 182	99.32 74	97.21 245	97.90 66	99.05 85	99.01 123	96.86 206	99.08 66	99.36 33	92.97 240	95.97 246	96.25 224

CDS-MVSNet		97.75 175	97.68 161	97.83 214	99.08 211	98.20 198	98.68 172	98.61 208	95.63 186	97.80 207	99.24 101	96.93 204	94.09 248	97.96 148	97.82 146	98.71 176	97.99 170
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CNLPA		97.75 175	97.26 178	98.32 186	98.58 237	97.86 213	97.80 231	98.09 229	96.49 155	98.49 150	96.15 227	98.08 183	98.35 143	98.00 146	97.03 193	98.61 185	97.21 206

PLC	95.63 15	97.73 178	97.01 191	98.57 167	99.10 208	97.80 216	97.72 236	98.77 193	96.34 164	98.38 163	93.46 252	98.06 184	98.66 101	97.90 153	97.65 163	98.77 170	97.90 178
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVS_Test		97.69 179	97.15 187	98.33 184	99.27 189	98.43 184	98.25 213	99.29 120	95.00 198	97.39 229	98.86 129	98.00 187	97.14 200	95.38 231	96.22 212	98.62 184	98.15 159

GBi-Net		97.69 179	97.75 158	97.62 217	98.71 229	99.21 75	98.62 179	99.33 112	94.09 227	95.60 260	98.17 160	95.97 212	94.39 242	99.05 55	99.03 49	99.08 121	98.70 95

test1		97.69 179	97.75 158	97.62 217	98.71 229	99.21 75	98.62 179	99.33 112	94.09 227	95.60 260	98.17 160	95.97 212	94.39 242	99.05 55	99.03 49	99.08 121	98.70 95

CANet_DTU		97.65 182	97.50 172	97.82 215	99.19 199	98.08 204	98.41 195	98.67 204	94.40 219	99.16 69	98.32 152	98.69 162	93.96 251	97.87 154	97.61 165	97.51 224	97.56 194

IterMVS-SCA-FT		97.63 183	96.86 194	98.52 174	99.48 152	98.71 158	98.84 152	98.91 177	96.44 159	99.16 69	99.56 58	95.54 217	97.95 172	95.68 228	95.07 231	96.76 237	97.03 212

TSAR-MVS + COLMAP		97.62 184	97.31 176	97.98 204	98.47 245	97.39 227	98.29 209	98.25 224	96.68 140	97.54 220	98.87 128	98.04 186	97.08 201	96.78 207	96.26 211	98.26 205	97.12 208

MS-PatchMatch		97.60 185	97.22 182	98.04 203	98.67 233	97.18 232	97.91 227	98.28 223	95.82 182	98.34 167	97.66 180	98.38 176	97.77 179	97.10 203	97.25 187	97.27 226	97.18 207

PCF-MVS	95.58 16	97.60 185	96.67 195	98.69 151	99.44 161	98.23 196	98.37 200	98.81 190	93.01 243	98.22 178	97.97 171	99.59 57	98.20 154	95.72 227	95.08 229	99.08 121	97.09 211
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HQP-MVS		97.58 187	96.65 198	98.66 155	99.30 183	97.99 208	97.88 230	98.65 205	94.58 210	98.66 127	94.65 247	99.15 123	98.59 108	96.10 219	95.59 220	98.90 157	98.50 114

DI_MVS_pp		97.57 188	96.55 200	98.77 141	99.55 131	98.76 151	99.22 91	99.00 171	97.08 121	97.95 201	97.78 177	91.35 239	98.02 165	96.20 217	96.81 199	98.87 159	97.87 180

AdaColmap		97.57 188	96.57 199	98.74 143	99.25 192	98.01 206	98.36 204	98.98 173	94.44 216	98.47 155	92.44 254	97.91 189	98.62 104	98.19 136	97.74 155	98.73 174	97.28 203

baseline		97.50 190	97.51 170	97.50 221	99.18 200	97.38 228	98.00 223	98.00 231	96.52 154	97.49 223	99.28 96	99.43 81	95.31 229	95.27 233	96.22 212	96.99 229	98.47 116

IterMVS		97.40 191	96.67 195	98.25 189	99.45 157	98.66 166	98.87 149	98.73 197	96.40 161	98.94 101	99.56 58	95.26 219	97.58 185	95.38 231	94.70 233	95.90 247	96.72 215
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		97.38 192	96.15 209	98.82 138	99.39 171	98.34 188	98.65 175	98.88 182	90.80 263	98.86 112	92.35 255	95.13 220	98.09 159	98.84 78	98.88 62	99.06 128	98.71 94

CVMVSNet		97.38 192	97.39 173	97.37 225	98.58 237	97.72 219	98.70 170	97.42 243	97.21 112	95.95 259	99.46 73	93.31 234	97.38 194	97.60 175	97.78 148	96.18 243	98.66 98

new-patchmatchnet		97.26 194	96.12 210	98.58 162	99.55 131	98.63 168	99.14 109	97.04 247	98.80 18	99.19 61	99.92 4	99.19 115	98.92 79	95.51 230	87.04 258	97.66 221	93.73 248

MIMVSNet		97.24 195	97.15 187	97.36 226	99.03 215	98.52 178	98.55 185	99.73 23	94.94 202	94.94 267	97.98 170	97.37 198	93.66 252	97.60 175	97.34 183	98.23 208	96.29 223

PatchMatch-RL		97.24 195	96.45 203	98.17 193	98.70 232	97.57 224	97.31 250	98.48 217	94.42 218	98.39 162	95.74 235	96.35 211	97.88 177	97.75 166	97.48 175	98.24 207	95.87 232

dtuonlycased		97.23 197	97.32 175	97.13 231	99.59 120	98.67 163	98.87 149	97.72 238	97.34 103	92.21 274	99.35 89	99.39 87	98.07 163	95.98 223	94.57 234	96.35 240	95.94 231

thisisatest0530		97.20 198	95.95 214	98.66 155	99.46 155	98.84 142	98.29 209	99.20 141	94.51 211	98.25 176	97.42 189	85.03 257	97.68 182	98.43 112	98.56 101	99.08 121	98.89 75

tttt0517		97.18 199	95.92 215	98.65 158	99.49 150	98.92 133	98.29 209	99.20 141	94.37 221	98.17 180	97.37 192	84.72 260	97.68 182	98.55 102	98.56 101	99.10 114	98.95 68

MDTV_nov1_ep13_2view		97.12 200	96.19 208	98.22 192	99.13 207	98.05 205	99.24 89	99.47 79	97.61 88	99.15 72	99.59 48	99.01 142	98.40 135	94.87 240	90.14 243	93.91 258	94.04 247

MAR-MVS		97.12 200	96.28 206	98.11 197	98.94 218	97.22 230	97.65 240	99.38 97	90.93 262	98.15 183	95.17 240	97.13 201	96.48 214	97.71 167	97.40 178	98.06 212	98.40 128
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		96.99 202	96.46 202	97.61 219	98.98 216	97.89 211	97.54 244	99.76 19	93.43 237	96.55 256	94.93 244	98.06 184	94.32 245	96.93 205	96.50 208	98.53 193	97.47 196

FPMVS		96.97 203	97.20 183	96.70 245	97.75 261	96.11 253	97.72 236	95.47 254	97.13 119	98.02 196	97.57 183	96.67 207	92.97 256	99.00 64	98.34 113	98.28 204	95.58 234

TAMVS		96.95 204	96.94 193	96.97 239	99.07 213	97.67 223	97.98 225	97.12 246	95.04 197	95.41 263	99.27 97	95.57 216	94.09 248	97.32 196	97.11 191	98.16 210	96.59 216

FMVSNet3		96.85 205	96.67 195	97.06 233	97.56 264	99.01 119	97.99 224	99.33 112	94.09 227	95.60 260	98.17 160	95.97 212	93.26 255	94.76 242	96.22 212	98.59 188	98.46 118

GA-MVS		96.84 206	95.86 217	97.98 204	99.16 203	98.29 189	97.91 227	98.64 206	95.14 193	97.71 213	98.04 167	88.90 243	96.50 213	96.41 215	96.61 206	97.97 217	97.60 192

CHOSEN 280x420		96.80 207	96.30 205	97.39 223	99.09 209	96.52 245	98.76 167	99.29 120	93.88 232	97.65 214	98.34 150	93.66 232	96.29 222	98.28 131	97.73 157	93.27 261	95.70 233

gg-mvs-nofinetune		96.77 208	96.52 201	97.06 233	99.66 99	97.82 215	97.54 244	99.86 8	98.69 24	98.61 131	99.94 2	89.62 241	88.37 270	97.55 178	96.67 203	98.30 203	95.35 235

dtuonly		96.75 209	96.24 207	97.34 227	99.41 169	96.98 237	98.07 221	97.70 239	95.68 184	98.07 193	99.07 114	99.23 105	96.32 218	95.14 238	93.82 237	94.49 253	93.72 249

DPM-MVS		96.73 210	95.70 220	97.95 207	98.93 219	97.26 229	97.39 249	98.44 219	95.47 189	97.62 216	90.71 258	98.47 174	97.03 204	95.02 239	95.27 225	98.26 205	97.67 187

baseline1		96.72 211	95.40 222	98.26 187	99.53 140	98.81 143	98.32 206	98.80 191	94.96 200	96.78 254	96.50 220	84.87 259	96.68 209	97.42 190	97.91 139	99.46 58	97.33 201

N_pmnet		96.68 212	95.70 220	97.84 213	99.42 167	98.00 207	99.35 66	98.21 225	98.40 36	98.13 185	99.42 82	99.30 98	97.44 192	94.00 246	88.79 245	94.47 254	91.96 258

pmnet_mix02		96.61 213	95.32 223	98.11 197	99.41 169	97.68 221	99.05 118	97.59 241	98.16 48	99.05 85	99.48 70	99.11 129	98.32 145	92.36 251	87.67 253	95.26 249	92.80 255

new_pmnet		96.59 214	96.40 204	96.81 242	98.24 257	95.46 262	97.71 238	94.75 261	96.92 127	96.80 253	99.23 103	97.81 191	96.69 207	96.58 211	95.16 227	96.69 238	93.64 250

PMMVS		96.47 215	95.81 218	97.23 228	97.38 266	95.96 257	97.31 250	96.91 248	93.21 240	97.93 203	97.14 198	97.64 194	95.70 225	95.24 234	96.18 215	98.17 209	95.33 236

EPNet		96.44 216	96.08 211	96.86 241	99.32 180	97.15 233	97.69 239	99.32 116	93.67 234	98.11 189	95.64 236	93.44 233	89.07 268	96.86 206	96.83 198	97.67 220	98.97 63
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thres600view7		96.35 217	94.27 227	98.79 140	99.66 99	99.18 85	98.94 138	99.38 97	94.37 221	97.21 238	87.19 263	84.10 261	98.10 157	98.16 138	99.47 20	99.42 65	97.43 197

EPNet_dtu		96.31 218	95.96 213	96.72 244	99.18 200	95.39 263	97.03 259	99.13 156	93.02 242	99.35 40	97.23 195	97.07 202	90.70 267	95.74 226	95.08 229	94.94 251	98.16 158
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs3		96.30 219	95.87 216	96.80 243	97.66 263	96.48 246	97.93 226	93.80 263	93.40 238	98.54 141	98.27 154	97.50 195	97.37 197	97.49 183	93.11 239	95.52 248	94.85 240

PMMVS2		96.29 220	97.05 189	95.40 255	98.32 255	96.16 250	98.18 217	97.46 242	97.20 114	84.51 277	99.60 46	98.68 164	96.37 215	98.59 100	97.38 180	97.58 223	91.76 259

thres200		96.23 221	94.13 228	98.69 151	99.44 161	99.18 85	98.58 183	99.38 97	93.52 236	97.35 231	86.33 268	85.83 254	97.93 173	98.16 138	98.78 77	99.42 65	97.10 209

thres400		96.22 222	94.08 231	98.72 145	99.58 123	99.05 109	98.83 153	99.22 135	94.01 230	97.40 228	86.34 267	84.91 258	97.93 173	97.85 158	99.08 45	99.37 73	97.28 203

tfpn200view9		96.17 223	94.08 231	98.60 160	99.37 173	99.18 85	98.68 172	99.39 92	92.02 250	97.30 234	86.53 265	86.34 251	97.45 191	98.15 140	99.08 45	99.43 64	97.28 203

CMPMVS	74.71 19	96.17 223	96.06 212	96.30 249	97.41 265	94.52 266	94.83 271	95.46 255	91.57 255	97.26 237	94.45 248	98.33 178	94.98 232	98.28 131	97.59 167	97.86 219	97.68 186
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test2506		96.12 225	93.35 243	99.35 54	99.83 24	99.58 23	99.37 59	99.67 34	98.02 56	98.44 159	97.51 186	60.03 281	99.10 63	99.77 5	99.70 6	99.72 26	98.86 77

blended_shiyan8		96.02 226	94.28 226	98.05 201	98.55 243	97.09 234	98.98 130	95.56 252	95.13 194	99.23 54	98.03 169	94.19 227	98.73 94	90.28 254	88.65 246	97.22 227	96.56 219

blended_shiyan6		96.02 226	94.29 225	98.05 201	98.56 240	97.09 234	98.99 127	95.56 252	95.11 195	99.21 57	98.04 167	94.28 226	98.74 93	90.26 255	88.64 247	97.22 227	96.57 217

gbinet_0.2-2-1-0.02		95.92 228	94.09 229	98.06 199	98.81 224	97.08 236	99.13 110	96.47 249	94.88 203	99.08 81	98.47 146	94.16 228	98.02 165	90.43 253	87.61 254	96.86 232	95.99 227

IB-MVS	95.85 14	95.87 229	94.88 224	97.02 236	99.09 209	98.25 194	97.16 252	97.38 244	91.97 253	97.77 208	83.61 273	97.29 199	92.03 265	97.16 201	97.66 161	98.66 180	98.20 152
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		95.81 230	95.77 219	95.85 254	99.20 196	98.15 201	97.49 248	98.50 215	92.24 246	92.74 273	96.82 211	92.70 235	88.60 269	97.31 198	97.01 194	98.57 190	96.19 226

thres100view900		95.74 231	93.66 242	98.17 193	99.37 173	98.59 171	98.10 219	98.33 222	92.02 250	97.30 234	86.53 265	86.34 251	96.69 207	96.77 208	98.47 106	99.24 96	96.89 213

wanda-best-256-512		95.72 232	93.88 236	97.86 211	98.45 246	96.92 238	98.82 156	95.29 257	94.75 205	99.18 63	97.92 174	94.13 229	98.59 108	89.77 257	87.74 249	96.86 232	95.95 229

FE-blended-shiyan7		95.72 232	93.88 236	97.86 211	98.45 246	96.92 238	98.82 156	95.29 257	94.75 205	99.18 63	97.92 174	94.13 229	98.59 108	89.77 257	87.74 249	96.86 232	95.95 229

ET-MVSNet_ETH3D		95.72 232	93.85 238	97.89 208	97.30 267	98.09 203	98.19 216	98.40 220	94.46 215	98.01 199	96.71 213	77.85 277	96.76 206	96.08 220	96.39 209	98.70 178	97.36 199

baseline2		95.58 235	94.04 233	97.38 224	98.80 226	98.16 199	97.14 253	97.80 237	91.45 257	97.49 223	95.22 239	83.63 262	94.98 232	96.42 214	96.66 204	98.06 212	96.76 214

PatchT		95.49 236	93.29 244	98.06 199	98.65 234	96.20 249	98.91 142	99.73 23	92.00 252	98.50 146	96.67 215	83.25 263	96.34 216	94.40 243	95.50 221	96.21 242	95.04 238

CR-MVSNet		95.38 237	93.01 245	98.16 195	98.63 235	95.85 259	97.64 241	99.78 16	91.27 259	98.50 146	96.84 210	82.16 264	96.34 216	94.40 243	95.50 221	98.05 214	95.04 238

MVSTER		95.38 237	93.99 235	97.01 237	98.83 223	98.95 128	96.62 260	99.14 153	92.17 248	97.44 226	97.29 193	77.88 276	91.63 266	97.45 187	96.18 215	98.41 200	97.99 170

MVS-HIRNet		94.86 239	93.83 239	96.07 250	97.07 268	94.00 268	94.31 272	99.17 147	91.23 261	98.17 180	98.69 135	97.43 196	95.66 226	94.05 245	91.92 241	92.04 268	89.46 267

test-LLR		94.79 240	93.71 240	96.06 251	99.20 196	96.16 250	96.31 262	98.50 215	89.98 264	94.08 268	97.01 202	86.43 249	92.20 263	96.76 209	95.31 223	96.05 244	94.31 244

RPMNet		94.72 241	92.01 250	97.88 210	98.56 240	95.85 259	97.78 232	99.70 29	91.27 259	98.33 168	93.69 250	81.88 265	94.91 235	92.60 249	94.34 236	98.01 216	94.46 243

gm-plane-assit		94.62 242	91.39 252	98.39 178	99.90 11	99.47 33	99.40 55	99.65 39	97.44 98	99.56 20	99.68 30	59.40 282	94.23 246	96.17 218	94.77 232	97.61 222	92.79 256

test-mter		94.62 242	94.02 234	95.32 256	97.72 262	96.75 242	96.23 264	95.67 251	89.83 267	93.23 272	96.99 204	85.94 253	92.66 261	97.32 196	96.11 217	96.44 239	95.22 237

FMVSNet5		94.57 244	92.77 246	96.67 246	97.88 259	98.72 157	97.54 244	98.70 201	88.64 268	95.11 265	86.90 264	81.77 266	93.27 254	97.92 151	98.07 129	97.50 225	97.34 200

SCA		94.53 245	91.95 251	97.55 220	98.58 237	97.86 213	98.49 189	99.68 30	95.11 195	99.07 82	95.87 232	87.24 246	96.53 212	89.77 257	87.08 257	92.96 263	90.69 262

MDTV_nov1_ep13		94.47 246	92.15 248	97.17 229	98.54 244	96.42 247	98.10 219	98.89 179	94.49 213	98.02 196	97.41 190	86.49 247	95.56 227	90.85 252	87.95 248	93.91 258	91.45 261

TESTMET0.1,1		94.44 247	93.71 240	95.30 257	97.84 260	96.16 250	96.31 262	95.32 256	89.98 264	94.08 268	97.01 202	86.43 249	92.20 263	96.76 209	95.31 223	96.05 244	94.31 244

ADS-MVSNet		94.41 248	92.13 249	97.07 232	98.86 221	96.60 244	98.38 199	98.47 218	96.13 173	98.02 196	96.98 205	87.50 245	95.87 224	89.89 256	87.58 255	92.79 265	90.27 264

tpm		93.89 249	91.21 253	97.03 235	98.36 253	96.07 254	97.53 247	99.65 39	92.24 246	98.64 128	97.23 195	74.67 280	94.64 240	92.68 248	90.73 242	93.37 260	94.82 241

PatchmatchNet		93.88 250	91.08 254	97.14 230	98.75 228	96.01 256	98.25 213	99.39 92	94.95 201	98.96 96	96.32 223	85.35 256	95.50 228	88.89 262	85.89 261	91.99 269	90.15 265
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		93.67 251	90.82 255	96.99 238	98.62 236	96.39 248	98.40 197	99.11 158	95.54 188	97.87 206	97.14 198	81.27 268	94.97 234	88.54 264	86.80 259	92.95 264	90.06 266

FE-MVSNET3		93.58 252	90.22 256	97.50 221	98.45 246	96.92 238	98.82 156	95.29 257	94.75 205	96.98 246	86.26 269	79.50 271	98.59 108	89.77 257	87.74 249	96.86 232	96.57 217

usedtu_blend_shiyan5		93.31 253	90.20 257	96.93 240	98.45 246	96.92 238	95.44 268	95.29 257	94.75 205	96.98 246	86.26 269	79.50 271	98.59 108	89.77 257	87.74 249	96.86 232	96.46 220

MVE	82.47 18	93.12 254	94.09 229	91.99 264	90.79 273	82.50 275	93.93 273	96.30 250	96.06 174	88.81 275	98.19 158	96.38 210	97.56 186	97.24 199	95.18 226	84.58 275	93.07 252
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CostFormer		92.75 255	89.49 259	96.55 247	98.78 227	95.83 261	97.55 243	98.59 210	91.83 254	97.34 232	96.31 224	78.53 275	94.50 241	86.14 266	84.92 262	92.54 266	92.84 254

tpmrst		92.45 256	89.48 260	95.92 253	98.43 251	95.03 264	97.14 253	97.92 235	94.16 225	97.56 218	97.86 176	81.63 267	93.56 253	85.89 267	82.86 266	90.91 273	88.95 269

dps		92.35 257	88.78 262	96.52 248	98.21 258	95.94 258	97.78 232	98.38 221	89.88 266	96.81 252	95.07 242	75.31 279	94.70 238	88.62 263	86.21 260	93.21 262	90.41 263

E-PMN		92.28 258	90.12 258	94.79 259	98.56 240	90.90 272	95.16 270	93.68 264	95.36 191	95.10 266	96.56 217	89.05 242	95.24 230	95.21 235	81.84 268	90.98 271	81.94 272

EMVS		91.84 259	89.39 261	94.70 260	98.44 250	90.84 273	95.27 269	93.53 265	95.18 192	95.26 264	95.62 237	87.59 244	94.77 237	94.87 240	80.72 269	90.95 272	80.88 273

tpm cat1		91.52 260	87.70 264	95.97 252	98.33 254	94.98 265	97.06 256	98.03 230	92.11 249	98.03 195	94.77 246	77.19 278	92.71 259	83.56 268	82.24 267	91.67 270	89.04 268

blend_shiyan4		91.30 261	88.16 263	94.96 258	89.60 274	96.63 243	93.72 274	93.90 262	82.52 272	96.98 246	86.26 269	79.50 271	98.59 108	88.21 265	87.51 256	96.99 229	96.46 220

0.4-1-1-0.1		90.20 262	87.09 265	93.83 261	91.98 270	94.48 267	96.12 265	88.26 266	84.35 269	97.04 245	88.99 259	79.83 269	94.68 239	83.11 269	84.34 263	94.87 252	94.55 242

0.3-1-1-0.015		89.53 263	86.18 266	93.43 262	91.67 272	93.80 269	95.70 266	87.54 267	83.38 270	96.98 246	87.42 261	79.50 271	94.21 247	81.99 271	83.67 264	94.46 255	93.50 251

0.4-1-1-0.2		89.46 264	86.17 267	93.30 263	91.74 271	93.59 271	95.48 267	87.42 268	83.04 271	96.95 250	88.20 260	79.80 270	93.99 250	82.16 270	83.38 265	94.21 257	93.03 253

test_method		77.69 265	85.40 268	68.69 265	42.66 278	55.39 278	82.17 277	52.05 271	92.83 244	84.52 276	94.88 245	95.41 218	65.37 271	92.49 250	79.32 270	85.36 274	87.50 270

GG-mvs-BLEND		65.66 266	92.62 247	34.20 268	1.45 283	93.75 270	85.40 276	1.64 277	91.37 258	17.21 280	87.25 262	94.78 224	3.25 279	95.64 229	93.80 238	96.27 241	91.74 260

VLMVS_CLIP		64.13 267	75.30 270	51.09 267	78.61 276	71.68 276	44.27 279	52.07 270	67.28 274	32.13 279	78.44 275	86.48 248	54.65 273	78.08 273	71.19 272	44.79 277	73.98 274

MVS_clip		56.91 268	76.74 269	33.76 269	54.66 277	53.09 279	31.90 281	17.78 273	73.21 273	9.18 283	81.68 274	85.59 255	58.85 272	80.87 272	77.88 271	30.20 278	84.88 271

VLMVS		34.07 269	45.54 271	20.69 270	38.22 279	31.90 280	12.64 282	15.62 274	42.63 275	9.57 282	44.68 276	57.03 283	34.96 275	43.33 274	43.85 273	13.11 279	55.36 276

MVS_baseline		22.56 270	36.20 272	6.64 271	10.19 280	9.26 281	1.84 285	0.00 278	36.68 276	0.00 285	39.69 277	45.33 284	27.64 276	29.68 275	28.88 274	0.18 282	63.87 275

testmvs		9.73 271	13.38 273	5.48 273	3.62 281	4.12 282	6.40 283	3.19 276	14.92 277	7.68 284	22.10 278	13.89 286	6.83 277	13.47 276	10.38 276	5.14 281	14.81 277

test123		9.37 272	12.26 274	6.00 272	3.32 282	4.06 283	6.39 284	3.41 275	13.20 278	10.48 281	16.43 279	16.22 285	6.76 278	11.37 277	10.40 275	5.62 280	14.10 278

uanet_test		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet-low-res		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

ACM-MVS					98.32 255	97.44 226	97.06 256		92.73 245	97.56 218	96.20 226	98.80 155	92.76 258			98.03 215	98.46 118

PatchmatchNet2					99.32 180	97.53 225	99.28 84
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												99.26 103	97.46 189	93.87 247	88.80 244	94.45 256	91.98 257
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										98.11 189	99.45 76
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							99.34 70	98.89 179		98.10 192						99.01 140

TPM-MVS					98.38 252	97.20 231	96.44 261			97.17 241	95.17 240	98.68 164	92.69 260			98.11 211	97.67 187
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												98.83 154

SR-MVS					99.62 111			99.47 79				99.40 85

Anonymous202405211			98.44 98		99.79 40	99.32 57	99.05 118	99.34 109	96.59 145		97.95 172	97.68 193	97.16 199	99.36 33	99.28 35	99.61 39	98.90 73

our_test_3					99.29 186	97.72 219	98.98 130

ambc			97.89 152		99.45 157	97.88 212	97.78 232		97.27 107	99.80 3	98.99 125	98.48 172	98.55 118	97.80 162	96.68 202	98.54 191	98.10 164

MTAPA										99.19 61		99.68 36

MTMP										99.20 59		99.54 63

Patchmatch-RL test							32.47 280

tmp_tt				65.28 266	82.24 275	71.50 277	70.81 278	23.21 272	96.14 171	81.70 278	85.98 272	92.44 236	49.84 274	95.81 224	94.36 235	83.86 276

XVS					99.77 50	99.07 105	99.46 49			98.95 98		99.37 90				99.33 81

X-MVStestdata					99.77 50	99.07 105	99.46 49			98.95 98		99.37 90				99.33 81

mPP-MVS					99.75 65							99.49 76

NP-MVS									93.07 241

Patchmtry						96.05 255	97.64 241	99.78 16		98.50 146

DeepMVS_CX						87.86 274	92.27 275	61.98 269	93.64 235	93.62 271	91.17 256	91.67 237	94.90 236	95.99 222		92.48 267	94.18 246

High-resolution multi-view benchmark