High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

LTVRE_ROB	99.39 1	99.90 1	99.87 1	99.93 1	99.97 2	99.82 8	99.91 3	99.92 38	99.75 4	99.93 8	99.89 34	100.00 1	99.87 2	99.93 3	99.82 10	99.96 3	99.90 2
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
v7n		99.89 2	99.86 3	99.93 1	99.97 2	99.83 4	99.93 1	99.96 12	99.77 3	99.89 21	99.99 1	99.86 102	99.84 5	99.89 11	99.81 11	99.97 1	99.88 7

SixPastTwentyTwo		99.89 2	99.85 5	99.93 1	99.97 2	99.88 1	99.92 2	99.97 1	99.66 21	99.94 6	99.94 11	99.74 140	99.81 7	99.97 1	99.89 1	99.96 3	99.89 5

pmmvs6		99.88 4	99.87 1	99.89 9	99.97 2	99.76 22	99.89 5	99.96 12	99.82 2	99.90 18	99.92 18	99.95 37	99.68 34	99.93 3	99.88 3	99.95 7	99.86 13

anonymousdsp		99.87 5	99.86 3	99.88 13	99.95 10	99.75 28	99.90 4	99.96 12	99.69 13	99.83 59	99.96 4	99.99 5	99.74 22	99.95 2	99.83 7	99.91 25	99.88 7

FC-MVSNet-test		99.84 6	99.80 6	99.89 9	99.96 7	99.83 4	99.84 17	99.95 23	99.37 77	99.77 81	99.95 6	99.96 24	99.85 3	99.93 3	99.83 7	99.95 7	99.72 43

WB-MVS		99.82 7	99.76 9	99.89 9	99.94 23	99.82 8	99.79 31	99.93 27	99.67 16	99.97 2	99.83 62	99.78 136	99.79 12	99.72 39	99.70 22	99.95 7	99.78 30

UniMVSNet_ETH3D		99.81 8	99.79 7	99.85 20	99.98 1	99.76 22	99.73 54	99.96 12	99.68 15	99.87 37	99.59 118	99.91 78	99.58 54	99.90 10	99.85 6	99.96 3	99.81 22

TDRefinement		99.81 8	99.76 9	99.86 16	99.83 114	99.53 77	99.89 5	99.91 44	99.73 5	99.88 30	99.83 62	99.96 24	99.76 17	99.91 9	99.81 11	99.86 44	99.59 80

WR-MVS		99.79 10	99.68 14	99.91 5	99.95 10	99.83 4	99.87 9	99.96 12	99.39 75	99.93 8	99.87 43	99.29 187	99.77 15	99.83 22	99.72 20	99.97 1	99.82 18

MIMVSNet1		99.79 10	99.75 11	99.84 23	99.89 50	99.83 4	99.84 17	99.89 55	99.31 82	99.93 8	99.92 18	99.97 17	99.68 34	99.89 11	99.64 28	99.82 60	99.66 57

pm-mvs1		99.77 12	99.69 13	99.86 16	99.94 23	99.68 37	99.84 17	99.93 27	99.59 37	99.87 37	99.92 18	99.21 190	99.65 40	99.88 15	99.77 16	99.93 21	99.78 30

PEN-MVS		99.77 12	99.65 20	99.91 5	99.95 10	99.80 16	99.86 11	99.97 1	99.08 113	99.89 21	99.69 101	99.68 151	99.84 5	99.81 27	99.64 28	99.95 7	99.81 22

FE-MVSNET2		99.76 14	99.67 15	99.86 16	99.94 23	99.68 37	99.87 9	99.90 53	99.50 58	99.94 6	99.78 78	100.00 1	99.69 32	99.71 43	99.43 54	99.85 47	99.58 89

EU-MVSNet		99.76 14	99.74 12	99.78 44	99.82 124	99.81 13	99.88 7	99.87 61	99.31 82	99.75 90	99.91 27	99.76 138	99.78 13	99.84 21	99.74 19	99.56 166	99.81 22

Vis-MVSNet		99.76 14	99.78 8	99.75 55	99.92 33	99.77 21	99.83 20	99.85 73	99.43 68	99.85 50	99.84 58	100.00 1	99.13 149	99.83 22	99.66 25	99.90 29	99.90 2
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS		99.75 17	99.66 19	99.85 20	99.87 69	99.86 2	99.83 20	99.91 44	98.84 154	99.92 12	99.57 120	99.85 108	99.60 49	99.82 25	99.79 13	99.94 16	99.87 11

SPE-MVS-test		99.75 17	99.67 15	99.84 23	99.91 37	99.85 3	99.85 14	99.92 38	98.75 164	99.89 21	99.64 108	99.95 37	99.55 57	99.89 11	99.79 13	99.92 22	99.83 16

DTE-MVSNet		99.75 17	99.61 33	99.92 4	99.95 10	99.81 13	99.86 11	99.96 12	99.18 101	99.92 12	99.66 104	99.45 172	99.85 3	99.80 28	99.56 34	99.96 3	99.79 29

tfpnnormal		99.74 20	99.63 27	99.86 16	99.93 30	99.75 28	99.80 30	99.89 55	99.31 82	99.88 30	99.43 144	99.66 155	99.77 15	99.80 28	99.71 21	99.92 22	99.76 34

DeepC-MVS	99.05 5	99.74 20	99.64 23	99.84 23	99.90 43	99.39 126	99.79 31	99.81 103	99.69 13	99.90 18	99.87 43	99.98 11	99.81 7	99.62 57	99.32 67	99.83 56	99.65 61
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
thisisatest0515		99.73 22	99.67 15	99.81 33	99.93 30	99.74 30	99.68 65	99.91 44	99.59 37	99.88 30	99.73 88	99.81 122	99.55 57	99.59 58	99.53 39	99.89 34	99.70 51

PS-CasMVS		99.73 22	99.59 39	99.90 8	99.95 10	99.80 16	99.85 14	99.97 1	98.95 138	99.86 43	99.73 88	99.36 179	99.81 7	99.83 22	99.67 24	99.95 7	99.83 16

WR-MVS_H		99.73 22	99.61 33	99.88 13	99.95 10	99.82 8	99.83 20	99.96 12	99.01 127	99.84 54	99.71 98	99.41 178	99.74 22	99.77 33	99.70 22	99.95 7	99.82 18

TransMVSNet (Re)		99.72 25	99.59 39	99.88 13	99.95 10	99.76 22	99.88 7	99.94 24	99.58 39	99.92 12	99.90 31	98.55 207	99.65 40	99.89 11	99.76 17	99.95 7	99.70 51

ACMH	99.11 4	99.72 25	99.63 27	99.84 23	99.87 69	99.59 55	99.83 20	99.88 60	99.46 63	99.87 37	99.66 104	99.95 37	99.76 17	99.73 38	99.47 48	99.84 51	99.52 115
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FC-MVSNet-train		99.70 27	99.67 15	99.74 61	99.94 23	99.71 33	99.82 26	99.91 44	99.14 109	99.53 167	99.70 99	99.88 93	99.33 101	99.88 15	99.61 33	99.94 16	99.77 32

EC-MVSNet		99.70 27	99.57 43	99.85 20	99.95 10	99.81 13	99.85 14	99.93 27	98.39 202	99.76 84	99.48 140	99.94 49	99.70 31	99.85 19	99.66 25	99.91 25	99.87 11

COLMAP_ROB	99.18 2	99.70 27	99.60 37	99.81 33	99.84 106	99.37 136	99.76 39	99.84 82	99.54 49	99.82 62	99.64 108	99.95 37	99.75 19	99.79 30	99.56 34	99.83 56	99.37 160
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
casdiffseed414692147		99.69 30	99.62 31	99.76 50	99.91 37	99.55 67	99.73 54	99.82 94	99.63 30	99.78 76	99.88 40	100.00 1	99.47 87	99.49 67	99.19 79	99.83 56	99.63 66

ACMH+	98.94 6	99.69 30	99.59 39	99.81 33	99.88 62	99.41 121	99.75 43	99.86 66	99.43 68	99.80 67	99.54 124	99.97 17	99.73 25	99.82 25	99.52 41	99.85 47	99.43 143

E6new		99.68 32	99.65 20	99.72 65	99.89 50	99.59 55	99.58 90	99.80 111	99.71 7	99.78 76	99.89 34	99.99 5	99.48 82	99.42 82	99.31 68	99.82 60	99.63 66

E6		99.68 32	99.65 20	99.72 65	99.89 50	99.59 55	99.58 90	99.80 111	99.71 7	99.78 76	99.89 34	99.99 5	99.48 82	99.42 82	99.31 68	99.82 60	99.63 66

test20.03		99.68 32	99.60 37	99.76 50	99.91 37	99.70 36	99.68 65	99.87 61	99.05 122	99.88 30	99.92 18	99.88 93	99.50 74	99.77 33	99.42 57	99.75 90	99.49 123

CP-MVSNet		99.68 32	99.51 55	99.89 9	99.95 10	99.76 22	99.83 20	99.96 12	98.83 158	99.84 54	99.65 107	99.09 193	99.80 10	99.78 31	99.62 32	99.95 7	99.82 18

casdiffmvs_mvg		99.67 36	99.61 33	99.74 61	99.94 23	99.60 49	99.62 79	99.77 129	99.54 49	99.67 135	99.82 69	99.80 128	99.52 67	99.40 86	99.51 42	99.91 25	99.59 80
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Casviewmamba		99.66 37	99.63 27	99.69 74	99.87 69	99.60 49	99.54 106	99.70 158	99.58 39	99.73 106	99.86 53	99.93 59	99.42 92	99.40 86	99.37 61	99.90 29	99.66 57

hybridcas		99.66 37	99.63 27	99.68 76	99.88 62	99.60 49	99.58 90	99.67 175	99.61 34	99.67 135	99.87 43	99.95 37	99.38 93	99.40 86	99.37 61	99.90 29	99.64 64

viewdifsd2359ckpt11		99.66 37	99.64 23	99.68 76	99.90 43	99.67 40	99.56 96	99.72 151	99.67 16	99.69 124	99.87 43	99.93 59	99.53 61	99.51 64	99.23 74	99.69 118	99.60 76

viewmsd2359difaftdt		99.66 37	99.64 23	99.68 76	99.90 43	99.67 40	99.56 96	99.72 151	99.67 16	99.69 124	99.87 43	99.93 59	99.53 61	99.51 64	99.23 74	99.69 118	99.60 76

PVSNet_Blended_VisFu		99.66 37	99.64 23	99.67 80	99.91 37	99.71 33	99.61 80	99.79 116	99.41 70	99.91 16	99.85 56	99.61 159	99.00 164	99.67 47	99.42 57	99.81 65	99.81 22

v10		99.65 42	99.51 55	99.81 33	99.83 114	99.61 48	99.75 43	99.94 24	99.56 44	99.76 84	99.94 11	99.60 161	99.73 25	99.11 157	99.01 120	99.85 47	99.74 38

CHOSEN 1792x2688		99.65 42	99.55 48	99.77 49	99.93 30	99.60 49	99.79 31	99.92 38	99.73 5	99.74 97	99.93 16	99.98 11	99.80 10	98.83 203	99.01 120	99.45 189	99.76 34

UA-Net		99.64 44	99.62 31	99.66 84	99.97 2	99.82 8	99.14 201	99.96 12	98.95 138	99.52 173	99.38 154	99.86 102	99.55 57	99.72 39	99.66 25	99.80 70	99.94 1

viewmacassd2359aftdt		99.63 45	99.56 46	99.71 68	99.89 50	99.56 65	99.55 101	99.77 129	99.65 22	99.72 110	99.84 58	99.99 5	99.53 61	99.25 122	99.09 104	99.81 65	99.57 96

GeoE		99.63 45	99.51 55	99.78 44	99.91 37	99.57 61	99.78 34	99.97 1	99.23 92	99.72 110	99.72 94	99.80 128	99.50 74	99.45 80	99.10 102	99.79 75	99.71 49

Baseline_NR-MVSNet		99.62 47	99.48 64	99.78 44	99.85 100	99.76 22	99.59 86	99.82 94	98.84 154	99.88 30	99.91 27	99.04 194	99.61 47	99.46 73	99.78 15	99.94 16	99.60 76

E4		99.61 48	99.56 46	99.67 80	99.89 50	99.56 65	99.52 112	99.76 139	99.70 9	99.76 84	99.87 43	99.99 5	99.31 108	99.21 131	99.06 108	99.79 75	99.55 103

pmmvs-eth3d		99.61 48	99.48 64	99.75 55	99.87 69	99.30 153	99.75 43	99.89 55	99.23 92	99.85 50	99.88 40	99.97 17	99.49 79	99.46 73	99.01 120	99.68 121	99.52 115

v1144		99.61 48	99.43 76	99.82 28	99.88 62	99.41 121	99.76 39	99.86 66	99.64 25	99.84 54	99.95 6	99.49 170	99.74 22	99.00 172	98.93 132	99.84 51	99.58 89

v8		99.61 48	99.45 72	99.79 43	99.80 130	99.59 55	99.73 54	99.93 27	99.48 61	99.77 81	99.90 31	99.48 171	99.67 37	99.11 157	98.89 141	99.84 51	99.73 40

casdiffmvs		99.61 48	99.55 48	99.68 76	99.89 50	99.53 77	99.64 73	99.68 170	99.51 55	99.62 147	99.90 31	99.96 24	99.37 95	99.28 115	99.25 73	99.88 36	99.44 140
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CSCG		99.61 48	99.52 53	99.71 68	99.89 50	99.62 46	99.52 112	99.76 139	99.61 34	99.69 124	99.73 88	99.96 24	99.57 55	99.27 118	98.62 175	99.81 65	99.85 15

v1192		99.60 54	99.41 80	99.82 28	99.89 50	99.43 111	99.81 28	99.84 82	99.63 30	99.85 50	99.95 6	99.35 182	99.72 27	99.01 168	98.90 140	99.82 60	99.58 89

APDe-MVS		99.60 54	99.48 64	99.73 64	99.85 100	99.51 92	99.75 43	99.85 73	99.17 102	99.81 65	99.56 122	99.94 49	99.44 89	99.42 82	99.22 76	99.67 123	99.54 107
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
FE-MVSNET		99.59 56	99.41 80	99.80 38	99.80 130	99.53 77	99.83 20	99.87 61	99.06 118	99.88 30	99.47 141	99.94 49	99.71 30	99.58 60	99.06 108	99.73 101	99.26 179

v1921920		99.59 56	99.40 84	99.82 28	99.88 62	99.45 105	99.81 28	99.83 87	99.65 22	99.86 43	99.95 6	99.29 187	99.75 19	98.98 175	98.86 145	99.78 78	99.59 80

TranMVSNet+NR-MVSNet		99.59 56	99.42 79	99.80 38	99.87 69	99.55 67	99.64 73	99.86 66	99.05 122	99.88 30	99.72 94	99.33 185	99.64 44	99.47 72	99.14 88	99.91 25	99.67 56

EG-PatchMatch MVS		99.59 56	99.49 63	99.70 72	99.82 124	99.26 160	99.39 153	99.83 87	98.99 130	99.93 8	99.54 124	99.92 70	99.51 70	99.78 31	99.50 43	99.73 101	99.41 148

viewdifsd2359ckpt07		99.58 60	99.59 39	99.56 118	99.86 89	99.53 77	99.31 169	99.65 182	99.62 33	99.71 118	99.78 78	99.94 49	99.29 111	99.35 96	99.29 71	99.57 161	99.62 72

pmmvs5		99.58 60	99.47 67	99.70 72	99.84 106	99.50 93	99.58 90	99.80 111	98.98 133	99.73 106	99.92 18	99.81 122	99.49 79	99.28 115	99.05 113	99.77 82	99.73 40

v144192		99.58 60	99.39 86	99.80 38	99.87 69	99.44 107	99.77 35	99.84 82	99.64 25	99.86 43	99.93 16	99.35 182	99.72 27	98.92 181	98.82 150	99.74 96	99.66 57

v148		99.58 60	99.43 76	99.76 50	99.87 69	99.40 124	99.76 39	99.85 73	99.48 61	99.83 59	99.82 69	99.83 116	99.51 70	99.20 135	98.82 150	99.75 90	99.45 137

v1240		99.58 60	99.38 90	99.82 28	99.89 50	99.49 95	99.82 26	99.83 87	99.63 30	99.86 43	99.96 4	98.92 200	99.75 19	99.15 147	98.96 129	99.76 84	99.56 98

E5new		99.57 65	99.51 55	99.64 91	99.89 50	99.55 67	99.49 127	99.74 147	99.70 9	99.75 90	99.83 62	99.98 11	99.17 133	99.06 163	98.92 133	99.80 70	99.51 118

E5		99.57 65	99.51 55	99.64 91	99.89 50	99.55 67	99.49 127	99.74 147	99.70 9	99.75 90	99.83 62	99.98 11	99.17 133	99.06 163	98.92 133	99.80 70	99.51 118

V42		99.57 65	99.41 80	99.75 55	99.84 106	99.37 136	99.73 54	99.83 87	99.41 70	99.75 90	99.89 34	99.42 176	99.60 49	99.15 147	98.96 129	99.76 84	99.65 61

E3		99.56 68	99.50 61	99.62 98	99.87 69	99.52 86	99.43 143	99.72 151	99.64 25	99.74 97	99.83 62	99.97 17	99.18 131	99.13 153	98.92 133	99.76 84	99.51 118

TSAR-MVS + MP.		99.56 68	99.54 51	99.58 105	99.69 180	99.14 182	99.73 54	99.45 221	99.50 58	99.35 209	99.60 116	99.93 59	99.50 74	99.56 61	99.37 61	99.77 82	99.64 64
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
v2v482		99.56 68	99.35 94	99.81 33	99.87 69	99.35 142	99.75 43	99.85 73	99.56 44	99.87 37	99.95 6	99.44 174	99.66 38	98.91 184	98.76 157	99.86 44	99.45 137

E3new		99.55 71	99.50 61	99.61 100	99.87 69	99.52 86	99.43 143	99.71 156	99.64 25	99.74 97	99.83 62	99.97 17	99.18 131	99.13 153	98.92 133	99.76 84	99.51 118

Gipuma		99.55 71	99.23 120	99.91 5	99.87 69	99.52 86	99.86 11	99.93 27	99.87 1	99.96 3	96.72 254	99.55 166	99.97 1	99.77 33	99.46 50	99.87 42	99.74 38
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
viewmanbaseed2359cas		99.53 73	99.46 70	99.61 100	99.85 100	99.49 95	99.37 156	99.69 162	99.54 49	99.68 133	99.73 88	99.96 24	99.32 104	99.14 150	98.86 145	99.76 84	99.52 115

DVP-MVS		99.53 73	99.51 55	99.55 119	99.82 124	99.58 59	99.54 106	99.78 121	99.28 88	99.21 221	99.70 99	99.97 17	99.32 104	99.32 103	99.14 88	99.64 136	99.58 89
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
diffmvs_AUTHOR		99.52 75	99.47 67	99.57 111	99.90 43	99.47 102	99.45 136	99.70 158	99.70 9	99.57 161	99.92 18	99.95 37	99.20 126	98.88 189	98.92 133	99.63 138	99.48 126

NR-MVSNet		99.52 75	99.29 106	99.80 38	99.96 7	99.38 132	99.55 101	99.81 103	98.86 151	99.87 37	99.51 135	98.81 202	99.72 27	99.86 18	99.04 115	99.89 34	99.54 107

usedtu_dtu_shiyan2		99.51 77	99.38 90	99.67 80	99.94 23	99.48 98	99.77 35	99.32 235	99.13 111	99.96 3	99.92 18	99.96 24	99.52 67	99.40 86	98.35 200	99.52 176	99.39 156

viewcassd2359sk11		99.51 77	99.45 72	99.57 111	99.84 106	99.50 93	99.37 156	99.67 175	99.58 39	99.72 110	99.79 76	99.92 70	99.08 153	99.07 162	98.81 153	99.73 101	99.48 126

ACMMPR		99.51 77	99.32 101	99.72 65	99.87 69	99.33 146	99.61 80	99.85 73	99.19 99	99.73 106	98.73 207	99.95 37	99.61 47	99.35 96	99.14 88	99.66 126	99.58 89

UniMVSNet (Re)		99.50 80	99.29 106	99.75 55	99.86 89	99.47 102	99.51 116	99.82 94	98.90 146	99.89 21	99.64 108	99.00 195	99.54 60	99.32 103	99.08 106	99.90 29	99.59 80

FMVSNet1		99.50 80	99.57 43	99.42 151	99.67 189	99.65 43	99.60 84	99.91 44	99.40 73	99.39 201	99.83 62	99.27 189	98.14 213	99.68 44	99.50 43	99.81 65	99.68 53

HyFIR lowres test		99.50 80	99.26 114	99.80 38	99.95 10	99.62 46	99.76 39	99.97 1	99.67 16	99.56 162	99.94 11	98.40 210	99.78 13	98.84 201	98.59 180	99.76 84	99.72 43

PM-MVS		99.49 83	99.43 76	99.57 111	99.76 156	99.34 145	99.53 108	99.77 129	98.93 142	99.75 90	99.46 142	99.83 116	99.11 151	99.72 39	99.29 71	99.49 183	99.46 136

MED-MVS		99.48 84	99.44 75	99.53 123	99.79 135	99.39 126	99.49 127	99.78 121	99.44 66	99.40 200	99.77 82	99.91 78	99.02 162	99.26 120	99.03 117	99.70 116	99.27 174

Anonymous20231206		99.48 84	99.31 103	99.69 74	99.79 135	99.57 61	99.63 77	99.79 116	98.88 148	99.91 16	99.72 94	99.93 59	99.59 51	99.24 123	98.63 173	99.43 193	99.18 183

DU-MVS		99.48 84	99.26 114	99.75 55	99.85 100	99.38 132	99.50 120	99.81 103	98.86 151	99.89 21	99.51 135	98.98 196	99.59 51	99.46 73	98.97 127	99.87 42	99.63 66

RPSCF		99.48 84	99.45 72	99.52 130	99.73 173	99.33 146	99.13 202	99.77 129	99.33 80	99.47 187	99.39 153	99.92 70	99.36 96	99.63 54	99.13 96	99.63 138	99.41 148

ACMMP_NAP		99.47 88	99.33 98	99.63 94	99.85 100	99.28 158	99.56 96	99.83 87	98.75 164	99.48 183	99.03 194	99.95 37	99.47 87	99.48 69	99.19 79	99.57 161	99.59 80

Anonymous20231211		99.47 88	99.39 86	99.57 111	99.89 50	99.60 49	99.50 120	99.69 162	98.91 145	99.62 147	99.17 180	99.35 182	98.86 183	99.63 54	99.46 50	99.84 51	99.62 72

SteuartSystems-ACMMP		99.47 88	99.22 123	99.76 50	99.88 62	99.36 138	99.65 72	99.84 82	98.47 189	99.80 67	98.68 210	99.96 24	99.68 34	99.37 93	99.06 108	99.72 109	99.66 57
Skip Steuart: Steuart Systems R&D Blog.
ACMM	98.37 12	99.47 88	99.23 120	99.74 61	99.86 89	99.19 176	99.68 65	99.86 66	99.16 106	99.71 118	98.52 220	99.95 37	99.62 46	99.35 96	99.02 118	99.74 96	99.42 146
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
E2		99.46 92	99.40 84	99.53 123	99.83 114	99.48 98	99.30 175	99.63 186	99.52 53	99.70 121	99.75 84	99.85 108	98.99 167	99.01 168	98.71 164	99.71 113	99.47 132

DVP-MVS++		99.46 92	99.57 43	99.33 173	99.75 160	99.57 61	99.44 139	99.81 103	99.38 76	98.56 262	99.81 73	99.99 5	98.79 189	99.33 101	99.13 96	99.62 146	99.81 22

HFP-MVS		99.46 92	99.30 104	99.65 86	99.82 124	99.25 164	99.50 120	99.82 94	99.23 92	99.58 158	98.86 198	99.94 49	99.56 56	99.14 150	99.12 100	99.63 138	99.56 98

LGP-MVS_train		99.46 92	99.18 134	99.78 44	99.87 69	99.25 164	99.71 62	99.87 61	98.02 221	99.79 72	98.90 197	99.96 24	99.66 38	99.49 67	99.17 84	99.79 75	99.49 123

dtuplus		99.45 96	99.35 94	99.58 105	99.83 114	99.43 111	99.60 84	99.72 151	99.41 70	99.50 177	99.80 74	99.91 78	99.08 153	98.84 201	98.54 182	99.73 101	99.48 126

viewdifsd2359ckpt13		99.45 96	99.39 86	99.53 123	99.83 114	99.44 107	99.17 196	99.66 180	99.51 55	99.66 140	99.75 84	99.92 70	99.14 145	99.01 168	98.62 175	99.72 109	99.47 132

MVSMamba_PlusPlus		99.45 96	99.52 53	99.36 170	99.79 135	99.54 73	98.88 233	99.26 238	98.97 134	99.22 219	99.51 135	99.80 128	99.29 111	99.65 51	99.37 61	99.73 101	99.82 18

SED-MVS		99.45 96	99.46 70	99.42 151	99.77 151	99.57 61	99.42 145	99.80 111	99.06 118	99.38 202	99.66 104	99.96 24	98.65 199	99.31 105	99.14 88	99.53 174	99.55 103

ETV-MVS		99.45 96	99.32 101	99.60 102	99.79 135	99.60 49	99.40 150	99.78 121	97.88 227	99.83 59	99.33 158	99.70 149	98.97 168	99.74 36	99.43 54	99.84 51	99.58 89

ACMP	98.32 13	99.44 101	99.18 134	99.75 55	99.83 114	99.18 177	99.64 73	99.83 87	98.81 160	99.79 72	98.42 229	99.96 24	99.64 44	99.46 73	98.98 126	99.74 96	99.44 140
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
viewmamba		99.43 102	99.36 92	99.50 134	99.87 69	99.40 124	99.29 179	99.62 189	99.64 25	99.56 162	99.87 43	99.94 49	99.16 138	98.78 208	98.50 187	99.54 172	99.37 160

DCV-MVSNet		99.43 102	99.23 120	99.67 80	99.92 33	99.76 22	99.64 73	99.93 27	99.06 118	99.68 133	97.77 241	98.97 197	98.97 168	99.72 39	99.54 38	99.88 36	99.81 22

SMA-MVS		99.43 102	99.41 80	99.45 146	99.82 124	99.31 151	99.02 217	99.59 197	99.06 118	99.34 212	99.53 130	99.96 24	99.38 93	99.29 110	99.13 96	99.53 174	99.59 80
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
testgi		99.43 102	99.47 67	99.38 160	99.90 43	99.67 40	99.30 175	99.73 150	98.64 177	99.53 167	99.52 132	99.90 83	98.08 216	99.65 51	99.40 60	99.75 90	99.55 103

DELS-MVS		99.42 106	99.53 52	99.29 177	99.52 217	99.43 111	99.42 145	99.28 237	99.16 106	99.72 110	99.82 69	99.97 17	98.17 210	99.56 61	99.16 85	99.65 128	99.59 80
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
3Dnovator	99.16 3	99.42 106	99.22 123	99.65 86	99.78 142	99.13 186	99.50 120	99.85 73	99.40 73	99.80 67	98.59 216	99.79 133	99.30 110	99.20 135	99.06 108	99.71 113	99.35 164

onestephybrid01		99.41 108	99.35 94	99.49 136	99.88 62	99.41 121	99.45 136	99.61 190	99.44 66	99.59 154	99.88 40	99.90 83	98.88 181	98.83 203	98.60 179	99.54 172	99.35 164

viewmambaseed2359dif		99.41 108	99.27 112	99.58 105	99.83 114	99.42 116	99.56 96	99.68 170	99.27 89	99.58 158	99.80 74	99.85 108	99.14 145	98.70 215	98.41 195	99.67 123	99.47 132

DPE-MVS		99.41 108	99.36 92	99.47 140	99.66 190	99.48 98	99.46 135	99.75 145	98.65 173	99.41 197	99.67 102	99.95 37	98.82 184	99.21 131	99.14 88	99.72 109	99.40 153
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UniMVSNet_NR-MVSNet		99.41 108	99.12 146	99.76 50	99.86 89	99.48 98	99.50 120	99.81 103	98.84 154	99.89 21	99.45 143	98.32 213	99.59 51	99.22 127	98.89 141	99.90 29	99.63 66

CP-MVS		99.41 108	99.20 129	99.65 86	99.80 130	99.23 171	99.44 139	99.75 145	98.60 182	99.74 97	98.66 211	99.93 59	99.48 82	99.33 101	99.16 85	99.73 101	99.48 126

QAPM		99.41 108	99.21 128	99.64 91	99.78 142	99.16 179	99.51 116	99.85 73	99.20 96	99.72 110	99.43 144	99.81 122	99.25 119	98.87 191	98.71 164	99.71 113	99.30 170

aaEdge-Enhanced		99.40 114	99.34 97	99.48 138	99.78 142	99.36 138	99.75 43	99.46 219	99.08 113	99.38 202	99.77 82	99.89 86	99.07 156	99.16 146	98.84 148	99.41 197	99.27 174

UGNet		99.40 114	99.61 33	99.16 199	99.88 62	99.64 44	99.61 80	99.77 129	99.31 82	99.63 146	99.33 158	99.93 59	96.46 251	99.63 54	99.53 39	99.63 138	99.89 5
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
Vis-MVSNet (Re-imp)		99.40 114	99.28 109	99.55 119	99.92 33	99.68 37	99.31 169	99.87 61	98.69 170	99.16 224	99.08 189	98.64 206	99.20 126	99.65 51	99.46 50	99.83 56	99.72 43

hybridnocas07		99.39 117	99.33 98	99.47 140	99.86 89	99.39 126	99.35 162	99.63 186	99.55 46	99.48 183	99.87 43	99.83 116	98.90 180	98.71 214	98.44 193	99.56 166	99.50 122

OPM-MVS		99.39 117	99.22 123	99.59 103	99.76 156	98.82 212	99.51 116	99.79 116	99.17 102	99.53 167	99.31 163	99.95 37	99.35 97	99.22 127	98.79 156	99.60 152	99.27 174
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Fast-Effi-MVS+		99.39 117	99.18 134	99.63 94	99.86 89	99.28 158	99.45 136	99.91 44	98.47 189	99.61 150	99.50 138	99.57 163	99.17 133	99.24 123	98.66 170	99.78 78	99.59 80

LS3D		99.39 117	99.28 109	99.52 130	99.77 151	99.39 126	99.55 101	99.82 94	98.93 142	99.64 144	98.52 220	99.67 153	98.58 203	99.74 36	99.63 30	99.75 90	99.06 200

diffmvs		99.38 121	99.33 98	99.45 146	99.87 69	99.39 126	99.28 184	99.58 201	99.55 46	99.50 177	99.85 56	99.85 108	98.94 174	98.58 221	98.68 168	99.51 180	99.39 156
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt09		99.37 122	99.29 106	99.46 143	99.83 114	99.42 116	99.12 205	99.63 186	99.52 53	99.67 135	99.73 88	99.67 153	98.91 176	98.81 206	98.47 188	99.61 148	99.42 146

usedtu_dtu_shiyan1		99.36 123	99.20 129	99.55 119	99.40 245	99.35 142	99.56 96	99.69 162	98.96 136	99.81 65	99.52 132	99.66 155	99.24 120	99.14 150	98.63 173	99.60 152	99.18 183

CANet		99.36 123	99.39 86	99.34 172	99.80 130	99.35 142	99.41 149	99.47 216	99.20 96	99.74 97	99.54 124	99.68 151	98.05 218	99.23 125	98.97 127	99.57 161	99.73 40

ACMMP		99.36 123	99.06 154	99.71 68	99.86 89	99.36 138	99.63 77	99.85 73	98.33 204	99.72 110	97.73 243	99.94 49	99.53 61	99.37 93	99.13 96	99.65 128	99.56 98
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
hybrid		99.35 126	99.28 109	99.44 148	99.86 89	99.39 126	99.32 166	99.61 190	99.51 55	99.49 180	99.87 43	99.72 144	98.92 175	98.65 218	98.40 196	99.47 186	99.40 153

SD-MVS		99.35 126	99.26 114	99.46 143	99.66 190	99.15 181	98.92 228	99.67 175	99.55 46	99.35 209	98.83 200	99.91 78	99.35 97	99.19 138	98.53 184	99.78 78	99.68 53
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
MP-MVS		99.35 126	99.09 152	99.65 86	99.84 106	99.22 172	99.59 86	99.78 121	98.13 213	99.67 135	98.44 225	99.93 59	99.43 91	99.31 105	99.09 104	99.60 152	99.49 123
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
pmmvs4		99.34 129	99.15 141	99.57 111	99.77 151	98.90 205	99.51 116	99.77 129	99.07 116	99.73 106	99.72 94	99.84 114	99.07 156	98.85 196	98.39 198	99.55 170	99.27 174

EPP-MVSNet		99.34 129	99.10 150	99.62 98	99.94 23	99.74 30	99.66 71	99.80 111	99.07 116	98.93 243	99.61 113	96.13 229	99.49 79	99.67 47	99.63 30	99.92 22	99.86 13

TSAR-MVS + GP.		99.33 131	99.17 138	99.51 132	99.71 178	99.00 199	98.84 237	99.71 156	98.23 210	99.74 97	99.53 130	99.90 83	99.35 97	99.38 92	98.85 147	99.72 109	99.31 168

PHI-MVS		99.33 131	99.19 132	99.49 136	99.69 180	99.25 164	99.27 185	99.59 197	98.44 193	99.78 76	99.15 181	99.92 70	98.95 173	99.39 90	99.04 115	99.64 136	99.18 183

MSP-MVS		99.32 133	99.26 114	99.38 160	99.76 156	99.54 73	99.42 145	99.72 151	98.92 144	98.84 251	98.96 196	99.96 24	98.91 176	98.72 213	99.14 88	99.63 138	99.58 89
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
PGM-MVS		99.32 133	98.99 163	99.71 68	99.86 89	99.31 151	99.59 86	99.86 66	97.51 238	99.75 90	98.23 233	99.94 49	99.53 61	99.29 110	99.08 106	99.65 128	99.54 107

DeepC-MVS_fast	98.69 9	99.32 133	99.13 144	99.53 123	99.63 196	98.78 215	99.53 108	99.33 234	99.08 113	99.77 81	99.18 179	99.89 86	99.29 111	99.00 172	98.70 166	99.65 128	99.30 170
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSDG		99.32 133	99.09 152	99.58 105	99.75 160	98.74 219	99.36 159	99.54 205	99.14 109	99.72 110	99.24 169	99.89 86	99.51 70	99.30 107	98.76 157	99.62 146	98.54 221

TSAR-MVS + ACMM		99.31 137	99.26 114	99.37 166	99.66 190	98.97 202	99.20 193	99.56 203	99.33 80	99.19 223	99.54 124	99.91 78	99.32 104	99.12 155	98.34 202	99.29 209	99.65 61

3Dnovator+	98.92 7	99.31 137	99.03 158	99.63 94	99.77 151	98.90 205	99.52 112	99.81 103	99.37 77	99.72 110	98.03 238	99.73 143	99.32 104	98.99 174	98.81 153	99.67 123	99.36 162

X-MVS		99.30 139	98.99 163	99.66 84	99.85 100	99.30 153	99.49 127	99.82 94	98.32 205	99.69 124	97.31 252	99.93 59	99.50 74	99.37 93	99.16 85	99.60 152	99.53 110

MVS_111021_HR		99.30 139	99.14 142	99.48 138	99.58 213	99.25 164	99.27 185	99.61 190	98.74 166	99.66 140	99.02 195	99.84 114	99.33 101	99.20 135	98.76 157	99.44 190	99.18 183

TAPA-MVS	98.54 10	99.30 139	99.24 119	99.36 170	99.44 235	98.77 217	99.00 219	99.41 225	99.23 92	99.60 152	99.50 138	99.86 102	99.15 143	99.29 110	98.95 131	99.56 166	99.08 196
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CLD-MVS		99.30 139	99.01 162	99.63 94	99.75 160	98.89 208	99.35 162	99.60 194	98.53 187	99.86 43	99.57 120	99.94 49	99.52 67	98.96 176	98.10 215	99.70 116	99.08 196
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
USDC		99.29 143	98.98 165	99.65 86	99.72 175	98.87 210	99.47 132	99.66 180	99.35 79	99.87 37	99.58 119	99.87 100	99.51 70	98.85 196	97.93 221	99.65 128	98.38 225

PMVS	94.32 17	99.27 144	99.55 48	98.94 216	99.60 205	99.43 111	99.39 153	99.54 205	98.99 130	99.69 124	99.60 116	99.81 122	95.68 258	99.88 15	99.83 7	99.73 101	99.31 168
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
dtuonlycased		99.26 145	99.27 112	99.24 185	99.84 106	99.49 95	99.47 132	99.22 240	99.27 89	99.21 221	99.94 11	99.76 138	99.11 151	99.12 155	98.54 182	98.62 235	98.76 215

FA-MVS(training)		99.26 145	99.12 146	99.44 148	99.60 205	99.26 160	99.24 190	99.97 1	98.84 154	99.76 84	99.43 144	98.74 203	98.47 206	99.39 90	99.10 102	99.57 161	99.07 199

MVS_111021_LR		99.25 147	99.13 144	99.39 156	99.50 225	99.14 182	99.23 191	99.50 213	98.67 171	99.61 150	99.12 185	99.81 122	99.16 138	99.28 115	98.67 169	99.35 205	99.21 182

ECVR-MVS		99.24 148	98.74 189	99.82 28	99.95 10	99.78 18	99.67 69	99.93 27	99.45 64	99.80 67	99.86 53	92.58 255	99.65 40	99.93 3	99.88 3	99.94 16	99.71 49

baseline		99.24 148	99.30 104	99.17 198	99.78 142	99.14 182	99.10 207	99.69 162	98.97 134	99.49 180	99.84 58	99.88 93	97.99 223	98.85 196	98.73 162	98.98 224	99.72 43

EIA-MVS		99.23 150	99.03 158	99.47 140	99.83 114	99.64 44	99.16 198	99.81 103	97.11 251	99.65 143	98.44 225	99.78 136	98.61 202	99.46 73	99.22 76	99.75 90	99.59 80

HPM-MVS++		99.23 150	98.98 165	99.53 123	99.75 160	99.02 197	99.44 139	99.77 129	98.65 173	99.52 173	98.72 208	99.92 70	99.33 101	98.77 211	98.40 196	99.40 199	99.36 162

PMMVS2		99.23 150	99.22 123	99.24 185	99.80 130	99.14 182	99.50 120	99.82 94	99.12 112	98.41 268	99.91 27	99.98 11	98.51 204	99.48 69	98.76 157	99.38 201	98.14 233

MGCNet		99.22 153	99.22 123	99.23 187	99.87 69	99.58 59	99.70 63	99.59 197	99.58 39	98.98 239	99.40 151	97.31 226	97.53 232	99.41 85	99.43 54	99.69 118	99.81 22

test1111		99.21 154	98.67 195	99.84 23	99.96 7	99.82 8	99.72 59	99.94 24	99.54 49	99.78 76	99.89 34	91.89 258	99.69 32	99.93 3	99.89 1	99.95 7	99.75 36

CPTT-MVS		99.21 154	98.89 175	99.58 105	99.72 175	99.12 189	99.30 175	99.76 139	98.62 178	99.66 140	97.51 248	99.89 86	99.48 82	99.01 168	98.64 172	99.58 160	99.40 153

TinyColmap		99.21 154	98.89 175	99.59 103	99.61 201	98.61 227	99.47 132	99.67 175	99.02 126	99.82 62	99.15 181	99.74 140	99.35 97	99.17 144	98.33 203	99.63 138	98.22 231

Effi-MVS+		99.20 157	98.93 170	99.50 134	99.79 135	99.26 160	98.82 240	99.96 12	98.37 203	99.60 152	99.12 185	98.36 211	99.05 160	98.93 179	98.82 150	99.78 78	99.68 53

PVSNet_BlendedMVS		99.20 157	99.17 138	99.23 187	99.69 180	99.33 146	99.04 212	99.13 242	98.41 198	99.79 72	99.33 158	99.36 179	98.10 214	99.29 110	98.87 143	99.65 128	99.56 98

PVSNet_Blended		99.20 157	99.17 138	99.23 187	99.69 180	99.33 146	99.04 212	99.13 242	98.41 198	99.79 72	99.33 158	99.36 179	98.10 214	99.29 110	98.87 143	99.65 128	99.56 98

MCST-MVS		99.17 160	98.82 184	99.57 111	99.75 160	98.70 223	99.25 189	99.69 162	98.62 178	99.59 154	98.54 218	99.79 133	99.53 61	98.48 225	98.15 211	99.63 138	99.43 143

APD-MVS		99.17 160	98.92 171	99.46 143	99.78 142	99.24 169	99.34 164	99.78 121	97.79 230	99.48 183	98.25 232	99.88 93	98.77 191	99.18 141	98.92 133	99.63 138	99.18 183
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
OpenMVS	98.82 8	99.17 160	98.85 179	99.53 123	99.75 160	99.06 195	99.36 159	99.82 94	98.28 207	99.76 84	98.47 222	99.61 159	98.91 176	98.80 207	98.70 166	99.60 152	99.04 204

IterMVS-LS		99.16 163	98.82 184	99.57 111	99.87 69	99.71 33	99.58 90	99.92 38	99.24 91	99.71 118	99.73 88	95.79 230	98.91 176	98.82 205	98.66 170	99.43 193	99.77 32
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DeepPCF-MVS	98.38 11	99.16 163	99.20 129	99.12 203	99.20 258	98.71 222	98.85 236	99.06 245	99.17 102	98.96 242	99.61 113	99.86 102	99.29 111	99.17 144	98.72 163	99.36 203	99.15 192

IterMVS-SCA-FT		99.15 165	98.96 167	99.38 160	99.87 69	99.54 73	99.53 108	99.79 116	98.94 140	99.82 62	99.92 18	97.65 220	98.82 184	98.95 178	98.26 205	98.45 237	99.47 132

CDS-MVSNet		99.15 165	99.10 150	99.21 194	99.59 210	99.22 172	99.48 131	99.47 216	98.89 147	99.41 197	99.84 58	98.11 216	97.76 226	99.26 120	99.01 120	99.57 161	99.38 158
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IS_MVSNet		99.15 165	99.12 146	99.19 196	99.92 33	99.73 32	99.55 101	99.86 66	98.45 192	96.91 274	98.74 206	98.33 212	99.02 162	99.54 63	99.47 48	99.88 36	99.61 75

dmvs_re		99.14 168	98.76 187	99.58 105	99.75 160	99.38 132	99.30 175	99.68 170	96.94 256	99.74 97	97.70 244	99.20 191	99.29 111	99.22 127	99.35 65	99.73 101	99.55 103

MDA-MVSNet-bldmvs		99.11 169	99.11 149	99.12 203	99.91 37	99.38 132	99.77 35	98.72 249	99.31 82	99.85 50	99.43 144	98.26 214	99.48 82	99.85 19	98.47 188	96.99 257	99.08 196

OMC-MVS		99.11 169	98.95 168	99.29 177	99.37 247	98.57 229	99.19 194	99.20 241	98.87 150	99.58 158	99.13 183	99.88 93	99.00 164	99.19 138	98.46 190	99.43 193	98.57 220

MVS_Test		99.09 171	98.92 171	99.29 177	99.61 201	99.07 194	99.04 212	99.81 103	98.58 184	99.37 206	99.74 86	98.87 201	98.41 208	98.61 220	98.01 219	99.50 182	99.57 96

CNVR-MVS		99.08 172	98.83 181	99.37 166	99.61 201	98.74 219	99.15 199	99.54 205	98.59 183	99.37 206	98.15 235	99.88 93	99.08 153	98.91 184	98.46 190	99.48 184	99.06 200

IterMVS		99.08 172	98.90 174	99.29 177	99.87 69	99.53 77	99.52 112	99.77 129	98.94 140	99.75 90	99.91 27	97.52 224	98.72 195	98.86 194	98.14 212	98.09 240	99.43 143
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet2		99.07 174	99.19 132	98.93 218	99.02 263	99.53 77	99.31 169	99.84 82	98.86 151	98.88 246	99.64 108	98.44 209	96.92 244	99.35 96	99.00 124	99.61 148	99.53 110

CVMVSNet		99.06 175	98.88 178	99.28 181	99.52 217	99.53 77	99.42 145	99.69 162	98.74 166	98.27 270	99.89 34	95.48 236	99.44 89	99.46 73	99.33 66	99.32 208	99.75 36

CDPH-MVS		99.05 176	98.63 196	99.54 122	99.75 160	98.78 215	99.59 86	99.68 170	97.79 230	99.37 206	98.20 234	99.86 102	99.14 145	98.58 221	98.01 219	99.68 121	99.16 190

TAMVS		99.05 176	99.02 161	99.08 208	99.69 180	99.22 172	99.33 165	99.32 235	99.16 106	98.97 241	99.87 43	97.36 225	97.76 226	99.21 131	99.00 124	99.44 190	99.33 166

dtuonly		99.03 178	98.84 180	99.25 184	99.90 43	98.95 203	99.44 139	99.47 216	99.05 122	99.30 214	99.94 11	99.72 144	98.81 186	98.29 228	97.35 232	98.60 236	98.59 219

CANet_DTU		99.03 178	99.18 134	98.87 221	99.58 213	99.03 196	99.18 195	99.41 225	98.65 173	99.74 97	99.55 123	99.71 146	96.13 256	99.19 138	98.92 133	99.17 218	99.18 183

Effi-MVS+-dtu		99.01 180	99.05 155	98.98 212	99.60 205	99.13 186	99.03 216	99.61 190	98.52 188	99.01 236	98.53 219	99.83 116	96.95 243	99.48 69	98.59 180	99.66 126	99.25 181

sasdasda		99.00 181	98.68 193	99.37 166	99.68 186	99.42 116	98.94 226	99.89 55	99.00 128	98.99 237	98.43 227	95.69 232	98.96 171	99.18 141	99.18 81	99.74 96	99.88 7

canonicalmvs		99.00 181	98.68 193	99.37 166	99.68 186	99.42 116	98.94 226	99.89 55	99.00 128	98.99 237	98.43 227	95.69 232	98.96 171	99.18 141	99.18 81	99.74 96	99.88 7

MIMVSNet		99.00 181	99.03 158	98.97 215	99.32 253	99.32 150	99.39 153	99.91 44	98.41 198	98.76 254	99.24 169	99.17 192	97.13 237	99.30 107	98.80 155	99.29 209	99.01 205

CHOSEN 280x420		98.99 184	98.91 173	99.07 209	99.77 151	99.26 160	99.55 101	99.92 38	98.62 178	98.67 259	99.62 112	97.20 227	98.44 207	99.50 66	99.18 81	98.08 241	98.99 208

MGCFI-Net		98.98 185	98.69 192	99.33 173	99.68 186	99.42 116	98.95 224	99.90 53	99.04 125	98.88 246	98.45 224	95.64 234	98.81 186	99.15 147	99.21 78	99.75 90	99.90 2

SF-MVS		98.96 186	98.95 168	98.98 212	99.64 195	98.89 208	98.00 267	99.58 201	98.42 196	99.08 229	98.63 213	99.83 116	98.04 220	99.02 167	98.76 157	99.52 176	99.13 193

GBi-Net		98.96 186	99.05 155	98.85 222	99.02 263	99.53 77	99.31 169	99.78 121	98.13 213	98.48 264	99.43 144	97.58 221	96.92 244	99.68 44	99.50 43	99.61 148	99.53 110

test1		98.96 186	99.05 155	98.85 222	99.02 263	99.53 77	99.31 169	99.78 121	98.13 213	98.48 264	99.43 144	97.58 221	96.92 244	99.68 44	99.50 43	99.61 148	99.53 110

PCF-MVS	97.86 15	98.95 189	98.53 201	99.44 148	99.70 179	98.80 214	98.96 221	99.69 162	98.65 173	99.59 154	99.33 158	99.94 49	99.12 150	98.01 236	97.11 233	99.59 159	97.83 242
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MS-PatchMatch		98.94 190	98.71 191	99.21 194	99.52 217	98.22 245	98.97 220	99.53 210	98.76 162	99.50 177	98.59 216	99.56 165	98.68 196	98.63 219	98.45 192	99.05 221	98.73 216

AdaColmap		98.93 191	98.53 201	99.39 156	99.52 217	98.65 226	99.11 206	99.59 197	98.08 217	99.44 190	97.46 250	99.45 172	99.24 120	98.92 181	98.44 193	99.44 190	98.73 216

MSLP-MVS++		98.92 192	98.73 190	99.14 200	99.44 235	99.00 199	98.36 256	99.35 231	98.82 159	99.38 202	96.06 258	99.79 133	99.07 156	98.88 189	99.05 113	99.27 211	99.53 110

new_pmnet		98.91 193	98.89 175	98.94 216	99.51 223	98.27 241	99.15 199	98.66 250	99.17 102	99.48 183	99.79 76	99.80 128	98.49 205	99.23 125	98.20 209	98.34 238	97.74 246

train_agg		98.89 194	98.48 206	99.38 160	99.69 180	98.76 218	99.31 169	99.60 194	97.71 232	98.98 239	97.89 239	99.89 86	99.29 111	98.32 226	97.59 228	99.42 196	99.16 190

NCCC		98.88 195	98.42 207	99.42 151	99.62 197	98.81 213	99.10 207	99.54 205	98.76 162	99.53 167	95.97 259	99.80 128	99.16 138	98.49 224	98.06 218	99.55 170	99.05 202

PLC	97.83 16	98.88 195	98.52 203	99.30 176	99.45 233	98.60 228	98.65 246	99.49 214	98.66 172	99.59 154	96.33 255	99.59 162	99.17 133	98.87 191	98.53 184	99.46 187	99.05 202
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
pmmvs3		98.85 197	98.60 197	99.13 201	99.66 190	98.72 221	99.37 156	99.06 245	98.43 195	99.76 84	99.74 86	99.55 166	99.15 143	99.04 165	96.00 241	97.80 245	98.72 218

Fast-Effi-MVS+-dtu		98.82 198	98.80 186	98.84 224	99.51 223	98.90 205	98.96 221	99.91 44	98.29 206	99.11 228	98.47 222	99.63 158	96.03 257	99.21 131	98.12 213	99.52 176	99.01 205

CNLPA		98.82 198	98.52 203	99.18 197	99.21 257	98.50 233	98.73 244	99.34 233	98.73 168	99.56 162	97.55 247	99.42 176	99.06 159	98.93 179	98.10 215	99.21 217	98.38 225

PatchMatch-RL		98.80 200	98.52 203	99.12 203	99.38 246	98.70 223	98.56 249	99.55 204	97.81 229	99.34 212	97.57 246	99.31 186	98.67 197	99.27 118	98.62 175	99.22 216	98.35 227

thisisatest0530		98.78 201	98.26 210	99.39 156	99.78 142	99.43 111	99.07 209	99.64 184	98.44 193	99.42 195	99.22 173	92.68 254	98.63 200	99.30 107	99.14 88	99.80 70	99.60 76

tttt0517		98.77 202	98.25 212	99.38 160	99.79 135	99.46 104	99.07 209	99.64 184	98.40 201	99.38 202	99.21 175	92.54 256	98.63 200	99.34 100	99.14 88	99.80 70	99.62 72

DI_MVS_pp		98.74 203	98.08 220	99.51 132	99.79 135	99.29 157	99.61 80	99.60 194	99.20 96	99.46 188	99.09 188	92.93 248	98.97 168	98.27 230	98.35 200	99.65 128	99.45 137

TSAR-MVS + COLMAP		98.74 203	98.58 199	98.93 218	99.29 254	98.23 242	99.04 212	99.24 239	98.79 161	98.80 253	99.37 155	99.71 146	98.06 217	98.02 235	97.46 230	99.16 219	98.48 223

MDTV_nov1_ep13_2view		98.73 205	98.31 209	99.22 191	99.75 160	99.24 169	99.75 43	99.93 27	99.31 82	99.84 54	99.86 53	99.81 122	99.31 108	97.40 245	94.77 243	96.73 259	97.81 243

PMMVS		98.71 206	98.55 200	98.90 220	99.28 255	98.45 235	98.53 252	99.45 221	97.67 234	99.15 226	98.76 204	99.54 168	97.79 225	98.77 211	98.23 207	99.16 219	98.46 224

HQP-MVS		98.70 207	98.19 216	99.28 181	99.61 201	98.52 231	98.71 245	99.35 231	97.97 224	99.53 167	97.38 251	99.85 108	99.14 145	97.53 240	96.85 237	99.36 203	99.26 179

N_pmnet		98.64 208	98.23 215	99.11 206	99.78 142	99.25 164	99.75 43	99.39 229	99.65 22	99.70 121	99.78 78	99.89 86	98.81 186	97.60 239	94.28 245	97.24 255	97.15 254

CMPMVS	76.62 19	98.64 208	98.60 197	98.68 234	99.33 251	97.07 267	98.11 265	98.50 251	97.69 233	99.26 216	98.35 231	99.66 155	97.62 229	99.43 81	99.02 118	99.24 214	99.01 205
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet3		98.63 210	98.75 188	98.49 241	98.10 269	99.44 107	99.02 217	99.78 121	98.13 213	98.48 264	99.43 144	97.58 221	96.16 255	98.85 196	98.39 198	99.40 199	99.41 148

GA-MVS		98.59 211	98.15 217	99.09 207	99.59 210	99.13 186	98.84 237	99.52 212	98.61 181	99.35 209	99.67 102	93.03 247	97.73 228	98.90 188	98.26 205	99.51 180	99.48 126

MAR-MVS		98.54 212	98.15 217	98.98 212	99.37 247	98.09 248	98.56 249	99.65 182	96.11 266	99.27 215	97.16 253	99.50 169	98.03 221	98.87 191	98.23 207	99.01 222	99.13 193
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
new-patchmatchnet		98.49 213	97.60 222	99.53 123	99.90 43	99.55 67	99.77 35	99.48 215	99.67 16	99.86 43	99.98 3	99.98 11	99.50 74	96.90 247	91.52 251	98.67 232	95.62 263

FPMVS		98.48 214	98.83 181	98.07 252	99.09 261	97.98 252	99.07 209	98.04 257	98.99 130	99.22 219	98.85 199	99.43 175	93.79 267	99.66 49	99.11 101	99.24 214	97.76 244

MVS-HIRNet		98.45 215	98.25 212	98.69 233	99.12 259	97.81 258	98.55 251	99.85 73	98.58 184	99.67 135	99.61 113	99.86 102	97.46 233	97.95 237	96.37 239	97.49 252	97.56 249

test0.0.03 1		98.41 216	98.41 208	98.40 245	99.62 197	99.16 179	98.87 234	99.41 225	97.15 249	96.60 276	99.31 163	97.00 228	96.55 250	98.91 184	98.51 186	99.37 202	98.82 212

gg-mvs-nofinetune		98.40 217	98.26 210	98.57 238	99.83 114	98.86 211	98.77 243	99.97 1	99.57 43	99.99 1	99.99 1	93.81 244	93.50 268	98.91 184	98.20 209	99.33 207	98.52 222

baseline1		98.39 218	97.59 223	99.31 175	99.78 142	99.45 105	99.13 202	99.53 210	98.06 219	98.87 248	98.63 213	90.04 262	98.76 192	98.85 196	98.84 148	99.81 65	99.28 172

pmnet_mix02		98.28 219	97.48 225	99.22 191	99.78 142	99.12 189	99.68 65	99.39 229	99.49 60	99.86 43	99.82 69	99.89 86	99.23 122	95.54 250	92.36 248	97.38 253	96.14 261

PatchT		98.11 220	97.12 231	99.26 183	99.65 194	98.34 239	99.57 95	99.97 1	97.48 240	99.43 192	99.04 193	90.84 260	98.15 211	98.04 233	97.78 222	98.82 229	98.30 228

DPM-MVS		98.10 221	97.32 229	99.01 211	99.52 217	97.92 253	98.47 254	99.45 221	98.25 208	98.91 244	93.99 268	99.69 150	98.73 194	96.29 249	96.32 240	99.00 223	98.77 213

EPNet_dtu		98.09 222	98.25 212	97.91 254	99.58 213	98.02 251	98.19 261	99.67 175	97.94 225	99.74 97	99.07 191	98.71 205	93.40 269	97.50 241	97.09 234	96.89 258	99.44 140
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPNet		98.06 223	98.11 219	98.00 253	99.60 205	98.99 201	98.38 255	99.68 170	98.18 212	98.85 250	97.89 239	95.60 235	92.72 270	98.30 227	98.10 215	98.76 230	99.72 43
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		97.91 224	96.80 234	99.22 191	99.60 205	98.23 242	98.91 229	99.97 1	96.89 259	99.43 192	99.10 187	89.24 265	98.15 211	98.04 233	97.78 222	99.26 212	98.30 228

thres200		97.87 225	96.56 236	99.39 156	99.76 156	99.52 86	99.13 202	99.76 139	96.88 261	98.66 260	92.87 272	88.77 268	99.16 138	99.11 157	99.42 57	99.88 36	99.33 166

baseline2		97.87 225	97.18 230	98.67 235	99.34 250	99.17 178	98.48 253	98.82 248	97.08 252	98.83 252	98.75 205	89.47 264	97.03 242	98.67 217	98.27 204	99.52 176	98.83 211

thres600view7		97.86 227	96.53 239	99.41 154	99.84 106	99.52 86	99.36 159	99.76 139	97.32 247	98.38 269	93.24 269	87.25 270	99.23 122	99.11 157	99.75 18	99.88 36	99.48 126

tfpn200view9		97.85 228	96.54 237	99.38 160	99.74 171	99.52 86	99.17 196	99.76 139	96.10 267	98.70 257	92.99 270	89.10 266	99.00 164	99.11 157	99.56 34	99.88 36	99.41 148

thres400		97.82 229	96.47 240	99.40 155	99.81 129	99.44 107	99.29 179	99.69 162	97.15 249	98.57 261	92.82 273	87.96 269	99.16 138	98.96 176	99.55 37	99.86 44	99.41 148

IB-MVS	98.10 14	97.76 230	97.40 228	98.18 248	99.62 197	99.11 191	98.24 259	98.35 253	96.56 263	99.44 190	91.28 274	98.96 199	93.84 266	98.09 232	98.62 175	99.56 166	99.18 183
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
test-LLR		97.74 231	97.46 226	98.08 250	99.62 197	98.37 237	98.26 257	99.41 225	97.03 253	97.38 272	99.54 124	92.89 249	95.12 263	98.78 208	97.68 226	98.65 233	97.90 240

RPMNet		97.70 232	96.54 237	99.06 210	99.57 216	98.23 242	98.95 224	99.97 1	96.89 259	99.49 180	99.13 183	89.63 263	97.09 239	96.68 248	97.02 235	99.26 212	98.19 232

thres100view900		97.69 233	96.37 241	99.23 187	99.74 171	99.21 175	98.81 241	99.43 224	96.10 267	98.70 257	92.99 270	89.10 266	98.88 181	98.58 221	99.31 68	99.82 60	99.27 174

FMVSNet5		97.69 233	96.98 232	98.53 240	98.53 267	99.36 138	98.90 232	99.54 205	96.38 264	98.44 267	95.38 265	90.08 261	97.05 241	99.46 73	99.06 108	98.73 231	99.12 195

MVE	91.08 18	97.68 235	97.65 221	97.71 260	98.46 268	91.62 276	97.92 268	98.86 247	98.73 168	97.99 271	98.64 212	99.96 24	99.17 133	99.59 58	97.75 224	93.87 276	97.27 251
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test-mter		97.65 236	97.57 224	97.75 258	98.90 266	98.56 230	98.15 263	98.45 252	96.92 258	96.84 275	99.52 132	92.53 257	95.24 262	99.04 165	98.12 213	98.90 226	98.29 230

TESTMET0.1,1		97.62 237	97.46 226	97.81 256	99.07 262	98.37 237	98.26 257	98.35 253	97.03 253	97.38 272	99.54 124	92.89 249	95.12 263	98.78 208	97.68 226	98.65 233	97.90 240

test2506		97.57 238	95.67 249	99.78 44	99.95 10	99.78 18	99.67 69	99.93 27	99.45 64	99.55 166	99.20 176	71.73 284	99.65 40	99.93 3	99.88 3	99.94 16	99.72 43

MVSTER		97.55 239	96.75 235	98.48 242	99.46 231	99.54 73	98.24 259	99.77 129	97.56 237	99.41 197	99.31 163	84.86 278	94.66 265	98.86 194	97.75 224	99.34 206	99.38 158

ET-MVSNet_ETH3D		97.44 240	96.29 242	98.78 227	97.93 270	98.95 203	98.91 229	99.09 244	98.00 222	99.24 217	98.83 200	84.62 279	98.02 222	97.43 244	97.38 231	99.48 184	98.84 210

MDTV_nov1_ep13		97.41 241	96.26 243	98.76 229	99.47 228	98.43 236	99.26 188	99.82 94	98.06 219	99.23 218	99.22 173	92.86 251	98.05 218	95.33 252	93.66 247	96.73 259	96.26 259

ADS-MVSNet		97.29 242	96.17 244	98.59 237	99.59 210	98.70 223	99.32 166	99.86 66	98.47 189	99.56 162	99.08 189	98.16 215	97.34 235	92.92 255	91.17 252	95.91 265	94.72 266

SCA		97.25 243	96.05 245	98.64 236	99.36 249	99.02 197	99.27 185	99.96 12	98.25 208	99.69 124	98.71 209	94.66 243	97.95 224	93.95 253	92.35 249	95.64 266	95.40 265

blended_shiyan6		97.14 244	95.70 247	98.81 225	99.47 228	97.70 260	99.40 150	96.81 259	97.62 235	99.89 21	99.26 167	95.11 238	99.28 117	92.23 260	90.01 257	98.03 242	97.96 237

blended_shiyan8		97.13 245	95.69 248	98.81 225	99.46 231	97.71 259	99.40 150	96.81 259	97.60 236	99.90 18	99.25 168	95.03 240	99.27 118	92.25 259	90.02 256	98.03 242	97.96 237

gbinet_0.2-2-1-0.02		97.02 246	95.51 250	98.78 227	99.43 241	97.67 261	99.53 108	97.49 258	97.49 239	99.80 67	99.37 155	95.13 237	98.67 197	92.47 257	88.93 265	97.76 246	97.53 250

wanda-best-256-512		96.92 247	95.40 253	98.70 231	99.44 235	97.57 262	99.29 179	96.63 261	97.37 241	99.89 21	99.24 169	95.00 241	99.21 124	91.82 262	89.19 261	97.76 246	97.57 247

FE-blended-shiyan7		96.92 247	95.39 254	98.70 231	99.44 235	97.57 262	99.29 179	96.63 261	97.37 241	99.89 21	99.24 169	95.00 241	99.21 124	91.82 262	89.19 261	97.76 246	97.57 247

gm-plane-assit		96.82 249	94.84 257	99.13 201	99.95 10	99.78 18	99.69 64	99.92 38	99.19 99	99.84 54	99.92 18	72.93 283	96.44 253	98.21 231	97.01 236	98.92 225	96.87 257

PatchmatchNet		96.81 250	95.41 252	98.43 244	99.43 241	98.30 240	99.23 191	99.93 27	98.19 211	99.64 144	98.81 203	93.50 246	97.43 234	92.89 256	90.78 254	94.94 271	95.41 264
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		96.76 251	95.30 256	98.46 243	99.42 243	98.47 234	99.32 166	99.91 44	98.42 196	99.51 175	99.07 191	92.81 252	97.12 238	92.39 258	91.71 250	95.51 267	94.20 268

E-PMN		96.72 252	95.78 246	97.81 256	99.45 233	95.46 271	98.14 264	98.33 255	97.99 223	98.73 255	98.09 236	98.97 197	97.54 231	97.45 243	91.09 253	94.70 273	91.40 272

tpm		96.56 253	94.68 258	98.74 230	99.12 259	97.90 254	98.79 242	99.93 27	96.79 262	99.69 124	99.19 178	81.48 281	97.56 230	95.46 251	93.97 246	97.37 254	97.99 234

EMVS		96.47 254	95.38 255	97.74 259	99.42 243	95.37 272	98.07 266	98.27 256	97.85 228	98.90 245	97.48 249	98.73 204	97.20 236	97.21 246	90.39 255	94.59 275	90.65 273

tpmrst		96.18 255	94.47 259	98.18 248	99.52 217	97.89 255	98.96 221	99.79 116	98.07 218	99.16 224	99.30 166	92.69 253	96.69 248	90.76 268	88.85 267	94.96 270	93.69 269

FE-MVSNET3		95.98 256	93.76 260	98.56 239	99.44 235	97.57 262	99.29 179	96.63 261	97.37 241	99.06 231	95.50 262	86.90 273	99.19 128	91.82 262	89.19 261	97.76 246	97.96 237

usedtu_blend_shiyan5		95.81 257	93.76 260	98.20 247	99.44 235	97.57 262	97.14 274	96.63 261	97.37 241	99.06 231	95.50 262	86.90 273	99.19 128	91.82 262	89.19 261	97.76 246	97.97 235

CostFormer		95.61 258	93.35 264	98.24 246	99.48 227	98.03 250	98.65 246	99.83 87	96.93 257	99.42 195	98.83 200	83.65 280	97.08 240	90.39 269	89.54 259	94.94 271	96.11 262

dps		95.59 259	93.46 263	98.08 250	99.33 251	98.22 245	98.87 234	99.70 158	96.17 265	98.87 248	97.75 242	86.85 277	96.60 249	91.24 266	89.62 258	95.10 269	94.34 267

tpm cat1		95.52 260	93.49 262	97.88 255	99.28 255	97.87 256	98.65 246	99.77 129	97.27 248	99.46 188	98.04 237	90.99 259	95.46 259	88.57 270	88.14 268	94.64 274	93.54 270

blend_shiyan4		94.55 261	92.63 265	96.78 261	92.84 275	97.35 266	96.16 275	95.49 265	90.66 271	99.06 231	95.50 262	86.90 273	99.19 128	90.80 267	89.27 260	97.96 244	97.97 235

0.4-1-1-0.1		93.74 262	91.90 266	95.88 262	94.52 272	95.84 270	97.60 270	90.78 266	91.61 269	99.07 230	96.32 256	87.13 271	96.82 247	87.50 271	87.82 269	96.48 261	97.11 255

0.3-1-1-0.015		93.30 263	91.34 267	95.58 263	94.35 274	95.28 273	97.33 271	90.14 267	90.90 270	99.06 231	95.88 260	86.90 273	96.46 251	86.55 273	87.27 270	96.15 263	96.61 258

0.4-1-1-0.2		93.22 264	91.27 268	95.51 264	94.46 273	95.09 274	97.17 272	90.11 268	90.61 272	99.06 231	96.14 257	87.05 272	96.30 254	86.75 272	87.00 271	95.95 264	96.22 260

test_method		91.96 265	95.51 250	87.82 266	70.84 279	82.79 278	92.13 277	87.74 270	98.88 148	95.40 277	99.20 176	98.04 217	85.65 272	97.71 238	94.95 242	95.13 268	97.00 256

VLMVS_CLIP		79.71 266	89.12 269	68.73 267	87.10 276	83.02 277	68.48 279	62.62 271	85.86 274	55.42 279	94.79 266	95.73 231	69.45 274	91.99 261	85.95 272	69.31 277	86.50 274

MVS_clip		72.01 267	88.45 270	52.83 269	72.73 278	69.46 280	60.04 281	23.84 274	89.07 273	26.54 282	91.03 275	95.05 239	73.26 273	93.36 254	88.91 266	60.59 278	92.27 271

GG-mvs-BLEND		70.44 268	96.91 233	39.57 270	3.32 283	96.51 268	91.01 278	4.05 277	97.03 253	33.20 281	94.67 267	97.75 219	7.59 279	98.28 229	96.85 237	98.24 239	97.26 252

VLMVS		68.79 269	81.89 271	53.50 268	73.23 277	71.71 279	49.28 282	45.32 273	76.63 275	43.34 280	82.92 276	93.75 245	61.37 275	81.04 274	84.50 273	48.48 279	82.68 275

MVS_baseline		40.44 270	64.23 272	12.69 273	22.83 280	30.63 281	7.48 285	0.00 278	58.33 276	0.00 285	68.10 277	80.56 282	45.13 276	61.60 275	68.12 274	0.70 282	82.28 276

testmvs		22.33 271	29.66 273	13.79 271	8.97 281	10.35 282	15.53 284	8.09 276	32.51 277	19.87 283	45.18 278	30.56 286	17.05 278	29.96 276	24.74 275	13.21 280	34.30 277

test123		21.52 272	28.47 274	13.42 272	7.29 282	10.12 283	15.70 283	8.31 275	31.54 278	19.34 284	36.33 279	37.40 285	17.14 277	27.45 277	23.17 276	12.73 281	33.30 278

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					99.50 225	98.08 249	98.16 262		97.35 246	98.73 255	98.36 230	99.85 108	95.40 260			98.85 228	99.28 172

PatchmatchNet2					99.75 160	99.11 191	99.74 52
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												99.87 100	98.79 189	97.50 241	94.35 244	97.24 255	97.22 253
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										99.70 121	99.78 78
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							99.75 43	99.46 219		99.15 226						99.41 197

TPM-MVS					99.47 228	97.86 257	97.79 269			98.49 263	97.62 245	99.83 116	95.33 261			98.90 226	98.77 213
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										99.96 3

9.14												99.57 163

SR-MVS					99.73 173			99.74 147				99.88 93

Anonymous202405211			99.14 142		99.87 69	99.55 67	99.50 120	99.70 158	98.55 186		98.61 215	98.46 208	98.76 192	99.66 49	99.50 43	99.85 47	99.63 66

our_test_3					99.75 160	99.11 191	99.74 52

ambc			98.83 181		99.72 175	98.52 231	98.84 237		98.96 136	99.92 12	99.34 157	99.74 140	99.04 161	98.68 216	97.57 229	99.46 187	98.99 208

MTAPA										99.62 147		99.95 37

MTMP										99.53 167		99.92 70

Patchmatch-RL test							65.75 280

tmp_tt				88.14 265	96.68 271	91.91 275	93.70 276	61.38 272	99.61 34	90.51 278	99.40 151	99.71 146	90.32 271	99.22 127	99.44 53	96.25 262

XVS					99.86 89	99.30 153	99.72 59			99.69 124		99.93 59				99.60 152

X-MVStestdata					99.86 89	99.30 153	99.72 59			99.69 124		99.93 59				99.60 152

mPP-MVS					99.84 106							99.92 70

NP-MVS									97.37 241

Patchmtry						98.19 247	98.91 229	99.97 1		99.43 192

DeepMVS_CX						96.39 269	97.15 273	88.89 269	97.94 225	99.51 175	95.71 261	97.88 218	98.19 209	98.92 181		97.73 251	97.75 245

High-resolution multi-view benchmark