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 32	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 95	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	99.74 129	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 16	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 69	99.77 81	99.95 6	99.96 24	99.85 3	99.93 3	99.83 7	99.95 7	99.72 42

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 54	99.78 126	99.79 12	99.72 39	99.70 22	99.95 7	99.78 29

UniMVSNet_ETH3D		99.81 8	99.79 7	99.85 20	99.98 1	99.76 22	99.73 53	99.96 12	99.68 15	99.87 37	99.59 107	99.91 75	99.58 54	99.90 10	99.85 6	99.96 3	99.81 21

TDRefinement		99.81 8	99.76 9	99.86 16	99.83 106	99.53 74	99.89 5	99.91 44	99.73 5	99.88 30	99.83 54	99.96 24	99.76 17	99.91 9	99.81 11	99.86 42	99.59 77

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 67	99.93 8	99.87 40	99.29 174	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 49	99.83 4	99.84 17	99.89 55	99.31 74	99.93 8	99.92 16	99.97 17	99.68 34	99.89 11	99.64 28	99.82 58	99.66 56

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 35	99.87 37	99.92 16	99.21 177	99.65 40	99.88 15	99.77 16	99.93 21	99.78 29

PEN-MVS		99.77 12	99.65 20	99.91 5	99.95 10	99.80 16	99.86 11	99.97 1	99.08 104	99.89 21	99.69 90	99.68 138	99.84 5	99.81 27	99.64 28	99.95 7	99.81 21

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 53	99.94 6	99.78 69	100.00 1	99.69 32	99.71 43	99.43 54	99.85 45	99.58 86

EU-MVSNet		99.76 14	99.74 12	99.78 44	99.82 115	99.81 13	99.88 7	99.87 61	99.31 74	99.75 90	99.91 25	99.76 128	99.78 13	99.84 21	99.74 19	99.56 161	99.81 21

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 61	99.85 50	99.84 50	100.00 1	99.13 145	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 66	99.86 2	99.83 20	99.91 44	98.84 143	99.92 12	99.57 109	99.85 101	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	98.75 153	99.89 21	99.64 97	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 31	99.92 4	99.95 10	99.81 13	99.86 11	99.96 12	99.18 92	99.92 12	99.66 93	99.45 159	99.85 3	99.80 28	99.56 34	99.96 3	99.79 28

tfpnnormal		99.74 20	99.63 27	99.86 16	99.93 30	99.75 28	99.80 30	99.89 55	99.31 74	99.88 30	99.43 132	99.66 142	99.77 15	99.80 28	99.71 21	99.92 22	99.76 33

DeepC-MVS	99.05 5	99.74 20	99.64 23	99.84 23	99.90 43	99.39 119	99.79 31	99.81 103	99.69 13	99.90 18	99.87 40	99.98 11	99.81 7	99.62 56	99.32 64	99.83 54	99.65 59
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 64	99.91 44	99.59 35	99.88 30	99.73 77	99.81 113	99.55 57	99.59 57	99.53 39	99.89 32	99.70 50

PS-CasMVS		99.73 22	99.59 37	99.90 8	99.95 10	99.80 16	99.85 14	99.97 1	98.95 127	99.86 43	99.73 77	99.36 166	99.81 7	99.83 22	99.67 24	99.95 7	99.83 16

WR-MVS_H		99.73 22	99.61 31	99.88 13	99.95 10	99.82 8	99.83 20	99.96 12	99.01 117	99.84 54	99.71 87	99.41 165	99.74 22	99.77 33	99.70 22	99.95 7	99.82 18

TransMVSNet (Re)		99.72 25	99.59 37	99.88 13	99.95 10	99.76 22	99.88 7	99.94 24	99.58 37	99.92 12	99.90 29	98.55 194	99.65 40	99.89 11	99.76 17	99.95 7	99.70 50

ACMH	99.11 4	99.72 25	99.63 27	99.84 23	99.87 66	99.59 53	99.83 20	99.88 60	99.46 58	99.87 37	99.66 93	99.95 37	99.76 17	99.73 38	99.47 48	99.84 49	99.52 112
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	99.14 100	99.53 162	99.70 88	99.88 87	99.33 99	99.88 15	99.61 33	99.94 16	99.77 31

EC-MVSNet		99.70 27	99.57 41	99.85 20	99.95 10	99.81 13	99.85 14	99.93 27	98.39 191	99.76 84	99.48 128	99.94 48	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 35	99.81 33	99.84 99	99.37 126	99.76 39	99.84 82	99.54 45	99.82 62	99.64 97	99.95 37	99.75 19	99.79 30	99.56 34	99.83 54	99.37 154
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 29	99.76 50	99.91 37	99.55 65	99.73 53	99.82 94	99.63 29	99.78 76	99.88 38	100.00 1	99.47 87	99.49 66	99.19 76	99.83 54	99.63 63

ACMH+	98.94 6	99.69 30	99.59 37	99.81 33	99.88 61	99.41 116	99.75 43	99.86 66	99.43 61	99.80 67	99.54 113	99.97 17	99.73 25	99.82 25	99.52 41	99.85 45	99.43 138

E6new		99.68 32	99.65 20	99.72 65	99.89 49	99.59 53	99.58 88	99.80 111	99.71 7	99.78 76	99.89 32	99.99 5	99.48 82	99.42 81	99.31 65	99.82 58	99.63 63

E6		99.68 32	99.65 20	99.72 65	99.89 49	99.59 53	99.58 88	99.80 111	99.71 7	99.78 76	99.89 32	99.99 5	99.48 82	99.42 81	99.31 65	99.82 58	99.63 63

test20.03		99.68 32	99.60 35	99.76 50	99.91 37	99.70 36	99.68 64	99.87 61	99.05 113	99.88 30	99.92 16	99.88 87	99.50 74	99.77 33	99.42 57	99.75 88	99.49 119

CP-MVSNet		99.68 32	99.51 52	99.89 9	99.95 10	99.76 22	99.83 20	99.96 12	98.83 147	99.84 54	99.65 96	99.09 180	99.80 10	99.78 31	99.62 32	99.95 7	99.82 18

casdiffmvs_mvg		99.67 36	99.61 31	99.74 61	99.94 23	99.60 49	99.62 78	99.77 128	99.54 45	99.67 133	99.82 61	99.80 119	99.52 67	99.40 85	99.51 42	99.91 25	99.59 77
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt11		99.66 37	99.64 23	99.68 75	99.90 43	99.67 40	99.56 93	99.72 150	99.67 16	99.69 122	99.87 40	99.93 57	99.53 61	99.51 63	99.23 71	99.69 113	99.60 73

viewmsd2359difaftdt		99.66 37	99.64 23	99.68 75	99.90 43	99.67 40	99.56 93	99.72 150	99.67 16	99.69 122	99.87 40	99.93 57	99.53 61	99.51 63	99.23 71	99.69 113	99.60 73

PVSNet_Blended_VisFu		99.66 37	99.64 23	99.67 78	99.91 37	99.71 33	99.61 79	99.79 116	99.41 63	99.91 16	99.85 48	99.61 146	99.00 157	99.67 47	99.42 57	99.81 63	99.81 21

v10		99.65 40	99.51 52	99.81 33	99.83 106	99.61 48	99.75 43	99.94 24	99.56 41	99.76 84	99.94 11	99.60 148	99.73 25	99.11 152	99.01 116	99.85 45	99.74 37

CHOSEN 1792x2688		99.65 40	99.55 46	99.77 49	99.93 30	99.60 49	99.79 31	99.92 38	99.73 5	99.74 97	99.93 14	99.98 11	99.80 10	98.83 197	99.01 116	99.45 180	99.76 33

UA-Net		99.64 42	99.62 29	99.66 82	99.97 2	99.82 8	99.14 190	99.96 12	98.95 127	99.52 168	99.38 142	99.86 95	99.55 57	99.72 39	99.66 25	99.80 68	99.94 1

viewmacassd2359aftdt		99.63 43	99.56 44	99.71 68	99.89 49	99.56 63	99.55 98	99.77 128	99.65 22	99.72 109	99.84 50	99.99 5	99.53 61	99.25 118	99.09 101	99.81 63	99.57 93

GeoE		99.63 43	99.51 52	99.78 44	99.91 37	99.57 59	99.78 34	99.97 1	99.23 83	99.72 109	99.72 83	99.80 119	99.50 74	99.45 79	99.10 99	99.79 73	99.71 48

Baseline_NR-MVSNet		99.62 45	99.48 61	99.78 44	99.85 93	99.76 22	99.59 84	99.82 94	98.84 143	99.88 30	99.91 25	99.04 181	99.61 47	99.46 72	99.78 15	99.94 16	99.60 73

E4		99.61 46	99.56 44	99.67 78	99.89 49	99.56 63	99.52 108	99.76 138	99.70 9	99.76 84	99.87 40	99.99 5	99.31 106	99.21 127	99.06 105	99.79 73	99.55 100

pmmvs-eth3d		99.61 46	99.48 61	99.75 55	99.87 66	99.30 143	99.75 43	99.89 55	99.23 83	99.85 50	99.88 38	99.97 17	99.49 79	99.46 72	99.01 116	99.68 116	99.52 112

v1144		99.61 46	99.43 72	99.82 28	99.88 61	99.41 116	99.76 39	99.86 66	99.64 25	99.84 54	99.95 6	99.49 157	99.74 22	99.00 167	98.93 128	99.84 49	99.58 86

v8		99.61 46	99.45 69	99.79 43	99.80 121	99.59 53	99.73 53	99.93 27	99.48 56	99.77 81	99.90 29	99.48 158	99.67 37	99.11 152	98.89 137	99.84 49	99.73 39

casdiffmvs		99.61 46	99.55 46	99.68 75	99.89 49	99.53 74	99.64 72	99.68 167	99.51 51	99.62 144	99.90 29	99.96 24	99.37 93	99.28 112	99.25 70	99.88 34	99.44 135
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 46	99.52 51	99.71 68	99.89 49	99.62 46	99.52 108	99.76 138	99.61 33	99.69 122	99.73 77	99.96 24	99.57 55	99.27 115	98.62 171	99.81 63	99.85 15

v1192		99.60 52	99.41 76	99.82 28	99.89 49	99.43 107	99.81 28	99.84 82	99.63 29	99.85 50	99.95 6	99.35 169	99.72 27	99.01 163	98.90 136	99.82 58	99.58 86

APDe-MVS		99.60 52	99.48 61	99.73 64	99.85 93	99.51 89	99.75 43	99.85 73	99.17 93	99.81 65	99.56 111	99.94 48	99.44 89	99.42 81	99.22 73	99.67 118	99.54 104
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
FE-MVSNET		99.59 54	99.41 76	99.80 38	99.80 121	99.53 74	99.83 20	99.87 61	99.06 109	99.88 30	99.47 129	99.94 48	99.71 30	99.58 59	99.06 105	99.73 99	99.26 169

v1921920		99.59 54	99.40 80	99.82 28	99.88 61	99.45 101	99.81 28	99.83 87	99.65 22	99.86 43	99.95 6	99.29 174	99.75 19	98.98 170	98.86 141	99.78 76	99.59 77

TranMVSNet+NR-MVSNet		99.59 54	99.42 75	99.80 38	99.87 66	99.55 65	99.64 72	99.86 66	99.05 113	99.88 30	99.72 83	99.33 172	99.64 44	99.47 71	99.14 85	99.91 25	99.67 55

EG-PatchMatch MVS		99.59 54	99.49 60	99.70 72	99.82 115	99.26 150	99.39 145	99.83 87	98.99 120	99.93 8	99.54 113	99.92 67	99.51 70	99.78 31	99.50 43	99.73 99	99.41 143

viewdifsd2359ckpt07		99.58 58	99.59 37	99.56 115	99.86 84	99.53 74	99.31 159	99.65 178	99.62 32	99.71 117	99.78 69	99.94 48	99.29 109	99.35 93	99.29 68	99.57 156	99.62 69

pmmvs5		99.58 58	99.47 64	99.70 72	99.84 99	99.50 90	99.58 88	99.80 111	98.98 123	99.73 106	99.92 16	99.81 113	99.49 79	99.28 112	99.05 110	99.77 80	99.73 39

v144192		99.58 58	99.39 82	99.80 38	99.87 66	99.44 103	99.77 35	99.84 82	99.64 25	99.86 43	99.93 14	99.35 169	99.72 27	98.92 176	98.82 146	99.74 94	99.66 56

v148		99.58 58	99.43 72	99.76 50	99.87 66	99.40 118	99.76 39	99.85 73	99.48 56	99.83 59	99.82 61	99.83 108	99.51 70	99.20 131	98.82 146	99.75 88	99.45 132

v1240		99.58 58	99.38 86	99.82 28	99.89 49	99.49 92	99.82 26	99.83 87	99.63 29	99.86 43	99.96 4	98.92 187	99.75 19	99.15 143	98.96 125	99.76 82	99.56 95

E5new		99.57 63	99.51 52	99.64 89	99.89 49	99.55 65	99.49 123	99.74 146	99.70 9	99.75 90	99.83 54	99.98 11	99.17 130	99.06 158	98.92 129	99.80 68	99.51 115

E5		99.57 63	99.51 52	99.64 89	99.89 49	99.55 65	99.49 123	99.74 146	99.70 9	99.75 90	99.83 54	99.98 11	99.17 130	99.06 158	98.92 129	99.80 68	99.51 115

V42		99.57 63	99.41 76	99.75 55	99.84 99	99.37 126	99.73 53	99.83 87	99.41 63	99.75 90	99.89 32	99.42 163	99.60 49	99.15 143	98.96 125	99.76 82	99.65 59

E3		99.56 66	99.50 58	99.62 96	99.87 66	99.52 83	99.43 135	99.72 150	99.64 25	99.74 97	99.83 54	99.97 17	99.18 128	99.13 149	98.92 129	99.76 82	99.51 115

TSAR-MVS + MP.		99.56 66	99.54 49	99.58 103	99.69 168	99.14 172	99.73 53	99.45 212	99.50 53	99.35 200	99.60 105	99.93 57	99.50 74	99.56 60	99.37 61	99.77 80	99.64 62
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 66	99.35 89	99.81 33	99.87 66	99.35 132	99.75 43	99.85 73	99.56 41	99.87 37	99.95 6	99.44 161	99.66 38	98.91 179	98.76 153	99.86 42	99.45 132

E3new		99.55 69	99.50 58	99.61 98	99.87 66	99.52 83	99.43 135	99.71 154	99.64 25	99.74 97	99.83 54	99.97 17	99.18 128	99.13 149	98.92 129	99.76 82	99.51 115

Gipuma		99.55 69	99.23 110	99.91 5	99.87 66	99.52 83	99.86 11	99.93 27	99.87 1	99.96 3	96.72 241	99.55 153	99.97 1	99.77 33	99.46 50	99.87 40	99.74 37
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
viewmanbaseed2359cas		99.53 71	99.46 67	99.61 98	99.85 93	99.49 92	99.37 148	99.69 159	99.54 45	99.68 131	99.73 77	99.96 24	99.32 102	99.14 146	98.86 141	99.76 82	99.52 112

DVP-MVS		99.53 71	99.51 52	99.55 116	99.82 115	99.58 57	99.54 103	99.78 121	99.28 80	99.21 210	99.70 88	99.97 17	99.32 102	99.32 100	99.14 85	99.64 131	99.58 86
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 73	99.47 64	99.57 108	99.90 43	99.47 98	99.45 130	99.70 156	99.70 9	99.57 157	99.92 16	99.95 37	99.20 123	98.88 184	98.92 129	99.63 134	99.48 122

NR-MVSNet		99.52 73	99.29 98	99.80 38	99.96 7	99.38 122	99.55 98	99.81 103	98.86 140	99.87 37	99.51 124	98.81 189	99.72 27	99.86 18	99.04 112	99.89 32	99.54 104

usedtu_dtu_shiyan2		99.51 75	99.38 86	99.67 78	99.94 23	99.48 94	99.77 35	99.32 226	99.13 102	99.96 3	99.92 16	99.96 24	99.52 67	99.40 85	98.35 190	99.52 168	99.39 150

viewcassd2359sk11		99.51 75	99.45 69	99.57 108	99.84 99	99.50 90	99.37 148	99.67 172	99.58 37	99.72 109	99.79 67	99.92 67	99.08 148	99.07 157	98.81 149	99.73 99	99.48 122

ACMMPR		99.51 75	99.32 93	99.72 65	99.87 66	99.33 136	99.61 79	99.85 73	99.19 90	99.73 106	98.73 195	99.95 37	99.61 47	99.35 93	99.14 85	99.66 121	99.58 86

UniMVSNet (Re)		99.50 78	99.29 98	99.75 55	99.86 84	99.47 98	99.51 112	99.82 94	98.90 135	99.89 21	99.64 97	99.00 182	99.55 57	99.32 100	99.08 103	99.90 29	99.59 77

FMVSNet1		99.50 78	99.57 41	99.42 143	99.67 177	99.65 43	99.60 83	99.91 44	99.40 65	99.39 192	99.83 54	99.27 176	98.14 201	99.68 44	99.50 43	99.81 63	99.68 52

HyFIR lowres test		99.50 78	99.26 104	99.80 38	99.95 10	99.62 46	99.76 39	99.97 1	99.67 16	99.56 158	99.94 11	98.40 197	99.78 13	98.84 196	98.59 175	99.76 82	99.72 42

PM-MVS		99.49 81	99.43 72	99.57 108	99.76 145	99.34 135	99.53 104	99.77 128	98.93 131	99.75 90	99.46 130	99.83 108	99.11 147	99.72 39	99.29 68	99.49 175	99.46 131

Anonymous20231206		99.48 82	99.31 95	99.69 74	99.79 126	99.57 59	99.63 76	99.79 116	98.88 137	99.91 16	99.72 83	99.93 57	99.59 51	99.24 119	98.63 169	99.43 184	99.18 173

DU-MVS		99.48 82	99.26 104	99.75 55	99.85 93	99.38 122	99.50 116	99.81 103	98.86 140	99.89 21	99.51 124	98.98 183	99.59 51	99.46 72	98.97 123	99.87 40	99.63 63

RPSCF		99.48 82	99.45 69	99.52 126	99.73 161	99.33 136	99.13 191	99.77 128	99.33 72	99.47 179	99.39 141	99.92 67	99.36 94	99.63 53	99.13 93	99.63 134	99.41 143

ACMMP_NAP		99.47 85	99.33 91	99.63 92	99.85 93	99.28 148	99.56 93	99.83 87	98.75 153	99.48 176	99.03 182	99.95 37	99.47 87	99.48 68	99.19 76	99.57 156	99.59 77

Anonymous20231211		99.47 85	99.39 82	99.57 108	99.89 49	99.60 49	99.50 116	99.69 159	98.91 134	99.62 144	99.17 168	99.35 169	98.86 173	99.63 53	99.46 50	99.84 49	99.62 69

SteuartSystems-ACMMP		99.47 85	99.22 113	99.76 50	99.88 61	99.36 128	99.65 71	99.84 82	98.47 178	99.80 67	98.68 198	99.96 24	99.68 34	99.37 90	99.06 105	99.72 105	99.66 56
Skip Steuart: Steuart Systems R&D Blog.
ACMM	98.37 12	99.47 85	99.23 110	99.74 61	99.86 84	99.19 166	99.68 64	99.86 66	99.16 97	99.71 117	98.52 208	99.95 37	99.62 46	99.35 93	99.02 114	99.74 94	99.42 141
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
E2		99.46 89	99.40 80	99.53 120	99.83 106	99.48 94	99.30 165	99.63 182	99.52 49	99.70 120	99.75 73	99.85 101	98.99 160	99.01 163	98.71 160	99.71 109	99.47 127

DVP-MVS++		99.46 89	99.57 41	99.33 164	99.75 149	99.57 59	99.44 132	99.81 103	99.38 68	98.56 249	99.81 65	99.99 5	98.79 178	99.33 98	99.13 93	99.62 141	99.81 21

HFP-MVS		99.46 89	99.30 96	99.65 84	99.82 115	99.25 154	99.50 116	99.82 94	99.23 83	99.58 154	98.86 186	99.94 48	99.56 56	99.14 146	99.12 97	99.63 134	99.56 95

LGP-MVS_train		99.46 89	99.18 124	99.78 44	99.87 66	99.25 154	99.71 61	99.87 61	98.02 210	99.79 72	98.90 185	99.96 24	99.66 38	99.49 66	99.17 81	99.79 73	99.49 119

viewdifsd2359ckpt13		99.45 93	99.39 82	99.53 120	99.83 106	99.44 103	99.17 185	99.66 176	99.51 51	99.66 137	99.75 73	99.92 67	99.14 141	99.01 163	98.62 171	99.72 105	99.47 127

SED-MVS		99.45 93	99.46 67	99.42 143	99.77 140	99.57 59	99.42 137	99.80 111	99.06 109	99.38 193	99.66 93	99.96 24	98.65 187	99.31 102	99.14 85	99.53 166	99.55 100

ETV-MVS		99.45 93	99.32 93	99.60 100	99.79 126	99.60 49	99.40 142	99.78 121	97.88 216	99.83 59	99.33 146	99.70 136	98.97 161	99.74 36	99.43 54	99.84 49	99.58 86

ACMP	98.32 13	99.44 96	99.18 124	99.75 55	99.83 106	99.18 167	99.64 72	99.83 87	98.81 149	99.79 72	98.42 217	99.96 24	99.64 44	99.46 72	98.98 122	99.74 94	99.44 135
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DCV-MVSNet		99.43 97	99.23 110	99.67 78	99.92 33	99.76 22	99.64 72	99.93 27	99.06 109	99.68 131	97.77 228	98.97 184	98.97 161	99.72 39	99.54 38	99.88 34	99.81 21

SMA-MVS		99.43 97	99.41 76	99.45 139	99.82 115	99.31 141	99.02 206	99.59 189	99.06 109	99.34 203	99.53 119	99.96 24	99.38 92	99.29 107	99.13 93	99.53 166	99.59 77
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 97	99.47 64	99.38 152	99.90 43	99.67 40	99.30 165	99.73 149	98.64 166	99.53 162	99.52 121	99.90 78	98.08 204	99.65 51	99.40 60	99.75 88	99.55 100

DELS-MVS		99.42 100	99.53 50	99.29 168	99.52 205	99.43 107	99.42 137	99.28 228	99.16 97	99.72 109	99.82 61	99.97 17	98.17 198	99.56 60	99.16 82	99.65 123	99.59 77
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	99.42 100	99.22 113	99.65 84	99.78 131	99.13 176	99.50 116	99.85 73	99.40 65	99.80 67	98.59 204	99.79 123	99.30 108	99.20 131	99.06 105	99.71 109	99.35 157

viewmambaseed2359dif		99.41 102	99.27 103	99.58 103	99.83 106	99.42 111	99.56 93	99.68 167	99.27 81	99.58 154	99.80 66	99.85 101	99.14 141	98.70 206	98.41 186	99.67 118	99.47 127

DPE-MVS		99.41 102	99.36 88	99.47 134	99.66 178	99.48 94	99.46 129	99.75 144	98.65 162	99.41 189	99.67 91	99.95 37	98.82 174	99.21 127	99.14 85	99.72 105	99.40 148
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UniMVSNet_NR-MVSNet		99.41 102	99.12 136	99.76 50	99.86 84	99.48 94	99.50 116	99.81 103	98.84 143	99.89 21	99.45 131	98.32 200	99.59 51	99.22 123	98.89 137	99.90 29	99.63 63

CP-MVS		99.41 102	99.20 119	99.65 84	99.80 121	99.23 161	99.44 132	99.75 144	98.60 171	99.74 97	98.66 199	99.93 57	99.48 82	99.33 98	99.16 82	99.73 99	99.48 122

QAPM		99.41 102	99.21 118	99.64 89	99.78 131	99.16 169	99.51 112	99.85 73	99.20 87	99.72 109	99.43 132	99.81 113	99.25 116	98.87 186	98.71 160	99.71 109	99.30 162

ME-MVS		99.40 107	99.34 90	99.48 132	99.78 131	99.36 128	99.75 43	99.46 210	99.08 104	99.38 193	99.77 72	99.89 80	99.07 150	99.16 142	98.84 144	99.41 188	99.27 165

UGNet		99.40 107	99.61 31	99.16 188	99.88 61	99.64 44	99.61 79	99.77 128	99.31 74	99.63 143	99.33 146	99.93 57	96.46 239	99.63 53	99.53 39	99.63 134	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)		99.40 107	99.28 101	99.55 116	99.92 33	99.68 37	99.31 159	99.87 61	98.69 159	99.16 212	99.08 177	98.64 193	99.20 123	99.65 51	99.46 50	99.83 54	99.72 42

OPM-MVS		99.39 110	99.22 113	99.59 101	99.76 145	98.82 200	99.51 112	99.79 116	99.17 93	99.53 162	99.31 151	99.95 37	99.35 95	99.22 123	98.79 152	99.60 147	99.27 165
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Fast-Effi-MVS+		99.39 110	99.18 124	99.63 92	99.86 84	99.28 148	99.45 130	99.91 44	98.47 178	99.61 147	99.50 126	99.57 150	99.17 130	99.24 119	98.66 166	99.78 76	99.59 77

LS3D		99.39 110	99.28 101	99.52 126	99.77 140	99.39 119	99.55 98	99.82 94	98.93 131	99.64 141	98.52 208	99.67 140	98.58 191	99.74 36	99.63 30	99.75 88	99.06 190

diffmvs		99.38 113	99.33 91	99.45 139	99.87 66	99.39 119	99.28 173	99.58 193	99.55 43	99.50 172	99.85 48	99.85 101	98.94 167	98.58 211	98.68 164	99.51 172	99.39 150
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		99.37 114	99.29 98	99.46 136	99.83 106	99.42 111	99.12 194	99.63 182	99.52 49	99.67 133	99.73 77	99.67 140	98.91 168	98.81 199	98.47 180	99.61 143	99.42 141

usedtu_dtu_shiyan1		99.36 115	99.20 119	99.55 116	99.40 232	99.35 132	99.56 93	99.69 159	98.96 125	99.81 65	99.52 121	99.66 142	99.24 117	99.14 146	98.63 169	99.60 147	99.18 173

CANet		99.36 115	99.39 82	99.34 163	99.80 121	99.35 132	99.41 141	99.47 208	99.20 87	99.74 97	99.54 113	99.68 138	98.05 206	99.23 121	98.97 123	99.57 156	99.73 39

ACMMP		99.36 115	99.06 144	99.71 68	99.86 84	99.36 128	99.63 76	99.85 73	98.33 193	99.72 109	97.73 230	99.94 48	99.53 61	99.37 90	99.13 93	99.65 123	99.56 95
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
SD-MVS		99.35 118	99.26 104	99.46 136	99.66 178	99.15 171	98.92 217	99.67 172	99.55 43	99.35 200	98.83 188	99.91 75	99.35 95	99.19 134	98.53 177	99.78 76	99.68 52
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		99.35 118	99.09 142	99.65 84	99.84 99	99.22 162	99.59 84	99.78 121	98.13 202	99.67 133	98.44 213	99.93 57	99.43 91	99.31 102	99.09 101	99.60 147	99.49 119
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
pmmvs4		99.34 120	99.15 131	99.57 108	99.77 140	98.90 193	99.51 112	99.77 128	99.07 107	99.73 106	99.72 83	99.84 106	99.07 150	98.85 191	98.39 188	99.55 164	99.27 165

EPP-MVSNet		99.34 120	99.10 140	99.62 96	99.94 23	99.74 30	99.66 70	99.80 111	99.07 107	98.93 231	99.61 102	96.13 216	99.49 79	99.67 47	99.63 30	99.92 22	99.86 13

TSAR-MVS + GP.		99.33 122	99.17 128	99.51 128	99.71 166	99.00 188	98.84 225	99.71 154	98.23 199	99.74 97	99.53 119	99.90 78	99.35 95	99.38 89	98.85 143	99.72 105	99.31 160

PHI-MVS		99.33 122	99.19 122	99.49 131	99.69 168	99.25 154	99.27 174	99.59 189	98.44 182	99.78 76	99.15 169	99.92 67	98.95 166	99.39 87	99.04 112	99.64 131	99.18 173

MSP-MVS		99.32 124	99.26 104	99.38 152	99.76 145	99.54 71	99.42 137	99.72 150	98.92 133	98.84 239	98.96 184	99.96 24	98.91 168	98.72 205	99.14 85	99.63 134	99.58 86
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		99.32 124	98.99 153	99.71 68	99.86 84	99.31 141	99.59 84	99.86 66	97.51 227	99.75 90	98.23 220	99.94 48	99.53 61	99.29 107	99.08 103	99.65 123	99.54 104

DeepC-MVS_fast	98.69 9	99.32 124	99.13 134	99.53 120	99.63 184	98.78 203	99.53 104	99.33 225	99.08 104	99.77 81	99.18 167	99.89 80	99.29 109	99.00 167	98.70 162	99.65 123	99.30 162
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSDG		99.32 124	99.09 142	99.58 103	99.75 149	98.74 207	99.36 151	99.54 197	99.14 100	99.72 109	99.24 157	99.89 80	99.51 70	99.30 104	98.76 153	99.62 141	98.54 209

TSAR-MVS + ACMM		99.31 128	99.26 104	99.37 158	99.66 178	98.97 191	99.20 182	99.56 195	99.33 72	99.19 211	99.54 113	99.91 75	99.32 102	99.12 151	98.34 192	99.29 200	99.65 59

3Dnovator+	98.92 7	99.31 128	99.03 148	99.63 92	99.77 140	98.90 193	99.52 108	99.81 103	99.37 69	99.72 109	98.03 225	99.73 132	99.32 102	98.99 169	98.81 149	99.67 118	99.36 155

X-MVS		99.30 130	98.99 153	99.66 82	99.85 93	99.30 143	99.49 123	99.82 94	98.32 194	99.69 122	97.31 239	99.93 57	99.50 74	99.37 90	99.16 82	99.60 147	99.53 107

MVS_111021_HR		99.30 130	99.14 132	99.48 132	99.58 201	99.25 154	99.27 174	99.61 184	98.74 155	99.66 137	99.02 183	99.84 106	99.33 99	99.20 131	98.76 153	99.44 181	99.18 173

TAPA-MVS	98.54 10	99.30 130	99.24 109	99.36 162	99.44 222	98.77 205	99.00 208	99.41 216	99.23 83	99.60 149	99.50 126	99.86 95	99.15 139	99.29 107	98.95 127	99.56 161	99.08 186
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CLD-MVS		99.30 130	99.01 152	99.63 92	99.75 149	98.89 196	99.35 154	99.60 186	98.53 176	99.86 43	99.57 109	99.94 48	99.52 67	98.96 171	98.10 205	99.70 112	99.08 186
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
USDC		99.29 134	98.98 155	99.65 84	99.72 163	98.87 198	99.47 127	99.66 176	99.35 71	99.87 37	99.58 108	99.87 94	99.51 70	98.85 191	97.93 211	99.65 123	98.38 213

PMVS	94.32 17	99.27 135	99.55 46	98.94 205	99.60 193	99.43 107	99.39 145	99.54 197	98.99 120	99.69 122	99.60 105	99.81 113	95.68 246	99.88 15	99.83 7	99.73 99	99.31 160
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FA-MVS(training)		99.26 136	99.12 136	99.44 141	99.60 193	99.26 150	99.24 179	99.97 1	98.84 143	99.76 84	99.43 132	98.74 190	98.47 194	99.39 87	99.10 99	99.57 156	99.07 189

MVS_111021_LR		99.25 137	99.13 134	99.39 148	99.50 213	99.14 172	99.23 180	99.50 205	98.67 160	99.61 147	99.12 173	99.81 113	99.16 135	99.28 112	98.67 165	99.35 196	99.21 172

ECVR-MVS		99.24 138	98.74 178	99.82 28	99.95 10	99.78 18	99.67 68	99.93 27	99.45 59	99.80 67	99.86 46	92.58 239	99.65 40	99.93 3	99.88 3	99.94 16	99.71 48

baseline		99.24 138	99.30 96	99.17 187	99.78 131	99.14 172	99.10 196	99.69 159	98.97 124	99.49 174	99.84 50	99.88 87	97.99 211	98.85 191	98.73 158	98.98 215	99.72 42

EIA-MVS		99.23 140	99.03 148	99.47 134	99.83 106	99.64 44	99.16 187	99.81 103	97.11 239	99.65 140	98.44 213	99.78 126	98.61 190	99.46 72	99.22 73	99.75 88	99.59 77

HPM-MVS++		99.23 140	98.98 155	99.53 120	99.75 149	99.02 186	99.44 132	99.77 128	98.65 162	99.52 168	98.72 196	99.92 67	99.33 99	98.77 203	98.40 187	99.40 190	99.36 155

PMMVS2		99.23 140	99.22 113	99.24 175	99.80 121	99.14 172	99.50 116	99.82 94	99.12 103	98.41 255	99.91 25	99.98 11	98.51 192	99.48 68	98.76 153	99.38 192	98.14 221

MGCNet		99.22 143	99.22 113	99.23 176	99.87 66	99.58 57	99.70 62	99.59 189	99.58 37	98.98 227	99.40 139	97.31 213	97.53 220	99.41 84	99.43 54	99.69 113	99.81 21

test1111		99.21 144	98.67 184	99.84 23	99.96 7	99.82 8	99.72 58	99.94 24	99.54 45	99.78 76	99.89 32	91.89 242	99.69 32	99.93 3	99.89 1	99.95 7	99.75 35

CPTT-MVS		99.21 144	98.89 165	99.58 103	99.72 163	99.12 179	99.30 165	99.76 138	98.62 167	99.66 137	97.51 235	99.89 80	99.48 82	99.01 163	98.64 168	99.58 155	99.40 148

TinyColmap		99.21 144	98.89 165	99.59 101	99.61 189	98.61 215	99.47 127	99.67 172	99.02 116	99.82 62	99.15 169	99.74 129	99.35 95	99.17 140	98.33 193	99.63 134	98.22 219

Effi-MVS+		99.20 147	98.93 160	99.50 130	99.79 126	99.26 150	98.82 228	99.96 12	98.37 192	99.60 149	99.12 173	98.36 198	99.05 154	98.93 174	98.82 146	99.78 76	99.68 52

PVSNet_BlendedMVS		99.20 147	99.17 128	99.23 176	99.69 168	99.33 136	99.04 201	99.13 231	98.41 187	99.79 72	99.33 146	99.36 166	98.10 202	99.29 107	98.87 139	99.65 123	99.56 95

PVSNet_Blended		99.20 147	99.17 128	99.23 176	99.69 168	99.33 136	99.04 201	99.13 231	98.41 187	99.79 72	99.33 146	99.36 166	98.10 202	99.29 107	98.87 139	99.65 123	99.56 95

MCST-MVS		99.17 150	98.82 173	99.57 108	99.75 149	98.70 211	99.25 178	99.69 159	98.62 167	99.59 151	98.54 206	99.79 123	99.53 61	98.48 215	98.15 201	99.64 131	99.43 138

APD-MVS		99.17 150	98.92 161	99.46 136	99.78 131	99.24 159	99.34 155	99.78 121	97.79 219	99.48 176	98.25 219	99.88 87	98.77 179	99.18 137	98.92 129	99.63 134	99.18 173
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
OpenMVS	98.82 8	99.17 150	98.85 169	99.53 120	99.75 149	99.06 184	99.36 151	99.82 94	98.28 196	99.76 84	98.47 210	99.61 146	98.91 168	98.80 200	98.70 162	99.60 147	99.04 194

IterMVS-LS		99.16 153	98.82 173	99.57 108	99.87 66	99.71 33	99.58 88	99.92 38	99.24 82	99.71 117	99.73 77	95.79 217	98.91 168	98.82 198	98.66 166	99.43 184	99.77 31
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DeepPCF-MVS	98.38 11	99.16 153	99.20 119	99.12 192	99.20 245	98.71 210	98.85 224	99.06 234	99.17 93	98.96 230	99.61 102	99.86 95	99.29 109	99.17 140	98.72 159	99.36 194	99.15 182

IterMVS-SCA-FT		99.15 155	98.96 157	99.38 152	99.87 66	99.54 71	99.53 104	99.79 116	98.94 129	99.82 62	99.92 16	97.65 207	98.82 174	98.95 173	98.26 195	98.45 225	99.47 127

CDS-MVSNet		99.15 155	99.10 140	99.21 183	99.59 198	99.22 162	99.48 126	99.47 208	98.89 136	99.41 189	99.84 50	98.11 203	97.76 214	99.26 117	99.01 116	99.57 156	99.38 152
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IS_MVSNet		99.15 155	99.12 136	99.19 185	99.92 33	99.73 32	99.55 98	99.86 66	98.45 181	96.91 261	98.74 194	98.33 199	99.02 156	99.54 62	99.47 48	99.88 34	99.61 72

dmvs_re		99.14 158	98.76 176	99.58 103	99.75 149	99.38 122	99.30 165	99.68 167	96.94 244	99.74 97	97.70 231	99.20 178	99.29 109	99.22 123	99.35 62	99.73 99	99.55 100

MDA-MVSNet-bldmvs		99.11 159	99.11 139	99.12 192	99.91 37	99.38 122	99.77 35	98.72 238	99.31 74	99.85 50	99.43 132	98.26 201	99.48 82	99.85 19	98.47 180	96.99 244	99.08 186

OMC-MVS		99.11 159	98.95 158	99.29 168	99.37 234	98.57 217	99.19 183	99.20 230	98.87 139	99.58 154	99.13 171	99.88 87	99.00 157	99.19 134	98.46 182	99.43 184	98.57 208

MVS_Test		99.09 161	98.92 161	99.29 168	99.61 189	99.07 183	99.04 201	99.81 103	98.58 173	99.37 197	99.74 75	98.87 188	98.41 196	98.61 210	98.01 209	99.50 174	99.57 93

CNVR-MVS		99.08 162	98.83 170	99.37 158	99.61 189	98.74 207	99.15 188	99.54 197	98.59 172	99.37 197	98.15 222	99.88 87	99.08 148	98.91 179	98.46 182	99.48 176	99.06 190

IterMVS		99.08 162	98.90 164	99.29 168	99.87 66	99.53 74	99.52 108	99.77 128	98.94 129	99.75 90	99.91 25	97.52 211	98.72 183	98.86 189	98.14 202	98.09 228	99.43 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet2		99.07 164	99.19 122	98.93 207	99.02 250	99.53 74	99.31 159	99.84 82	98.86 140	98.88 234	99.64 97	98.44 196	96.92 232	99.35 93	99.00 120	99.61 143	99.53 107

CVMVSNet		99.06 165	98.88 168	99.28 172	99.52 205	99.53 74	99.42 137	99.69 159	98.74 155	98.27 257	99.89 32	95.48 222	99.44 89	99.46 72	99.33 63	99.32 199	99.75 35

CDPH-MVS		99.05 166	98.63 185	99.54 119	99.75 149	98.78 203	99.59 84	99.68 167	97.79 219	99.37 197	98.20 221	99.86 95	99.14 141	98.58 211	98.01 209	99.68 116	99.16 180

TAMVS		99.05 166	99.02 151	99.08 197	99.69 168	99.22 162	99.33 156	99.32 226	99.16 97	98.97 229	99.87 40	97.36 212	97.76 214	99.21 127	99.00 120	99.44 181	99.33 158

CANet_DTU		99.03 168	99.18 124	98.87 210	99.58 201	99.03 185	99.18 184	99.41 216	98.65 162	99.74 97	99.55 112	99.71 133	96.13 244	99.19 134	98.92 129	99.17 209	99.18 173

Effi-MVS+-dtu		99.01 169	99.05 145	98.98 201	99.60 193	99.13 176	99.03 205	99.61 184	98.52 177	99.01 224	98.53 207	99.83 108	96.95 231	99.48 68	98.59 175	99.66 121	99.25 171

sasdasda		99.00 170	98.68 182	99.37 158	99.68 174	99.42 111	98.94 215	99.89 55	99.00 118	98.99 225	98.43 215	95.69 218	98.96 164	99.18 137	99.18 78	99.74 94	99.88 7

canonicalmvs		99.00 170	98.68 182	99.37 158	99.68 174	99.42 111	98.94 215	99.89 55	99.00 118	98.99 225	98.43 215	95.69 218	98.96 164	99.18 137	99.18 78	99.74 94	99.88 7

MIMVSNet		99.00 170	99.03 148	98.97 204	99.32 240	99.32 140	99.39 145	99.91 44	98.41 187	98.76 242	99.24 157	99.17 179	97.13 225	99.30 104	98.80 151	99.29 200	99.01 195

CHOSEN 280x420		98.99 173	98.91 163	99.07 198	99.77 140	99.26 150	99.55 98	99.92 38	98.62 167	98.67 246	99.62 101	97.20 214	98.44 195	99.50 65	99.18 78	98.08 229	98.99 198

MGCFI-Net		98.98 174	98.69 181	99.33 164	99.68 174	99.42 111	98.95 213	99.90 53	99.04 115	98.88 234	98.45 212	95.64 220	98.81 176	99.15 143	99.21 75	99.75 88	99.90 2

SF-MVS		98.96 175	98.95 158	98.98 201	99.64 183	98.89 196	98.00 254	99.58 193	98.42 185	99.08 217	98.63 201	99.83 108	98.04 208	99.02 162	98.76 153	99.52 168	99.13 183

GBi-Net		98.96 175	99.05 145	98.85 211	99.02 250	99.53 74	99.31 159	99.78 121	98.13 202	98.48 251	99.43 132	97.58 208	96.92 232	99.68 44	99.50 43	99.61 143	99.53 107

test1		98.96 175	99.05 145	98.85 211	99.02 250	99.53 74	99.31 159	99.78 121	98.13 202	98.48 251	99.43 132	97.58 208	96.92 232	99.68 44	99.50 43	99.61 143	99.53 107

PCF-MVS	97.86 15	98.95 178	98.53 190	99.44 141	99.70 167	98.80 202	98.96 210	99.69 159	98.65 162	99.59 151	99.33 146	99.94 48	99.12 146	98.01 225	97.11 222	99.59 154	97.83 230
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MS-PatchMatch		98.94 179	98.71 180	99.21 183	99.52 205	98.22 233	98.97 209	99.53 202	98.76 151	99.50 172	98.59 204	99.56 152	98.68 184	98.63 209	98.45 184	99.05 212	98.73 205

AdaColmap		98.93 180	98.53 190	99.39 148	99.52 205	98.65 214	99.11 195	99.59 189	98.08 206	99.44 182	97.46 237	99.45 159	99.24 117	98.92 176	98.44 185	99.44 181	98.73 205

MSLP-MVS++		98.92 181	98.73 179	99.14 189	99.44 222	99.00 188	98.36 244	99.35 222	98.82 148	99.38 193	96.06 245	99.79 123	99.07 150	98.88 184	99.05 110	99.27 202	99.53 107

new_pmnet		98.91 182	98.89 165	98.94 205	99.51 211	98.27 229	99.15 188	98.66 239	99.17 93	99.48 176	99.79 67	99.80 119	98.49 193	99.23 121	98.20 199	98.34 226	97.74 234

train_agg		98.89 183	98.48 195	99.38 152	99.69 168	98.76 206	99.31 159	99.60 186	97.71 221	98.98 227	97.89 226	99.89 80	99.29 109	98.32 216	97.59 218	99.42 187	99.16 180

NCCC		98.88 184	98.42 196	99.42 143	99.62 185	98.81 201	99.10 196	99.54 197	98.76 151	99.53 162	95.97 246	99.80 119	99.16 135	98.49 214	98.06 208	99.55 164	99.05 192

PLC	97.83 16	98.88 184	98.52 192	99.30 167	99.45 220	98.60 216	98.65 234	99.49 206	98.66 161	99.59 151	96.33 242	99.59 149	99.17 130	98.87 186	98.53 177	99.46 178	99.05 192
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
pmmvs3		98.85 186	98.60 186	99.13 190	99.66 178	98.72 209	99.37 148	99.06 234	98.44 182	99.76 84	99.74 75	99.55 153	99.15 139	99.04 160	96.00 230	97.80 233	98.72 207

Fast-Effi-MVS+-dtu		98.82 187	98.80 175	98.84 213	99.51 211	98.90 193	98.96 210	99.91 44	98.29 195	99.11 216	98.47 210	99.63 145	96.03 245	99.21 127	98.12 203	99.52 168	99.01 195

CNLPA		98.82 187	98.52 192	99.18 186	99.21 244	98.50 221	98.73 232	99.34 224	98.73 157	99.56 158	97.55 234	99.42 163	99.06 153	98.93 174	98.10 205	99.21 208	98.38 213

PatchMatch-RL		98.80 189	98.52 192	99.12 192	99.38 233	98.70 211	98.56 237	99.55 196	97.81 218	99.34 203	97.57 233	99.31 173	98.67 185	99.27 115	98.62 171	99.22 207	98.35 215

thisisatest0530		98.78 190	98.26 199	99.39 148	99.78 131	99.43 107	99.07 198	99.64 180	98.44 182	99.42 187	99.22 161	92.68 238	98.63 188	99.30 104	99.14 85	99.80 68	99.60 73

tttt0517		98.77 191	98.25 201	99.38 152	99.79 126	99.46 100	99.07 198	99.64 180	98.40 190	99.38 193	99.21 163	92.54 240	98.63 188	99.34 97	99.14 85	99.80 68	99.62 69

DI_MVS_pp		98.74 192	98.08 209	99.51 128	99.79 126	99.29 147	99.61 79	99.60 186	99.20 87	99.46 180	99.09 176	92.93 232	98.97 161	98.27 219	98.35 190	99.65 123	99.45 132

TSAR-MVS + COLMAP		98.74 192	98.58 188	98.93 207	99.29 241	98.23 230	99.04 201	99.24 229	98.79 150	98.80 241	99.37 143	99.71 133	98.06 205	98.02 224	97.46 220	99.16 210	98.48 211

MDTV_nov1_ep13_2view		98.73 194	98.31 198	99.22 180	99.75 149	99.24 159	99.75 43	99.93 27	99.31 74	99.84 54	99.86 46	99.81 113	99.31 106	97.40 233	94.77 232	96.73 246	97.81 231

PMMVS		98.71 195	98.55 189	98.90 209	99.28 242	98.45 223	98.53 240	99.45 212	97.67 223	99.15 214	98.76 192	99.54 155	97.79 213	98.77 203	98.23 197	99.16 210	98.46 212

HQP-MVS		98.70 196	98.19 205	99.28 172	99.61 189	98.52 219	98.71 233	99.35 222	97.97 213	99.53 162	97.38 238	99.85 101	99.14 141	97.53 229	96.85 226	99.36 194	99.26 169

N_pmnet		98.64 197	98.23 204	99.11 195	99.78 131	99.25 154	99.75 43	99.39 220	99.65 22	99.70 120	99.78 69	99.89 80	98.81 176	97.60 228	94.28 233	97.24 243	97.15 241

CMPMVS	76.62 19	98.64 197	98.60 186	98.68 223	99.33 238	97.07 254	98.11 252	98.50 240	97.69 222	99.26 206	98.35 218	99.66 142	97.62 217	99.43 80	99.02 114	99.24 205	99.01 195
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet3		98.63 199	98.75 177	98.49 230	98.10 256	99.44 103	99.02 206	99.78 121	98.13 202	98.48 251	99.43 132	97.58 208	96.16 243	98.85 191	98.39 188	99.40 190	99.41 143

GA-MVS		98.59 200	98.15 206	99.09 196	99.59 198	99.13 176	98.84 225	99.52 204	98.61 170	99.35 200	99.67 91	93.03 231	97.73 216	98.90 183	98.26 195	99.51 172	99.48 122

MAR-MVS		98.54 201	98.15 206	98.98 201	99.37 234	98.09 236	98.56 237	99.65 178	96.11 254	99.27 205	97.16 240	99.50 156	98.03 209	98.87 186	98.23 197	99.01 213	99.13 183
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		98.49 202	97.60 211	99.53 120	99.90 43	99.55 65	99.77 35	99.48 207	99.67 16	99.86 43	99.98 3	99.98 11	99.50 74	96.90 235	91.52 239	98.67 222	95.62 250

FPMVS		98.48 203	98.83 170	98.07 241	99.09 248	97.98 239	99.07 198	98.04 246	98.99 120	99.22 209	98.85 187	99.43 162	93.79 254	99.66 49	99.11 98	99.24 205	97.76 232

MVS-HIRNet		98.45 204	98.25 201	98.69 222	99.12 246	97.81 245	98.55 239	99.85 73	98.58 173	99.67 133	99.61 102	99.86 95	97.46 221	97.95 226	96.37 228	97.49 240	97.56 237

test0.0.03 1		98.41 205	98.41 197	98.40 234	99.62 185	99.16 169	98.87 222	99.41 216	97.15 237	96.60 263	99.31 151	97.00 215	96.55 238	98.91 179	98.51 179	99.37 193	98.82 202

gg-mvs-nofinetune		98.40 206	98.26 199	98.57 227	99.83 106	98.86 199	98.77 231	99.97 1	99.57 40	99.99 1	99.99 1	93.81 229	93.50 255	98.91 179	98.20 199	99.33 198	98.52 210

baseline1		98.39 207	97.59 212	99.31 166	99.78 131	99.45 101	99.13 191	99.53 202	98.06 208	98.87 236	98.63 201	90.04 246	98.76 180	98.85 191	98.84 144	99.81 63	99.28 164

pmnet_mix02		98.28 208	97.48 214	99.22 180	99.78 131	99.12 179	99.68 64	99.39 220	99.49 55	99.86 43	99.82 61	99.89 80	99.23 119	95.54 238	92.36 236	97.38 241	96.14 248

PatchT		98.11 209	97.12 220	99.26 174	99.65 182	98.34 227	99.57 92	99.97 1	97.48 229	99.43 184	99.04 181	90.84 244	98.15 199	98.04 222	97.78 212	98.82 219	98.30 216

DPM-MVS		98.10 210	97.32 218	99.01 200	99.52 205	97.92 240	98.47 242	99.45 212	98.25 197	98.91 232	93.99 254	99.69 137	98.73 182	96.29 237	96.32 229	99.00 214	98.77 203

EPNet_dtu		98.09 211	98.25 201	97.91 243	99.58 201	98.02 238	98.19 249	99.67 172	97.94 214	99.74 97	99.07 179	98.71 192	93.40 256	97.50 230	97.09 223	96.89 245	99.44 135
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPNet		98.06 212	98.11 208	98.00 242	99.60 193	98.99 190	98.38 243	99.68 167	98.18 201	98.85 238	97.89 226	95.60 221	92.72 257	98.30 217	98.10 205	98.76 220	99.72 42
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		97.91 213	96.80 223	99.22 180	99.60 193	98.23 230	98.91 218	99.97 1	96.89 247	99.43 184	99.10 175	89.24 249	98.15 199	98.04 222	97.78 212	99.26 203	98.30 216

thres200		97.87 214	96.56 225	99.39 148	99.76 145	99.52 83	99.13 191	99.76 138	96.88 249	98.66 247	92.87 258	88.77 252	99.16 135	99.11 152	99.42 57	99.88 34	99.33 158

baseline2		97.87 214	97.18 219	98.67 224	99.34 237	99.17 168	98.48 241	98.82 237	97.08 240	98.83 240	98.75 193	89.47 248	97.03 230	98.67 208	98.27 194	99.52 168	98.83 201

thres600view7		97.86 216	96.53 228	99.41 146	99.84 99	99.52 83	99.36 151	99.76 138	97.32 235	98.38 256	93.24 255	87.25 254	99.23 119	99.11 152	99.75 18	99.88 34	99.48 122

tfpn200view9		97.85 217	96.54 226	99.38 152	99.74 159	99.52 83	99.17 185	99.76 138	96.10 255	98.70 244	92.99 256	89.10 250	99.00 157	99.11 152	99.56 34	99.88 34	99.41 143

thres400		97.82 218	96.47 229	99.40 147	99.81 120	99.44 103	99.29 169	99.69 159	97.15 237	98.57 248	92.82 259	87.96 253	99.16 135	98.96 171	99.55 37	99.86 42	99.41 143

IB-MVS	98.10 14	97.76 219	97.40 217	98.18 237	99.62 185	99.11 181	98.24 247	98.35 242	96.56 251	99.44 182	91.28 260	98.96 186	93.84 253	98.09 221	98.62 171	99.56 161	99.18 173
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		97.74 220	97.46 215	98.08 239	99.62 185	98.37 225	98.26 245	99.41 216	97.03 241	97.38 259	99.54 113	92.89 233	95.12 250	98.78 201	97.68 216	98.65 223	97.90 228

RPMNet		97.70 221	96.54 226	99.06 199	99.57 204	98.23 230	98.95 213	99.97 1	96.89 247	99.49 174	99.13 171	89.63 247	97.09 227	96.68 236	97.02 224	99.26 203	98.19 220

thres100view900		97.69 222	96.37 230	99.23 176	99.74 159	99.21 165	98.81 229	99.43 215	96.10 255	98.70 244	92.99 256	89.10 250	98.88 172	98.58 211	99.31 65	99.82 58	99.27 165

FMVSNet5		97.69 222	96.98 221	98.53 229	98.53 254	99.36 128	98.90 221	99.54 197	96.38 252	98.44 254	95.38 252	90.08 245	97.05 229	99.46 72	99.06 105	98.73 221	99.12 185

MVE	91.08 18	97.68 224	97.65 210	97.71 249	98.46 255	91.62 263	97.92 255	98.86 236	98.73 157	97.99 258	98.64 200	99.96 24	99.17 130	99.59 57	97.75 214	93.87 263	97.27 239
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test-mter		97.65 225	97.57 213	97.75 247	98.90 253	98.56 218	98.15 250	98.45 241	96.92 246	96.84 262	99.52 121	92.53 241	95.24 249	99.04 160	98.12 203	98.90 217	98.29 218

TESTMET0.1,1		97.62 226	97.46 215	97.81 245	99.07 249	98.37 225	98.26 245	98.35 242	97.03 241	97.38 259	99.54 113	92.89 233	95.12 250	98.78 201	97.68 216	98.65 223	97.90 228

test2506		97.57 227	95.67 238	99.78 44	99.95 10	99.78 18	99.67 68	99.93 27	99.45 59	99.55 161	99.20 164	71.73 267	99.65 40	99.93 3	99.88 3	99.94 16	99.72 42

MVSTER		97.55 228	96.75 224	98.48 231	99.46 218	99.54 71	98.24 247	99.77 128	97.56 226	99.41 189	99.31 151	84.86 262	94.66 252	98.86 189	97.75 214	99.34 197	99.38 152

ET-MVSNet_ETH3D		97.44 229	96.29 231	98.78 216	97.93 257	98.95 192	98.91 218	99.09 233	98.00 211	99.24 207	98.83 188	84.62 263	98.02 210	97.43 232	97.38 221	99.48 176	98.84 200

MDTV_nov1_ep13		97.41 230	96.26 232	98.76 218	99.47 215	98.43 224	99.26 177	99.82 94	98.06 208	99.23 208	99.22 161	92.86 235	98.05 206	95.33 240	93.66 235	96.73 246	96.26 246

ADS-MVSNet		97.29 231	96.17 233	98.59 226	99.59 198	98.70 211	99.32 157	99.86 66	98.47 178	99.56 158	99.08 177	98.16 202	97.34 223	92.92 242	91.17 240	95.91 252	94.72 253

SCA		97.25 232	96.05 234	98.64 225	99.36 236	99.02 186	99.27 174	99.96 12	98.25 197	99.69 122	98.71 197	94.66 228	97.95 212	93.95 241	92.35 237	95.64 253	95.40 252

blended_shiyan6		97.14 233	95.70 236	98.81 214	99.47 215	97.70 247	99.40 142	96.81 248	97.62 224	99.89 21	99.26 155	95.11 224	99.28 114	92.23 247	90.01 245	98.03 230	97.96 225

blended_shiyan8		97.13 234	95.69 237	98.81 214	99.46 218	97.71 246	99.40 142	96.81 248	97.60 225	99.90 18	99.25 156	95.03 225	99.27 115	92.25 246	90.02 244	98.03 230	97.96 225

gbinet_0.2-2-1-0.02		97.02 235	95.51 239	98.78 216	99.43 228	97.67 248	99.53 104	97.49 247	97.49 228	99.80 67	99.37 143	95.13 223	98.67 185	92.47 244	88.93 253	97.76 234	97.53 238

wanda-best-256-512		96.92 236	95.40 242	98.70 220	99.44 222	97.57 249	99.29 169	96.63 250	97.37 230	99.89 21	99.24 157	95.00 226	99.21 121	91.82 248	89.19 249	97.76 234	97.57 235

FE-blended-shiyan7		96.92 236	95.39 243	98.70 220	99.44 222	97.57 249	99.29 169	96.63 250	97.37 230	99.89 21	99.24 157	95.00 226	99.21 121	91.82 248	89.19 249	97.76 234	97.57 235

gm-plane-assit		96.82 238	94.84 246	99.13 190	99.95 10	99.78 18	99.69 63	99.92 38	99.19 90	99.84 54	99.92 16	72.93 266	96.44 241	98.21 220	97.01 225	98.92 216	96.87 244

PatchmatchNet		96.81 239	95.41 241	98.43 233	99.43 228	98.30 228	99.23 180	99.93 27	98.19 200	99.64 141	98.81 191	93.50 230	97.43 222	92.89 243	90.78 242	94.94 258	95.41 251
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		96.76 240	95.30 245	98.46 232	99.42 230	98.47 222	99.32 157	99.91 44	98.42 185	99.51 170	99.07 179	92.81 236	97.12 226	92.39 245	91.71 238	95.51 254	94.20 255

E-PMN		96.72 241	95.78 235	97.81 245	99.45 220	95.46 258	98.14 251	98.33 244	97.99 212	98.73 243	98.09 223	98.97 184	97.54 219	97.45 231	91.09 241	94.70 260	91.40 258

tpm		96.56 242	94.68 247	98.74 219	99.12 246	97.90 241	98.79 230	99.93 27	96.79 250	99.69 122	99.19 166	81.48 265	97.56 218	95.46 239	93.97 234	97.37 242	97.99 222

EMVS		96.47 243	95.38 244	97.74 248	99.42 230	95.37 259	98.07 253	98.27 245	97.85 217	98.90 233	97.48 236	98.73 191	97.20 224	97.21 234	90.39 243	94.59 262	90.65 259

tpmrst		96.18 244	94.47 248	98.18 237	99.52 205	97.89 242	98.96 210	99.79 116	98.07 207	99.16 212	99.30 154	92.69 237	96.69 236	90.76 254	88.85 254	94.96 257	93.69 256

FE-MVSNET3		95.98 245	93.76 249	98.56 228	99.44 222	97.57 249	99.29 169	96.63 250	97.37 230	99.06 219	95.50 249	86.90 257	99.19 125	91.82 248	89.19 249	97.76 234	97.96 225

usedtu_blend_shiyan5		95.81 246	93.76 249	98.20 236	99.44 222	97.57 249	97.14 261	96.63 250	97.37 230	99.06 219	95.50 249	86.90 257	99.19 125	91.82 248	89.19 249	97.76 234	97.97 223

CostFormer		95.61 247	93.35 253	98.24 235	99.48 214	98.03 237	98.65 234	99.83 87	96.93 245	99.42 187	98.83 188	83.65 264	97.08 228	90.39 255	89.54 247	94.94 258	96.11 249

dps		95.59 248	93.46 252	98.08 239	99.33 238	98.22 233	98.87 222	99.70 156	96.17 253	98.87 236	97.75 229	86.85 261	96.60 237	91.24 252	89.62 246	95.10 256	94.34 254

tpm cat1		95.52 249	93.49 251	97.88 244	99.28 242	97.87 243	98.65 234	99.77 128	97.27 236	99.46 180	98.04 224	90.99 243	95.46 247	88.57 256	88.14 255	94.64 261	93.54 257

blend_shiyan4		94.55 250	92.63 254	96.78 250	92.84 262	97.35 253	96.16 262	95.49 254	90.66 259	99.06 219	95.50 249	86.90 257	99.19 125	90.80 253	89.27 248	97.96 232	97.97 223

0.4-1-1-0.1		93.74 251	91.90 255	95.88 251	94.52 259	95.84 257	97.60 257	90.78 255	91.61 257	99.07 218	96.32 243	87.13 255	96.82 235	87.50 257	87.82 256	96.48 248	97.11 242

0.3-1-1-0.015		93.30 252	91.34 256	95.58 252	94.35 261	95.28 260	97.33 258	90.14 256	90.90 258	99.06 219	95.88 247	86.90 257	96.46 239	86.55 259	87.27 257	96.15 250	96.61 245

0.4-1-1-0.2		93.22 253	91.27 257	95.51 253	94.46 260	95.09 261	97.17 259	90.11 257	90.61 260	99.06 219	96.14 244	87.05 256	96.30 242	86.75 258	87.00 258	95.95 251	96.22 247

test_method		91.96 254	95.51 239	87.82 255	70.84 263	82.79 264	92.13 264	87.74 259	98.88 137	95.40 264	99.20 164	98.04 204	85.65 259	97.71 227	94.95 231	95.13 255	97.00 243

GG-mvs-BLEND		70.44 255	96.91 222	39.57 256	3.32 266	96.51 255	91.01 265	4.05 263	97.03 241	33.20 266	94.67 253	97.75 206	7.59 262	98.28 218	96.85 226	98.24 227	97.26 240

testmvs		22.33 256	29.66 258	13.79 257	8.97 264	10.35 265	15.53 268	8.09 262	32.51 261	19.87 267	45.18 261	30.56 269	17.05 261	29.96 260	24.74 259	13.21 264	34.30 260

test123		21.52 257	28.47 259	13.42 258	7.29 265	10.12 266	15.70 267	8.31 261	31.54 262	19.34 268	36.33 262	37.40 268	17.14 260	27.45 261	23.17 260	12.73 265	33.30 261

uanet_test		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet-low-res		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

TestfortrainingZip							99.75 43	99.46 210		99.15 214						99.41 188

TPM-MVS					99.47 215	97.86 244	97.79 256			98.49 250	97.62 232	99.83 108	95.33 248			98.90 217	98.77 203
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												99.57 150

SR-MVS					99.73 161			99.74 146				99.88 87

Anonymous202405211			99.14 132		99.87 66	99.55 65	99.50 116	99.70 156	98.55 175		98.61 203	98.46 195	98.76 180	99.66 49	99.50 43	99.85 45	99.63 63

our_test_3					99.75 149	99.11 181	99.74 52

ambc			98.83 170		99.72 163	98.52 219	98.84 225		98.96 125	99.92 12	99.34 145	99.74 129	99.04 155	98.68 207	97.57 219	99.46 178	98.99 198

MTAPA										99.62 144		99.95 37

MTMP										99.53 162		99.92 67

Patchmatch-RL test							65.75 266

tmp_tt				88.14 254	96.68 258	91.91 262	93.70 263	61.38 260	99.61 33	90.51 265	99.40 139	99.71 133	90.32 258	99.22 123	99.44 53	96.25 249

XVS					99.86 84	99.30 143	99.72 58			99.69 122		99.93 57				99.60 147

X-MVStestdata					99.86 84	99.30 143	99.72 58			99.69 122		99.93 57				99.60 147

mPP-MVS					99.84 99							99.92 67

NP-MVS									97.37 230

Patchmtry						98.19 235	98.91 218	99.97 1		99.43 184

DeepMVS_CX						96.39 256	97.15 260	88.89 258	97.94 214	99.51 170	95.71 248	97.88 205	98.19 197	98.92 176		97.73 239	97.75 233

High-resolution multi-view benchmark