High-res multi-view results

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

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

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

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

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

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

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

LTVRE_ROB	98.82 1	99.76 1	99.75 1	99.77 7	99.87 16	99.71 10	99.77 8	99.76 19	99.52 2	99.80 3	99.79 22	99.91 1	99.56 13	99.83 3	99.75 4	99.86 9	99.75 1
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
pmmvs6		99.74 2	99.75 1	99.73 11	99.92 5	99.67 15	99.76 10	99.84 11	99.59 1	99.52 24	99.87 11	99.91 1	99.43 27	99.87 1	99.81 2	99.89 6	99.52 12

SixPastTwentyTwo		99.70 3	99.59 4	99.82 2	99.93 3	99.80 1	99.86 2	99.87 6	98.87 12	99.79 5	99.85 14	99.33 96	99.74 5	99.85 2	99.82 1	99.74 24	99.63 5

v7n		99.68 4	99.61 3	99.76 8	99.89 12	99.74 7	99.87 1	99.82 13	99.20 6	99.71 6	99.96 1	99.73 24	99.76 3	99.58 20	99.59 16	99.52 47	99.46 18

anonymousdsp		99.64 5	99.55 6	99.74 10	99.87 16	99.56 27	99.82 3	99.73 23	98.54 30	99.71 6	99.92 4	99.84 8	99.61 9	99.70 9	99.63 9	99.69 33	99.64 3

UniMVSNet_ETH3D		99.61 6	99.59 4	99.63 13	99.96 1	99.70 11	99.53 37	99.86 8	99.28 5	99.48 32	99.44 80	99.86 6	99.01 71	99.78 4	99.76 3	99.90 2	99.33 25

WR-MVS		99.61 6	99.44 8	99.82 2	99.92 5	99.80 1	99.80 4	99.89 1	98.54 30	99.66 13	99.78 23	99.16 121	99.68 7	99.70 9	99.63 9	99.94 1	99.49 16

PEN-MVS		99.54 8	99.30 17	99.83 1	99.92 5	99.76 4	99.80 4	99.88 3	97.60 90	99.71 6	99.59 49	99.52 68	99.75 4	99.64 15	99.51 20	99.90 2	99.46 18

TDRefinement		99.54 8	99.50 7	99.60 17	99.70 85	99.35 49	99.77 8	99.58 51	99.40 4	99.28 50	99.66 35	99.41 83	99.55 15	99.74 8	99.65 8	99.70 30	99.25 30

DTE-MVSNet		99.52 10	99.27 18	99.82 2	99.93 3	99.77 3	99.79 6	99.87 6	97.89 68	99.70 11	99.55 63	99.21 111	99.77 2	99.65 13	99.43 24	99.90 2	99.36 22

PS-CasMVS		99.50 11	99.23 21	99.82 2	99.92 5	99.75 6	99.78 7	99.89 1	97.30 105	99.71 6	99.60 47	99.23 106	99.71 6	99.65 13	99.55 18	99.90 2	99.56 8

WR-MVS_H		99.48 12	99.23 21	99.76 8	99.91 9	99.76 4	99.75 12	99.88 3	97.27 108	99.58 17	99.56 59	99.24 105	99.56 13	99.60 18	99.60 15	99.88 8	99.58 7

pm-mvs1		99.47 13	99.38 10	99.57 21	99.82 30	99.49 31	99.63 24	99.65 39	98.88 11	99.31 44	99.85 14	99.02 142	99.23 47	99.60 18	99.58 17	99.80 15	99.22 37

MIMVSNet1		99.46 14	99.34 11	99.60 17	99.83 24	99.68 14	99.74 15	99.71 27	98.20 47	99.41 37	99.86 13	99.66 42	99.41 30	99.50 24	99.39 27	99.50 55	99.10 49

TransMVSNet (Re)		99.45 15	99.32 14	99.61 15	99.88 14	99.60 21	99.75 12	99.63 43	99.11 7	99.28 50	99.83 19	98.35 178	99.27 44	99.70 9	99.62 13	99.84 10	99.03 57

ACMH	97.81 6	99.44 16	99.33 12	99.56 22	99.81 34	99.42 38	99.73 16	99.58 51	99.02 8	99.10 79	99.41 85	99.69 33	99.60 10	99.45 28	99.26 38	99.55 43	99.05 54
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CP-MVSNet		99.39 17	99.04 32	99.80 6	99.91 9	99.70 11	99.75 12	99.88 3	96.82 134	99.68 12	99.32 93	98.86 151	99.68 7	99.57 21	99.47 21	99.89 6	99.52 12

COLMAP_ROB	98.29 2	99.37 18	99.25 19	99.51 31	99.74 72	99.12 99	99.56 34	99.39 92	98.96 10	99.17 67	99.44 80	99.63 50	99.58 11	99.48 26	99.27 37	99.60 40	98.81 83
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
DeepC-MVS	97.88 4	99.33 19	99.15 25	99.53 30	99.73 78	99.05 110	99.49 43	99.40 90	98.42 35	99.55 21	99.71 27	99.89 4	99.49 19	99.14 45	98.81 73	99.54 44	99.02 59
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
FC-MVSNet-test		99.32 20	99.33 12	99.31 58	99.87 16	99.65 18	99.63 24	99.75 21	97.76 73	97.29 237	99.87 11	99.63 50	99.52 16	99.66 12	99.63 9	99.77 20	99.12 45

UA-Net		99.30 21	99.22 23	99.39 45	99.94 2	99.66 17	98.91 142	99.86 8	97.74 79	98.74 123	99.00 125	99.60 57	99.17 56	99.50 24	99.39 27	99.70 30	99.64 3

RA-MVS		99.29 22	99.42 9	99.14 79	99.83 24	99.58 23	98.50 189	99.39 92	98.54 30	99.27 52	99.61 43	99.90 3	98.58 115	99.27 40	99.52 19	99.28 89	99.50 15

ACMH+	97.53 7	99.29 22	99.20 24	99.40 44	99.81 34	99.22 75	99.59 31	99.50 72	98.64 26	98.29 174	99.21 107	99.69 33	99.57 12	99.53 23	99.33 32	99.66 34	98.81 83

FE-MVSNET2		99.25 24	99.00 34	99.55 26	99.77 51	99.40 40	99.76 10	99.54 59	98.10 52	99.50 28	99.71 27	99.81 13	99.39 33	98.44 111	99.00 54	99.36 77	98.50 115

Vis-MVSNet		99.25 24	99.32 14	99.17 73	99.65 103	99.55 29	99.63 24	99.33 113	98.16 49	99.29 47	99.65 39	99.77 21	97.56 187	99.44 30	99.14 43	99.58 41	99.51 14
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TranMVSNet+NR-MVSNet		99.23 26	98.91 46	99.61 15	99.81 34	99.45 35	99.47 46	99.68 30	97.28 107	99.39 38	99.54 65	99.08 136	99.45 22	99.09 51	98.84 69	99.83 11	99.04 55

CSCG		99.23 26	99.15 25	99.32 57	99.83 24	99.45 35	98.97 133	99.21 139	98.83 16	99.04 90	99.43 82	99.64 48	99.26 45	98.85 78	98.20 120	99.62 38	99.62 6

Gipuma		99.22 28	98.86 52	99.64 12	99.70 85	99.24 69	99.17 99	99.63 43	99.52 2	99.89 1	96.54 220	99.14 125	99.93 1	99.42 32	99.15 42	99.52 47	99.04 55
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tfpnnormal		99.19 29	98.90 47	99.54 27	99.81 34	99.55 29	99.60 29	99.54 59	98.53 33	99.23 55	98.40 149	98.23 181	99.40 31	99.29 37	99.36 30	99.63 37	98.95 69

Baseline_NR-MVSNet		99.18 30	98.87 49	99.54 27	99.74 72	99.56 27	99.36 62	99.62 48	96.53 154	99.29 47	99.85 14	98.64 170	99.40 31	99.03 62	99.63 9	99.83 11	98.86 78

thisisatest0515		99.16 31	98.94 41	99.41 39	99.75 66	99.43 37	99.36 62	99.63 43	97.68 85	99.35 40	99.31 94	98.90 148	99.09 65	98.95 67	99.20 39	99.27 92	99.11 46

SPE-MVS-test		99.16 31	98.78 59	99.60 17	99.80 40	99.72 9	99.69 17	99.73 23	95.88 178	99.51 27	98.53 144	99.54 64	99.21 50	99.24 41	99.43 24	99.66 34	99.15 44

CS-MVS		99.15 33	98.75 64	99.62 14	99.76 61	99.73 8	99.60 29	99.75 21	95.67 186	99.50 28	98.53 144	99.39 88	99.29 41	99.21 43	99.46 23	99.79 18	99.29 28

APDe-MVS		99.15 33	98.95 38	99.39 45	99.77 51	99.28 61	99.52 38	99.54 59	97.22 112	99.06 84	99.20 108	99.64 48	99.05 69	99.14 45	99.02 53	99.39 70	99.17 41
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
WB-MVS		99.14 35	99.31 16	98.95 113	99.81 34	99.61 20	98.85 151	99.51 69	99.01 9	97.37 231	99.33 91	99.56 62	98.70 97	99.44 30	99.29 34	99.45 60	98.96 68

FC-MVSNet-train		99.13 36	99.05 29	99.21 65	99.87 16	99.57 26	99.67 19	99.60 50	96.75 139	98.28 175	99.48 71	99.52 68	98.10 158	99.47 27	99.37 29	99.76 22	99.21 38

E6new		99.12 37	99.05 29	99.20 69	99.78 45	99.33 53	99.32 74	99.34 110	98.86 13	98.62 130	99.74 24	99.83 9	98.98 73	98.53 105	98.64 93	99.16 109	98.46 119

E6		99.12 37	99.05 29	99.20 69	99.78 45	99.33 53	99.32 74	99.34 110	98.86 13	98.62 130	99.74 24	99.83 9	98.98 73	98.53 105	98.64 93	99.16 109	98.46 119

NR-MVSNet		99.10 39	98.68 76	99.58 20	99.89 12	99.23 72	99.35 66	99.63 43	96.58 147	99.36 39	99.05 119	98.67 168	99.46 20	99.63 16	98.73 87	99.80 15	98.88 77

DVP-MVS++		99.09 40	99.25 19	98.90 121	99.53 141	99.37 47	99.17 99	99.48 77	98.28 45	97.95 202	99.54 65	99.88 5	98.13 157	99.08 52	98.94 58	99.15 112	99.65 2

DVP-MVS		99.09 40	99.07 28	99.12 81	99.55 132	99.40 40	99.36 62	99.44 89	97.75 76	98.23 178	99.23 104	99.80 17	98.97 75	99.08 52	98.96 55	99.19 101	99.25 30
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
UniMVSNet (Re)		99.08 42	98.69 74	99.54 27	99.75 66	99.33 53	99.29 79	99.64 42	96.75 139	99.48 32	99.30 96	98.69 163	99.26 45	98.94 69	98.76 83	99.78 19	99.02 59

casdiffseed414692147		99.06 43	98.93 45	99.21 65	99.79 41	99.26 63	99.49 43	99.35 106	98.20 47	98.46 158	99.68 30	99.82 11	98.84 86	98.72 95	98.36 113	99.34 79	98.45 124

Casviewmamba		99.05 44	99.04 32	99.07 89	99.77 51	99.38 44	99.29 79	99.21 139	98.63 27	97.91 205	99.46 74	99.69 33	98.73 94	98.76 91	98.77 80	99.52 47	98.57 106

ACMMPR		99.05 44	98.72 68	99.44 33	99.79 41	99.12 99	99.35 66	99.56 54	97.74 79	99.21 58	97.72 180	99.55 63	99.29 41	98.90 76	98.80 75	99.41 68	99.19 39

DU-MVS		99.04 46	98.59 81	99.56 22	99.74 72	99.23 72	99.29 79	99.63 43	96.58 147	99.55 21	99.05 119	98.68 165	99.36 36	99.03 62	98.60 96	99.77 20	98.97 64

usedtu_dtu_shiyan2		99.03 47	98.84 55	99.27 63	99.87 16	99.20 82	99.52 38	98.77 194	98.46 34	99.52 24	99.84 18	99.65 46	98.85 84	98.75 92	97.80 148	99.05 132	98.15 160

MED-MVS		99.02 48	98.99 36	99.06 93	99.68 91	99.17 89	99.02 124	99.37 102	98.30 44	98.53 144	99.59 49	99.49 77	98.38 139	98.84 79	98.77 80	99.38 72	98.74 90

TSAR-MVS + MP.		99.02 48	98.95 38	99.11 85	99.23 196	98.79 148	99.51 40	98.73 198	97.50 96	98.56 140	99.03 122	99.59 58	99.16 58	99.29 37	99.17 41	99.50 55	99.24 34
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
v10		99.01 50	98.66 77	99.41 39	99.52 146	99.39 42	99.57 33	99.66 37	97.59 91	99.32 43	99.88 9	99.23 106	99.50 18	97.77 166	97.98 136	98.92 156	98.78 88

EG-PatchMatch MVS		99.01 50	98.77 63	99.28 62	99.64 108	98.90 139	98.81 161	99.27 124	96.55 151	99.71 6	99.31 94	99.66 42	99.17 56	99.28 39	99.11 45	99.10 115	98.57 106

hybridcas		98.99 52	98.99 36	98.98 110	99.77 51	99.34 50	99.30 77	99.15 153	98.66 25	97.64 216	99.45 77	99.70 31	98.61 105	98.61 100	98.79 77	99.41 68	98.40 129

viewmacassd2359aftdt		98.99 52	98.89 48	99.12 81	99.78 45	99.27 62	99.21 93	99.26 126	98.73 23	98.30 172	99.61 43	99.82 11	98.94 78	98.26 135	98.29 115	99.20 100	98.24 146

E4		98.98 54	98.87 49	99.11 85	99.78 45	99.26 63	99.20 95	99.27 124	98.81 17	98.57 138	99.68 30	99.81 13	98.69 99	98.08 145	98.23 117	99.15 112	98.24 146

PVSNet_Blended_VisFu		98.98 54	98.79 57	99.21 65	99.76 61	99.34 50	99.35 66	99.35 106	97.12 121	99.46 34	99.56 59	98.89 149	98.08 162	99.05 56	98.58 98	99.27 92	98.98 63

HFP-MVS		98.97 56	98.70 72	99.29 60	99.67 95	98.98 123	99.13 110	99.53 64	97.76 73	98.90 105	98.07 164	99.50 75	99.14 61	98.64 99	98.78 78	99.37 73	99.18 40

UniMVSNet_NR-MVSNet		98.97 56	98.46 94	99.56 22	99.76 61	99.34 50	99.29 79	99.61 49	96.55 151	99.55 21	99.05 119	97.96 189	99.36 36	98.84 79	98.50 105	99.81 14	98.97 64

casdiffmvs_mvg		98.96 58	98.87 49	99.07 89	99.82 30	99.36 48	99.36 62	99.22 136	98.13 51	97.74 210	99.42 83	99.46 81	98.59 108	98.39 116	98.95 57	99.71 29	98.39 131
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EC-MVSNet		98.96 58	98.45 97	99.56 22	99.88 14	99.70 11	99.68 18	99.78 16	94.15 227	98.97 94	98.26 156	99.21 111	99.35 38	99.30 36	99.14 43	99.73 25	99.40 21

SED-MVS		98.94 60	98.95 38	98.91 120	99.43 165	99.38 44	99.12 113	99.46 82	97.05 126	98.43 161	99.23 104	99.79 18	97.99 168	99.05 56	98.94 58	99.05 132	99.23 35

ACMMP_NAP		98.94 60	98.72 68	99.21 65	99.67 95	99.08 105	99.26 86	99.39 92	96.84 131	98.88 110	98.22 157	99.68 37	98.82 87	99.06 55	98.90 61	99.25 95	99.25 30

v1144		98.94 60	98.53 88	99.42 37	99.62 112	99.03 117	99.58 32	99.36 103	97.99 59	99.49 31	99.91 8	99.20 114	99.51 17	97.61 174	97.85 146	98.95 149	98.10 165

v8		98.94 60	98.60 79	99.35 54	99.54 138	99.39 42	99.55 35	99.67 34	97.48 97	99.13 75	99.81 20	99.10 132	99.39 33	97.86 157	97.89 144	98.81 167	98.66 99

SteuartSystems-ACMMP		98.94 60	98.52 90	99.43 36	99.79 41	99.13 97	99.33 72	99.55 56	96.17 171	99.04 90	97.53 186	99.65 46	99.46 20	99.04 61	98.76 83	99.44 63	99.35 23
Skip Steuart: Steuart Systems R&D Blog.
E5new		98.92 65	98.78 59	99.07 89	99.77 51	99.25 67	99.16 103	99.23 134	98.80 18	98.58 135	99.61 43	99.81 13	98.50 129	97.83 160	98.01 132	99.17 104	98.17 156

E5		98.92 65	98.78 59	99.07 89	99.77 51	99.25 67	99.16 103	99.23 134	98.80 18	98.58 135	99.61 43	99.81 13	98.50 129	97.83 160	98.01 132	99.17 104	98.17 156

viewdifsd2359ckpt11		98.92 65	98.94 41	98.90 121	99.71 83	99.16 91	99.16 103	98.82 189	98.78 21	98.12 188	99.68 30	99.78 19	98.52 124	98.80 86	98.11 125	99.05 132	98.25 144

viewmsd2359difaftdt		98.92 65	98.94 41	98.90 121	99.71 83	99.16 91	99.16 103	98.82 189	98.78 21	98.12 188	99.68 30	99.78 19	98.52 124	98.80 86	98.11 125	99.05 132	98.25 144

v1192		98.91 69	98.48 93	99.41 39	99.61 116	99.03 117	99.64 21	99.25 130	97.91 65	99.58 17	99.92 4	99.07 138	99.45 22	97.55 179	97.68 161	98.93 152	98.23 149

FMVSNet1		98.90 70	99.10 27	98.67 154	99.54 138	99.48 32	99.22 91	99.66 37	98.39 38	97.50 223	99.66 35	99.04 141	96.58 211	99.05 56	99.03 50	99.52 47	99.08 51

ACMM	96.66 11	98.90 70	98.44 99	99.44 33	99.74 72	98.95 129	99.47 46	99.55 56	97.66 88	99.09 80	96.43 222	99.41 83	99.35 38	98.95 67	98.67 90	99.45 60	99.03 57
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20231211		98.89 72	98.79 57	98.99 108	99.82 30	99.41 39	99.18 98	99.31 119	96.92 128	98.54 142	98.58 142	98.84 154	97.46 190	99.45 28	99.29 34	99.65 36	99.08 51

v1921920		98.89 72	98.46 94	99.39 45	99.58 124	99.04 115	99.64 21	99.17 148	97.91 65	99.64 15	99.92 4	98.99 146	99.44 25	97.44 190	97.57 170	98.84 165	98.35 134

GeoE		98.88 74	98.43 104	99.41 39	99.83 24	99.24 69	99.51 40	99.82 13	96.55 151	99.22 57	98.76 133	99.22 110	98.96 76	98.55 103	98.15 122	99.10 115	98.56 110

v144192		98.88 74	98.46 94	99.37 52	99.56 131	99.03 117	99.61 27	99.26 126	97.79 71	99.58 17	99.88 9	99.11 130	99.43 27	97.38 195	97.61 166	98.80 168	98.43 127

aaEdge-Enhanced		98.87 76	98.78 59	98.98 110	99.67 95	99.13 97	99.34 70	98.89 180	97.44 99	98.49 151	99.59 49	99.54 64	98.49 131	98.48 109	98.52 104	99.01 141	98.74 90

SMA-MVS		98.87 76	98.73 67	99.04 99	99.72 81	99.05 110	98.64 176	99.17 148	96.31 166	98.80 117	99.07 115	99.70 31	98.67 100	98.93 72	98.82 70	99.23 98	99.23 35
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
ACMP	96.54 13	98.87 76	98.40 108	99.41 39	99.74 72	98.88 141	99.29 79	99.50 72	96.85 130	98.96 97	97.05 202	99.66 42	99.43 27	98.98 66	98.60 96	99.52 47	98.81 83
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DCV-MVSNet		98.86 79	98.57 86	99.19 71	99.86 21	99.67 15	99.39 56	99.71 27	97.53 95	98.69 127	95.85 234	98.48 173	97.75 181	99.57 21	99.41 26	99.72 26	99.48 17

v1240		98.86 79	98.41 106	99.38 50	99.59 121	99.05 110	99.65 20	99.14 154	97.68 85	99.66 13	99.93 3	98.72 162	99.45 22	97.38 195	97.72 159	98.79 169	98.35 134

CP-MVS		98.86 79	98.43 104	99.36 53	99.68 91	98.97 127	99.19 96	99.46 82	96.60 145	99.20 60	97.11 201	99.51 73	99.15 60	98.92 73	98.82 70	99.45 60	99.08 51

E3new		98.85 82	98.72 68	99.01 103	99.73 78	99.20 82	99.08 115	99.18 146	98.57 28	98.50 147	99.54 65	99.73 24	98.52 124	97.87 155	97.97 137	99.06 129	98.14 163

E3		98.85 82	98.72 68	99.01 103	99.73 78	99.20 82	99.08 115	99.18 146	98.57 28	98.51 146	99.54 65	99.73 24	98.52 124	97.86 157	97.97 137	99.06 129	98.14 163

v2v482		98.85 82	98.40 108	99.38 50	99.65 103	98.98 123	99.55 35	99.39 92	97.92 64	99.35 40	99.85 14	99.14 125	99.39 33	97.50 183	97.78 149	98.98 146	97.60 193

DPE-MVS		98.84 85	98.69 74	99.00 105	99.05 215	99.26 63	99.19 96	99.35 106	95.85 180	98.74 123	99.27 98	99.66 42	98.30 148	98.90 76	98.93 60	99.37 73	99.00 61
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
OPM-MVS		98.84 85	98.59 81	99.12 81	99.52 146	98.50 180	99.13 110	99.22 136	97.76 73	98.76 119	98.70 135	99.61 53	98.90 80	98.67 97	98.37 111	99.19 101	98.57 106
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test20.03		98.84 85	98.74 66	98.95 113	99.77 51	99.33 53	99.21 93	99.46 82	97.29 106	98.88 110	99.65 39	99.10 132	97.07 203	99.11 48	98.76 83	99.32 84	97.98 174

casdiffmvs		98.84 85	98.75 64	98.94 117	99.75 66	99.21 76	99.33 72	99.04 167	98.04 55	97.46 226	99.72 26	99.72 28	98.60 106	98.30 128	98.37 111	99.48 57	97.92 178
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LGP-MVS_train		98.84 85	98.33 115	99.44 33	99.78 45	98.98 123	99.39 56	99.55 56	95.41 191	98.90 105	97.51 187	99.68 37	99.44 25	99.03 62	98.81 73	99.57 42	98.91 73

RPSCF		98.84 85	98.81 56	98.89 126	99.37 174	98.95 129	98.51 188	98.85 186	97.73 81	98.33 169	98.97 127	99.14 125	98.95 77	99.18 44	98.68 89	99.31 85	98.99 62

ACMMP		98.82 91	98.33 115	99.39 45	99.77 51	99.14 95	99.37 59	99.54 59	96.47 158	99.03 92	96.26 226	99.52 68	99.28 43	98.92 73	98.80 75	99.37 73	99.16 42
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
FE-MVSNET		98.81 92	98.41 106	99.27 63	99.55 132	99.09 102	99.61 27	99.46 82	97.15 118	98.70 126	99.18 110	99.17 118	99.23 47	97.94 150	98.48 106	99.10 115	97.88 180

V42		98.81 92	98.49 92	99.18 72	99.52 146	98.92 134	99.50 42	99.29 121	97.43 101	98.97 94	99.81 20	99.00 145	99.30 40	97.93 151	98.01 132	98.51 198	98.34 138

viewdifsd2359ckpt07		98.79 94	98.85 54	98.72 146	99.74 72	99.14 95	98.97 133	98.91 178	98.84 15	98.32 171	99.48 71	99.73 24	98.40 136	98.29 129	98.12 123	97.96 219	98.31 140

LS3D		98.79 94	98.52 90	99.12 81	99.64 108	99.09 102	99.24 89	99.46 82	97.75 76	98.93 103	97.47 189	98.23 181	97.98 170	99.36 33	99.30 33	99.46 58	98.42 128

MP-MVS		98.78 96	98.30 117	99.34 56	99.75 66	98.95 129	99.26 86	99.46 82	95.78 184	99.17 67	96.98 206	99.72 28	99.06 68	98.84 79	98.74 86	99.33 81	99.11 46
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
viewmanbaseed2359cas		98.77 97	98.64 78	98.93 118	99.70 85	99.16 91	98.95 137	99.09 163	98.35 41	98.14 185	99.33 91	99.69 33	98.63 103	97.91 153	97.90 141	99.08 122	98.15 160

v148		98.77 97	98.45 97	99.15 76	99.68 91	98.94 133	99.49 43	99.31 119	97.95 61	98.91 104	99.65 39	99.62 52	99.18 53	97.99 148	97.64 165	98.33 203	97.38 199

test1111		98.75 99	98.14 135	99.46 32	99.86 21	99.63 19	99.47 46	99.68 30	98.34 42	98.76 119	99.66 35	90.92 241	99.23 47	99.77 5	99.71 5	99.75 23	98.95 69

viewcassd2359sk11		98.74 100	98.58 83	98.93 118	99.69 88	99.16 91	98.98 130	99.10 161	98.36 39	98.45 159	99.39 87	99.61 53	98.38 139	97.68 171	97.77 154	98.99 144	98.08 167

ECVR-MVS		98.74 100	98.15 132	99.42 37	99.83 24	99.58 23	99.37 59	99.67 34	98.02 57	98.85 114	99.59 49	91.66 239	99.10 63	99.77 5	99.70 6	99.72 26	98.73 92

SD-MVS		98.73 102	98.54 87	98.95 113	99.14 205	98.76 152	98.46 193	99.14 154	97.71 83	98.56 140	98.06 166	99.61 53	98.85 84	98.56 102	97.74 156	99.54 44	99.32 26
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
MSP-MVS		98.72 103	98.60 79	98.87 128	99.67 95	99.33 53	99.15 107	99.26 126	96.99 127	97.90 206	98.19 159	99.74 23	98.29 149	97.69 170	98.96 55	98.96 147	99.27 29
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
PGM-MVS		98.69 104	98.09 140	99.39 45	99.76 61	99.07 106	99.30 77	99.51 69	94.76 205	99.18 64	96.70 215	99.51 73	99.20 51	98.79 88	98.71 88	99.39 70	99.11 46

pmmvs-eth3d		98.68 105	98.14 135	99.29 60	99.49 151	98.45 183	99.45 51	99.38 98	97.21 113	99.50 28	99.65 39	99.21 111	99.16 58	97.11 203	97.56 171	98.79 169	97.82 183

EU-MVSNet		98.68 105	98.94 41	98.37 182	99.14 205	98.74 156	99.64 21	98.20 228	98.21 46	99.17 67	99.66 35	99.18 117	99.08 66	99.11 48	98.86 64	95.00 251	98.83 80

PMVS	92.51 17	98.66 107	98.86 52	98.43 177	99.26 191	98.98 123	98.60 182	98.59 211	97.73 81	99.45 35	99.38 88	98.54 172	95.24 231	99.62 17	99.61 14	99.42 65	98.17 156
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DeepC-MVS_fast	97.38 8	98.65 108	98.34 114	99.02 102	99.33 178	98.29 190	98.99 127	98.71 201	97.40 102	99.31 44	98.20 158	99.40 86	98.54 122	98.33 125	98.18 121	99.23 98	98.58 104
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator	98.16 3	98.65 108	98.35 113	99.00 105	99.59 121	98.70 160	98.90 146	99.36 103	97.97 60	99.09 80	96.55 219	99.09 134	97.97 171	98.70 96	98.65 92	99.12 114	98.81 83

TSAR-MVS + ACMM		98.64 110	98.58 83	98.72 146	99.17 203	98.63 169	98.69 171	99.10 161	97.69 84	98.30 172	99.12 113	99.38 90	98.70 97	98.45 110	97.51 174	98.35 202	99.25 30

E2		98.63 111	98.44 99	98.86 131	99.65 103	99.12 99	98.88 148	99.03 168	98.10 52	98.40 162	99.27 98	99.48 79	98.24 152	97.51 182	97.56 171	98.93 152	98.05 168

DELS-MVS		98.63 111	98.70 72	98.55 172	99.24 195	99.04 115	98.96 135	98.52 215	96.83 133	98.38 164	99.58 54	99.68 37	97.06 204	98.74 94	98.44 108	99.10 115	98.59 103
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
QAPM		98.62 113	98.40 108	98.89 126	99.57 130	98.80 146	98.63 177	99.35 106	96.82 134	98.60 133	98.85 132	99.08 136	98.09 160	98.31 126	98.21 118	99.08 122	98.72 93

EPP-MVSNet		98.61 114	98.19 129	99.11 85	99.86 21	99.60 21	99.44 52	99.53 64	97.37 103	96.85 252	98.69 136	93.75 232	99.18 53	99.22 42	99.35 31	99.82 13	99.32 26

3Dnovator+	97.85 5	98.61 114	98.14 135	99.15 76	99.62 112	98.37 187	99.10 114	99.51 69	98.04 55	98.98 93	96.07 231	98.75 161	98.55 119	98.51 107	98.40 109	99.17 104	98.82 81

viewdifsd2359ckpt13		98.60 116	98.39 111	98.85 135	99.67 95	99.05 110	98.77 166	99.05 166	97.89 68	98.19 180	99.25 101	99.54 64	98.37 141	97.55 179	97.45 177	99.04 137	97.99 171

X-MVS		98.59 117	97.99 147	99.30 59	99.75 66	99.07 106	99.17 99	99.50 72	96.62 143	98.95 99	93.95 250	99.37 91	99.11 62	98.94 69	98.86 64	99.35 78	99.09 50

MVSMamba_PlusPlus		98.58 118	98.58 83	98.57 168	99.48 153	99.17 89	98.03 223	98.59 211	96.47 158	97.74 210	98.40 149	99.07 138	98.40 136	98.84 79	98.77 80	99.17 104	99.35 23

MVS_111021_HR		98.58 118	98.26 120	98.96 112	99.32 181	98.81 144	98.48 191	98.99 173	96.81 136	99.16 70	98.07 164	99.23 106	98.89 82	98.43 113	98.27 116	98.90 158	98.24 146

MGCNet		98.57 120	98.44 99	98.71 149	99.76 61	99.31 59	99.43 53	99.24 132	97.79 71	98.35 167	98.48 146	96.64 209	96.30 220	98.91 75	98.82 70	99.18 103	99.16 42

PM-MVS		98.57 120	98.24 125	98.95 113	99.26 191	98.59 172	99.03 122	98.74 197	96.84 131	99.44 36	99.13 112	98.31 180	98.75 92	98.03 146	98.21 118	98.48 199	98.58 104

PHI-MVS		98.57 120	98.20 128	99.00 105	99.48 153	98.91 136	98.68 172	99.17 148	94.97 200	99.27 52	98.33 152	99.33 96	98.05 165	98.82 84	98.62 95	99.34 79	98.38 132

diffmvs_AUTHOR		98.56 123	98.53 88	98.60 161	99.69 88	98.90 139	99.01 126	98.86 185	98.36 39	97.21 239	99.70 29	99.67 41	98.08 162	97.61 174	97.45 177	98.77 171	98.00 170

HPM-MVS++		98.56 123	98.08 141	99.11 85	99.53 141	98.61 171	99.02 124	99.32 117	96.29 168	99.06 84	97.23 196	99.50 75	98.77 90	98.15 141	97.90 141	98.96 147	98.90 74

TSAR-MVS + GP.		98.54 125	98.29 119	98.82 139	99.28 189	98.59 172	97.73 236	99.24 132	95.93 177	98.59 134	99.07 115	99.17 118	98.86 83	98.44 111	98.10 127	99.26 94	98.72 93

viewdifsd2359ckpt09		98.53 126	98.25 122	98.86 131	99.68 91	99.09 102	98.73 169	99.12 158	97.85 70	98.38 164	99.07 115	99.28 102	98.25 151	97.06 205	97.39 180	98.99 144	98.02 169

UGNet		98.52 127	99.00 34	97.96 207	99.58 124	99.26 63	99.27 85	99.40 90	98.07 54	98.28 175	98.76 133	99.71 30	92.24 263	98.94 69	98.85 66	99.00 143	99.43 20
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
Anonymous20231206		98.50 128	98.03 144	99.05 97	99.50 149	99.01 120	99.15 107	99.26 126	96.38 163	99.12 77	99.50 70	99.12 128	98.60 106	97.68 171	97.24 189	98.66 181	97.30 203

CLD-MVS		98.48 129	98.15 132	98.86 131	99.53 141	98.35 188	98.55 185	97.83 237	96.02 176	98.97 94	99.08 114	99.75 22	99.03 70	98.10 144	97.33 185	99.28 89	98.44 126
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CANet		98.47 130	98.30 117	98.67 154	99.65 103	98.87 142	98.82 156	99.01 171	96.14 172	99.29 47	98.86 130	99.01 143	96.54 212	98.36 120	98.08 129	98.72 176	98.80 87

APD-MVS		98.47 130	97.97 148	99.05 97	99.64 108	98.91 136	98.94 138	99.45 88	94.40 220	98.77 118	97.26 195	99.41 83	98.21 154	98.67 97	98.57 101	99.31 85	98.57 106
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
viewmamba		98.46 132	98.36 112	98.58 163	99.65 103	98.80 146	98.82 156	98.72 200	98.33 43	97.54 221	99.58 54	99.61 53	97.96 172	97.71 168	96.86 198	98.76 174	97.65 191

Vis-MVSNet (Re-imp)		98.46 132	98.23 126	98.73 145	99.81 34	99.29 60	98.79 163	99.50 72	96.20 170	96.03 259	98.29 154	96.98 204	98.54 122	99.11 48	99.08 46	99.70 30	98.62 101

Fast-Effi-MVS+		98.42 134	97.79 156	99.15 76	99.69 88	98.66 167	98.94 138	99.68 30	94.49 214	99.05 86	98.06 166	98.86 151	98.48 132	98.18 138	97.78 149	99.05 132	98.54 113

ETV-MVS		98.41 135	97.76 157	99.17 73	99.58 124	99.01 120	98.91 142	99.50 72	93.33 240	99.31 44	96.82 212	98.42 176	98.17 156	99.13 47	99.08 46	99.54 44	98.56 110

dtuplus		98.39 136	98.22 127	98.58 163	99.58 124	98.69 161	99.05 118	98.83 188	97.68 85	97.19 241	99.46 74	99.59 58	97.89 177	97.47 186	96.69 202	98.95 149	97.97 175

MVS_111021_LR		98.39 136	98.11 138	98.71 149	99.08 212	98.54 178	98.23 216	98.56 214	96.57 149	99.13 75	98.41 148	98.86 151	98.65 102	98.23 136	97.87 145	98.65 183	98.28 141

onestephybrid01		98.38 138	98.25 122	98.53 174	99.61 116	98.79 148	99.04 121	98.68 203	97.17 117	97.58 218	99.58 54	99.57 61	97.51 189	97.79 165	97.14 191	98.77 171	97.71 186

pmmvs5		98.37 139	97.81 155	99.03 100	99.46 156	98.97 127	99.03 122	98.96 175	95.85 180	99.05 86	99.45 77	98.66 169	98.79 89	96.02 222	97.52 173	98.87 160	98.21 152

OMC-MVS		98.35 140	98.10 139	98.64 160	98.85 223	97.99 209	98.56 184	98.21 226	97.26 110	98.87 112	98.54 143	99.27 103	98.43 134	98.34 123	97.66 162	98.92 156	97.65 191

sasdasda		98.34 141	97.92 151	98.83 136	99.45 158	99.21 76	98.37 201	99.53 64	97.06 123	97.74 210	96.95 209	95.05 222	98.36 142	98.77 89	98.85 66	99.51 53	99.53 10

canonicalmvs		98.34 141	97.92 151	98.83 136	99.45 158	99.21 76	98.37 201	99.53 64	97.06 123	97.74 210	96.95 209	95.05 222	98.36 142	98.77 89	98.85 66	99.51 53	99.53 10

hybridnocas07		98.31 143	98.25 122	98.38 181	99.61 116	98.75 154	98.81 161	98.68 203	97.57 92	97.09 245	99.58 54	99.47 80	97.38 195	97.67 173	96.91 197	98.71 177	97.82 183

CHOSEN 1792x2688		98.31 143	98.02 145	98.66 156	99.55 132	98.57 175	99.38 58	99.25 130	98.42 35	98.48 154	99.58 54	99.85 7	98.31 147	95.75 226	95.71 220	96.96 232	98.27 143

viewmambaseed2359dif		98.30 145	98.05 143	98.58 163	99.55 132	98.69 161	98.99 127	98.76 196	97.06 123	97.32 234	99.40 86	99.52 68	97.99 168	97.22 201	96.54 208	98.85 164	97.95 176

CPTT-MVS		98.28 146	97.51 171	99.16 75	99.54 138	98.78 150	98.96 135	99.36 103	96.30 167	98.89 109	93.10 254	99.30 99	99.20 51	98.35 122	97.96 139	99.03 139	98.82 81

usedtu_dtu_shiyan1		98.27 147	97.72 161	98.90 121	98.96 218	98.75 154	99.17 99	98.96 175	96.35 164	98.90 105	98.69 136	99.05 140	98.55 119	96.31 217	97.36 183	98.86 162	97.55 196

TinyColmap		98.27 147	97.62 168	99.03 100	99.29 187	97.79 218	98.92 141	98.95 177	97.48 97	99.52 24	98.65 139	97.86 191	98.90 80	98.34 123	97.27 187	98.64 184	95.97 229

diffmvs		98.26 149	98.16 130	98.39 179	99.61 116	98.78 150	98.79 163	98.61 209	97.94 62	97.11 244	99.51 69	99.52 68	97.61 185	96.55 213	96.93 196	98.61 186	97.87 181
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
USDC		98.26 149	97.57 169	99.06 93	99.42 168	97.98 211	98.83 153	98.85 186	97.57 92	99.59 16	99.15 111	98.59 171	98.99 72	97.42 191	96.08 219	98.69 180	96.23 226

SF-MVS		98.25 151	98.16 130	98.35 183	99.43 165	98.42 186	97.05 259	99.09 163	96.42 161	98.13 186	97.73 179	99.20 114	97.22 199	98.36 120	98.38 110	99.16 109	98.62 101

MCST-MVS		98.25 151	97.57 169	99.06 93	99.53 141	98.24 196	98.63 177	99.17 148	95.88 178	98.58 135	96.11 229	99.09 134	99.18 53	97.58 178	97.31 186	99.25 95	98.75 89

hybrid		98.24 153	98.15 132	98.34 184	99.60 120	98.74 156	98.76 167	98.62 208	97.54 94	97.16 243	99.55 63	99.35 95	97.39 194	97.49 184	96.72 201	98.53 194	97.66 190

MGCFI-Net		98.23 154	97.93 150	98.58 163	99.44 162	99.20 82	98.37 201	99.54 59	97.14 119	96.70 256	96.98 206	95.04 224	97.92 176	98.75 92	98.89 62	99.52 47	99.55 9

IterMVS-LS		98.23 154	97.66 164	98.90 121	99.63 111	99.38 44	99.07 117	99.48 77	97.75 76	98.81 116	99.37 89	94.57 226	97.88 178	96.54 214	97.04 193	98.53 194	98.97 64
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TAPA-MVS	96.65 12	98.23 154	97.96 149	98.55 172	98.81 225	98.16 200	98.40 198	97.94 235	96.68 141	98.49 151	98.61 140	98.89 149	98.57 117	97.45 188	97.59 168	99.09 121	98.35 134
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CNVR-MVS		98.22 157	97.76 157	98.76 143	99.33 178	98.26 194	98.48 191	98.88 183	96.22 169	98.47 156	95.79 235	99.33 96	98.35 144	98.37 119	97.99 135	99.02 140	98.38 132

IS_MVSNet		98.20 158	98.00 146	98.44 176	99.82 30	99.48 32	99.25 88	99.56 54	95.58 188	93.93 271	97.56 185	96.52 210	98.27 150	99.08 52	99.20 39	99.80 15	98.56 110

DeepPCF-MVS	96.68 10	98.20 158	98.26 120	98.12 197	97.03 270	98.11 203	98.44 195	97.70 240	96.77 138	98.52 145	98.91 128	99.17 118	98.58 115	98.41 115	98.02 131	98.46 200	98.46 119

MSDG		98.20 158	97.88 154	98.56 170	99.33 178	97.74 219	98.27 213	98.10 229	97.20 115	98.06 195	98.59 141	99.16 121	98.76 91	98.39 116	97.71 160	98.86 162	96.38 223

testgi		98.18 161	98.44 99	97.89 209	99.78 45	99.23 72	98.78 165	99.21 139	97.26 110	97.41 228	97.39 192	99.36 94	92.85 258	98.82 84	98.66 91	99.31 85	98.35 134

Effi-MVS+		98.11 162	97.29 178	99.06 93	99.62 112	98.55 176	98.16 219	99.80 15	94.64 210	99.15 73	96.59 217	97.43 197	98.44 133	97.46 187	97.90 141	99.17 104	98.45 124

FA-MVS(training)		98.08 163	97.68 162	98.56 170	99.14 205	98.69 161	98.41 196	99.83 12	95.85 180	98.57 138	97.95 173	96.92 206	96.85 206	98.51 107	98.09 128	98.54 192	97.74 185

HyFIR lowres test		98.08 163	97.16 187	99.14 79	99.72 81	98.91 136	99.41 54	99.58 51	97.93 63	98.82 115	99.24 102	95.81 216	98.73 94	95.16 237	95.13 229	98.60 188	97.94 177

EIA-MVS		98.03 165	97.20 184	98.99 108	99.66 100	99.24 69	98.53 187	99.52 68	91.56 257	99.25 54	95.34 239	98.78 158	97.72 182	98.38 118	98.58 98	99.28 89	98.54 113

train_agg		97.99 166	97.26 179	98.83 136	99.43 165	98.22 198	98.91 142	99.07 165	94.43 218	97.96 201	96.42 223	99.30 99	98.81 88	97.39 193	96.62 206	98.82 166	98.47 117

MSLP-MVS++		97.99 166	97.64 167	98.40 178	98.91 221	98.47 182	97.12 256	98.78 193	96.49 156	98.48 154	93.57 252	99.12 128	98.51 128	98.31 126	98.58 98	98.58 190	98.95 69

CDPH-MVS		97.99 166	97.23 182	98.87 128	99.58 124	98.29 190	98.83 153	99.20 142	93.76 234	98.11 190	96.11 229	99.16 121	98.23 153	97.80 163	97.22 190	99.29 88	98.28 141

FMVSNet2		97.94 169	98.08 141	97.77 217	98.71 230	99.21 76	98.62 179	99.47 79	96.62 143	96.37 258	99.20 108	97.70 193	94.39 243	97.39 193	97.75 155	99.08 122	98.70 96

PVSNet_BlendedMVS		97.93 170	97.66 164	98.25 190	99.30 184	98.67 164	98.31 208	97.95 233	94.30 224	98.75 121	97.63 182	98.76 159	96.30 220	98.29 129	97.78 149	98.93 152	98.18 154

PVSNet_Blended		97.93 170	97.66 164	98.25 190	99.30 184	98.67 164	98.31 208	97.95 233	94.30 224	98.75 121	97.63 182	98.76 159	96.30 220	98.29 129	97.78 149	98.93 152	98.18 154

OpenMVS	97.26 9	97.88 172	97.17 186	98.70 151	99.50 149	98.55 176	98.34 206	99.11 159	93.92 232	98.90 105	95.04 244	98.23 181	97.38 195	98.11 143	98.12 123	98.95 149	98.23 149

pmmvs4		97.87 173	97.02 191	98.86 131	99.20 197	97.68 222	98.89 147	99.03 168	96.57 149	99.12 77	99.03 122	97.26 201	98.42 135	95.16 237	96.34 211	98.53 194	97.10 210

NCCC		97.84 174	96.96 193	98.87 128	99.39 172	98.27 193	98.46 193	99.02 170	96.78 137	98.73 125	91.12 258	98.91 147	98.57 117	97.83 160	97.49 175	99.04 137	98.33 139

Effi-MVS+-dtu		97.78 175	97.37 175	98.26 188	99.25 193	98.50 180	97.89 230	99.19 145	94.51 212	98.16 183	95.93 232	98.80 156	95.97 224	98.27 134	97.38 181	99.10 115	98.23 149

MDA-MVSNet-bldmvs		97.75 176	97.26 179	98.33 185	99.35 177	98.45 183	99.32 74	97.21 246	97.90 67	99.05 86	99.01 124	96.86 207	99.08 66	99.36 33	92.97 241	95.97 247	96.25 225

CDS-MVSNet		97.75 176	97.68 162	97.83 215	99.08 212	98.20 199	98.68 172	98.61 209	95.63 187	97.80 208	99.24 102	96.93 205	94.09 249	97.96 149	97.82 147	98.71 177	97.99 171
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CNLPA		97.75 176	97.26 179	98.32 187	98.58 238	97.86 214	97.80 232	98.09 230	96.49 156	98.49 151	96.15 228	98.08 184	98.35 144	98.00 147	97.03 194	98.61 186	97.21 207

PLC	95.63 15	97.73 179	97.01 192	98.57 168	99.10 209	97.80 217	97.72 237	98.77 194	96.34 165	98.38 164	93.46 253	98.06 185	98.66 101	97.90 154	97.65 164	98.77 171	97.90 179
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVS_Test		97.69 180	97.15 188	98.33 185	99.27 190	98.43 185	98.25 214	99.29 121	95.00 199	97.39 230	98.86 130	98.00 188	97.14 201	95.38 232	96.22 213	98.62 185	98.15 160

GBi-Net		97.69 180	97.75 159	97.62 218	98.71 230	99.21 76	98.62 179	99.33 113	94.09 228	95.60 261	98.17 161	95.97 213	94.39 243	99.05 56	99.03 50	99.08 122	98.70 96

test1		97.69 180	97.75 159	97.62 218	98.71 230	99.21 76	98.62 179	99.33 113	94.09 228	95.60 261	98.17 161	95.97 213	94.39 243	99.05 56	99.03 50	99.08 122	98.70 96

CANet_DTU		97.65 183	97.50 173	97.82 216	99.19 200	98.08 205	98.41 196	98.67 205	94.40 220	99.16 70	98.32 153	98.69 163	93.96 252	97.87 155	97.61 166	97.51 225	97.56 195

IterMVS-SCA-FT		97.63 184	96.86 195	98.52 175	99.48 153	98.71 159	98.84 152	98.91 178	96.44 160	99.16 70	99.56 59	95.54 218	97.95 173	95.68 229	95.07 232	96.76 238	97.03 213

TSAR-MVS + COLMAP		97.62 185	97.31 177	97.98 205	98.47 246	97.39 228	98.29 210	98.25 225	96.68 141	97.54 221	98.87 129	98.04 187	97.08 202	96.78 208	96.26 212	98.26 206	97.12 209

MS-PatchMatch		97.60 186	97.22 183	98.04 204	98.67 234	97.18 233	97.91 228	98.28 224	95.82 183	98.34 168	97.66 181	98.38 177	97.77 180	97.10 204	97.25 188	97.27 227	97.18 208

PCF-MVS	95.58 16	97.60 186	96.67 196	98.69 152	99.44 162	98.23 197	98.37 201	98.81 191	93.01 244	98.22 179	97.97 172	99.59 58	98.20 155	95.72 228	95.08 230	99.08 122	97.09 212
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HQP-MVS		97.58 188	96.65 199	98.66 156	99.30 184	97.99 209	97.88 231	98.65 206	94.58 211	98.66 128	94.65 248	99.15 124	98.59 108	96.10 220	95.59 221	98.90 158	98.50 115

DI_MVS_pp		97.57 189	96.55 201	98.77 142	99.55 132	98.76 152	99.22 91	99.00 172	97.08 122	97.95 202	97.78 178	91.35 240	98.02 166	96.20 218	96.81 200	98.87 160	97.87 181

AdaColmap		97.57 189	96.57 200	98.74 144	99.25 193	98.01 207	98.36 205	98.98 174	94.44 217	98.47 156	92.44 255	97.91 190	98.62 104	98.19 137	97.74 156	98.73 175	97.28 204

baseline		97.50 191	97.51 171	97.50 222	99.18 201	97.38 229	98.00 224	98.00 232	96.52 155	97.49 224	99.28 97	99.43 82	95.31 230	95.27 234	96.22 213	96.99 230	98.47 117

IterMVS		97.40 192	96.67 196	98.25 190	99.45 158	98.66 167	98.87 149	98.73 198	96.40 162	98.94 102	99.56 59	95.26 220	97.58 186	95.38 232	94.70 234	95.90 248	96.72 216
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		97.38 193	96.15 210	98.82 139	99.39 172	98.34 189	98.65 175	98.88 183	90.80 264	98.86 113	92.35 256	95.13 221	98.09 160	98.84 79	98.88 63	99.06 129	98.71 95

CVMVSNet		97.38 193	97.39 174	97.37 226	98.58 238	97.72 220	98.70 170	97.42 244	97.21 113	95.95 260	99.46 74	93.31 235	97.38 195	97.60 176	97.78 149	96.18 244	98.66 99

new-patchmatchnet		97.26 195	96.12 211	98.58 163	99.55 132	98.63 169	99.14 109	97.04 248	98.80 18	99.19 62	99.92 4	99.19 116	98.92 79	95.51 231	87.04 259	97.66 222	93.73 249

MIMVSNet		97.24 196	97.15 188	97.36 227	99.03 216	98.52 179	98.55 185	99.73 23	94.94 203	94.94 268	97.98 171	97.37 199	93.66 253	97.60 176	97.34 184	98.23 209	96.29 224

PatchMatch-RL		97.24 196	96.45 204	98.17 194	98.70 233	97.57 225	97.31 251	98.48 218	94.42 219	98.39 163	95.74 236	96.35 212	97.88 178	97.75 167	97.48 176	98.24 208	95.87 233

dtuonlycased		97.23 198	97.32 176	97.13 232	99.59 121	98.67 164	98.87 149	97.72 239	97.34 104	92.21 275	99.35 90	99.39 88	98.07 164	95.98 224	94.57 235	96.35 241	95.94 232

thisisatest0530		97.20 199	95.95 215	98.66 156	99.46 156	98.84 143	98.29 210	99.20 142	94.51 212	98.25 177	97.42 190	85.03 258	97.68 183	98.43 113	98.56 102	99.08 122	98.89 76

tttt0517		97.18 200	95.92 216	98.65 159	99.49 151	98.92 134	98.29 210	99.20 142	94.37 222	98.17 181	97.37 193	84.72 261	97.68 183	98.55 103	98.56 102	99.10 115	98.95 69

MDTV_nov1_ep13_2view		97.12 201	96.19 209	98.22 193	99.13 208	98.05 206	99.24 89	99.47 79	97.61 89	99.15 73	99.59 49	99.01 143	98.40 136	94.87 241	90.14 244	93.91 259	94.04 248

MAR-MVS		97.12 201	96.28 207	98.11 198	98.94 219	97.22 231	97.65 241	99.38 98	90.93 263	98.15 184	95.17 241	97.13 202	96.48 215	97.71 168	97.40 179	98.06 213	98.40 129
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
Fast-Effi-MVS+-dtu		96.99 203	96.46 203	97.61 220	98.98 217	97.89 212	97.54 245	99.76 19	93.43 238	96.55 257	94.93 245	98.06 185	94.32 246	96.93 206	96.50 209	98.53 194	97.47 197

FPMVS		96.97 204	97.20 184	96.70 246	97.75 262	96.11 254	97.72 237	95.47 255	97.13 120	98.02 197	97.57 184	96.67 208	92.97 257	99.00 65	98.34 114	98.28 205	95.58 235

TAMVS		96.95 205	96.94 194	96.97 240	99.07 214	97.67 224	97.98 226	97.12 247	95.04 198	95.41 264	99.27 98	95.57 217	94.09 249	97.32 197	97.11 192	98.16 211	96.59 217

FMVSNet3		96.85 206	96.67 196	97.06 234	97.56 265	99.01 120	97.99 225	99.33 113	94.09 228	95.60 261	98.17 161	95.97 213	93.26 256	94.76 243	96.22 213	98.59 189	98.46 119

GA-MVS		96.84 207	95.86 218	97.98 205	99.16 204	98.29 190	97.91 228	98.64 207	95.14 194	97.71 214	98.04 168	88.90 244	96.50 214	96.41 216	96.61 207	97.97 218	97.60 193

CHOSEN 280x420		96.80 208	96.30 206	97.39 224	99.09 210	96.52 246	98.76 167	99.29 121	93.88 233	97.65 215	98.34 151	93.66 233	96.29 223	98.28 132	97.73 158	93.27 262	95.70 234

gg-mvs-nofinetune		96.77 209	96.52 202	97.06 234	99.66 100	97.82 216	97.54 245	99.86 8	98.69 24	98.61 132	99.94 2	89.62 242	88.37 271	97.55 179	96.67 204	98.30 204	95.35 236

dtuonly		96.75 210	96.24 208	97.34 228	99.41 170	96.98 238	98.07 222	97.70 240	95.68 185	98.07 194	99.07 115	99.23 106	96.32 219	95.14 239	93.82 238	94.49 254	93.72 250

DPM-MVS		96.73 211	95.70 221	97.95 208	98.93 220	97.26 230	97.39 250	98.44 220	95.47 190	97.62 217	90.71 259	98.47 175	97.03 205	95.02 240	95.27 226	98.26 206	97.67 188

baseline1		96.72 212	95.40 223	98.26 188	99.53 141	98.81 144	98.32 207	98.80 192	94.96 201	96.78 255	96.50 221	84.87 260	96.68 210	97.42 191	97.91 140	99.46 58	97.33 202

N_pmnet		96.68 213	95.70 221	97.84 214	99.42 168	98.00 208	99.35 66	98.21 226	98.40 37	98.13 186	99.42 83	99.30 99	97.44 193	94.00 247	88.79 246	94.47 255	91.96 259

pmnet_mix02		96.61 214	95.32 224	98.11 198	99.41 170	97.68 222	99.05 118	97.59 242	98.16 49	99.05 86	99.48 71	99.11 130	98.32 146	92.36 252	87.67 254	95.26 250	92.80 256

new_pmnet		96.59 215	96.40 205	96.81 243	98.24 258	95.46 263	97.71 239	94.75 262	96.92 128	96.80 254	99.23 104	97.81 192	96.69 208	96.58 212	95.16 228	96.69 239	93.64 251

PMMVS		96.47 216	95.81 219	97.23 229	97.38 267	95.96 258	97.31 251	96.91 249	93.21 241	97.93 204	97.14 199	97.64 195	95.70 226	95.24 235	96.18 216	98.17 210	95.33 237

EPNet		96.44 217	96.08 212	96.86 242	99.32 181	97.15 234	97.69 240	99.32 117	93.67 235	98.11 190	95.64 237	93.44 234	89.07 269	96.86 207	96.83 199	97.67 221	98.97 64
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thres600view7		96.35 218	94.27 228	98.79 141	99.66 100	99.18 86	98.94 138	99.38 98	94.37 222	97.21 239	87.19 264	84.10 262	98.10 158	98.16 139	99.47 21	99.42 65	97.43 198

EPNet_dtu		96.31 219	95.96 214	96.72 245	99.18 201	95.39 264	97.03 260	99.13 157	93.02 243	99.35 40	97.23 196	97.07 203	90.70 268	95.74 227	95.08 230	94.94 252	98.16 159
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs3		96.30 220	95.87 217	96.80 244	97.66 264	96.48 247	97.93 227	93.80 264	93.40 239	98.54 142	98.27 155	97.50 196	97.37 198	97.49 184	93.11 240	95.52 249	94.85 241

PMMVS2		96.29 221	97.05 190	95.40 256	98.32 256	96.16 251	98.18 218	97.46 243	97.20 115	84.51 278	99.60 47	98.68 165	96.37 216	98.59 101	97.38 181	97.58 224	91.76 260

thres200		96.23 222	94.13 229	98.69 152	99.44 162	99.18 86	98.58 183	99.38 98	93.52 237	97.35 232	86.33 269	85.83 255	97.93 174	98.16 139	98.78 78	99.42 65	97.10 210

thres400		96.22 223	94.08 232	98.72 146	99.58 124	99.05 110	98.83 153	99.22 136	94.01 231	97.40 229	86.34 268	84.91 259	97.93 174	97.85 159	99.08 46	99.37 73	97.28 204

tfpn200view9		96.17 224	94.08 232	98.60 161	99.37 174	99.18 86	98.68 172	99.39 92	92.02 251	97.30 235	86.53 266	86.34 252	97.45 192	98.15 141	99.08 46	99.43 64	97.28 204

CMPMVS	74.71 19	96.17 224	96.06 213	96.30 250	97.41 266	94.52 267	94.83 272	95.46 256	91.57 256	97.26 238	94.45 249	98.33 179	94.98 233	98.28 132	97.59 168	97.86 220	97.68 187
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test2506		96.12 226	93.35 244	99.35 54	99.83 24	99.58 23	99.37 59	99.67 34	98.02 57	98.44 160	97.51 187	60.03 282	99.10 63	99.77 5	99.70 6	99.72 26	98.86 78

blended_shiyan8		96.02 227	94.28 227	98.05 202	98.55 244	97.09 235	98.98 130	95.56 253	95.13 195	99.23 55	98.03 170	94.19 228	98.73 94	90.28 255	88.65 247	97.22 228	96.56 220

blended_shiyan6		96.02 227	94.29 226	98.05 202	98.56 241	97.09 235	98.99 127	95.56 253	95.11 196	99.21 58	98.04 168	94.28 227	98.74 93	90.26 256	88.64 248	97.22 228	96.57 218

gbinet_0.2-2-1-0.02		95.92 229	94.09 230	98.06 200	98.81 225	97.08 237	99.13 110	96.47 250	94.88 204	99.08 82	98.47 147	94.16 229	98.02 166	90.43 254	87.61 255	96.86 233	95.99 228

IB-MVS	95.85 14	95.87 230	94.88 225	97.02 237	99.09 210	98.25 195	97.16 253	97.38 245	91.97 254	97.77 209	83.61 274	97.29 200	92.03 266	97.16 202	97.66 162	98.66 181	98.20 153
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
test0.0.03 1		95.81 231	95.77 220	95.85 255	99.20 197	98.15 202	97.49 249	98.50 216	92.24 247	92.74 274	96.82 212	92.70 236	88.60 270	97.31 199	97.01 195	98.57 191	96.19 227

thres100view900		95.74 232	93.66 243	98.17 194	99.37 174	98.59 172	98.10 220	98.33 223	92.02 251	97.30 235	86.53 266	86.34 252	96.69 208	96.77 209	98.47 107	99.24 97	96.89 214

wanda-best-256-512		95.72 233	93.88 237	97.86 212	98.45 247	96.92 239	98.82 156	95.29 258	94.75 206	99.18 64	97.92 175	94.13 230	98.59 108	89.77 258	87.74 250	96.86 233	95.95 230

FE-blended-shiyan7		95.72 233	93.88 237	97.86 212	98.45 247	96.92 239	98.82 156	95.29 258	94.75 206	99.18 64	97.92 175	94.13 230	98.59 108	89.77 258	87.74 250	96.86 233	95.95 230

ET-MVSNet_ETH3D		95.72 233	93.85 239	97.89 209	97.30 268	98.09 204	98.19 217	98.40 221	94.46 216	98.01 200	96.71 214	77.85 278	96.76 207	96.08 221	96.39 210	98.70 179	97.36 200

baseline2		95.58 236	94.04 234	97.38 225	98.80 227	98.16 200	97.14 254	97.80 238	91.45 258	97.49 224	95.22 240	83.63 263	94.98 233	96.42 215	96.66 205	98.06 213	96.76 215

PatchT		95.49 237	93.29 245	98.06 200	98.65 235	96.20 250	98.91 142	99.73 23	92.00 253	98.50 147	96.67 216	83.25 264	96.34 217	94.40 244	95.50 222	96.21 243	95.04 239

CR-MVSNet		95.38 238	93.01 246	98.16 196	98.63 236	95.85 260	97.64 242	99.78 16	91.27 260	98.50 147	96.84 211	82.16 265	96.34 217	94.40 244	95.50 222	98.05 215	95.04 239

MVSTER		95.38 238	93.99 236	97.01 238	98.83 224	98.95 129	96.62 261	99.14 154	92.17 249	97.44 227	97.29 194	77.88 277	91.63 267	97.45 188	96.18 216	98.41 201	97.99 171

MVS-HIRNet		94.86 240	93.83 240	96.07 251	97.07 269	94.00 269	94.31 273	99.17 148	91.23 262	98.17 181	98.69 136	97.43 197	95.66 227	94.05 246	91.92 242	92.04 269	89.46 268

test-LLR		94.79 241	93.71 241	96.06 252	99.20 197	96.16 251	96.31 263	98.50 216	89.98 265	94.08 269	97.01 203	86.43 250	92.20 264	96.76 210	95.31 224	96.05 245	94.31 245

RPMNet		94.72 242	92.01 251	97.88 211	98.56 241	95.85 260	97.78 233	99.70 29	91.27 260	98.33 169	93.69 251	81.88 266	94.91 236	92.60 250	94.34 237	98.01 217	94.46 244

gm-plane-assit		94.62 243	91.39 253	98.39 179	99.90 11	99.47 34	99.40 55	99.65 39	97.44 99	99.56 20	99.68 30	59.40 283	94.23 247	96.17 219	94.77 233	97.61 223	92.79 257

test-mter		94.62 243	94.02 235	95.32 257	97.72 263	96.75 243	96.23 265	95.67 252	89.83 268	93.23 273	96.99 205	85.94 254	92.66 262	97.32 197	96.11 218	96.44 240	95.22 238

FMVSNet5		94.57 245	92.77 247	96.67 247	97.88 260	98.72 158	97.54 245	98.70 202	88.64 269	95.11 266	86.90 265	81.77 267	93.27 255	97.92 152	98.07 130	97.50 226	97.34 201

SCA		94.53 246	91.95 252	97.55 221	98.58 238	97.86 214	98.49 190	99.68 30	95.11 196	99.07 83	95.87 233	87.24 247	96.53 213	89.77 258	87.08 258	92.96 264	90.69 263

MDTV_nov1_ep13		94.47 247	92.15 249	97.17 230	98.54 245	96.42 248	98.10 220	98.89 180	94.49 214	98.02 197	97.41 191	86.49 248	95.56 228	90.85 253	87.95 249	93.91 259	91.45 262

TESTMET0.1,1		94.44 248	93.71 241	95.30 258	97.84 261	96.16 251	96.31 263	95.32 257	89.98 265	94.08 269	97.01 203	86.43 250	92.20 264	96.76 210	95.31 224	96.05 245	94.31 245

ADS-MVSNet		94.41 249	92.13 250	97.07 233	98.86 222	96.60 245	98.38 200	98.47 219	96.13 174	98.02 197	96.98 206	87.50 246	95.87 225	89.89 257	87.58 256	92.79 266	90.27 265

tpm		93.89 250	91.21 254	97.03 236	98.36 254	96.07 255	97.53 248	99.65 39	92.24 247	98.64 129	97.23 196	74.67 281	94.64 241	92.68 249	90.73 243	93.37 261	94.82 242

PatchmatchNet		93.88 251	91.08 255	97.14 231	98.75 229	96.01 257	98.25 214	99.39 92	94.95 202	98.96 97	96.32 224	85.35 257	95.50 229	88.89 263	85.89 262	91.99 270	90.15 266
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		93.67 252	90.82 256	96.99 239	98.62 237	96.39 249	98.40 198	99.11 159	95.54 189	97.87 207	97.14 199	81.27 269	94.97 235	88.54 265	86.80 260	92.95 265	90.06 267

FE-MVSNET3		93.58 253	90.22 257	97.50 222	98.45 247	96.92 239	98.82 156	95.29 258	94.75 206	96.98 247	86.26 270	79.50 272	98.59 108	89.77 258	87.74 250	96.86 233	96.57 218

usedtu_blend_shiyan5		93.31 254	90.20 258	96.93 241	98.45 247	96.92 239	95.44 269	95.29 258	94.75 206	96.98 247	86.26 270	79.50 272	98.59 108	89.77 258	87.74 250	96.86 233	96.46 221

MVE	82.47 18	93.12 255	94.09 230	91.99 265	90.79 274	82.50 276	93.93 274	96.30 251	96.06 175	88.81 276	98.19 159	96.38 211	97.56 187	97.24 200	95.18 227	84.58 276	93.07 253
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CostFormer		92.75 256	89.49 260	96.55 248	98.78 228	95.83 262	97.55 244	98.59 211	91.83 255	97.34 233	96.31 225	78.53 276	94.50 242	86.14 267	84.92 263	92.54 267	92.84 255

tpmrst		92.45 257	89.48 261	95.92 254	98.43 252	95.03 265	97.14 254	97.92 236	94.16 226	97.56 219	97.86 177	81.63 268	93.56 254	85.89 268	82.86 267	90.91 274	88.95 270

dps		92.35 258	88.78 263	96.52 249	98.21 259	95.94 259	97.78 233	98.38 222	89.88 267	96.81 253	95.07 243	75.31 280	94.70 239	88.62 264	86.21 261	93.21 263	90.41 264

E-PMN		92.28 259	90.12 259	94.79 260	98.56 241	90.90 273	95.16 271	93.68 265	95.36 192	95.10 267	96.56 218	89.05 243	95.24 231	95.21 236	81.84 269	90.98 272	81.94 273

EMVS		91.84 260	89.39 262	94.70 261	98.44 251	90.84 274	95.27 270	93.53 266	95.18 193	95.26 265	95.62 238	87.59 245	94.77 238	94.87 241	80.72 270	90.95 273	80.88 274

tpm cat1		91.52 261	87.70 265	95.97 253	98.33 255	94.98 266	97.06 257	98.03 231	92.11 250	98.03 196	94.77 247	77.19 279	92.71 260	83.56 269	82.24 268	91.67 271	89.04 269

blend_shiyan4		91.30 262	88.16 264	94.96 259	89.60 275	96.63 244	93.72 275	93.90 263	82.52 273	96.98 247	86.26 270	79.50 272	98.59 108	88.21 266	87.51 257	96.99 230	96.46 221

0.4-1-1-0.1		90.20 263	87.09 266	93.83 262	91.98 271	94.48 268	96.12 266	88.26 267	84.35 270	97.04 246	88.99 260	79.83 270	94.68 240	83.11 270	84.34 264	94.87 253	94.55 243

0.3-1-1-0.015		89.53 264	86.18 267	93.43 263	91.67 273	93.80 270	95.70 267	87.54 268	83.38 271	96.98 247	87.42 262	79.50 272	94.21 248	81.99 272	83.67 265	94.46 256	93.50 252

0.4-1-1-0.2		89.46 265	86.17 268	93.30 264	91.74 272	93.59 272	95.48 268	87.42 269	83.04 272	96.95 251	88.20 261	79.80 271	93.99 251	82.16 271	83.38 266	94.21 258	93.03 254

test_method		77.69 266	85.40 269	68.69 266	42.66 279	55.39 279	82.17 278	52.05 272	92.83 245	84.52 277	94.88 246	95.41 219	65.37 272	92.49 251	79.32 271	85.36 275	87.50 271

GG-mvs-BLEND		65.66 267	92.62 248	34.20 269	1.45 284	93.75 271	85.40 277	1.64 278	91.37 259	17.21 281	87.25 263	94.78 225	3.25 280	95.64 230	93.80 239	96.27 242	91.74 261

VLMVS_CLIP		64.13 268	75.30 271	51.09 268	78.61 277	71.68 277	44.27 280	52.07 271	67.28 275	32.13 280	78.44 276	86.48 249	54.65 274	78.08 274	71.19 273	44.79 278	73.98 275

MVS_clip		56.91 269	76.74 270	33.76 270	54.66 278	53.09 280	31.90 282	17.78 274	73.21 274	9.18 284	81.68 275	85.59 256	58.85 273	80.87 273	77.88 272	30.20 279	84.88 272

VLMVS		34.07 270	45.54 272	20.69 271	38.22 280	31.90 281	12.64 283	15.62 275	42.63 276	9.57 283	44.68 277	57.03 284	34.96 276	43.33 275	43.85 274	13.11 280	55.36 277

MVS_baseline		22.56 271	36.20 273	6.64 272	10.19 281	9.26 282	1.84 286	0.00 279	36.68 277	0.00 286	39.69 278	45.33 285	27.64 277	29.68 276	28.88 275	0.18 283	63.87 276

testmvs		9.73 272	13.38 274	5.48 274	3.62 282	4.12 283	6.40 284	3.19 277	14.92 278	7.68 285	22.10 279	13.89 287	6.83 278	13.47 277	10.38 277	5.14 282	14.81 278

test123		9.37 273	12.26 275	6.00 273	3.32 283	4.06 284	6.39 285	3.41 276	13.20 279	10.48 282	16.43 280	16.22 286	6.76 279	11.37 278	10.40 276	5.62 281	14.10 279

uanet_test		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet-low-res		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

ACM-MVS					98.32 256	97.44 227	97.06 257		92.73 246	97.56 219	96.20 227	98.80 156	92.76 259			98.03 216	98.46 119

PatchmatchNet2					99.32 181	97.53 226	99.28 84
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												99.26 104	97.46 190	93.87 248	88.80 245	94.45 257	91.98 258
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										98.11 190	99.45 77
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							99.34 70	98.89 180		98.10 193						99.01 141

TPM-MVS					98.38 253	97.20 232	96.44 262			97.17 242	95.17 241	98.68 165	92.69 261			98.11 212	97.67 188
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										99.88 2

9.14												98.83 155

SR-MVS					99.62 112			99.47 79				99.40 86

Anonymous202405211			98.44 99		99.79 41	99.32 58	99.05 118	99.34 110	96.59 146		97.95 173	97.68 194	97.16 200	99.36 33	99.28 36	99.61 39	98.90 74

our_test_3					99.29 187	97.72 220	98.98 130

ambc			97.89 153		99.45 158	97.88 213	97.78 233		97.27 108	99.80 3	98.99 126	98.48 173	98.55 119	97.80 163	96.68 203	98.54 192	98.10 165

MTAPA										99.19 62		99.68 37

MTMP										99.20 60		99.54 64

Patchmatch-RL test							32.47 281

tmp_tt				65.28 267	82.24 276	71.50 278	70.81 279	23.21 273	96.14 172	81.70 279	85.98 273	92.44 237	49.84 275	95.81 225	94.36 236	83.86 277

XVS					99.77 51	99.07 106	99.46 49			98.95 99		99.37 91				99.33 81

X-MVStestdata					99.77 51	99.07 106	99.46 49			98.95 99		99.37 91				99.33 81

mPP-MVS					99.75 66							99.49 77

NP-MVS									93.07 242

Patchmtry						96.05 256	97.64 242	99.78 16		98.50 147

DeepMVS_CX						87.86 275	92.27 276	61.98 270	93.64 236	93.62 272	91.17 257	91.67 238	94.90 237	95.99 223		92.48 268	94.18 247

High-resolution multi-view benchmark