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.

pmmvs6		99.74 2	99.75 2	99.73 11	99.92 6	99.67 15	99.76 10	99.84 11	99.59 1	99.52 25	99.87 11	99.91 1	99.43 27	99.87 1	99.81 3	99.89 6	99.52 11

test_part1		99.72 3	99.79 1	99.64 12	99.95 2	99.88 1	99.71 16	99.83 12	99.58 2	99.48 29	99.79 21	99.78 10	98.98 72	99.86 2	99.85 1	99.88 8	99.82 1

LTVRE_ROB	98.82 1	99.76 1	99.75 2	99.77 7	99.87 18	99.71 10	99.77 8	99.76 20	99.52 3	99.80 3	99.79 21	99.91 1	99.56 13	99.83 4	99.75 5	99.86 10	99.75 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
Gipuma		99.22 27	98.86 39	99.64 12	99.70 68	99.24 56	99.17 86	99.63 42	99.52 3	99.89 1	96.54 176	99.14 92	99.93 1	99.42 32	99.15 41	99.52 47	99.04 52
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
TDRefinement		99.54 9	99.50 8	99.60 19	99.70 68	99.35 45	99.77 8	99.58 51	99.40 5	99.28 50	99.66 27	99.41 56	99.55 15	99.74 9	99.65 9	99.70 31	99.25 27

UniMVSNet_ETH3D		99.61 7	99.59 5	99.63 14	99.96 1	99.70 11	99.53 36	99.86 8	99.28 6	99.48 29	99.44 55	99.86 5	99.01 70	99.78 5	99.76 4	99.90 2	99.33 22

v7n		99.68 5	99.61 4	99.76 8	99.89 13	99.74 9	99.87 1	99.82 13	99.20 7	99.71 6	99.96 1	99.73 14	99.76 3	99.58 21	99.59 17	99.52 47	99.46 16

TransMVSNet (Re)		99.45 16	99.32 14	99.61 17	99.88 15	99.60 21	99.75 11	99.63 42	99.11 8	99.28 50	99.83 18	98.35 142	99.27 43	99.70 10	99.62 14	99.84 11	99.03 54

ACMH	97.81 6	99.44 17	99.33 12	99.56 23	99.81 34	99.42 37	99.73 15	99.58 51	99.02 9	99.10 75	99.41 59	99.69 20	99.60 10	99.45 29	99.26 37	99.55 43	99.05 51
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
COLMAP_ROB	98.29 2	99.37 19	99.25 18	99.51 31	99.74 59	99.12 74	99.56 33	99.39 88	98.96 10	99.17 62	99.44 55	99.63 35	99.58 11	99.48 27	99.27 35	99.60 40	98.81 80
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
pm-mvs1		99.47 14	99.38 10	99.57 22	99.82 31	99.49 30	99.63 25	99.65 38	98.88 11	99.31 43	99.85 14	99.02 107	99.23 47	99.60 19	99.58 18	99.80 16	99.22 35

SixPastTwentyTwo		99.70 4	99.59 5	99.82 2	99.93 4	99.80 3	99.86 2	99.87 6	98.87 12	99.79 5	99.85 14	99.33 67	99.74 5	99.85 3	99.82 2	99.74 25	99.63 6

CSCG		99.23 25	99.15 24	99.32 58	99.83 26	99.45 34	98.97 104	99.21 124	98.83 13	99.04 85	99.43 57	99.64 33	99.26 45	98.85 77	98.20 104	99.62 38	99.62 7

new-patchmatchnet		97.26 158	96.12 172	98.58 134	99.55 101	98.63 131	99.14 91	97.04 209	98.80 14	99.19 59	99.92 4	99.19 84	98.92 76	95.51 193	87.04 211	97.66 183	93.73 201

gg-mvs-nofinetune		96.77 171	96.52 165	97.06 190	99.66 76	97.82 179	97.54 198	99.86 8	98.69 15	98.61 122	99.94 2	89.62 196	88.37 219	97.55 149	96.67 168	98.30 168	95.35 189

ACMH+	97.53 7	99.29 23	99.20 23	99.40 44	99.81 34	99.22 62	99.59 30	99.50 69	98.64 16	98.29 150	99.21 74	99.69 20	99.57 12	99.53 24	99.33 31	99.66 35	98.81 80

anonymousdsp		99.64 6	99.55 7	99.74 10	99.87 18	99.56 26	99.82 3	99.73 23	98.54 17	99.71 6	99.92 4	99.84 7	99.61 9	99.70 10	99.63 10	99.69 34	99.64 4

WR-MVS		99.61 7	99.44 9	99.82 2	99.92 6	99.80 3	99.80 4	99.89 1	98.54 17	99.66 13	99.78 23	99.16 88	99.68 7	99.70 10	99.63 10	99.94 1	99.49 14

tfpnnormal		99.19 28	98.90 37	99.54 27	99.81 34	99.55 28	99.60 29	99.54 60	98.53 19	99.23 54	98.40 109	98.23 145	99.40 31	99.29 38	99.36 29	99.63 37	98.95 66

CHOSEN 1792x2688		98.31 112	98.02 113	98.66 128	99.55 101	98.57 137	99.38 54	99.25 119	98.42 20	98.48 137	99.58 40	99.85 6	98.31 114	95.75 188	95.71 183	96.96 190	98.27 129

DeepC-MVS	97.88 4	99.33 20	99.15 24	99.53 30	99.73 64	99.05 82	99.49 41	99.40 86	98.42 20	99.55 22	99.71 25	99.89 3	99.49 19	99.14 43	98.81 67	99.54 44	99.02 56
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
N_pmnet		96.68 174	95.70 182	97.84 173	99.42 133	98.00 171	99.35 61	98.21 189	98.40 22	98.13 160	99.42 58	99.30 70	97.44 148	94.00 208	88.79 206	94.47 205	91.96 207

FMVSNet1		98.90 55	99.10 26	98.67 126	99.54 105	99.48 31	99.22 80	99.66 36	98.39 23	97.50 185	99.66 27	99.04 106	96.58 166	99.05 55	99.03 49	99.52 47	99.08 48

test1111		98.75 78	98.14 104	99.46 32	99.86 23	99.63 20	99.47 43	99.68 29	98.34 24	98.76 112	99.66 27	90.92 195	99.23 47	99.77 6	99.71 6	99.75 24	98.95 66

DVP-MVS++		99.09 36	99.25 18	98.90 102	99.53 108	99.37 44	99.17 86	99.48 74	98.28 25	97.95 172	99.54 47	99.88 4	98.13 122	99.08 51	98.94 55	99.15 98	99.65 3

EU-MVSNet		98.68 83	98.94 34	98.37 146	99.14 167	98.74 123	99.64 22	98.20 191	98.21 26	99.17 62	99.66 27	99.18 85	99.08 65	99.11 46	98.86 60	95.00 203	98.83 77

MIMVSNet1		99.46 15	99.34 11	99.60 19	99.83 26	99.68 14	99.74 14	99.71 26	98.20 27	99.41 35	99.86 13	99.66 27	99.41 30	99.50 25	99.39 26	99.50 52	99.10 46

pmnet_mix02		96.61 175	95.32 185	98.11 162	99.41 135	97.68 185	99.05 97	97.59 203	98.16 28	99.05 81	99.48 51	99.11 97	98.32 113	92.36 212	87.67 208	95.26 202	92.80 205

Vis-MVSNet		99.25 24	99.32 14	99.17 69	99.65 79	99.55 28	99.63 25	99.33 104	98.16 28	99.29 46	99.65 31	99.77 11	97.56 144	99.44 31	99.14 42	99.58 41	99.51 13
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UGNet		98.52 100	99.00 30	97.96 168	99.58 94	99.26 54	99.27 73	99.40 86	98.07 30	98.28 151	98.76 97	99.71 18	92.24 211	98.94 69	98.85 62	99.00 118	99.43 18
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
casdiffmvs		98.84 67	98.75 45	98.94 100	99.75 53	99.21 63	99.33 65	99.04 146	98.04 31	97.46 188	99.72 24	99.72 16	98.60 94	98.30 111	98.37 98	99.48 54	97.92 147

3Dnovator+	97.85 5	98.61 91	98.14 104	99.15 72	99.62 86	98.37 150	99.10 95	99.51 67	98.04 31	98.98 88	96.07 186	98.75 125	98.55 100	98.51 93	98.40 95	99.17 94	98.82 78

test2506		96.12 187	93.35 200	99.35 55	99.83 26	99.58 23	99.37 55	99.67 33	98.02 33	98.44 141	97.51 144	60.03 228	99.10 62	99.77 6	99.70 7	99.72 27	98.86 75

ECVR-MVS		98.74 79	98.15 102	99.42 37	99.83 26	99.58 23	99.37 55	99.67 33	98.02 33	98.85 107	99.59 37	91.66 193	99.10 62	99.77 6	99.70 7	99.72 27	98.73 87

v1144		98.94 48	98.53 66	99.42 37	99.62 86	99.03 88	99.58 31	99.36 97	97.99 35	99.49 28	99.91 8	99.20 82	99.51 17	97.61 145	97.85 121	98.95 122	98.10 141

3Dnovator	98.16 3	98.65 86	98.35 86	99.00 91	99.59 92	98.70 126	98.90 116	99.36 97	97.97 36	99.09 76	96.55 175	99.09 101	97.97 131	98.70 85	98.65 82	99.12 99	98.81 80

v148		98.77 77	98.45 74	99.15 72	99.68 71	98.94 104	99.49 41	99.31 110	97.95 37	98.91 99	99.65 31	99.62 37	99.18 51	97.99 129	97.64 139	98.33 167	97.38 161

diffmvs		98.26 116	98.16 100	98.39 143	99.61 90	98.78 119	98.79 125	98.61 173	97.94 38	97.11 200	99.51 49	99.52 45	97.61 142	96.55 177	96.93 164	98.61 152	97.87 149

HyFIR lowres test		98.08 128	97.16 150	99.14 75	99.72 65	98.91 108	99.41 50	99.58 51	97.93 39	98.82 108	99.24 69	95.81 178	98.73 88	95.16 199	95.13 192	98.60 154	97.94 146

v2v482		98.85 66	98.40 82	99.38 50	99.65 79	98.98 94	99.55 34	99.39 88	97.92 40	99.35 38	99.85 14	99.14 92	99.39 33	97.50 151	97.78 124	98.98 119	97.60 155

v1921920		98.89 57	98.46 71	99.39 45	99.58 94	99.04 86	99.64 22	99.17 130	97.91 41	99.64 15	99.92 4	98.99 111	99.44 25	97.44 156	97.57 144	98.84 134	98.35 121

v1192		98.91 54	98.48 70	99.41 39	99.61 90	99.03 88	99.64 22	99.25 119	97.91 41	99.58 17	99.92 4	99.07 105	99.45 22	97.55 149	97.68 135	98.93 124	98.23 131

MDA-MVSNet-bldmvs		97.75 140	97.26 142	98.33 149	99.35 140	98.45 145	99.32 67	97.21 207	97.90 43	99.05 81	99.01 88	96.86 170	99.08 65	99.36 33	92.97 202	95.97 199	96.25 182

DTE-MVSNet		99.52 11	99.27 17	99.82 2	99.93 4	99.77 5	99.79 6	99.87 6	97.89 44	99.70 11	99.55 46	99.21 79	99.77 2	99.65 14	99.43 24	99.90 2	99.36 20

v144192		98.88 59	98.46 71	99.37 52	99.56 100	99.03 88	99.61 28	99.26 116	97.79 45	99.58 17	99.88 9	99.11 97	99.43 27	97.38 161	97.61 140	98.80 138	98.43 116

OPM-MVS		98.84 67	98.59 60	99.12 76	99.52 113	98.50 142	99.13 92	99.22 122	97.76 46	98.76 112	98.70 99	99.61 38	98.90 77	98.67 86	98.37 98	99.19 92	98.57 101
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
FC-MVSNet-test		99.32 21	99.33 12	99.31 59	99.87 18	99.65 18	99.63 25	99.75 22	97.76 46	97.29 197	99.87 11	99.63 35	99.52 16	99.66 13	99.63 10	99.77 20	99.12 41

HFP-MVS		98.97 45	98.70 51	99.29 61	99.67 73	98.98 94	99.13 92	99.53 63	97.76 46	98.90 100	98.07 125	99.50 51	99.14 60	98.64 88	98.78 71	99.37 67	99.18 38

DVP-MVS		99.09 36	99.07 27	99.12 76	99.55 101	99.40 39	99.36 58	99.44 85	97.75 49	98.23 154	99.23 71	99.80 8	98.97 73	99.08 51	98.96 53	99.19 92	99.25 27
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
IterMVS-LS		98.23 120	97.66 128	98.90 102	99.63 85	99.38 42	99.07 96	99.48 74	97.75 49	98.81 109	99.37 61	94.57 185	97.88 135	96.54 178	97.04 161	98.53 159	98.97 61
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
LS3D		98.79 75	98.52 67	99.12 76	99.64 82	99.09 76	99.24 77	99.46 79	97.75 49	98.93 98	97.47 146	98.23 145	97.98 130	99.36 33	99.30 32	99.46 55	98.42 117

UA-Net		99.30 22	99.22 22	99.39 45	99.94 3	99.66 17	98.91 112	99.86 8	97.74 52	98.74 116	99.00 89	99.60 40	99.17 54	99.50 25	99.39 26	99.70 31	99.64 4

ACMMPR		99.05 39	98.72 49	99.44 33	99.79 39	99.12 74	99.35 61	99.56 54	97.74 52	99.21 56	97.72 137	99.55 43	99.29 41	98.90 75	98.81 67	99.41 64	99.19 37

RPSCF		98.84 67	98.81 41	98.89 104	99.37 137	98.95 100	98.51 146	98.85 158	97.73 54	98.33 147	98.97 91	99.14 92	98.95 75	99.18 42	98.68 79	99.31 78	98.99 59

PMVS	92.51 17	98.66 85	98.86 39	98.43 141	99.26 153	98.98 94	98.60 140	98.59 175	97.73 54	99.45 33	99.38 60	98.54 136	95.24 184	99.62 18	99.61 15	99.42 61	98.17 138
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SD-MVS		98.73 80	98.54 65	98.95 97	99.14 167	98.76 121	98.46 150	99.14 135	97.71 56	98.56 126	98.06 127	99.61 38	98.85 81	98.56 90	97.74 130	99.54 44	99.32 23
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
TSAR-MVS + ACMM		98.64 88	98.58 62	98.72 120	99.17 165	98.63 131	98.69 130	99.10 142	97.69 57	98.30 149	99.12 79	99.38 61	98.70 89	98.45 94	97.51 147	98.35 166	99.25 27

thisisatest0515		99.16 30	98.94 34	99.41 39	99.75 53	99.43 36	99.36 58	99.63 42	97.68 58	99.35 38	99.31 63	98.90 113	99.09 64	98.95 67	99.20 38	99.27 84	99.11 42

v1240		98.86 63	98.41 81	99.38 50	99.59 92	99.05 82	99.65 21	99.14 135	97.68 58	99.66 13	99.93 3	98.72 126	99.45 22	97.38 161	97.72 133	98.79 139	98.35 121

ACMM	96.66 11	98.90 55	98.44 76	99.44 33	99.74 59	98.95 100	99.47 43	99.55 56	97.66 60	99.09 76	96.43 178	99.41 56	99.35 37	98.95 67	98.67 80	99.45 57	99.03 54
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MDTV_nov1_ep13_2view		97.12 163	96.19 171	98.22 157	99.13 169	98.05 168	99.24 77	99.47 76	97.61 61	99.15 69	99.59 37	99.01 108	98.40 109	94.87 202	90.14 205	93.91 206	94.04 200

PEN-MVS		99.54 9	99.30 16	99.83 1	99.92 6	99.76 6	99.80 4	99.88 3	97.60 62	99.71 6	99.59 37	99.52 45	99.75 4	99.64 16	99.51 20	99.90 2	99.46 16

v10		99.01 42	98.66 57	99.41 39	99.52 113	99.39 40	99.57 32	99.66 36	97.59 63	99.32 42	99.88 9	99.23 75	99.50 18	97.77 140	97.98 114	98.92 127	98.78 85

USDC		98.26 116	97.57 133	99.06 82	99.42 133	97.98 174	98.83 120	98.85 158	97.57 64	99.59 16	99.15 77	98.59 134	98.99 71	97.42 157	96.08 182	98.69 146	96.23 183

DCV-MVSNet		98.86 63	98.57 63	99.19 67	99.86 23	99.67 15	99.39 52	99.71 26	97.53 65	98.69 119	95.85 189	98.48 137	97.75 138	99.57 22	99.41 25	99.72 27	99.48 15

TSAR-MVS + MP.		99.02 41	98.95 31	99.11 79	99.23 158	98.79 118	99.51 38	98.73 165	97.50 66	98.56 126	99.03 86	99.59 41	99.16 56	99.29 38	99.17 40	99.50 52	99.24 31
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
v8		98.94 48	98.60 58	99.35 55	99.54 105	99.39 40	99.55 34	99.67 33	97.48 67	99.13 71	99.81 19	99.10 99	99.39 33	97.86 135	97.89 119	98.81 136	98.66 93

TinyColmap		98.27 115	97.62 132	99.03 88	99.29 149	97.79 181	98.92 110	98.95 154	97.48 67	99.52 25	98.65 102	97.86 155	98.90 77	98.34 106	97.27 156	98.64 150	95.97 185

gm-plane-assit		94.62 199	91.39 209	98.39 143	99.90 12	99.47 33	99.40 51	99.65 38	97.44 69	99.56 20	99.68 26	59.40 229	94.23 199	96.17 182	94.77 196	97.61 184	92.79 206

V42		98.81 74	98.49 69	99.18 68	99.52 113	98.92 106	99.50 40	99.29 112	97.43 70	98.97 89	99.81 19	99.00 110	99.30 40	97.93 131	98.01 112	98.51 162	98.34 125

DeepC-MVS_fast	97.38 8	98.65 86	98.34 87	99.02 90	99.33 141	98.29 152	98.99 102	98.71 167	97.40 71	99.31 43	98.20 119	99.40 59	98.54 102	98.33 108	98.18 105	99.23 90	98.58 99
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
zzz-MVS		98.94 48	98.57 63	99.37 52	99.77 44	99.15 71	99.24 77	99.55 56	97.38 72	99.16 65	96.64 172	99.69 20	99.15 58	99.09 49	98.92 58	99.37 67	99.11 42

EPP-MVSNet		98.61 91	98.19 99	99.11 79	99.86 23	99.60 21	99.44 49	99.53 63	97.37 73	96.85 201	98.69 100	93.75 186	99.18 51	99.22 41	99.35 30	99.82 14	99.32 23

PS-CasMVS		99.50 12	99.23 20	99.82 2	99.92 6	99.75 8	99.78 7	99.89 1	97.30 74	99.71 6	99.60 35	99.23 75	99.71 6	99.65 14	99.55 19	99.90 2	99.56 9

test20.03		98.84 67	98.74 46	98.95 97	99.77 44	99.33 48	99.21 82	99.46 79	97.29 75	98.88 104	99.65 31	99.10 99	97.07 158	99.11 46	98.76 73	99.32 77	97.98 145

TranMVSNet+NR-MVSNet		99.23 25	98.91 36	99.61 17	99.81 34	99.45 34	99.47 43	99.68 29	97.28 76	99.39 36	99.54 47	99.08 103	99.45 22	99.09 49	98.84 64	99.83 12	99.04 52

ambc			97.89 119		99.45 124	97.88 176	97.78 186		97.27 77	99.80 3	98.99 90	98.48 137	98.55 100	97.80 138	96.68 167	98.54 158	98.10 141

WR-MVS_H		99.48 13	99.23 20	99.76 8	99.91 10	99.76 6	99.75 11	99.88 3	97.27 77	99.58 17	99.56 42	99.24 74	99.56 13	99.60 19	99.60 16	99.88 8	99.58 8

testgi		98.18 126	98.44 76	97.89 170	99.78 42	99.23 59	98.78 127	99.21 124	97.26 79	97.41 190	97.39 149	99.36 66	92.85 208	98.82 80	98.66 81	99.31 78	98.35 121

OMC-MVS		98.35 110	98.10 108	98.64 132	98.85 184	97.99 172	98.56 142	98.21 189	97.26 79	98.87 106	98.54 106	99.27 73	98.43 107	98.34 106	97.66 136	98.92 127	97.65 154

APDe-MVS		99.15 31	98.95 31	99.39 45	99.77 44	99.28 53	99.52 37	99.54 60	97.22 81	99.06 79	99.20 75	99.64 33	99.05 68	99.14 43	99.02 52	99.39 65	99.17 39

pmmvs-eth3d		98.68 83	98.14 104	99.29 61	99.49 118	98.45 145	99.45 48	99.38 93	97.21 82	99.50 27	99.65 31	99.21 79	99.16 56	97.11 168	97.56 145	98.79 139	97.82 151

CVMVSNet		97.38 157	97.39 138	97.37 184	98.58 198	97.72 183	98.70 129	97.42 205	97.21 82	95.95 208	99.46 53	93.31 189	97.38 149	97.60 146	97.78 124	96.18 196	98.66 93

PMMVS2		96.29 182	97.05 153	95.40 211	98.32 209	96.16 202	98.18 172	97.46 204	97.20 84	84.51 225	99.60 35	98.68 129	96.37 171	98.59 89	97.38 151	97.58 185	91.76 208

MSDG		98.20 123	97.88 120	98.56 136	99.33 141	97.74 182	98.27 167	98.10 192	97.20 84	98.06 165	98.59 104	99.16 88	98.76 86	98.39 99	97.71 134	98.86 133	96.38 180

FPMVS		96.97 166	97.20 147	96.70 201	97.75 214	96.11 205	97.72 190	95.47 213	97.13 86	98.02 167	97.57 141	96.67 171	92.97 207	99.00 65	98.34 100	98.28 169	95.58 188

PVSNet_Blended_VisFu		98.98 44	98.79 42	99.21 64	99.76 50	99.34 46	99.35 61	99.35 100	97.12 87	99.46 32	99.56 42	98.89 114	98.08 126	99.05 55	98.58 86	99.27 84	98.98 60

DI_MVS_plusplus_trai		97.57 153	96.55 164	98.77 116	99.55 101	98.76 121	99.22 80	99.00 150	97.08 88	97.95 172	97.78 134	91.35 194	98.02 128	96.20 181	96.81 166	98.87 131	97.87 149

canonicalmvs		98.34 111	97.92 118	98.83 111	99.45 124	99.21 63	98.37 157	99.53 63	97.06 89	97.74 179	96.95 165	95.05 183	98.36 110	98.77 83	98.85 62	99.51 51	99.53 10

SED-MVS		98.94 48	98.95 31	98.91 101	99.43 129	99.38 42	99.12 94	99.46 79	97.05 90	98.43 142	99.23 71	99.79 9	97.99 129	99.05 55	98.94 55	99.05 113	99.23 32

MSP-MVS		98.72 81	98.60 58	98.87 106	99.67 73	99.33 48	99.15 89	99.26 116	96.99 91	97.90 175	98.19 120	99.74 13	98.29 116	97.69 143	98.96 53	98.96 120	99.27 26
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
Anonymous20231211		98.89 57	98.79 42	98.99 94	99.82 31	99.41 38	99.18 85	99.31 110	96.92 92	98.54 129	98.58 105	98.84 119	97.46 146	99.45 29	99.29 33	99.65 36	99.08 48

new_pmnet		96.59 176	96.40 168	96.81 198	98.24 210	95.46 214	97.71 192	94.75 216	96.92 92	96.80 203	99.23 71	97.81 156	96.69 163	96.58 176	95.16 191	96.69 192	93.64 202

ACMP	96.54 13	98.87 61	98.40 82	99.41 39	99.74 59	98.88 112	99.29 69	99.50 69	96.85 94	98.96 92	97.05 159	99.66 27	99.43 27	98.98 66	98.60 84	99.52 47	98.81 80
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMMP_NAP		98.94 48	98.72 49	99.21 64	99.67 73	99.08 77	99.26 74	99.39 88	96.84 95	98.88 104	98.22 118	99.68 23	98.82 82	99.06 54	98.90 59	99.25 87	99.25 27

PM-MVS		98.57 95	98.24 95	98.95 97	99.26 153	98.59 134	99.03 99	98.74 164	96.84 95	99.44 34	99.13 78	98.31 144	98.75 87	98.03 127	98.21 102	98.48 163	98.58 99

DELS-MVS		98.63 89	98.70 51	98.55 137	99.24 157	99.04 86	98.96 105	98.52 178	96.83 97	98.38 144	99.58 40	99.68 23	97.06 159	98.74 84	98.44 94	99.10 100	98.59 98
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
CP-MVSNet		99.39 18	99.04 29	99.80 6	99.91 10	99.70 11	99.75 11	99.88 3	96.82 98	99.68 12	99.32 62	98.86 116	99.68 7	99.57 22	99.47 21	99.89 6	99.52 11

QAPM		98.62 90	98.40 82	98.89 104	99.57 99	98.80 117	98.63 135	99.35 100	96.82 98	98.60 123	98.85 96	99.08 103	98.09 125	98.31 109	98.21 102	99.08 106	98.72 88

MVS_111021_HR		98.58 94	98.26 93	98.96 96	99.32 144	98.81 115	98.48 148	98.99 151	96.81 100	99.16 65	98.07 125	99.23 75	98.89 79	98.43 96	98.27 101	98.90 129	98.24 130

NCCC		97.84 138	96.96 156	98.87 106	99.39 136	98.27 155	98.46 150	99.02 148	96.78 101	98.73 118	91.12 212	98.91 112	98.57 98	97.83 137	97.49 148	99.04 115	98.33 126

DeepPCF-MVS	96.68 10	98.20 123	98.26 93	98.12 161	97.03 222	98.11 165	98.44 152	97.70 202	96.77 102	98.52 131	98.91 92	99.17 86	98.58 97	98.41 98	98.02 111	98.46 164	98.46 112

MVS_0304		98.57 95	98.36 85	98.82 113	99.72 65	98.94 104	98.92 110	99.14 135	96.76 103	99.33 41	98.30 113	99.73 14	96.74 162	98.05 126	97.79 123	99.08 106	98.97 61

FC-MVSNet-train		99.13 33	99.05 28	99.21 64	99.87 18	99.57 25	99.67 20	99.60 50	96.75 104	98.28 151	99.48 51	99.52 45	98.10 123	99.47 28	99.37 28	99.76 22	99.21 36

UniMVSNet (Re)		99.08 38	98.69 53	99.54 27	99.75 53	99.33 48	99.29 69	99.64 41	96.75 104	99.48 29	99.30 65	98.69 127	99.26 45	98.94 69	98.76 73	99.78 19	99.02 56

TSAR-MVS + COLMAP		97.62 149	97.31 140	97.98 166	98.47 204	97.39 189	98.29 164	98.25 188	96.68 106	97.54 184	98.87 93	98.04 151	97.08 157	96.78 172	96.26 175	98.26 170	97.12 171

TAPA-MVS	96.65 12	98.23 120	97.96 117	98.55 137	98.81 186	98.16 162	98.40 154	97.94 198	96.68 106	98.49 135	98.61 103	98.89 114	98.57 98	97.45 154	97.59 142	99.09 105	98.35 121
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
X-MVS		98.59 93	97.99 115	99.30 60	99.75 53	99.07 78	99.17 86	99.50 69	96.62 108	98.95 94	93.95 205	99.37 62	99.11 61	98.94 69	98.86 60	99.35 72	99.09 47

FMVSNet2		97.94 133	98.08 110	97.77 176	98.71 190	99.21 63	98.62 137	99.47 76	96.62 108	96.37 206	99.20 75	97.70 157	94.39 195	97.39 159	97.75 129	99.08 106	98.70 90

CP-MVS		98.86 63	98.43 79	99.36 54	99.68 71	98.97 98	99.19 83	99.46 79	96.60 110	99.20 57	97.11 158	99.51 49	99.15 58	98.92 73	98.82 65	99.45 57	99.08 48

Anonymous202405211			98.44 76		99.79 39	99.32 51	99.05 97	99.34 103	96.59 111		97.95 132	97.68 158	97.16 155	99.36 33	99.28 34	99.61 39	98.90 71

DU-MVS		99.04 40	98.59 60	99.56 23	99.74 59	99.23 59	99.29 69	99.63 42	96.58 112	99.55 22	99.05 83	98.68 129	99.36 35	99.03 62	98.60 84	99.77 20	98.97 61

NR-MVSNet		99.10 35	98.68 56	99.58 21	99.89 13	99.23 59	99.35 61	99.63 42	96.58 112	99.36 37	99.05 83	98.67 131	99.46 20	99.63 17	98.73 77	99.80 16	98.88 74

pmmvs4		97.87 137	97.02 154	98.86 109	99.20 159	97.68 185	98.89 117	99.03 147	96.57 114	99.12 73	99.03 86	97.26 165	98.42 108	95.16 199	96.34 174	98.53 159	97.10 172

MVS_111021_LR		98.39 108	98.11 107	98.71 122	99.08 173	98.54 140	98.23 170	98.56 177	96.57 114	99.13 71	98.41 108	98.86 116	98.65 92	98.23 117	97.87 120	98.65 149	98.28 127

GeoE		98.88 59	98.43 79	99.41 39	99.83 26	99.24 56	99.51 38	99.82 13	96.55 116	99.22 55	98.76 97	99.22 78	98.96 74	98.55 91	98.15 106	99.10 100	98.56 104

UniMVSNet_NR-MVSNet		98.97 45	98.46 71	99.56 23	99.76 50	99.34 46	99.29 69	99.61 48	96.55 116	99.55 22	99.05 83	97.96 153	99.36 35	98.84 78	98.50 92	99.81 15	98.97 61

EG-PatchMatch MVS		99.01 42	98.77 44	99.28 63	99.64 82	98.90 111	98.81 124	99.27 115	96.55 116	99.71 6	99.31 63	99.66 27	99.17 54	99.28 40	99.11 44	99.10 100	98.57 101

Baseline_NR-MVSNet		99.18 29	98.87 38	99.54 27	99.74 59	99.56 26	99.36 58	99.62 47	96.53 119	99.29 46	99.85 14	98.64 133	99.40 31	99.03 62	99.63 10	99.83 12	98.86 75

baseline		97.50 155	97.51 135	97.50 181	99.18 163	97.38 190	98.00 177	98.00 195	96.52 120	97.49 186	99.28 66	99.43 55	95.31 183	95.27 196	96.22 176	96.99 189	98.47 110

MSLP-MVS++		97.99 130	97.64 131	98.40 142	98.91 182	98.47 144	97.12 209	98.78 162	96.49 121	98.48 137	93.57 207	99.12 95	98.51 104	98.31 109	98.58 86	98.58 156	98.95 66

CNLPA		97.75 140	97.26 142	98.32 151	98.58 198	97.86 177	97.80 185	98.09 193	96.49 121	98.49 135	96.15 183	98.08 148	98.35 111	98.00 128	97.03 162	98.61 152	97.21 169

ACMMP		98.82 73	98.33 88	99.39 45	99.77 44	99.14 72	99.37 55	99.54 60	96.47 123	99.03 87	96.26 182	99.52 45	99.28 42	98.92 73	98.80 70	99.37 67	99.16 40
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
IterMVS-SCA-FT		97.63 148	96.86 158	98.52 139	99.48 120	98.71 125	98.84 119	98.91 155	96.44 124	99.16 65	99.56 42	95.54 180	97.95 132	95.68 191	95.07 195	96.76 191	97.03 175

xxxxxxxxxxxxxcwj		98.28 113	98.23 96	98.35 147	99.43 129	98.42 148	97.05 211	99.09 143	96.42 125	98.13 160	97.73 135	99.65 31	97.22 152	98.36 102	98.38 96	99.16 96	98.62 95

SF-MVS		98.25 118	98.16 100	98.35 147	99.43 129	98.42 148	97.05 211	99.09 143	96.42 125	98.13 160	97.73 135	99.20 82	97.22 152	98.36 102	98.38 96	99.16 96	98.62 95

IterMVS		97.40 156	96.67 159	98.25 154	99.45 124	98.66 129	98.87 118	98.73 165	96.40 127	98.94 97	99.56 42	95.26 182	97.58 143	95.38 194	94.70 197	95.90 200	96.72 178
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Anonymous20231206		98.50 101	98.03 112	99.05 85	99.50 116	99.01 91	99.15 89	99.26 116	96.38 128	99.12 73	99.50 50	99.12 95	98.60 94	97.68 144	97.24 158	98.66 147	97.30 165

PLC	95.63 15	97.73 143	97.01 155	98.57 135	99.10 170	97.80 180	97.72 190	98.77 163	96.34 129	98.38 144	93.46 208	98.06 149	98.66 91	97.90 133	97.65 138	98.77 141	97.90 148
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SMA-MVS		98.87 61	98.73 48	99.04 87	99.72 65	99.05 82	98.64 134	99.17 130	96.31 130	98.80 110	99.07 81	99.70 19	98.67 90	98.93 72	98.82 65	99.23 90	99.23 32
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
CPTT-MVS		98.28 113	97.51 135	99.16 71	99.54 105	98.78 119	98.96 105	99.36 97	96.30 131	98.89 103	93.10 209	99.30 70	99.20 49	98.35 105	97.96 115	99.03 116	98.82 78

HPM-MVS++		98.56 98	98.08 110	99.11 79	99.53 108	98.61 133	99.02 101	99.32 108	96.29 132	99.06 79	97.23 153	99.50 51	98.77 85	98.15 122	97.90 117	98.96 120	98.90 71

CNVR-MVS		98.22 122	97.76 123	98.76 117	99.33 141	98.26 156	98.48 148	98.88 157	96.22 133	98.47 139	95.79 190	99.33 67	98.35 111	98.37 101	97.99 113	99.03 116	98.38 119

Vis-MVSNet (Re-imp)		98.46 105	98.23 96	98.73 119	99.81 34	99.29 52	98.79 125	99.50 69	96.20 134	96.03 207	98.29 114	96.98 168	98.54 102	99.11 46	99.08 45	99.70 31	98.62 95

SteuartSystems-ACMMP		98.94 48	98.52 67	99.43 36	99.79 39	99.13 73	99.33 65	99.55 56	96.17 135	99.04 85	97.53 143	99.65 31	99.46 20	99.04 60	98.76 73	99.44 59	99.35 21
Skip Steuart: Steuart Systems R&D Blog.
CANet		98.47 103	98.30 90	98.67 126	99.65 79	98.87 113	98.82 123	99.01 149	96.14 136	99.29 46	98.86 94	99.01 108	96.54 167	98.36 102	98.08 109	98.72 143	98.80 84

tmp_tt				65.28 218	82.24 224	71.50 225	70.81 226	23.21 222	96.14 136	81.70 226	85.98 221	92.44 191	49.84 221	95.81 187	94.36 198	83.86 224

ADS-MVSNet		94.41 205	92.13 206	97.07 189	98.86 183	96.60 196	98.38 156	98.47 182	96.13 138	98.02 167	96.98 163	87.50 200	95.87 178	89.89 214	87.58 209	92.79 213	90.27 213

MVE	82.47 18	93.12 209	94.09 189	91.99 216	90.79 223	82.50 224	93.93 222	96.30 211	96.06 139	88.81 223	98.19 120	96.38 173	97.56 144	97.24 166	95.18 190	84.58 223	93.07 203
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CLD-MVS		98.48 102	98.15 102	98.86 109	99.53 108	98.35 151	98.55 143	97.83 200	96.02 140	98.97 89	99.08 80	99.75 12	99.03 69	98.10 125	97.33 154	99.28 82	98.44 115
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
TSAR-MVS + GP.		98.54 99	98.29 92	98.82 113	99.28 151	98.59 134	97.73 189	99.24 121	95.93 141	98.59 124	99.07 81	99.17 86	98.86 80	98.44 95	98.10 108	99.26 86	98.72 88

MCST-MVS		98.25 118	97.57 133	99.06 82	99.53 108	98.24 158	98.63 135	99.17 130	95.88 142	98.58 125	96.11 184	99.09 101	99.18 51	97.58 148	97.31 155	99.25 87	98.75 86

DPE-MVS		98.84 67	98.69 53	99.00 91	99.05 176	99.26 54	99.19 83	99.35 100	95.85 143	98.74 116	99.27 67	99.66 27	98.30 115	98.90 75	98.93 57	99.37 67	99.00 58
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
pmmvs5		98.37 109	97.81 121	99.03 88	99.46 122	98.97 98	99.03 99	98.96 153	95.85 143	99.05 81	99.45 54	98.66 132	98.79 84	96.02 185	97.52 146	98.87 131	98.21 134

MS-PatchMatch		97.60 150	97.22 146	98.04 165	98.67 194	97.18 193	97.91 181	98.28 187	95.82 145	98.34 146	97.66 138	98.38 141	97.77 137	97.10 169	97.25 157	97.27 188	97.18 170

MP-MVS		98.78 76	98.30 90	99.34 57	99.75 53	98.95 100	99.26 74	99.46 79	95.78 146	99.17 62	96.98 163	99.72 16	99.06 67	98.84 78	98.74 76	99.33 74	99.11 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CS-MVS-test		99.15 31	98.74 46	99.62 15	99.88 15	99.86 2	99.68 18	99.78 16	95.77 147	99.29 46	98.28 115	99.47 54	99.35 37	99.30 36	99.27 35	99.76 22	99.23 32

CDS-MVSNet		97.75 140	97.68 127	97.83 174	99.08 173	98.20 161	98.68 131	98.61 173	95.63 148	97.80 177	99.24 69	96.93 169	94.09 200	97.96 130	97.82 122	98.71 144	97.99 143
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IS_MVSNet		98.20 123	98.00 114	98.44 140	99.82 31	99.48 31	99.25 76	99.56 54	95.58 149	93.93 219	97.56 142	96.52 172	98.27 117	99.08 51	99.20 38	99.80 16	98.56 104

EPMVS		93.67 208	90.82 212	96.99 195	98.62 197	96.39 200	98.40 154	99.11 140	95.54 150	97.87 176	97.14 156	81.27 221	94.97 188	88.54 218	86.80 212	92.95 212	90.06 215

CS-MVS		99.12 34	98.69 53	99.62 15	99.87 18	99.64 19	99.70 17	99.61 48	95.51 151	99.56 20	98.53 107	99.37 62	99.27 43	99.04 60	99.47 21	99.71 30	99.30 25

DPM-MVS		96.73 172	95.70 182	97.95 169	98.93 181	97.26 191	97.39 203	98.44 183	95.47 152	97.62 182	90.71 213	98.47 139	97.03 160	95.02 201	95.27 189	98.26 170	97.67 153

LGP-MVS_train		98.84 67	98.33 88	99.44 33	99.78 42	98.98 94	99.39 52	99.55 56	95.41 153	98.90 100	97.51 144	99.68 23	99.44 25	99.03 62	98.81 67	99.57 42	98.91 70

E-PMN		92.28 213	90.12 213	94.79 214	98.56 201	90.90 221	95.16 219	93.68 218	95.36 154	95.10 215	96.56 174	89.05 197	95.24 184	95.21 198	81.84 218	90.98 219	81.94 220

EMVS		91.84 214	89.39 216	94.70 215	98.44 205	90.84 222	95.27 218	93.53 219	95.18 155	95.26 213	95.62 193	87.59 199	94.77 191	94.87 202	80.72 219	90.95 220	80.88 221

GA-MVS		96.84 169	95.86 179	97.98 166	99.16 166	98.29 152	97.91 181	98.64 172	95.14 156	97.71 180	98.04 129	88.90 198	96.50 169	96.41 180	96.61 171	97.97 180	97.60 155

SCA		94.53 202	91.95 208	97.55 180	98.58 198	97.86 177	98.49 147	99.68 29	95.11 157	99.07 78	95.87 188	87.24 201	96.53 168	89.77 215	87.08 210	92.96 211	90.69 211

TAMVS		96.95 167	96.94 157	96.97 196	99.07 175	97.67 187	97.98 179	97.12 208	95.04 158	95.41 212	99.27 67	95.57 179	94.09 200	97.32 163	97.11 160	98.16 175	96.59 179

MVS_Test		97.69 144	97.15 151	98.33 149	99.27 152	98.43 147	98.25 168	99.29 112	95.00 159	97.39 192	98.86 94	98.00 152	97.14 156	95.38 194	96.22 176	98.62 151	98.15 140

PHI-MVS		98.57 95	98.20 98	99.00 91	99.48 120	98.91 108	98.68 131	99.17 130	94.97 160	99.27 52	98.33 111	99.33 67	98.05 127	98.82 80	98.62 83	99.34 73	98.38 119

baseline1		96.72 173	95.40 184	98.26 152	99.53 108	98.81 115	98.32 161	98.80 161	94.96 161	96.78 204	96.50 177	84.87 212	96.68 165	97.42 157	97.91 116	99.46 55	97.33 164

PatchmatchNet		93.88 207	91.08 211	97.14 188	98.75 189	96.01 208	98.25 168	99.39 88	94.95 162	98.96 92	96.32 180	85.35 209	95.50 182	88.89 216	85.89 214	91.99 217	90.15 214
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MIMVSNet		97.24 159	97.15 151	97.36 185	99.03 177	98.52 141	98.55 143	99.73 23	94.94 163	94.94 216	97.98 130	97.37 163	93.66 203	97.60 146	97.34 153	98.23 173	96.29 181

PGM-MVS		98.69 82	98.09 109	99.39 45	99.76 50	99.07 78	99.30 68	99.51 67	94.76 164	99.18 61	96.70 170	99.51 49	99.20 49	98.79 82	98.71 78	99.39 65	99.11 42

Effi-MVS+		98.11 127	97.29 141	99.06 82	99.62 86	98.55 138	98.16 173	99.80 15	94.64 165	99.15 69	96.59 173	97.43 161	98.44 106	97.46 153	97.90 117	99.17 94	98.45 114

HQP-MVS		97.58 152	96.65 162	98.66 128	99.30 146	97.99 172	97.88 184	98.65 170	94.58 166	98.66 120	94.65 202	99.15 91	98.59 96	96.10 183	95.59 184	98.90 129	98.50 109

thisisatest0530		97.20 161	95.95 176	98.66 128	99.46 122	98.84 114	98.29 164	99.20 126	94.51 167	98.25 153	97.42 147	85.03 210	97.68 140	98.43 96	98.56 90	99.08 106	98.89 73

Effi-MVS+-dtu		97.78 139	97.37 139	98.26 152	99.25 155	98.50 142	97.89 183	99.19 129	94.51 167	98.16 158	95.93 187	98.80 121	95.97 177	98.27 116	97.38 151	99.10 100	98.23 131

Fast-Effi-MVS+		98.42 106	97.79 122	99.15 72	99.69 70	98.66 129	98.94 107	99.68 29	94.49 169	99.05 81	98.06 127	98.86 116	98.48 105	98.18 119	97.78 124	99.05 113	98.54 107

MDTV_nov1_ep13		94.47 203	92.15 205	97.17 187	98.54 203	96.42 199	98.10 174	98.89 156	94.49 169	98.02 167	97.41 148	86.49 202	95.56 181	90.85 213	87.95 207	93.91 206	91.45 210

ET-MVSNet_ETH3D		95.72 191	93.85 195	97.89 170	97.30 220	98.09 166	98.19 171	98.40 184	94.46 171	98.01 170	96.71 169	77.85 224	96.76 161	96.08 184	96.39 173	98.70 145	97.36 162

AdaColmap		97.57 153	96.57 163	98.74 118	99.25 155	98.01 170	98.36 159	98.98 152	94.44 172	98.47 139	92.44 210	97.91 154	98.62 93	98.19 118	97.74 130	98.73 142	97.28 166

train_agg		97.99 130	97.26 142	98.83 111	99.43 129	98.22 160	98.91 112	99.07 145	94.43 173	97.96 171	96.42 179	99.30 70	98.81 83	97.39 159	96.62 170	98.82 135	98.47 110

PatchMatch-RL		97.24 159	96.45 167	98.17 158	98.70 193	97.57 188	97.31 204	98.48 181	94.42 174	98.39 143	95.74 191	96.35 174	97.88 135	97.75 141	97.48 149	98.24 172	95.87 186

CANet_DTU		97.65 147	97.50 137	97.82 175	99.19 162	98.08 167	98.41 153	98.67 169	94.40 175	99.16 65	98.32 112	98.69 127	93.96 202	97.87 134	97.61 140	97.51 186	97.56 157

APD-MVS		98.47 103	97.97 116	99.05 85	99.64 82	98.91 108	98.94 107	99.45 84	94.40 175	98.77 111	97.26 152	99.41 56	98.21 119	98.67 86	98.57 89	99.31 78	98.57 101
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
tttt0517		97.18 162	95.92 177	98.65 131	99.49 118	98.92 106	98.29 164	99.20 126	94.37 177	98.17 156	97.37 150	84.72 213	97.68 140	98.55 91	98.56 90	99.10 100	98.95 66

thres600view7		96.35 179	94.27 187	98.79 115	99.66 76	99.18 68	98.94 107	99.38 93	94.37 177	97.21 199	87.19 215	84.10 214	98.10 123	98.16 120	99.47 21	99.42 61	97.43 159

PVSNet_BlendedMVS		97.93 134	97.66 128	98.25 154	99.30 146	98.67 127	98.31 162	97.95 196	94.30 179	98.75 114	97.63 139	98.76 123	96.30 174	98.29 112	97.78 124	98.93 124	98.18 136

PVSNet_Blended		97.93 134	97.66 128	98.25 154	99.30 146	98.67 127	98.31 162	97.95 196	94.30 179	98.75 114	97.63 139	98.76 123	96.30 174	98.29 112	97.78 124	98.93 124	98.18 136

tpmrst		92.45 211	89.48 215	95.92 209	98.43 206	95.03 216	97.14 207	97.92 199	94.16 181	97.56 183	97.86 133	81.63 220	93.56 204	85.89 220	82.86 216	90.91 221	88.95 218

DROMVSNet		98.96 47	98.45 74	99.56 23	99.88 15	99.70 11	99.68 18	99.78 16	94.15 182	98.97 89	98.26 117	99.21 79	99.35 37	99.30 36	99.14 42	99.73 26	99.40 19

GBi-Net		97.69 144	97.75 125	97.62 177	98.71 190	99.21 63	98.62 137	99.33 104	94.09 183	95.60 209	98.17 122	95.97 175	94.39 195	99.05 55	99.03 49	99.08 106	98.70 90

test1		97.69 144	97.75 125	97.62 177	98.71 190	99.21 63	98.62 137	99.33 104	94.09 183	95.60 209	98.17 122	95.97 175	94.39 195	99.05 55	99.03 49	99.08 106	98.70 90

FMVSNet3		96.85 168	96.67 159	97.06 190	97.56 217	99.01 91	97.99 178	99.33 104	94.09 183	95.60 209	98.17 122	95.97 175	93.26 206	94.76 204	96.22 176	98.59 155	98.46 112

thres400		96.22 184	94.08 190	98.72 120	99.58 94	99.05 82	98.83 120	99.22 122	94.01 186	97.40 191	86.34 219	84.91 211	97.93 133	97.85 136	99.08 45	99.37 67	97.28 166

OpenMVS	97.26 9	97.88 136	97.17 149	98.70 123	99.50 116	98.55 138	98.34 160	99.11 140	93.92 187	98.90 100	95.04 198	98.23 145	97.38 149	98.11 124	98.12 107	98.95 122	98.23 131

CHOSEN 280x420		96.80 170	96.30 169	97.39 182	99.09 171	96.52 197	98.76 128	99.29 112	93.88 188	97.65 181	98.34 110	93.66 187	96.29 176	98.28 114	97.73 132	93.27 209	95.70 187

CDPH-MVS		97.99 130	97.23 145	98.87 106	99.58 94	98.29 152	98.83 120	99.20 126	93.76 189	98.11 163	96.11 184	99.16 88	98.23 118	97.80 138	97.22 159	99.29 81	98.28 127

EPNet		96.44 178	96.08 173	96.86 197	99.32 144	97.15 194	97.69 193	99.32 108	93.67 190	98.11 163	95.64 192	93.44 188	89.07 217	96.86 171	96.83 165	97.67 182	98.97 61
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepMVS_CX						87.86 223	92.27 223	61.98 220	93.64 191	93.62 220	91.17 211	91.67 192	94.90 190	95.99 186		92.48 215	94.18 199

thres200		96.23 183	94.13 188	98.69 124	99.44 127	99.18 68	98.58 141	99.38 93	93.52 192	97.35 193	86.33 220	85.83 208	97.93 133	98.16 120	98.78 71	99.42 61	97.10 172

Fast-Effi-MVS+-dtu		96.99 165	96.46 166	97.61 179	98.98 179	97.89 175	97.54 198	99.76 20	93.43 193	96.55 205	94.93 199	98.06 149	94.32 198	96.93 170	96.50 172	98.53 159	97.47 158

pmmvs3		96.30 181	95.87 178	96.80 199	97.66 216	96.48 198	97.93 180	93.80 217	93.40 194	98.54 129	98.27 116	97.50 160	97.37 151	97.49 152	93.11 201	95.52 201	94.85 194

ETV-MVS		98.41 107	97.76 123	99.17 69	99.58 94	99.01 91	98.91 112	99.50 69	93.33 195	99.31 43	96.82 167	98.42 140	98.17 121	99.13 45	99.08 45	99.54 44	98.56 104

abl_6				98.38 145	99.03 177	98.04 169	98.08 176	98.65 170	93.23 196	98.56 126	94.58 203	98.57 135	97.17 154			98.81 136	97.42 160

PMMVS		96.47 177	95.81 180	97.23 186	97.38 219	95.96 209	97.31 204	96.91 210	93.21 197	97.93 174	97.14 156	97.64 159	95.70 179	95.24 197	96.18 179	98.17 174	95.33 190

NP-MVS									93.07 198

EPNet_dtu		96.31 180	95.96 175	96.72 200	99.18 163	95.39 215	97.03 213	99.13 139	93.02 199	99.35 38	97.23 153	97.07 167	90.70 216	95.74 189	95.08 193	94.94 204	98.16 139
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PCF-MVS	95.58 16	97.60 150	96.67 159	98.69 124	99.44 127	98.23 159	98.37 157	98.81 160	93.01 200	98.22 155	97.97 131	99.59 41	98.20 120	95.72 190	95.08 193	99.08 106	97.09 174
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_method		77.69 216	85.40 219	68.69 217	42.66 225	55.39 226	82.17 225	52.05 221	92.83 201	84.52 224	94.88 200	95.41 181	65.37 220	92.49 211	79.32 220	85.36 222	87.50 219

test0.0.03 1		95.81 189	95.77 181	95.85 210	99.20 159	98.15 164	97.49 202	98.50 179	92.24 202	92.74 222	96.82 167	92.70 190	88.60 218	97.31 165	97.01 163	98.57 157	96.19 184

tpm		93.89 206	91.21 210	97.03 192	98.36 207	96.07 206	97.53 201	99.65 38	92.24 202	98.64 121	97.23 153	74.67 227	94.64 193	92.68 209	90.73 204	93.37 208	94.82 195

MVSTER		95.38 194	93.99 194	97.01 194	98.83 185	98.95 100	96.62 214	99.14 135	92.17 204	97.44 189	97.29 151	77.88 223	91.63 215	97.45 154	96.18 179	98.41 165	97.99 143

tpm cat1		91.52 215	87.70 218	95.97 208	98.33 208	94.98 217	97.06 210	98.03 194	92.11 205	98.03 166	94.77 201	77.19 225	92.71 209	83.56 221	82.24 217	91.67 218	89.04 217

thres100view900		95.74 190	93.66 199	98.17 158	99.37 137	98.59 134	98.10 174	98.33 186	92.02 206	97.30 195	86.53 217	86.34 205	96.69 163	96.77 173	98.47 93	99.24 89	96.89 176

tfpn200view9		96.17 185	94.08 190	98.60 133	99.37 137	99.18 68	98.68 131	99.39 88	92.02 206	97.30 195	86.53 217	86.34 205	97.45 147	98.15 122	99.08 45	99.43 60	97.28 166

PatchT		95.49 193	93.29 201	98.06 164	98.65 195	96.20 201	98.91 112	99.73 23	92.00 208	98.50 132	96.67 171	83.25 216	96.34 172	94.40 205	95.50 185	96.21 195	95.04 192

IB-MVS	95.85 14	95.87 188	94.88 186	97.02 193	99.09 171	98.25 157	97.16 206	97.38 206	91.97 209	97.77 178	83.61 222	97.29 164	92.03 214	97.16 167	97.66 136	98.66 147	98.20 135
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
CostFormer		92.75 210	89.49 214	96.55 203	98.78 188	95.83 213	97.55 197	98.59 175	91.83 210	97.34 194	96.31 181	78.53 222	94.50 194	86.14 219	84.92 215	92.54 214	92.84 204

CMPMVS	74.71 19	96.17 185	96.06 174	96.30 205	97.41 218	94.52 218	94.83 220	95.46 214	91.57 211	97.26 198	94.45 204	98.33 143	94.98 186	98.28 114	97.59 142	97.86 181	97.68 152
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EIA-MVS		98.03 129	97.20 147	98.99 94	99.66 76	99.24 56	98.53 145	99.52 66	91.56 212	99.25 53	95.34 194	98.78 122	97.72 139	98.38 100	98.58 86	99.28 82	98.54 107

baseline2		95.58 192	94.04 192	97.38 183	98.80 187	98.16 162	97.14 207	97.80 201	91.45 213	97.49 186	95.22 195	83.63 215	94.98 186	96.42 179	96.66 169	98.06 176	96.76 177

GG-mvs-BLEND		65.66 217	92.62 204	34.20 219	1.45 228	93.75 220	85.40 224	1.64 225	91.37 214	17.21 227	87.25 214	94.78 184	3.25 224	95.64 192	93.80 200	96.27 194	91.74 209

CR-MVSNet		95.38 194	93.01 202	98.16 160	98.63 196	95.85 211	97.64 195	99.78 16	91.27 215	98.50 132	96.84 166	82.16 217	96.34 172	94.40 205	95.50 185	98.05 178	95.04 192

RPMNet		94.72 198	92.01 207	97.88 172	98.56 201	95.85 211	97.78 186	99.70 28	91.27 215	98.33 147	93.69 206	81.88 218	94.91 189	92.60 210	94.34 199	98.01 179	94.46 196

MVS-HIRNet		94.86 196	93.83 196	96.07 206	97.07 221	94.00 219	94.31 221	99.17 130	91.23 217	98.17 156	98.69 100	97.43 161	95.66 180	94.05 207	91.92 203	92.04 216	89.46 216

MAR-MVS		97.12 163	96.28 170	98.11 162	98.94 180	97.22 192	97.65 194	99.38 93	90.93 218	98.15 159	95.17 196	97.13 166	96.48 170	97.71 142	97.40 150	98.06 176	98.40 118
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
test-LLR		94.79 197	93.71 197	96.06 207	99.20 159	96.16 202	96.31 215	98.50 179	89.98 219	94.08 217	97.01 160	86.43 203	92.20 212	96.76 174	95.31 187	96.05 197	94.31 197

TESTMET0.1,1		94.44 204	93.71 197	95.30 213	97.84 213	96.16 202	96.31 215	95.32 215	89.98 219	94.08 217	97.01 160	86.43 203	92.20 212	96.76 174	95.31 187	96.05 197	94.31 197

dps		92.35 212	88.78 217	96.52 204	98.21 211	95.94 210	97.78 186	98.38 185	89.88 221	96.81 202	95.07 197	75.31 226	94.70 192	88.62 217	86.21 213	93.21 210	90.41 212

test-mter		94.62 199	94.02 193	95.32 212	97.72 215	96.75 195	96.23 217	95.67 212	89.83 222	93.23 221	96.99 162	85.94 207	92.66 210	97.32 163	96.11 181	96.44 193	95.22 191

FMVSNet5		94.57 201	92.77 203	96.67 202	97.88 212	98.72 124	97.54 198	98.70 168	88.64 223	95.11 214	86.90 216	81.77 219	93.27 205	97.92 132	98.07 110	97.50 187	97.34 163

testmvs		9.73 218	13.38 220	5.48 221	3.62 226	4.12 227	6.40 228	3.19 224	14.92 224	7.68 229	22.10 223	13.89 231	6.83 222	13.47 222	10.38 222	5.14 226	14.81 222

test123		9.37 219	12.26 221	6.00 220	3.32 227	4.06 228	6.39 229	3.41 223	13.20 225	10.48 228	16.43 224	16.22 230	6.76 223	11.37 223	10.40 221	5.62 225	14.10 223

uanet_test		0.00 220	0.00 222	0.00 222	0.00 229	0.00 229	0.00 230	0.00 226	0.00 226	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet-low-res		0.00 220	0.00 222	0.00 222	0.00 229	0.00 229	0.00 230	0.00 226	0.00 226	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet		0.00 220	0.00 222	0.00 222	0.00 229	0.00 229	0.00 230	0.00 226	0.00 226	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

RE-MVS-def										99.88 2

9.14												98.83 120

SR-MVS					99.62 86			99.47 76				99.40 59

our_test_3					99.29 149	97.72 183	98.98 103

MTAPA										99.19 59		99.68 23

MTMP										99.20 57		99.54 44

Patchmatch-RL test							32.47 227

XVS					99.77 44	99.07 78	99.46 46			98.95 94		99.37 62				99.33 74

X-MVStestdata					99.77 44	99.07 78	99.46 46			98.95 94		99.37 62				99.33 74

mPP-MVS					99.75 53							99.49 53

Patchmtry						96.05 207	97.64 195	99.78 16		98.50 132

High-resolution multi-view benchmark