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 1	99.73 11	99.92 5	99.67 12	99.76 10	99.84 11	99.59 1	99.52 23	99.87 11	99.91 1	99.43 27	99.87 1	99.81 2	99.89 6	99.52 9

LTVRE_ROB	98.82 1	99.76 1	99.75 1	99.77 7	99.87 15	99.71 8	99.77 8	99.76 16	99.52 2	99.80 2	99.79 21	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
Gipuma		99.22 26	98.86 36	99.64 12	99.70 61	99.24 48	99.17 79	99.63 35	99.52 2	99.89 1	96.54 163	99.14 83	99.93 1	99.42 28	99.15 36	99.52 41	99.04 46
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
TDRefinement		99.54 8	99.50 7	99.60 16	99.70 61	99.35 37	99.77 8	99.58 43	99.40 4	99.28 45	99.66 26	99.41 51	99.55 15	99.74 5	99.65 5	99.70 24	99.25 23

UniMVSNet_ETH3D		99.61 6	99.59 4	99.63 13	99.96 1	99.70 9	99.53 32	99.86 8	99.28 5	99.48 27	99.44 50	99.86 4	99.01 64	99.78 4	99.76 3	99.90 2	99.33 19

v7n		99.68 4	99.61 3	99.76 8	99.89 12	99.74 7	99.87 1	99.82 12	99.20 6	99.71 5	99.96 1	99.73 11	99.76 3	99.58 17	99.59 13	99.52 41	99.46 14

TransMVSNet (Re)		99.45 15	99.32 13	99.61 14	99.88 14	99.60 16	99.75 11	99.63 35	99.11 7	99.28 45	99.83 18	98.35 131	99.27 41	99.70 6	99.62 10	99.84 10	99.03 48

ACMH	97.81 6	99.44 16	99.33 11	99.56 20	99.81 26	99.42 31	99.73 15	99.58 43	99.02 8	99.10 71	99.41 54	99.69 17	99.60 10	99.45 25	99.26 31	99.55 38	99.05 45
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
COLMAP_ROB	98.29 2	99.37 18	99.25 17	99.51 27	99.74 51	99.12 65	99.56 29	99.39 79	98.96 9	99.17 58	99.44 50	99.63 31	99.58 11	99.48 23	99.27 30	99.60 33	98.81 72
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 13	99.38 9	99.57 19	99.82 23	99.49 23	99.63 21	99.65 31	98.88 10	99.31 40	99.85 14	99.02 97	99.23 44	99.60 15	99.58 14	99.80 15	99.22 29

SixPastTwentyTwo		99.70 3	99.59 4	99.82 2	99.93 3	99.80 1	99.86 2	99.87 6	98.87 11	99.79 4	99.85 14	99.33 61	99.74 5	99.85 2	99.82 1	99.74 22	99.63 4

CSCG		99.23 24	99.15 22	99.32 50	99.83 21	99.45 27	98.97 94	99.21 115	98.83 12	99.04 80	99.43 52	99.64 29	99.26 42	98.85 68	98.20 94	99.62 31	99.62 5

new-patchmatchnet		97.26 148	96.12 162	98.58 125	99.55 94	98.63 122	99.14 83	97.04 197	98.80 13	99.19 54	99.92 4	99.19 75	98.92 68	95.51 182	87.04 199	97.66 172	93.73 191

gg-mvs-nofinetune		96.77 161	96.52 155	97.06 178	99.66 69	97.82 168	97.54 189	99.86 8	98.69 14	98.61 114	99.94 2	89.62 183	88.37 208	97.55 138	96.67 157	98.30 157	95.35 179

ACMH+	97.53 7	99.29 22	99.20 21	99.40 37	99.81 26	99.22 53	99.59 26	99.50 61	98.64 15	98.29 140	99.21 68	99.69 17	99.57 12	99.53 20	99.33 26	99.66 28	98.81 72

anonymousdsp		99.64 5	99.55 6	99.74 10	99.87 15	99.56 19	99.82 3	99.73 19	98.54 16	99.71 5	99.92 4	99.84 6	99.61 9	99.70 6	99.63 6	99.69 27	99.64 2

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 16	99.66 12	99.78 22	99.16 79	99.68 7	99.70 6	99.63 6	99.94 1	99.49 12

tfpnnormal		99.19 27	98.90 34	99.54 23	99.81 26	99.55 21	99.60 25	99.54 52	98.53 18	99.23 49	98.40 101	98.23 135	99.40 31	99.29 32	99.36 24	99.63 30	98.95 60

CHOSEN 1792x2688		98.31 103	98.02 103	98.66 119	99.55 94	98.57 128	99.38 48	99.25 110	98.42 19	98.48 129	99.58 37	99.85 5	98.31 106	95.75 177	95.71 172	96.96 179	98.27 119

DeepC-MVS	97.88 4	99.33 19	99.15 22	99.53 26	99.73 56	99.05 73	99.49 36	99.40 77	98.42 19	99.55 20	99.71 24	99.89 3	99.49 19	99.14 37	98.81 58	99.54 39	99.02 50
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
N_pmnet		96.68 164	95.70 172	97.84 161	99.42 122	98.00 160	99.35 53	98.21 178	98.40 21	98.13 150	99.42 53	99.30 64	97.44 138	94.00 197	88.79 195	94.47 193	91.96 197

FMVSNet1		98.90 49	99.10 24	98.67 117	99.54 98	99.48 24	99.22 72	99.66 29	98.39 22	97.50 173	99.66 26	99.04 96	96.58 154	99.05 48	99.03 42	99.52 41	99.08 42

EU-MVSNet		98.68 75	98.94 31	98.37 137	99.14 155	98.74 114	99.64 18	98.20 180	98.21 23	99.17 58	99.66 26	99.18 76	99.08 59	99.11 39	98.86 51	95.00 191	98.83 69

MIMVSNet1		99.46 14	99.34 10	99.60 16	99.83 21	99.68 11	99.74 14	99.71 22	98.20 24	99.41 32	99.86 13	99.66 24	99.41 30	99.50 21	99.39 21	99.50 46	99.10 40

Vis-MVSNet		99.25 23	99.32 13	99.17 62	99.65 72	99.55 21	99.63 21	99.33 95	98.16 25	99.29 42	99.65 29	99.77 8	97.56 134	99.44 27	99.14 37	99.58 34	99.51 11
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UGNet		98.52 92	99.00 28	97.96 156	99.58 88	99.26 46	99.27 65	99.40 77	98.07 26	98.28 141	98.76 91	99.71 15	92.24 200	98.94 60	98.85 53	99.00 107	99.43 16
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 60	98.75 42	98.94 93	99.75 45	99.21 54	99.33 57	99.04 135	98.04 27	97.46 176	99.72 23	99.72 13	98.60 86	98.30 99	98.37 88	99.48 48	97.92 137

3Dnovator+	97.85 5	98.61 83	98.14 95	99.15 65	99.62 80	98.37 139	99.10 86	99.51 59	98.04 27	98.98 83	96.07 173	98.75 114	98.55 92	98.51 83	98.40 87	99.17 88	98.82 70

v1144		98.94 43	98.53 61	99.42 32	99.62 80	99.03 79	99.58 27	99.36 88	97.99 29	99.49 26	99.91 8	99.20 74	99.51 17	97.61 134	97.85 110	98.95 111	98.10 131

3Dnovator	98.16 3	98.65 78	98.35 80	99.00 84	99.59 86	98.70 117	98.90 105	99.36 88	97.97 30	99.09 72	96.55 162	99.09 91	97.97 121	98.70 76	98.65 74	99.12 90	98.81 72

v148		98.77 70	98.45 69	99.15 65	99.68 64	98.94 95	99.49 36	99.31 101	97.95 31	98.91 93	99.65 29	99.62 33	99.18 47	97.99 118	97.64 128	98.33 156	97.38 151

diffmvs		98.26 106	98.16 93	98.39 134	99.61 84	98.78 110	98.79 115	98.61 162	97.94 32	97.11 188	99.51 45	99.52 41	97.61 132	96.55 166	96.93 153	98.61 141	97.87 139

HyFIR lowres test		98.08 118	97.16 140	99.14 68	99.72 57	98.91 99	99.41 44	99.58 43	97.93 33	98.82 101	99.24 64	95.81 168	98.73 80	95.16 188	95.13 181	98.60 143	97.94 136

v2v482		98.85 59	98.40 75	99.38 43	99.65 72	98.98 85	99.55 30	99.39 79	97.92 34	99.35 35	99.85 14	99.14 83	99.39 33	97.50 140	97.78 113	98.98 108	97.60 145

v1921920		98.89 51	98.46 66	99.39 38	99.58 88	99.04 77	99.64 18	99.17 121	97.91 35	99.64 14	99.92 4	98.99 101	99.44 25	97.44 145	97.57 133	98.84 123	98.35 111

v1192		98.91 48	98.48 65	99.41 33	99.61 84	99.03 79	99.64 18	99.25 110	97.91 35	99.58 16	99.92 4	99.07 95	99.45 22	97.55 138	97.68 124	98.93 113	98.23 121

MDA-MVSNet-bldmvs		97.75 130	97.26 131	98.33 138	99.35 128	98.45 136	99.32 59	97.21 195	97.90 37	99.05 77	99.01 82	96.86 160	99.08 59	99.36 29	92.97 191	95.97 188	96.25 172

DTE-MVSNet		99.52 10	99.27 16	99.82 2	99.93 3	99.77 3	99.79 6	99.87 6	97.89 38	99.70 10	99.55 43	99.21 72	99.77 2	99.65 10	99.43 19	99.90 2	99.36 17

v144192		98.88 53	98.46 66	99.37 45	99.56 93	99.03 79	99.61 24	99.26 107	97.79 39	99.58 16	99.88 9	99.11 88	99.43 27	97.38 150	97.61 129	98.80 127	98.43 106

OPM-MVS		98.84 60	98.59 55	99.12 69	99.52 105	98.50 133	99.13 84	99.22 113	97.76 40	98.76 105	98.70 92	99.61 34	98.90 69	98.67 77	98.37 88	99.19 86	98.57 93

FC-MVSNet-test		99.32 20	99.33 11	99.31 51	99.87 15	99.65 15	99.63 21	99.75 18	97.76 40	97.29 185	99.87 11	99.63 31	99.52 16	99.66 9	99.63 6	99.77 19	99.12 35

HFP-MVS		98.97 41	98.70 47	99.29 53	99.67 66	98.98 85	99.13 84	99.53 55	97.76 40	98.90 94	98.07 116	99.50 47	99.14 56	98.64 79	98.78 62	99.37 61	99.18 32

DVP-MVS		99.09 33	99.07 25	99.12 69	99.55 94	99.40 33	99.36 50	99.44 75	97.75 43	98.23 144	99.23 66	99.80 7	98.97 66	99.08 45	98.96 46	99.19 86	99.25 23

IterMVS-LS		98.23 109	97.66 117	98.90 94	99.63 79	99.38 36	99.07 87	99.48 66	97.75 43	98.81 102	99.37 56	94.57 174	97.88 125	96.54 167	97.04 150	98.53 148	98.97 55
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
LS3D		98.79 68	98.52 62	99.12 69	99.64 75	99.09 67	99.24 69	99.46 70	97.75 43	98.93 92	97.47 134	98.23 135	97.98 120	99.36 29	99.30 27	99.46 49	98.42 107

UA-Net		99.30 21	99.22 20	99.39 38	99.94 2	99.66 14	98.91 102	99.86 8	97.74 46	98.74 108	99.00 83	99.60 36	99.17 50	99.50 21	99.39 21	99.70 24	99.64 2

ACMMPR		99.05 35	98.72 45	99.44 28	99.79 31	99.12 65	99.35 53	99.56 46	97.74 46	99.21 50	97.72 126	99.55 39	99.29 39	98.90 66	98.81 58	99.41 58	99.19 31

RPSCF		98.84 60	98.81 38	98.89 95	99.37 125	98.95 91	98.51 136	98.85 147	97.73 48	98.33 137	98.97 85	99.14 83	98.95 67	99.18 36	98.68 71	99.31 72	98.99 53

PMVS	92.51 17	98.66 77	98.86 36	98.43 132	99.26 141	98.98 85	98.60 130	98.59 164	97.73 48	99.45 30	99.38 55	98.54 125	95.24 173	99.62 14	99.61 11	99.42 55	98.17 128
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SD-MVS		98.73 72	98.54 60	98.95 90	99.14 155	98.76 112	98.46 140	99.14 126	97.71 50	98.56 118	98.06 118	99.61 34	98.85 73	98.56 81	97.74 119	99.54 39	99.32 20
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 80	98.58 57	98.72 111	99.17 153	98.63 122	98.69 120	99.10 133	97.69 51	98.30 139	99.12 73	99.38 56	98.70 81	98.45 84	97.51 136	98.35 155	99.25 23

thisisatest0515		99.16 29	98.94 31	99.41 33	99.75 45	99.43 30	99.36 50	99.63 35	97.68 52	99.35 35	99.31 58	98.90 103	99.09 58	98.95 58	99.20 32	99.27 78	99.11 36

v1240		98.86 56	98.41 74	99.38 43	99.59 86	99.05 73	99.65 17	99.14 126	97.68 52	99.66 12	99.93 3	98.72 115	99.45 22	97.38 150	97.72 122	98.79 128	98.35 111

ACMM	96.66 11	98.90 49	98.44 70	99.44 28	99.74 51	98.95 91	99.47 38	99.55 48	97.66 54	99.09 72	96.43 165	99.41 51	99.35 37	98.95 58	98.67 72	99.45 51	99.03 48
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MDTV_nov1_ep13_2view		97.12 153	96.19 161	98.22 146	99.13 157	98.05 157	99.24 69	99.47 67	97.61 55	99.15 65	99.59 35	99.01 98	98.40 102	94.87 191	90.14 194	93.91 194	94.04 190

PEN-MVS		99.54 8	99.30 15	99.83 1	99.92 5	99.76 4	99.80 4	99.88 3	97.60 56	99.71 5	99.59 35	99.52 41	99.75 4	99.64 12	99.51 16	99.90 2	99.46 14

v10		99.01 38	98.66 52	99.41 33	99.52 105	99.39 34	99.57 28	99.66 29	97.59 57	99.32 39	99.88 9	99.23 69	99.50 18	97.77 129	97.98 103	98.92 116	98.78 78

USDC		98.26 106	97.57 122	99.06 75	99.42 122	97.98 163	98.83 109	98.85 147	97.57 58	99.59 15	99.15 71	98.59 123	98.99 65	97.42 146	96.08 171	98.69 135	96.23 173

DCV-MVSNet		98.86 56	98.57 58	99.19 60	99.86 19	99.67 12	99.39 46	99.71 22	97.53 59	98.69 111	95.85 176	98.48 126	97.75 128	99.57 18	99.41 20	99.72 23	99.48 13

TSAR-MVS + MP.		99.02 37	98.95 29	99.11 72	99.23 146	98.79 109	99.51 34	98.73 154	97.50 60	98.56 118	99.03 80	99.59 37	99.16 52	99.29 32	99.17 35	99.50 46	99.24 27
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 43	98.60 53	99.35 48	99.54 98	99.39 34	99.55 30	99.67 28	97.48 61	99.13 67	99.81 19	99.10 89	99.39 33	97.86 124	97.89 108	98.81 125	98.66 86

TinyColmap		98.27 105	97.62 121	99.03 81	99.29 137	97.79 170	98.92 100	98.95 143	97.48 61	99.52 23	98.65 95	97.86 145	98.90 69	98.34 94	97.27 145	98.64 139	95.97 175

gm-plane-assit		94.62 187	91.39 197	98.39 134	99.90 11	99.47 26	99.40 45	99.65 31	97.44 63	99.56 19	99.68 25	59.40 216	94.23 188	96.17 171	94.77 185	97.61 173	92.79 195

V42		98.81 67	98.49 64	99.18 61	99.52 105	98.92 97	99.50 35	99.29 103	97.43 64	98.97 84	99.81 19	99.00 100	99.30 38	97.93 120	98.01 101	98.51 151	98.34 115

DeepC-MVS_fast	97.38 8	98.65 78	98.34 81	99.02 83	99.33 129	98.29 141	98.99 92	98.71 156	97.40 65	99.31 40	98.20 109	99.40 54	98.54 94	98.33 96	98.18 95	99.23 84	98.58 91
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 43	98.57 58	99.37 45	99.77 36	99.15 62	99.24 69	99.55 48	97.38 66	99.16 61	96.64 159	99.69 17	99.15 54	99.09 43	98.92 49	99.37 61	99.11 36

EPP-MVSNet		98.61 83	98.19 92	99.11 72	99.86 19	99.60 16	99.44 43	99.53 55	97.37 67	96.85 189	98.69 93	93.75 175	99.18 47	99.22 35	99.35 25	99.82 13	99.32 20

PS-CasMVS		99.50 11	99.23 18	99.82 2	99.92 5	99.75 6	99.78 7	99.89 1	97.30 68	99.71 5	99.60 33	99.23 69	99.71 6	99.65 10	99.55 15	99.90 2	99.56 7

test20.03		98.84 60	98.74 43	98.95 90	99.77 36	99.33 40	99.21 75	99.46 70	97.29 69	98.88 98	99.65 29	99.10 89	97.07 146	99.11 39	98.76 65	99.32 71	97.98 135

TranMVSNet+NR-MVSNet		99.23 24	98.91 33	99.61 14	99.81 26	99.45 27	99.47 38	99.68 25	97.28 70	99.39 33	99.54 44	99.08 93	99.45 22	99.09 43	98.84 55	99.83 11	99.04 46

ambc			97.89 109		99.45 116	97.88 165	97.78 177		97.27 71	99.80 2	98.99 84	98.48 126	98.55 92	97.80 127	96.68 156	98.54 147	98.10 131

WR-MVS_H		99.48 12	99.23 18	99.76 8	99.91 9	99.76 4	99.75 11	99.88 3	97.27 71	99.58 16	99.56 39	99.24 68	99.56 13	99.60 15	99.60 12	99.88 8	99.58 6

testgi		98.18 115	98.44 70	97.89 158	99.78 34	99.23 50	98.78 117	99.21 115	97.26 73	97.41 178	97.39 137	99.36 60	92.85 197	98.82 71	98.66 73	99.31 72	98.35 111

OMC-MVS		98.35 101	98.10 98	98.64 123	98.85 172	97.99 161	98.56 132	98.21 178	97.26 73	98.87 100	98.54 99	99.27 67	98.43 100	98.34 94	97.66 125	98.92 116	97.65 144

APDe-MVS		99.15 30	98.95 29	99.39 38	99.77 36	99.28 45	99.52 33	99.54 52	97.22 75	99.06 75	99.20 69	99.64 29	99.05 62	99.14 37	99.02 45	99.39 59	99.17 33

pmmvs-eth3d		98.68 75	98.14 95	99.29 53	99.49 110	98.45 136	99.45 42	99.38 84	97.21 76	99.50 25	99.65 29	99.21 72	99.16 52	97.11 157	97.56 134	98.79 128	97.82 141

CVMVSNet		97.38 147	97.39 127	97.37 172	98.58 186	97.72 172	98.70 119	97.42 193	97.21 76	95.95 196	99.46 48	93.31 178	97.38 139	97.60 135	97.78 113	96.18 185	98.66 86

PMMVS2		96.29 171	97.05 143	95.40 200	98.32 197	96.16 190	98.18 162	97.46 192	97.20 78	84.51 212	99.60 33	98.68 118	96.37 159	98.59 80	97.38 140	97.58 174	91.76 198

MSDG		98.20 112	97.88 110	98.56 127	99.33 129	97.74 171	98.27 157	98.10 181	97.20 78	98.06 153	98.59 97	99.16 79	98.76 78	98.39 89	97.71 123	98.86 122	96.38 170

FPMVS		96.97 156	97.20 137	96.70 189	97.75 203	96.11 193	97.72 181	95.47 201	97.13 80	98.02 155	97.57 130	96.67 161	92.97 196	99.00 56	98.34 90	98.28 158	95.58 178

PVSNet_Blended_VisFu		98.98 40	98.79 39	99.21 57	99.76 42	99.34 38	99.35 53	99.35 91	97.12 81	99.46 29	99.56 39	98.89 104	98.08 117	99.05 48	98.58 78	99.27 78	98.98 54

DI_MVS_plusplus_trai		97.57 143	96.55 154	98.77 107	99.55 94	98.76 112	99.22 72	99.00 139	97.08 82	97.95 161	97.78 125	91.35 182	98.02 119	96.20 170	96.81 155	98.87 120	97.87 139

canonicalmvs		98.34 102	97.92 108	98.83 102	99.45 116	99.21 54	98.37 147	99.53 55	97.06 83	97.74 167	96.95 153	95.05 172	98.36 103	98.77 74	98.85 53	99.51 45	99.53 8

MSP-MVS		98.72 73	98.60 53	98.87 97	99.67 66	99.33 40	99.15 81	99.26 107	96.99 84	97.90 163	98.19 110	99.74 10	98.29 108	97.69 132	98.96 46	98.96 109	99.27 22

Anonymous20231211		98.89 51	98.79 39	98.99 87	99.82 23	99.41 32	99.18 78	99.31 101	96.92 85	98.54 121	98.58 98	98.84 109	97.46 136	99.45 25	99.29 28	99.65 29	99.08 42

new_pmnet		96.59 165	96.40 158	96.81 186	98.24 199	95.46 203	97.71 183	94.75 205	96.92 85	96.80 191	99.23 66	97.81 146	96.69 151	96.58 165	95.16 180	96.69 181	93.64 192

ACMP	96.54 13	98.87 54	98.40 75	99.41 33	99.74 51	98.88 103	99.29 61	99.50 61	96.85 87	98.96 86	97.05 147	99.66 24	99.43 27	98.98 57	98.60 76	99.52 41	98.81 72
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMMP_NAP		98.94 43	98.72 45	99.21 57	99.67 66	99.08 68	99.26 66	99.39 79	96.84 88	98.88 98	98.22 108	99.68 20	98.82 74	99.06 47	98.90 50	99.25 81	99.25 23

PM-MVS		98.57 87	98.24 89	98.95 90	99.26 141	98.59 125	99.03 89	98.74 153	96.84 88	99.44 31	99.13 72	98.31 134	98.75 79	98.03 116	98.21 92	98.48 152	98.58 91

DELS-MVS		98.63 81	98.70 47	98.55 128	99.24 145	99.04 77	98.96 95	98.52 167	96.83 90	98.38 134	99.58 37	99.68 20	97.06 147	98.74 75	98.44 86	99.10 91	98.59 90
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 17	99.04 27	99.80 6	99.91 9	99.70 9	99.75 11	99.88 3	96.82 91	99.68 11	99.32 57	98.86 106	99.68 7	99.57 18	99.47 17	99.89 6	99.52 9

QAPM		98.62 82	98.40 75	98.89 95	99.57 92	98.80 108	98.63 125	99.35 91	96.82 91	98.60 115	98.85 90	99.08 93	98.09 116	98.31 97	98.21 92	99.08 96	98.72 80

MVS_111021_HR		98.58 86	98.26 87	98.96 89	99.32 132	98.81 106	98.48 138	98.99 140	96.81 93	99.16 61	98.07 116	99.23 69	98.89 71	98.43 86	98.27 91	98.90 118	98.24 120

NCCC		97.84 128	96.96 146	98.87 97	99.39 124	98.27 144	98.46 140	99.02 137	96.78 94	98.73 110	91.12 199	98.91 102	98.57 90	97.83 126	97.49 137	99.04 104	98.33 116

DeepPCF-MVS	96.68 10	98.20 112	98.26 87	98.12 150	97.03 211	98.11 154	98.44 142	97.70 191	96.77 95	98.52 123	98.91 86	99.17 77	98.58 89	98.41 88	98.02 100	98.46 153	98.46 102

MVS_0304		98.57 87	98.36 78	98.82 104	99.72 57	98.94 95	98.92 100	99.14 126	96.76 96	99.33 38	98.30 105	99.73 11	96.74 150	98.05 115	97.79 112	99.08 96	98.97 55

FC-MVSNet-train		99.13 31	99.05 26	99.21 57	99.87 15	99.57 18	99.67 16	99.60 42	96.75 97	98.28 141	99.48 47	99.52 41	98.10 114	99.47 24	99.37 23	99.76 21	99.21 30

UniMVSNet (Re)		99.08 34	98.69 49	99.54 23	99.75 45	99.33 40	99.29 61	99.64 34	96.75 97	99.48 27	99.30 60	98.69 116	99.26 42	98.94 60	98.76 65	99.78 18	99.02 50

TSAR-MVS + COLMAP		97.62 139	97.31 129	97.98 154	98.47 192	97.39 177	98.29 154	98.25 177	96.68 99	97.54 172	98.87 87	98.04 141	97.08 145	96.78 161	96.26 164	98.26 159	97.12 161

TAPA-MVS	96.65 12	98.23 109	97.96 107	98.55 128	98.81 174	98.16 151	98.40 144	97.94 187	96.68 99	98.49 127	98.61 96	98.89 104	98.57 90	97.45 143	97.59 131	99.09 95	98.35 111
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
X-MVS		98.59 85	97.99 105	99.30 52	99.75 45	99.07 69	99.17 79	99.50 61	96.62 101	98.95 88	93.95 191	99.37 57	99.11 57	98.94 60	98.86 51	99.35 66	99.09 41

FMVSNet2		97.94 123	98.08 100	97.77 164	98.71 178	99.21 54	98.62 127	99.47 67	96.62 101	96.37 194	99.20 69	97.70 147	94.39 184	97.39 148	97.75 118	99.08 96	98.70 82

CP-MVS		98.86 56	98.43 73	99.36 47	99.68 64	98.97 89	99.19 76	99.46 70	96.60 103	99.20 51	97.11 146	99.51 45	99.15 54	98.92 64	98.82 56	99.45 51	99.08 42

Anonymous202405211			98.44 70		99.79 31	99.32 43	99.05 88	99.34 94	96.59 104		97.95 123	97.68 148	97.16 143	99.36 29	99.28 29	99.61 32	98.90 64

DU-MVS		99.04 36	98.59 55	99.56 20	99.74 51	99.23 50	99.29 61	99.63 35	96.58 105	99.55 20	99.05 77	98.68 118	99.36 35	99.03 53	98.60 76	99.77 19	98.97 55

NR-MVSNet		99.10 32	98.68 51	99.58 18	99.89 12	99.23 50	99.35 53	99.63 35	96.58 105	99.36 34	99.05 77	98.67 120	99.46 20	99.63 13	98.73 69	99.80 15	98.88 67

pmmvs4		97.87 127	97.02 144	98.86 100	99.20 147	97.68 174	98.89 106	99.03 136	96.57 107	99.12 69	99.03 80	97.26 155	98.42 101	95.16 188	96.34 163	98.53 148	97.10 162

MVS_111021_LR		98.39 99	98.11 97	98.71 113	99.08 161	98.54 131	98.23 160	98.56 166	96.57 107	99.13 67	98.41 100	98.86 106	98.65 84	98.23 106	97.87 109	98.65 138	98.28 117

UniMVSNet_NR-MVSNet		98.97 41	98.46 66	99.56 20	99.76 42	99.34 38	99.29 61	99.61 41	96.55 109	99.55 20	99.05 77	97.96 143	99.36 35	98.84 69	98.50 84	99.81 14	98.97 55

EG-PatchMatch MVS		99.01 38	98.77 41	99.28 55	99.64 75	98.90 102	98.81 113	99.27 106	96.55 109	99.71 5	99.31 58	99.66 24	99.17 50	99.28 34	99.11 38	99.10 91	98.57 93

Baseline_NR-MVSNet		99.18 28	98.87 35	99.54 23	99.74 51	99.56 19	99.36 50	99.62 40	96.53 111	99.29 42	99.85 14	98.64 122	99.40 31	99.03 53	99.63 6	99.83 11	98.86 68

baseline		97.50 145	97.51 124	97.50 169	99.18 151	97.38 178	98.00 167	98.00 184	96.52 112	97.49 174	99.28 61	99.43 50	95.31 171	95.27 185	96.22 165	96.99 178	98.47 100

MSLP-MVS++		97.99 120	97.64 120	98.40 133	98.91 170	98.47 135	97.12 200	98.78 151	96.49 113	98.48 129	93.57 194	99.12 86	98.51 96	98.31 97	98.58 78	98.58 145	98.95 60

CNLPA		97.75 130	97.26 131	98.32 140	98.58 186	97.86 166	97.80 176	98.09 182	96.49 113	98.49 127	96.15 170	98.08 138	98.35 104	98.00 117	97.03 151	98.61 141	97.21 159

ACMMP		98.82 66	98.33 82	99.39 38	99.77 36	99.14 63	99.37 49	99.54 52	96.47 115	99.03 82	96.26 169	99.52 41	99.28 40	98.92 64	98.80 61	99.37 61	99.16 34
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		97.63 138	96.86 148	98.52 130	99.48 112	98.71 116	98.84 108	98.91 144	96.44 116	99.16 61	99.56 39	95.54 170	97.95 122	95.68 180	95.07 184	96.76 180	97.03 165

IterMVS		97.40 146	96.67 149	98.25 143	99.45 116	98.66 120	98.87 107	98.73 154	96.40 117	98.94 91	99.56 39	95.26 171	97.58 133	95.38 183	94.70 186	95.90 189	96.72 168
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Anonymous20231206		98.50 93	98.03 102	99.05 78	99.50 108	99.01 83	99.15 81	99.26 107	96.38 118	99.12 69	99.50 46	99.12 86	98.60 86	97.68 133	97.24 147	98.66 136	97.30 155

PLC	95.63 15	97.73 133	97.01 145	98.57 126	99.10 158	97.80 169	97.72 181	98.77 152	96.34 119	98.38 134	93.46 195	98.06 139	98.66 83	97.90 122	97.65 127	98.77 130	97.90 138
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SMA-MVS		98.87 54	98.73 44	99.04 80	99.72 57	99.05 73	98.64 124	99.17 121	96.31 120	98.80 103	99.07 75	99.70 16	98.67 82	98.93 63	98.82 56	99.23 84	99.23 28

CPTT-MVS		98.28 104	97.51 124	99.16 63	99.54 98	98.78 110	98.96 95	99.36 88	96.30 121	98.89 97	93.10 196	99.30 64	99.20 45	98.35 93	97.96 104	99.03 105	98.82 70

HPM-MVS++		98.56 90	98.08 100	99.11 72	99.53 101	98.61 124	99.02 91	99.32 99	96.29 122	99.06 75	97.23 141	99.50 47	98.77 77	98.15 111	97.90 106	98.96 109	98.90 64

CNVR-MVS		98.22 111	97.76 113	98.76 108	99.33 129	98.26 145	98.48 138	98.88 146	96.22 123	98.47 131	95.79 177	99.33 61	98.35 104	98.37 91	97.99 102	99.03 105	98.38 109

Vis-MVSNet (Re-imp)		98.46 97	98.23 90	98.73 110	99.81 26	99.29 44	98.79 115	99.50 61	96.20 124	96.03 195	98.29 106	96.98 158	98.54 94	99.11 39	99.08 39	99.70 24	98.62 89

SteuartSystems-ACMMP		98.94 43	98.52 62	99.43 31	99.79 31	99.13 64	99.33 57	99.55 48	96.17 125	99.04 80	97.53 132	99.65 28	99.46 20	99.04 52	98.76 65	99.44 53	99.35 18
Skip Steuart: Steuart Systems R&D Blog.
CANet		98.47 95	98.30 84	98.67 117	99.65 72	98.87 104	98.82 112	99.01 138	96.14 126	99.29 42	98.86 88	99.01 98	96.54 155	98.36 92	98.08 98	98.72 132	98.80 76

tmp_tt				65.28 206	82.24 213	71.50 214	70.81 214	23.21 210	96.14 126	81.70 213	85.98 209	92.44 180	49.84 209	95.81 176	94.36 187	83.86 212

ADS-MVSNet		94.41 193	92.13 194	97.07 177	98.86 171	96.60 184	98.38 146	98.47 171	96.13 128	98.02 155	96.98 151	87.50 187	95.87 166	89.89 201	87.58 197	92.79 202	90.27 203

ETV-MVS		98.77 70	98.36 78	99.25 56	99.64 75	99.03 79	99.22 72	99.44 75	96.06 129	99.20 51	98.09 115	98.33 132	98.45 98	99.10 42	99.18 34	99.56 36	98.70 82

MVE	82.47 18	93.12 197	94.09 178	91.99 205	90.79 212	82.50 213	93.93 211	96.30 199	96.06 129	88.81 211	98.19 110	96.38 163	97.56 134	97.24 155	95.18 179	84.58 211	93.07 193
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CLD-MVS		98.48 94	98.15 94	98.86 100	99.53 101	98.35 140	98.55 133	97.83 189	96.02 131	98.97 84	99.08 74	99.75 9	99.03 63	98.10 114	97.33 143	99.28 76	98.44 105
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 91	98.29 86	98.82 104	99.28 139	98.59 125	97.73 180	99.24 112	95.93 132	98.59 116	99.07 75	99.17 77	98.86 72	98.44 85	98.10 97	99.26 80	98.72 80

MCST-MVS		98.25 108	97.57 122	99.06 75	99.53 101	98.24 147	98.63 125	99.17 121	95.88 133	98.58 117	96.11 171	99.09 91	99.18 47	97.58 137	97.31 144	99.25 81	98.75 79

DPE-MVS		98.84 60	98.69 49	99.00 84	99.05 164	99.26 46	99.19 76	99.35 91	95.85 134	98.74 108	99.27 62	99.66 24	98.30 107	98.90 66	98.93 48	99.37 61	99.00 52

pmmvs5		98.37 100	97.81 111	99.03 81	99.46 114	98.97 89	99.03 89	98.96 142	95.85 134	99.05 77	99.45 49	98.66 121	98.79 76	96.02 174	97.52 135	98.87 120	98.21 124

MS-PatchMatch		97.60 140	97.22 136	98.04 153	98.67 182	97.18 181	97.91 172	98.28 176	95.82 136	98.34 136	97.66 127	98.38 130	97.77 127	97.10 158	97.25 146	97.27 177	97.18 160

MP-MVS		98.78 69	98.30 84	99.34 49	99.75 45	98.95 91	99.26 66	99.46 70	95.78 137	99.17 58	96.98 151	99.72 13	99.06 61	98.84 69	98.74 68	99.33 68	99.11 36
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CDS-MVSNet		97.75 130	97.68 116	97.83 162	99.08 161	98.20 150	98.68 121	98.61 162	95.63 138	97.80 165	99.24 64	96.93 159	94.09 189	97.96 119	97.82 111	98.71 133	97.99 133
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IS_MVSNet		98.20 112	98.00 104	98.44 131	99.82 23	99.48 24	99.25 68	99.56 46	95.58 139	93.93 207	97.56 131	96.52 162	98.27 109	99.08 45	99.20 32	99.80 15	98.56 96

EPMVS		93.67 196	90.82 200	96.99 183	98.62 185	96.39 188	98.40 144	99.11 131	95.54 140	97.87 164	97.14 144	81.27 208	94.97 177	88.54 205	86.80 200	92.95 201	90.06 205

DPM-MVS		96.73 162	95.70 172	97.95 157	98.93 169	97.26 179	97.39 194	98.44 172	95.47 141	97.62 170	90.71 200	98.47 128	97.03 148	95.02 190	95.27 178	98.26 159	97.67 143

LGP-MVS_train		98.84 60	98.33 82	99.44 28	99.78 34	98.98 85	99.39 46	99.55 48	95.41 142	98.90 94	97.51 133	99.68 20	99.44 25	99.03 53	98.81 58	99.57 35	98.91 63

E-PMN		92.28 201	90.12 201	94.79 203	98.56 189	90.90 210	95.16 208	93.68 207	95.36 143	95.10 203	96.56 161	89.05 184	95.24 173	95.21 187	81.84 207	90.98 208	81.94 209

EMVS		91.84 202	89.39 204	94.70 204	98.44 193	90.84 211	95.27 207	93.53 208	95.18 144	95.26 201	95.62 180	87.59 186	94.77 180	94.87 191	80.72 208	90.95 209	80.88 210

GA-MVS		96.84 159	95.86 169	97.98 154	99.16 154	98.29 141	97.91 172	98.64 161	95.14 145	97.71 168	98.04 120	88.90 185	96.50 157	96.41 169	96.61 160	97.97 169	97.60 145

SCA		94.53 190	91.95 196	97.55 168	98.58 186	97.86 166	98.49 137	99.68 25	95.11 146	99.07 74	95.87 175	87.24 188	96.53 156	89.77 202	87.08 198	92.96 200	90.69 201

TAMVS		96.95 157	96.94 147	96.97 184	99.07 163	97.67 175	97.98 170	97.12 196	95.04 147	95.41 200	99.27 62	95.57 169	94.09 189	97.32 152	97.11 149	98.16 164	96.59 169

MVS_Test		97.69 134	97.15 141	98.33 138	99.27 140	98.43 138	98.25 158	99.29 103	95.00 148	97.39 180	98.86 88	98.00 142	97.14 144	95.38 183	96.22 165	98.62 140	98.15 130

PHI-MVS		98.57 87	98.20 91	99.00 84	99.48 112	98.91 99	98.68 121	99.17 121	94.97 149	99.27 47	98.33 103	99.33 61	98.05 118	98.82 71	98.62 75	99.34 67	98.38 109

baseline1		96.72 163	95.40 174	98.26 141	99.53 101	98.81 106	98.32 151	98.80 150	94.96 150	96.78 192	96.50 164	84.87 199	96.68 153	97.42 146	97.91 105	99.46 49	97.33 154

PatchmatchNet		93.88 195	91.08 199	97.14 176	98.75 177	96.01 196	98.25 158	99.39 79	94.95 151	98.96 86	96.32 167	85.35 196	95.50 170	88.89 203	85.89 203	91.99 206	90.15 204
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MIMVSNet		97.24 149	97.15 141	97.36 173	99.03 165	98.52 132	98.55 133	99.73 19	94.94 152	94.94 204	97.98 121	97.37 153	93.66 192	97.60 135	97.34 142	98.23 162	96.29 171

PGM-MVS		98.69 74	98.09 99	99.39 38	99.76 42	99.07 69	99.30 60	99.51 59	94.76 153	99.18 57	96.70 157	99.51 45	99.20 45	98.79 73	98.71 70	99.39 59	99.11 36

Effi-MVS+		98.11 117	97.29 130	99.06 75	99.62 80	98.55 129	98.16 163	99.80 13	94.64 154	99.15 65	96.59 160	97.43 151	98.44 99	97.46 142	97.90 106	99.17 88	98.45 104

HQP-MVS		97.58 142	96.65 152	98.66 119	99.30 134	97.99 161	97.88 175	98.65 159	94.58 155	98.66 112	94.65 188	99.15 82	98.59 88	96.10 172	95.59 173	98.90 118	98.50 99

thisisatest0530		97.20 151	95.95 166	98.66 119	99.46 114	98.84 105	98.29 154	99.20 117	94.51 156	98.25 143	97.42 135	85.03 197	97.68 130	98.43 86	98.56 82	99.08 96	98.89 66

Effi-MVS+-dtu		97.78 129	97.37 128	98.26 141	99.25 143	98.50 133	97.89 174	99.19 120	94.51 156	98.16 148	95.93 174	98.80 110	95.97 165	98.27 105	97.38 140	99.10 91	98.23 121

Fast-Effi-MVS+		98.42 98	97.79 112	99.15 65	99.69 63	98.66 120	98.94 97	99.68 25	94.49 158	99.05 77	98.06 118	98.86 106	98.48 97	98.18 108	97.78 113	99.05 103	98.54 97

MDTV_nov1_ep13		94.47 191	92.15 193	97.17 175	98.54 191	96.42 187	98.10 164	98.89 145	94.49 158	98.02 155	97.41 136	86.49 189	95.56 169	90.85 200	87.95 196	93.91 194	91.45 200

ET-MVSNet_ETH3D		95.72 179	93.85 184	97.89 158	97.30 209	98.09 155	98.19 161	98.40 173	94.46 160	98.01 158	96.71 156	77.85 211	96.76 149	96.08 173	96.39 162	98.70 134	97.36 152

AdaColmap		97.57 143	96.57 153	98.74 109	99.25 143	98.01 159	98.36 149	98.98 141	94.44 161	98.47 131	92.44 197	97.91 144	98.62 85	98.19 107	97.74 119	98.73 131	97.28 156

train_agg		97.99 120	97.26 131	98.83 102	99.43 121	98.22 149	98.91 102	99.07 134	94.43 162	97.96 160	96.42 166	99.30 64	98.81 75	97.39 148	96.62 159	98.82 124	98.47 100

PatchMatch-RL		97.24 149	96.45 157	98.17 147	98.70 181	97.57 176	97.31 195	98.48 170	94.42 163	98.39 133	95.74 178	96.35 164	97.88 125	97.75 130	97.48 138	98.24 161	95.87 176

CANet_DTU		97.65 137	97.50 126	97.82 163	99.19 150	98.08 156	98.41 143	98.67 158	94.40 164	99.16 61	98.32 104	98.69 116	93.96 191	97.87 123	97.61 129	97.51 175	97.56 147

APD-MVS		98.47 95	97.97 106	99.05 78	99.64 75	98.91 99	98.94 97	99.45 74	94.40 164	98.77 104	97.26 140	99.41 51	98.21 111	98.67 77	98.57 81	99.31 72	98.57 93
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
tttt0517		97.18 152	95.92 167	98.65 122	99.49 110	98.92 97	98.29 154	99.20 117	94.37 166	98.17 146	97.37 138	84.72 200	97.68 130	98.55 82	98.56 82	99.10 91	98.95 60

thres600view7		96.35 168	94.27 176	98.79 106	99.66 69	99.18 59	98.94 97	99.38 84	94.37 166	97.21 187	87.19 203	84.10 201	98.10 114	98.16 109	99.47 17	99.42 55	97.43 149

PVSNet_BlendedMVS		97.93 124	97.66 117	98.25 143	99.30 134	98.67 118	98.31 152	97.95 185	94.30 168	98.75 106	97.63 128	98.76 112	96.30 162	98.29 101	97.78 113	98.93 113	98.18 126

PVSNet_Blended		97.93 124	97.66 117	98.25 143	99.30 134	98.67 118	98.31 152	97.95 185	94.30 168	98.75 106	97.63 128	98.76 112	96.30 162	98.29 101	97.78 113	98.93 113	98.18 126

tpmrst		92.45 199	89.48 203	95.92 198	98.43 194	95.03 205	97.14 198	97.92 188	94.16 170	97.56 171	97.86 124	81.63 207	93.56 193	85.89 208	82.86 205	90.91 210	88.95 208

GBi-Net		97.69 134	97.75 114	97.62 165	98.71 178	99.21 54	98.62 127	99.33 95	94.09 171	95.60 197	98.17 112	95.97 165	94.39 184	99.05 48	99.03 42	99.08 96	98.70 82

test1		97.69 134	97.75 114	97.62 165	98.71 178	99.21 54	98.62 127	99.33 95	94.09 171	95.60 197	98.17 112	95.97 165	94.39 184	99.05 48	99.03 42	99.08 96	98.70 82

FMVSNet3		96.85 158	96.67 149	97.06 178	97.56 206	99.01 83	97.99 169	99.33 95	94.09 171	95.60 197	98.17 112	95.97 165	93.26 195	94.76 193	96.22 165	98.59 144	98.46 102

thres400		96.22 173	94.08 179	98.72 111	99.58 88	99.05 73	98.83 109	99.22 113	94.01 174	97.40 179	86.34 207	84.91 198	97.93 123	97.85 125	99.08 39	99.37 61	97.28 156

OpenMVS	97.26 9	97.88 126	97.17 139	98.70 114	99.50 108	98.55 129	98.34 150	99.11 131	93.92 175	98.90 94	95.04 185	98.23 135	97.38 139	98.11 113	98.12 96	98.95 111	98.23 121

CHOSEN 280x420		96.80 160	96.30 159	97.39 170	99.09 159	96.52 185	98.76 118	99.29 103	93.88 176	97.65 169	98.34 102	93.66 176	96.29 164	98.28 103	97.73 121	93.27 198	95.70 177

CDPH-MVS		97.99 120	97.23 135	98.87 97	99.58 88	98.29 141	98.83 109	99.20 117	93.76 177	98.11 151	96.11 171	99.16 79	98.23 110	97.80 127	97.22 148	99.29 75	98.28 117

EPNet		96.44 167	96.08 163	96.86 185	99.32 132	97.15 182	97.69 184	99.32 99	93.67 178	98.11 151	95.64 179	93.44 177	89.07 206	96.86 160	96.83 154	97.67 171	98.97 55
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepMVS_CX						87.86 212	92.27 212	61.98 209	93.64 179	93.62 208	91.17 198	91.67 181	94.90 179	95.99 175		92.48 204	94.18 189

thres200		96.23 172	94.13 177	98.69 115	99.44 119	99.18 59	98.58 131	99.38 84	93.52 180	97.35 181	86.33 208	85.83 195	97.93 123	98.16 109	98.78 62	99.42 55	97.10 162

Fast-Effi-MVS+-dtu		96.99 155	96.46 156	97.61 167	98.98 167	97.89 164	97.54 189	99.76 16	93.43 181	96.55 193	94.93 186	98.06 139	94.32 187	96.93 159	96.50 161	98.53 148	97.47 148

pmmvs3		96.30 170	95.87 168	96.80 187	97.66 205	96.48 186	97.93 171	93.80 206	93.40 182	98.54 121	98.27 107	97.50 150	97.37 141	97.49 141	93.11 190	95.52 190	94.85 184

abl_6				98.38 136	99.03 165	98.04 158	98.08 166	98.65 159	93.23 183	98.56 118	94.58 189	98.57 124	97.17 142			98.81 125	97.42 150

PMMVS		96.47 166	95.81 170	97.23 174	97.38 208	95.96 197	97.31 195	96.91 198	93.21 184	97.93 162	97.14 144	97.64 149	95.70 167	95.24 186	96.18 168	98.17 163	95.33 180

CS-MVS		98.13 116	97.25 134	99.16 63	99.71 60	99.44 29	98.80 114	99.49 65	93.16 185	99.19 54	93.95 191	98.47 128	98.19 113	98.30 99	98.78 62	99.56 36	98.66 86

NP-MVS									93.07 186

EPNet_dtu		96.31 169	95.96 165	96.72 188	99.18 151	95.39 204	97.03 202	99.13 130	93.02 187	99.35 35	97.23 141	97.07 157	90.70 205	95.74 178	95.08 182	94.94 192	98.16 129
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PCF-MVS	95.58 16	97.60 140	96.67 149	98.69 115	99.44 119	98.23 148	98.37 147	98.81 149	93.01 188	98.22 145	97.97 122	99.59 37	98.20 112	95.72 179	95.08 182	99.08 96	97.09 164
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test0.0.03 1		95.81 177	95.77 171	95.85 199	99.20 147	98.15 153	97.49 193	98.50 168	92.24 189	92.74 210	96.82 155	92.70 179	88.60 207	97.31 154	97.01 152	98.57 146	96.19 174

tpm		93.89 194	91.21 198	97.03 180	98.36 195	96.07 194	97.53 192	99.65 31	92.24 189	98.64 113	97.23 141	74.67 214	94.64 182	92.68 198	90.73 193	93.37 197	94.82 185

MVSTER		95.38 182	93.99 183	97.01 182	98.83 173	98.95 91	96.62 203	99.14 126	92.17 191	97.44 177	97.29 139	77.88 210	91.63 204	97.45 143	96.18 168	98.41 154	97.99 133

tpm cat1		91.52 203	87.70 206	95.97 197	98.33 196	94.98 206	97.06 201	98.03 183	92.11 192	98.03 154	94.77 187	77.19 212	92.71 198	83.56 209	82.24 206	91.67 207	89.04 207

thres100view900		95.74 178	93.66 188	98.17 147	99.37 125	98.59 125	98.10 164	98.33 175	92.02 193	97.30 183	86.53 205	86.34 192	96.69 151	96.77 162	98.47 85	99.24 83	96.89 166

tfpn200view9		96.17 174	94.08 179	98.60 124	99.37 125	99.18 59	98.68 121	99.39 79	92.02 193	97.30 183	86.53 205	86.34 192	97.45 137	98.15 111	99.08 39	99.43 54	97.28 156

PatchT		95.49 181	93.29 189	98.06 152	98.65 183	96.20 189	98.91 102	99.73 19	92.00 195	98.50 124	96.67 158	83.25 203	96.34 160	94.40 194	95.50 174	96.21 184	95.04 182

IB-MVS	95.85 14	95.87 176	94.88 175	97.02 181	99.09 159	98.25 146	97.16 197	97.38 194	91.97 196	97.77 166	83.61 210	97.29 154	92.03 203	97.16 156	97.66 125	98.66 136	98.20 125
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		92.75 198	89.49 202	96.55 191	98.78 176	95.83 201	97.55 188	98.59 164	91.83 197	97.34 182	96.31 168	78.53 209	94.50 183	86.14 206	84.92 204	92.54 203	92.84 194

CMPMVS	74.71 19	96.17 174	96.06 164	96.30 194	97.41 207	94.52 207	94.83 209	95.46 202	91.57 198	97.26 186	94.45 190	98.33 132	94.98 175	98.28 103	97.59 131	97.86 170	97.68 142
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EIA-MVS		98.03 119	97.20 137	98.99 87	99.66 69	99.24 48	98.53 135	99.52 58	91.56 199	99.25 48	95.34 181	98.78 111	97.72 129	98.38 90	98.58 78	99.28 76	98.54 97

baseline2		95.58 180	94.04 181	97.38 171	98.80 175	98.16 151	97.14 198	97.80 190	91.45 200	97.49 174	95.22 182	83.63 202	94.98 175	96.42 168	96.66 158	98.06 165	96.76 167

GG-mvs-BLEND		65.66 205	92.62 192	34.20 207	1.45 216	93.75 209	85.40 213	1.64 213	91.37 201	17.21 214	87.25 202	94.78 173	3.25 212	95.64 181	93.80 189	96.27 183	91.74 199

CR-MVSNet		95.38 182	93.01 190	98.16 149	98.63 184	95.85 199	97.64 186	99.78 14	91.27 202	98.50 124	96.84 154	82.16 204	96.34 160	94.40 194	95.50 174	98.05 167	95.04 182

RPMNet		94.72 186	92.01 195	97.88 160	98.56 189	95.85 199	97.78 177	99.70 24	91.27 202	98.33 137	93.69 193	81.88 205	94.91 178	92.60 199	94.34 188	98.01 168	94.46 186

DWT-MVSNet_training		91.07 204	86.55 207	96.35 193	98.28 198	95.82 202	98.00 167	95.03 204	91.24 204	97.99 159	90.35 201	63.43 215	95.25 172	86.06 207	86.62 201	93.55 196	92.30 196

MVS-HIRNet		94.86 184	93.83 185	96.07 195	97.07 210	94.00 208	94.31 210	99.17 121	91.23 205	98.17 146	98.69 93	97.43 151	95.66 168	94.05 196	91.92 192	92.04 205	89.46 206

MAR-MVS		97.12 153	96.28 160	98.11 151	98.94 168	97.22 180	97.65 185	99.38 84	90.93 206	98.15 149	95.17 183	97.13 156	96.48 158	97.71 131	97.40 139	98.06 165	98.40 108
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		94.79 185	93.71 186	96.06 196	99.20 147	96.16 190	96.31 204	98.50 168	89.98 207	94.08 205	97.01 148	86.43 190	92.20 201	96.76 163	95.31 176	96.05 186	94.31 187

TESTMET0.1,1		94.44 192	93.71 186	95.30 202	97.84 202	96.16 190	96.31 204	95.32 203	89.98 207	94.08 205	97.01 148	86.43 190	92.20 201	96.76 163	95.31 176	96.05 186	94.31 187

dps		92.35 200	88.78 205	96.52 192	98.21 200	95.94 198	97.78 177	98.38 174	89.88 209	96.81 190	95.07 184	75.31 213	94.70 181	88.62 204	86.21 202	93.21 199	90.41 202

test-mter		94.62 187	94.02 182	95.32 201	97.72 204	96.75 183	96.23 206	95.67 200	89.83 210	93.23 209	96.99 150	85.94 194	92.66 199	97.32 152	96.11 170	96.44 182	95.22 181

FMVSNet5		94.57 189	92.77 191	96.67 190	97.88 201	98.72 115	97.54 189	98.70 157	88.64 211	95.11 202	86.90 204	81.77 206	93.27 194	97.92 121	98.07 99	97.50 176	97.34 153

testmvs		9.73 206	13.38 208	5.48 209	3.62 214	4.12 215	6.40 216	3.19 212	14.92 212	7.68 216	22.10 211	13.89 218	6.83 210	13.47 210	10.38 210	5.14 214	14.81 211

test123		9.37 207	12.26 209	6.00 208	3.32 215	4.06 216	6.39 217	3.41 211	13.20 213	10.48 215	16.43 212	16.22 217	6.76 211	11.37 211	10.40 209	5.62 213	14.10 212

sosnet-low-res		0.00 208	0.00 210	0.00 210	0.00 217	0.00 217	0.00 218	0.00 214	0.00 214	0.00 217	0.00 213	0.00 219	0.00 213	0.00 212	0.00 211	0.00 215	0.00 213

sosnet		0.00 208	0.00 210	0.00 210	0.00 217	0.00 217	0.00 218	0.00 214	0.00 214	0.00 217	0.00 213	0.00 219	0.00 213	0.00 212	0.00 211	0.00 215	0.00 213

SR-MVS					99.62 80			99.47 67				99.40 54

our_test_3					99.29 137	97.72 172	98.98 93

test_part1																	98.79 77

MTAPA										99.19 54		99.68 20

MTMP										99.20 51		99.54 40

Patchmatch-RL test							32.47 215

XVS					99.77 36	99.07 69	99.46 40			98.95 88		99.37 57				99.33 68

X-MVStestdata					99.77 36	99.07 69	99.46 40			98.95 88		99.37 57				99.33 68

mPP-MVS					99.75 45							99.49 49

Patchmtry						96.05 195	97.64 186	99.78 14		98.50 124

High-resolution multi-view benchmark