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.

Gipuma		98.43 20	98.15 32	98.76 14	99.00 60	98.29 67	97.91 99	98.06 62	99.02 3	99.50 1	96.33 119	98.67 71	99.22 1	99.02 24	98.02 69	98.88 56	97.66 64
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ambc			96.78 96		99.01 59	97.11 137	95.73 179		95.91 45	99.25 2	98.56 68	97.17 127	97.04 66	96.76 113	95.22 145	96.72 160	96.73 105

v7n		99.03 6	99.03 7	99.02 9	99.09 53	99.11 11	99.57 9	98.82 18	98.21 9	99.25 2	99.84 2	99.59 5	98.76 6	99.23 16	98.83 27	98.63 66	98.40 32

LTVRE_ROB	97.71 1	99.33 1	99.47 1	99.16 7	99.16 41	99.11 11	99.39 12	99.16 11	99.26 2	99.22 4	99.51 18	99.75 3	98.54 15	99.71 1	99.47 3	99.52 12	99.46 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
SixPastTwentyTwo		99.25 2	99.20 3	99.32 1	99.53 15	99.32 8	99.64 2	99.19 10	98.05 10	99.19 5	99.74 4	98.96 47	99.03 2	99.69 2	99.58 1	99.32 24	99.06 5

USDC		96.30 113	95.64 123	97.07 100	97.62 148	96.35 161	97.17 140	95.71 165	95.52 61	99.17 6	98.11 82	97.46 120	95.67 108	95.44 146	93.60 166	97.09 146	92.99 171

v1240		97.43 75	96.87 92	98.09 40	98.25 101	97.92 98	99.02 28	97.06 123	94.77 86	99.09 7	99.68 6	98.51 83	97.78 41	95.25 148	95.81 133	97.32 137	96.13 122

v1921920		97.50 69	97.00 85	98.07 47	98.20 106	97.94 97	99.03 27	97.06 123	95.29 67	99.01 8	99.62 11	98.73 70	97.74 43	95.52 143	95.78 135	97.39 133	96.12 123

anonymousdsp		98.85 12	98.88 11	98.83 11	98.69 79	98.20 70	99.68 1	97.35 115	97.09 21	98.98 9	99.86 1	99.43 8	98.94 3	99.28 14	99.19 13	99.33 22	99.08 4

TinyColmap		96.64 107	96.07 113	97.32 89	97.84 135	96.40 156	97.63 115	96.25 147	95.86 46	98.98 9	97.94 84	96.34 142	96.17 95	97.30 95	95.38 143	97.04 148	93.24 167

v1192		97.52 66	97.03 84	98.09 40	98.31 98	98.01 89	98.96 39	97.25 118	95.22 68	98.89 11	99.64 9	98.83 59	97.68 46	95.63 140	95.91 130	97.47 127	95.97 127

v144192		97.49 70	96.99 87	98.07 47	98.11 114	97.95 94	99.02 28	97.21 119	94.90 83	98.88 12	99.53 17	98.89 53	97.75 42	95.59 141	95.90 131	97.43 130	96.16 121

PS-CasMVS		99.08 4	98.90 10	99.28 3	99.65 3	99.56 4	99.59 6	99.39 3	96.36 33	98.83 13	99.46 21	99.09 31	98.62 10	99.51 7	99.36 8	99.63 3	98.97 6

EG-PatchMatch MVS		97.98 45	97.92 40	98.04 51	98.84 69	98.04 87	97.90 100	96.83 133	95.07 74	98.79 14	99.07 41	99.37 12	97.88 38	98.74 33	98.16 61	98.01 106	96.96 95

CP-MVSNet		98.91 11	98.61 18	99.25 4	99.63 5	99.50 6	99.55 10	99.36 5	95.53 60	98.77 15	99.11 40	98.64 74	98.57 13	99.42 11	99.28 11	99.61 4	98.78 11

PEN-MVS		99.08 4	98.95 8	99.23 5	99.65 3	99.59 2	99.64 2	99.34 6	96.68 26	98.65 16	99.43 23	99.33 14	98.47 17	99.50 8	99.32 9	99.60 5	98.79 10

v1144		97.51 67	97.05 83	98.04 51	98.26 100	97.98 91	98.88 45	97.42 109	95.38 65	98.56 17	99.59 14	99.01 41	97.65 47	95.77 137	96.06 127	97.47 127	95.56 139

DTE-MVSNet		99.03 6	98.88 11	99.21 6	99.66 2	99.59 2	99.62 5	99.34 6	96.92 22	98.52 18	99.36 29	98.98 43	98.57 13	99.49 9	99.23 12	99.56 9	98.55 23

UniMVSNet_NR-MVSNet		98.12 35	97.56 60	98.78 13	99.13 47	98.89 22	98.76 52	98.78 19	93.81 117	98.50 19	98.81 55	97.64 116	97.99 33	98.18 66	97.92 72	99.53 10	97.64 65

DU-MVS		98.23 25	97.74 53	98.81 12	99.23 34	98.77 33	98.76 52	98.88 15	94.10 109	98.50 19	98.87 51	98.32 93	97.99 33	98.40 55	98.08 67	99.49 16	97.64 65

WR-MVS		99.22 3	99.15 5	99.30 2	99.54 11	99.62 1	99.63 4	99.45 1	97.75 14	98.47 21	99.71 5	99.05 38	98.88 4	99.54 5	99.49 2	99.81 1	98.87 8

PMVS	90.51 17	97.77 54	97.98 39	97.53 79	98.68 80	98.14 78	97.67 110	97.03 125	96.43 29	98.38 22	98.72 62	97.03 131	94.44 130	99.37 12	99.30 10	98.98 42	96.86 101
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
WR-MVS_H		98.97 9	98.82 13	99.14 8	99.56 9	99.56 4	99.54 11	99.42 2	96.07 38	98.37 23	99.34 30	99.09 31	98.43 18	99.45 10	99.41 5	99.53 10	98.86 9

gm-plane-assit		91.85 179	87.91 190	96.44 132	99.14 45	98.25 68	99.02 28	97.38 111	95.57 56	98.31 24	99.34 30	51.00 219	88.93 184	93.16 176	91.57 180	95.85 172	86.50 198

pmmvs-eth3d		96.84 97	96.22 108	97.56 76	97.63 147	96.38 159	98.74 55	96.91 129	94.63 92	98.26 25	99.43 23	98.28 94	96.58 81	94.52 158	95.54 138	97.24 139	94.75 147

DeepC-MVS	96.08 5	98.58 17	98.49 23	98.68 17	99.37 27	98.52 58	99.01 32	98.17 54	97.17 20	98.25 26	99.56 15	99.62 4	98.29 22	98.40 55	98.09 64	98.97 43	98.08 44
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
v10		97.64 58	97.26 69	98.08 44	98.07 115	98.56 55	98.86 47	98.18 52	94.48 100	98.24 27	99.56 15	98.98 43	97.72 44	96.05 133	96.26 120	97.42 131	96.93 96

v2v482		97.33 77	96.84 93	97.90 59	98.19 107	97.83 100	98.74 55	97.44 106	95.42 64	98.23 28	99.46 21	98.84 58	97.46 52	95.51 144	96.10 125	97.36 135	94.72 148

PM-MVS		96.85 96	96.62 101	97.11 98	97.13 167	96.51 152	98.29 77	94.65 187	94.84 84	98.12 29	98.59 66	97.20 126	97.41 54	96.24 128	96.41 115	97.09 146	96.56 110

EIA-MVS		96.23 118	94.85 140	97.84 64	99.08 54	98.21 69	97.69 109	98.03 67	85.68 198	98.09 30	91.75 185	97.07 130	95.66 110	97.58 86	97.72 79	98.47 79	95.91 128

MVS_0304		97.18 85	96.84 93	97.58 75	99.15 42	98.19 71	98.11 87	97.81 83	92.36 137	98.06 31	97.43 96	99.06 35	94.24 134	96.80 112	96.54 111	98.12 101	97.52 74

Effi-MVS+		96.46 111	95.28 127	97.85 63	98.64 82	97.16 132	97.15 142	98.75 20	90.27 160	98.03 32	93.93 164	96.21 143	96.55 83	96.34 124	96.69 106	97.97 109	96.33 117

PHI-MVS		97.44 73	97.17 74	97.74 71	98.14 111	98.41 63	98.03 92	97.50 98	92.07 141	98.01 33	97.33 100	98.62 77	96.02 98	98.34 62	98.21 57	98.76 63	97.24 90

TDRefinement		99.00 8	99.13 6	98.86 10	98.99 61	99.05 16	99.58 7	98.29 42	98.96 4	97.96 34	99.40 26	98.67 71	98.87 5	99.60 3	99.46 4	99.46 18	98.74 13

UniMVSNet (Re)		98.23 25	97.85 45	98.67 18	99.15 42	98.87 23	98.74 55	98.84 17	94.27 107	97.94 35	99.01 42	98.39 89	97.82 40	98.35 60	98.29 55	99.51 15	97.78 56

UniMVSNet_ETH3D		98.93 10	99.20 3	98.63 20	99.54 11	99.33 7	98.73 58	99.37 4	98.87 5	97.86 36	99.27 34	99.78 2	96.59 79	99.52 6	99.40 6	99.67 2	98.21 39

DeepC-MVS_fast	95.38 6	97.53 65	97.30 68	97.79 68	98.83 70	97.64 110	98.18 82	97.14 121	95.57 56	97.83 37	97.10 107	98.80 63	96.53 84	97.41 91	97.32 89	98.24 94	97.26 87
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
COLMAP_ROB	96.84 2	98.75 14	98.82 13	98.66 19	99.14 45	98.79 31	99.30 15	97.67 87	98.33 8	97.82 38	99.20 37	99.18 29	98.76 6	99.27 15	98.96 19	99.29 26	98.03 45
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CS-MVS		96.24 116	94.67 143	98.08 44	99.10 51	98.62 48	98.25 80	98.12 57	87.70 183	97.76 39	88.13 199	96.08 146	96.39 88	97.64 84	98.10 63	98.84 60	96.39 115

CANet		96.81 98	96.50 102	97.17 97	99.10 51	97.96 93	97.86 104	97.51 96	91.30 146	97.75 40	97.64 90	97.89 109	93.39 147	96.98 108	96.73 104	97.40 132	96.99 94

thisisatest0515		97.82 52	97.67 55	97.99 57	98.49 85	98.07 83	98.48 69	98.06 62	95.35 66	97.74 41	98.83 54	97.61 117	96.74 73	97.53 87	98.30 54	98.43 84	98.01 47

PVSNet_Blended_VisFu		97.44 73	97.14 77	97.79 68	99.15 42	98.44 62	98.32 76	97.66 88	93.74 119	97.73 42	98.79 56	96.93 134	95.64 112	97.69 78	96.91 99	98.25 93	97.50 76

v8		97.51 67	97.16 75	97.91 58	97.99 121	98.48 61	98.76 52	98.17 54	94.54 98	97.69 43	99.48 20	98.76 68	97.63 49	96.10 132	96.14 122	97.20 141	96.64 107

EU-MVSNet		96.03 122	96.23 107	95.80 146	95.48 198	94.18 180	98.99 33	91.51 197	97.22 19	97.66 44	99.15 39	98.51 83	98.08 28	95.92 135	92.88 173	93.09 186	95.72 136

MTMP										97.63 45		99.03 39

ETV-MVS		96.54 110	95.27 128	98.02 54	99.07 56	97.48 121	98.16 85	98.19 50	87.33 188	97.58 46	92.67 175	95.93 149	96.22 92	98.49 53	98.46 39	98.91 50	96.50 113

Fast-Effi-MVS+		96.80 99	95.92 119	97.84 64	98.57 83	97.46 122	98.06 89	98.24 45	89.64 168	97.57 47	96.45 117	97.35 123	96.73 74	97.22 97	96.64 108	97.86 112	96.65 106

TranMVSNet+NR-MVSNet		98.45 18	98.22 29	98.72 16	99.32 32	99.06 14	98.99 33	98.89 14	95.52 61	97.53 48	99.42 25	98.83 59	98.01 32	98.55 47	98.34 50	99.57 8	97.80 55

DeepPCF-MVS	94.55 10	97.05 89	97.13 80	96.95 108	96.06 185	97.12 136	98.01 94	95.44 170	95.18 70	97.50 49	97.86 86	98.08 102	97.31 60	97.23 96	97.00 96	97.36 135	97.45 78

MDTV_nov1_ep13_2view		94.39 155	93.34 161	95.63 150	97.23 166	95.33 173	97.76 106	96.84 132	94.55 95	97.47 50	98.96 44	97.70 113	93.88 139	92.27 183	86.81 193	90.56 195	87.73 194

MVS_111021_LR		96.86 95	96.72 98	97.03 105	97.80 139	97.06 139	97.04 144	95.51 169	94.55 95	97.47 50	97.35 99	97.68 114	96.66 75	97.11 101	96.73 104	97.69 119	96.57 108

NR-MVSNet		98.00 41	97.88 43	98.13 38	98.33 93	98.77 33	98.83 49	98.88 15	94.10 109	97.46 52	98.87 51	98.58 79	95.78 102	99.13 22	98.16 61	99.52 12	97.53 73

MTAPA										97.43 53		99.27 20

zzz-MVS		98.14 32	97.78 50	98.55 23	99.58 6	98.58 52	98.98 35	98.48 26	95.98 42	97.39 54	94.73 148	99.27 20	97.98 35	98.81 31	98.64 36	98.90 51	98.46 28

EPNet_dtu		93.45 169	92.51 170	94.55 172	98.39 91	91.67 197	95.46 187	97.50 98	86.56 193	97.38 55	93.52 167	94.20 164	85.82 199	93.31 174	92.53 175	92.72 188	95.76 134
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CSCG		98.45 18	98.61 18	98.26 35	99.11 49	99.06 14	98.17 84	97.49 100	97.93 12	97.37 56	98.88 49	99.29 16	98.10 27	98.40 55	97.51 81	99.32 24	99.16 3

IterMVS-SCA-FT		95.16 141	93.95 153	96.56 127	97.89 128	96.69 149	96.94 147	96.05 152	93.06 131	97.35 57	98.79 56	91.45 175	95.93 101	92.78 179	91.00 183	95.22 176	93.91 162

V42		97.10 87	96.97 88	97.26 91	97.64 145	97.60 112	98.45 72	95.99 153	94.44 101	97.35 57	99.40 26	98.63 76	97.34 58	96.33 126	96.38 117	96.82 158	96.00 125

ACMH	95.26 7	98.75 14	98.93 9	98.54 24	98.86 66	99.01 18	99.58 7	98.10 60	98.67 6	97.30 59	99.18 38	99.42 9	98.40 19	99.19 18	98.86 25	98.99 41	98.19 40
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs4		95.37 137	94.25 149	96.67 121	97.01 170	95.28 174	97.60 116	96.07 150	93.11 128	97.29 60	98.09 83	94.23 163	95.21 116	91.56 189	93.91 163	96.82 158	93.59 165

CANet_DTU		94.96 144	94.62 145	95.35 156	98.03 116	96.11 164	96.92 149	95.60 167	88.59 175	97.27 61	95.27 137	96.50 139	88.77 186	95.53 142	95.59 137	95.54 174	94.78 146

HPM-MVS++		97.56 61	97.11 81	98.09 40	99.18 39	97.95 94	98.57 64	98.20 48	94.08 111	97.25 62	95.96 129	98.81 62	97.13 63	97.51 88	97.30 91	98.21 95	98.15 42

3Dnovator+	96.20 4	97.58 60	97.14 77	98.10 39	98.98 62	97.85 99	98.60 63	98.33 39	96.41 31	97.23 63	94.66 151	97.26 125	96.91 70	97.91 68	97.87 74	98.53 75	98.03 45

SCA		91.15 185	87.65 192	95.23 162	96.15 183	95.68 170	96.68 156	98.18 52	90.46 157	97.21 64	92.44 179	80.17 197	93.51 146	86.04 203	83.58 199	89.68 200	85.21 200

MP-MVS		97.98 45	97.53 61	98.50 25	99.56 9	98.58 52	98.97 36	98.39 34	93.49 120	97.14 65	96.08 125	99.23 26	98.06 29	98.50 52	98.38 47	98.90 51	98.44 30
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
3Dnovator	96.31 3	97.22 84	97.19 73	97.25 94	98.14 111	97.95 94	98.03 92	96.77 136	96.42 30	97.14 65	95.11 139	97.59 118	95.14 119	97.79 74	97.72 79	98.26 91	97.76 61

MVS_111021_HR		97.27 79	97.11 81	97.46 84	98.46 87	97.82 104	97.50 121	96.86 131	94.97 79	97.13 67	96.99 108	98.39 89	96.82 72	97.65 83	97.38 84	98.02 105	96.56 110

UA-Net		98.66 16	98.60 21	98.73 15	99.83 1	99.28 9	98.56 66	99.24 8	96.04 39	97.12 68	98.44 72	98.95 48	98.17 26	99.15 21	99.00 18	99.48 17	99.33 2

v148		96.99 93	96.70 99	97.34 87	97.89 128	97.23 128	98.33 75	96.96 126	95.57 56	97.12 68	98.99 43	99.40 10	97.23 61	96.22 129	95.45 140	96.50 163	94.02 160

OMC-MVS		97.23 83	97.21 72	97.25 94	97.85 130	97.52 119	97.92 98	95.77 164	95.83 48	97.09 70	97.86 86	98.52 82	96.62 77	97.51 88	96.65 107	98.26 91	96.57 108

Vis-MVSNet		98.01 39	98.42 24	97.54 78	96.89 172	98.82 29	99.14 22	97.59 90	96.30 34	97.04 71	99.26 35	98.83 59	96.01 99	98.73 34	98.21 57	98.58 72	98.75 12
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ACMMPR		98.31 22	98.07 36	98.60 21	99.58 6	98.83 27	99.09 24	98.48 26	96.25 35	97.03 72	96.81 109	99.09 31	98.39 20	98.55 47	98.45 42	99.01 38	98.53 26

CP-MVS		98.00 41	97.57 59	98.50 25	99.47 21	98.56 55	98.91 42	98.38 35	94.71 88	97.01 73	95.20 138	99.06 35	98.20 24	98.61 44	98.46 39	99.02 36	98.40 32

LS3D		97.93 49	97.80 47	98.08 44	99.20 37	98.77 33	98.89 44	97.92 74	96.59 28	96.99 74	96.71 112	97.14 129	96.39 88	99.04 23	98.96 19	99.10 35	97.39 81

Baseline_NR-MVSNet		98.17 29	97.90 42	98.48 27	99.23 34	98.59 50	98.83 49	98.73 21	93.97 114	96.95 75	99.66 7	98.23 98	97.90 37	98.40 55	99.06 16	99.25 27	97.42 80

ACMMP_NAP		98.12 35	98.08 35	98.18 36	99.34 29	98.74 41	98.97 36	98.00 69	95.13 72	96.90 76	97.54 94	99.27 20	97.18 62	98.72 36	98.45 42	98.68 65	98.69 15

ACMM	94.29 11	98.12 35	97.71 54	98.59 22	99.51 17	98.58 52	99.24 17	98.25 44	96.22 37	96.90 76	95.01 142	98.89 53	98.52 16	98.66 41	98.32 53	99.13 31	98.28 38
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs5		95.70 130	95.22 129	96.26 135	96.55 180	97.24 127	97.50 121	94.99 180	90.95 152	96.87 78	98.47 71	97.40 121	94.45 129	92.86 178	94.98 147	97.23 140	94.64 150

MDA-MVSNet-bldmvs		95.45 134	95.20 130	95.74 147	94.24 204	96.38 159	97.93 97	94.80 182	95.56 59	96.87 78	98.29 76	95.24 154	96.50 85	98.65 42	90.38 185	94.09 180	91.93 175

PatchmatchNet		89.98 189	86.23 202	94.36 175	96.56 179	91.90 196	96.07 171	96.72 137	90.18 161	96.87 78	93.36 171	78.06 201	91.46 158	84.71 207	81.40 205	88.45 203	83.97 206
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pmmvs6		98.77 13	99.35 2	98.09 40	98.32 95	98.92 20	98.57 64	99.03 12	99.36 1	96.86 81	99.77 3	99.86 1	96.20 94	99.56 4	99.39 7	99.59 6	98.61 20

PGM-MVS		97.82 52	97.25 70	98.48 27	99.54 11	98.75 40	99.02 28	98.35 38	92.41 136	96.84 82	95.39 135	98.99 42	98.24 23	98.43 54	98.34 50	98.90 51	98.41 31

SMA-MVS		98.13 34	98.22 29	98.02 54	99.44 24	98.73 42	98.24 81	97.87 78	95.22 68	96.76 83	98.66 65	99.35 13	97.03 67	98.53 50	98.39 46	98.80 61	98.69 15

TSAR-MVS + MP.		98.15 31	98.23 28	98.06 49	98.47 86	98.16 76	99.23 18	96.87 130	95.58 55	96.72 84	98.41 73	99.06 35	98.05 30	98.99 25	98.90 22	99.00 39	98.51 27
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SD-MVS		97.84 50	97.78 50	97.90 59	98.33 93	98.06 84	97.95 96	97.80 84	96.03 41	96.72 84	97.57 92	99.18 29	97.50 51	97.88 69	97.08 94	99.11 33	98.68 17
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
MAR-MVS		95.51 132	94.49 148	96.71 118	97.92 126	96.40 156	96.72 154	98.04 66	86.74 192	96.72 84	92.52 178	95.14 155	94.02 138	96.81 111	96.54 111	96.85 153	97.25 88
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
IterMVS-LS		96.35 112	95.85 120	96.93 110	97.53 151	98.00 90	97.37 128	97.97 71	95.49 63	96.71 87	98.94 45	93.23 167	94.82 124	93.15 177	95.05 146	97.17 143	97.12 92
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
OPM-MVS		98.01 39	98.01 38	98.00 56	99.11 49	98.12 79	98.68 59	97.72 85	96.65 27	96.68 88	98.40 74	99.28 19	97.44 53	98.20 63	97.82 78	98.40 85	97.58 70

TAPA-MVS	93.96 13	96.79 100	96.70 99	96.90 112	97.64 145	97.58 113	97.54 119	94.50 189	95.14 71	96.64 89	96.76 111	97.90 108	96.63 76	95.98 134	96.14 122	98.45 80	97.39 81
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MIMVSNet1		98.22 28	98.51 22	97.87 61	99.40 26	98.82 29	99.31 14	98.53 24	97.39 17	96.59 90	99.31 32	99.23 26	94.76 125	98.93 28	98.67 33	98.63 66	97.25 88

tpm		89.84 191	86.81 198	93.36 181	96.60 178	91.92 195	95.02 194	97.39 110	86.79 191	96.54 91	95.03 140	69.70 214	87.66 191	88.79 197	86.19 194	86.95 208	89.27 188

HFP-MVS		98.17 29	98.02 37	98.35 33	99.36 28	98.62 48	98.79 51	98.46 30	96.24 36	96.53 92	97.13 106	98.98 43	98.02 31	98.20 63	98.42 44	98.95 47	98.54 24

EPNet		94.33 158	93.52 159	95.27 159	98.81 71	94.71 178	96.77 152	98.20 48	88.12 181	96.53 92	92.53 177	91.19 176	85.25 204	95.22 149	95.26 144	96.09 171	97.63 69
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OpenMVS	94.63 9	95.75 129	95.04 136	96.58 125	97.85 130	97.55 117	96.71 155	96.07 150	90.15 163	96.47 94	90.77 194	95.95 148	94.41 131	97.01 107	96.95 97	98.00 107	96.90 97

CR-MVSNet		91.94 178	88.50 188	95.94 142	96.14 184	92.08 191	95.23 192	98.47 28	84.30 204	96.44 95	94.58 152	75.57 205	92.92 150	90.22 195	92.22 176	96.43 166	90.56 181

Patchmtry						92.70 186	95.23 192	98.47 28		96.44 95

PatchT		91.40 182	88.54 187	94.74 168	91.48 212	92.18 190	97.42 126	97.51 96	84.96 200	96.44 95	94.16 159	75.47 206	92.92 150	90.22 195	92.22 176	92.66 191	90.56 181

IterMVS		94.48 153	93.46 160	95.66 149	97.52 152	96.43 153	97.20 138	94.73 185	92.91 134	96.44 95	98.75 61	91.10 177	94.53 128	92.10 185	90.10 187	93.51 183	92.84 173
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
XVS					99.48 19	98.76 36	99.22 19			96.40 99		98.78 65				98.94 48

X-MVStestdata					99.48 19	98.76 36	99.22 19			96.40 99		98.78 65				98.94 48

X-MVS		97.60 59	97.00 85	98.29 34	99.50 18	98.76 36	98.90 43	98.37 36	94.67 91	96.40 99	91.47 187	98.78 65	97.60 50	98.55 47	98.50 37	98.96 45	98.29 35

TransMVSNet (Re)		98.23 25	98.72 15	97.66 72	98.22 104	98.73 42	98.66 60	98.03 67	98.60 7	96.40 99	99.60 12	98.24 96	95.26 115	99.19 18	99.05 17	99.36 19	97.64 65

ACMMP		97.99 43	97.60 58	98.45 29	99.53 15	98.83 27	99.13 23	98.30 40	94.57 94	96.39 103	95.32 136	98.95 48	98.37 21	98.61 44	98.47 38	99.00 39	98.45 29
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
CLD-MVS		96.73 103	96.92 89	96.51 128	98.70 76	97.57 115	97.64 113	92.07 195	93.10 130	96.31 104	98.29 76	99.02 40	95.99 100	97.20 98	96.47 113	98.37 87	96.81 103
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PVSNet_BlendedMVS		95.44 135	95.09 132	95.86 144	97.31 162	97.13 134	96.31 166	95.01 178	88.55 176	96.23 105	94.55 155	97.75 111	92.56 156	96.42 121	95.44 141	97.71 116	95.81 130

PVSNet_Blended		95.44 135	95.09 132	95.86 144	97.31 162	97.13 134	96.31 166	95.01 178	88.55 176	96.23 105	94.55 155	97.75 111	92.56 156	96.42 121	95.44 141	97.71 116	95.81 130

QAPM		97.04 90	97.14 77	96.93 110	97.78 142	98.02 88	97.36 130	96.72 137	94.68 90	96.23 105	97.21 102	97.68 114	95.70 106	97.37 92	97.24 93	97.78 115	97.77 59

CNLPA		96.24 116	95.97 116	96.57 126	97.48 156	97.10 138	96.75 153	94.95 181	94.92 82	96.20 108	94.81 147	96.61 137	96.25 90	96.94 109	95.64 136	97.79 114	95.74 135

MSLP-MVS++		96.66 106	96.46 105	96.89 113	98.02 117	97.71 108	95.57 181	96.96 126	94.36 104	96.19 109	91.37 188	98.24 96	97.07 65	97.69 78	97.89 73	97.52 125	97.95 48

pm-mvs1		98.14 32	98.66 17	97.53 79	97.93 125	98.49 60	98.14 86	98.19 50	97.95 11	96.17 110	99.63 10	98.85 56	95.41 113	98.91 29	98.89 23	99.34 21	97.86 53

tfpnnormal		97.66 56	97.79 48	97.52 81	98.32 95	98.53 57	98.45 72	97.69 86	97.59 16	96.12 111	97.79 88	96.70 135	95.69 107	98.35 60	98.34 50	98.85 58	97.22 91

NCCC		96.56 109	95.68 121	97.59 74	99.04 58	97.54 118	97.67 110	97.56 94	94.84 84	96.10 112	87.91 200	98.09 101	96.98 69	97.20 98	96.80 103	98.21 95	97.38 84

ACMP	94.03 12	97.97 47	97.61 57	98.39 31	99.43 25	98.51 59	98.97 36	98.06 62	94.63 92	96.10 112	96.12 124	99.20 28	98.63 9	98.68 39	98.20 60	99.14 30	97.93 50
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LGP-MVS_train		97.96 48	97.53 61	98.45 29	99.45 22	98.64 47	99.09 24	98.27 43	92.99 132	96.04 114	96.57 115	99.29 16	98.66 8	98.73 34	98.42 44	99.19 29	98.09 43

Effi-MVS+-dtu		95.94 125	95.08 134	96.94 109	98.54 84	97.38 123	96.66 157	97.89 76	88.68 173	95.92 115	92.90 174	97.28 124	94.18 136	96.68 117	96.13 124	98.45 80	96.51 112

AdaColmap		95.85 127	94.65 144	97.26 91	98.70 76	97.20 129	97.33 131	97.30 117	91.28 148	95.90 116	88.16 198	96.17 144	96.60 78	97.34 93	96.82 101	97.71 116	95.60 138

CPTT-MVS		97.08 88	96.25 106	98.05 50	99.21 36	98.30 66	98.54 67	97.98 70	94.28 105	95.89 117	89.57 196	98.54 81	98.18 25	97.82 73	97.32 89	98.54 73	97.91 52

SteuartSystems-ACMMP		98.06 38	97.78 50	98.39 31	99.54 11	98.79 31	98.94 40	98.42 32	93.98 113	95.85 118	96.66 114	99.25 24	98.61 11	98.71 38	98.38 47	98.97 43	98.67 18
Skip Steuart: Steuart Systems R&D Blog.
MCST-MVS		96.79 100	96.08 112	97.62 73	98.78 74	97.52 119	98.01 94	97.32 116	93.20 124	95.84 119	93.97 163	98.12 100	97.34 58	96.34 124	95.88 132	98.45 80	97.51 75

RPSCF		97.83 51	98.27 26	97.31 90	98.23 102	98.06 84	97.44 125	95.79 163	96.90 23	95.81 120	98.76 60	98.61 78	97.70 45	98.90 30	98.36 49	98.90 51	98.29 35

thisisatest0530		94.81 148	93.06 164	96.85 115	98.01 118	97.18 131	96.93 148	97.36 113	89.73 167	95.80 121	94.98 143	77.88 202	94.89 121	96.73 114	97.35 85	98.13 100	97.54 72

PatchMatch-RL		94.79 151	93.75 157	96.00 139	96.80 174	95.00 176	95.47 186	95.25 174	90.68 155	95.80 121	92.97 173	93.64 165	95.67 108	96.13 131	95.81 133	96.99 151	92.01 174

HQP-MVS		95.97 124	95.01 137	97.08 99	98.72 75	97.19 130	97.07 143	96.69 140	91.49 144	95.77 123	92.19 181	97.93 107	96.15 96	94.66 155	94.16 157	98.10 103	97.45 78

xxxxxxxxxxxxxcwj		97.26 80	97.43 63	97.05 102	98.80 72	97.83 100	96.02 172	97.44 106	94.98 77	95.74 124	97.16 103	98.45 87	95.72 104	97.85 70	97.97 70	98.60 69	97.78 56

xxxxxxxxxxxx		97.26 80	97.43 63	97.05 102	98.80 72	97.83 100	96.02 172	97.44 106	94.98 77	95.74 124	97.16 103	98.45 87	95.72 104	97.85 70	97.97 70	98.60 69	97.78 56

tttt0517		94.81 148	93.04 165	96.88 114	98.15 110	97.37 124	96.99 145	97.36 113	89.51 169	95.74 124	94.89 145	77.53 204	94.89 121	96.94 109	97.35 85	98.17 98	97.70 62

new-patchmatchnet		94.48 153	94.02 151	95.02 166	97.51 155	95.00 176	95.68 180	94.26 191	97.32 18	95.73 127	99.60 12	98.22 99	91.30 159	94.13 165	84.41 195	95.65 173	89.45 187

abl_6				96.45 131	97.79 141	97.28 126	97.16 141	96.16 149	89.92 166	95.72 128	91.59 186	97.16 128	94.37 132			97.51 126	95.49 140

PLC	92.55 15	96.10 119	95.36 124	96.96 107	98.13 113	96.88 143	96.49 161	96.67 141	94.07 112	95.71 129	91.14 189	96.09 145	96.84 71	96.70 115	96.58 110	97.92 111	96.03 124
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNVR-MVS		97.03 91	96.77 97	97.34 87	98.89 64	97.67 109	97.64 113	97.17 120	94.40 103	95.70 130	94.02 161	98.76 68	96.49 86	97.78 75	97.29 92	98.12 101	97.47 77

PCF-MVS	92.69 14	95.98 123	95.05 135	97.06 101	98.43 89	97.56 116	97.76 106	96.65 142	89.95 165	95.70 130	96.18 123	98.48 85	95.74 103	93.64 169	93.35 170	98.09 104	96.18 120
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ET-MVSNet_ETH3D		93.18 171	90.80 182	95.95 141	96.05 186	96.07 166	96.92 149	96.51 144	89.34 170	95.63 132	94.08 160	72.31 213	93.13 148	94.33 162	94.83 150	97.44 129	94.65 149

MSDG		96.27 115	96.17 111	96.38 134	97.85 130	96.27 162	96.55 160	94.41 190	94.55 95	95.62 133	97.56 93	97.80 110	96.22 92	97.17 100	96.27 119	97.67 121	93.60 164

DCV-MVSNet		97.56 61	97.63 56	97.47 83	98.41 90	99.12 10	98.63 61	98.57 22	95.71 51	95.60 134	93.79 166	98.01 106	94.25 133	99.16 20	98.88 24	99.35 20	98.74 13

RPMNet		90.52 187	86.27 201	95.48 154	95.95 189	92.08 191	95.55 185	98.12 57	84.30 204	95.60 134	87.49 201	72.78 210	91.24 160	87.93 198	89.34 188	96.41 167	89.98 184

TSAR-MVS + ACMM		97.54 63	97.79 48	97.26 91	98.23 102	98.10 82	97.71 108	97.88 77	95.97 43	95.57 136	98.71 63	98.57 80	97.36 56	97.74 76	96.81 102	96.83 156	98.59 21

DPE-MVS		97.99 43	98.12 33	97.84 64	98.65 81	98.86 24	98.86 47	98.05 65	94.18 108	95.49 137	98.90 47	99.33 14	97.11 64	98.53 50	98.65 35	98.86 57	98.39 34

MDTV_nov1_ep13		90.30 188	87.32 196	93.78 178	96.00 188	92.97 185	95.46 187	95.39 171	88.61 174	95.41 138	94.45 157	80.39 196	89.87 178	86.58 201	83.54 200	90.56 195	84.71 202

DELS-MVS		96.90 94	97.24 71	96.50 129	97.85 130	98.18 72	97.88 103	95.92 156	93.48 121	95.34 139	98.86 53	98.94 50	94.03 137	97.33 94	97.04 95	98.00 107	96.85 102
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
TSAR-MVS + COLMAP		96.05 121	95.94 117	96.18 137	97.46 157	96.41 155	97.26 136	95.83 160	94.69 89	95.30 140	98.31 75	96.52 138	94.71 126	95.48 145	94.87 148	96.54 162	95.33 142

TSAR-MVS + GP.		97.26 80	97.33 67	97.18 96	98.21 105	98.06 84	96.38 163	97.66 88	93.92 116	95.23 141	98.48 70	98.33 92	97.41 54	97.63 85	97.35 85	98.18 97	97.57 71

APD-MVS		97.47 72	97.16 75	97.84 64	99.32 32	98.39 64	98.47 71	98.21 47	92.08 140	95.23 141	96.68 113	98.90 51	96.99 68	98.20 63	98.21 57	98.80 61	97.67 63
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
train_agg		96.68 104	95.93 118	97.56 76	99.08 54	97.16 132	98.44 74	97.37 112	91.12 150	95.18 143	95.43 134	98.48 85	97.36 56	96.48 120	95.52 139	97.95 110	97.34 85

APDe-MVS		98.29 23	98.42 24	98.14 37	99.45 22	98.90 21	99.18 21	98.30 40	95.96 44	95.13 144	98.79 56	99.25 24	97.92 36	98.80 32	98.71 30	98.85 58	98.54 24

CDPH-MVS		96.68 104	95.99 115	97.48 82	99.13 47	97.64 110	98.08 88	97.46 102	90.56 156	95.13 144	94.87 146	98.27 95	96.56 82	97.09 102	96.45 114	98.54 73	97.08 93

gg-mvs-nofinetune		94.13 160	93.93 154	94.37 173	97.99 121	95.86 168	95.45 189	99.22 9	97.61 15	95.10 146	99.50 19	84.50 186	81.73 207	95.31 147	94.12 159	96.71 161	90.59 180

DI_MVS_plusplus_trai		95.48 133	94.51 146	96.61 122	97.13 167	97.30 125	98.05 91	96.79 135	93.75 118	95.08 147	96.38 118	89.76 181	94.95 120	93.97 168	94.82 152	97.64 123	95.63 137

GA-MVS		94.18 159	92.98 166	95.58 152	97.36 159	96.42 154	96.21 169	95.86 157	90.29 159	95.08 147	96.19 122	85.37 185	92.82 153	94.01 167	94.14 158	96.16 170	94.41 155

canonicalmvs		97.11 86	96.88 90	97.38 86	98.34 92	98.72 44	97.52 120	97.94 72	95.60 53	95.01 149	94.58 152	94.50 160	96.59 79	97.84 72	98.03 68	98.90 51	98.91 7

HyFIR lowres test		95.05 142	93.54 158	96.81 116	97.81 138	96.88 143	98.18 82	97.46 102	94.28 105	94.98 150	96.57 115	92.89 169	96.15 96	90.90 194	91.87 179	96.28 168	91.35 176

MVS-HIRNet		88.72 197	86.49 199	91.33 198	91.81 210	85.66 210	87.02 213	96.25 147	81.48 211	94.82 151	96.31 121	92.14 173	90.32 172	87.60 199	83.82 197	87.74 205	78.42 210

Anonymous20231211		97.49 70	97.91 41	97.00 106	98.31 98	98.72 44	98.27 78	97.84 81	94.76 87	94.77 152	98.14 81	98.38 91	93.60 143	98.96 27	98.66 34	99.22 28	97.77 59

UGNet		96.79 100	97.82 46	95.58 152	97.57 150	98.39 64	98.48 69	97.84 81	95.85 47	94.68 153	97.91 85	99.07 34	87.12 194	97.71 77	97.51 81	97.80 113	98.29 35
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
FPMVS		94.70 152	94.99 138	94.37 173	95.84 191	93.20 184	96.00 174	91.93 196	95.03 75	94.64 154	94.68 149	93.29 166	90.95 164	98.07 67	97.34 88	96.85 153	93.29 166

DPM-MVS		94.86 146	93.90 155	95.99 140	98.19 107	96.52 151	96.29 168	95.95 154	93.11 128	94.61 155	88.17 197	96.44 140	93.77 142	93.33 172	93.54 168	97.11 145	96.22 119

pmmvs3		91.20 183	91.40 180	90.96 199	91.71 211	91.08 198	95.41 190	81.34 210	87.36 187	94.57 156	95.02 141	94.30 162	90.42 170	94.28 163	89.26 189	92.30 192	88.49 192

DWT-MVSNet_training		86.69 203	81.24 209	93.05 185	95.31 200	92.06 193	95.75 178	91.51 197	84.32 203	94.49 157	83.46 204	55.37 218	90.81 166	82.76 209	83.19 202	90.45 197	87.52 195

FC-MVSNet-train		97.65 57	98.16 31	97.05 102	98.85 67	98.85 25	99.34 13	98.08 61	94.50 99	94.41 158	99.21 36	98.80 63	92.66 154	98.98 26	98.85 26	98.96 45	97.94 49

tpm cat1		87.19 201	82.78 208	92.33 192	95.66 193	90.61 201	94.19 202	95.27 173	86.97 189	94.38 159	90.91 191	69.40 215	87.21 193	79.57 211	77.82 208	87.25 207	84.18 204

DVP-MVS		98.27 24	98.61 18	97.87 61	99.17 40	99.03 17	99.07 26	98.17 54	96.75 25	94.35 160	98.92 46	99.58 6	97.86 39	98.67 40	98.70 31	98.63 66	98.63 19

CMPMVS	71.81 19	92.34 175	92.85 167	91.75 195	92.70 208	90.43 202	88.84 211	88.56 201	85.87 197	94.35 160	90.98 190	95.89 150	91.14 161	96.14 130	94.83 150	94.93 179	95.78 133
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
baseline2		92.06 176	89.82 185	94.68 170	97.32 160	95.72 169	94.97 196	95.08 176	84.75 201	94.34 162	90.68 195	77.75 203	90.13 174	93.38 170	93.58 167	96.25 169	92.90 172

CHOSEN 280x420		91.55 181	90.27 184	93.05 185	94.61 202	88.01 209	96.56 159	94.62 188	88.04 182	94.20 163	92.66 176	86.60 183	90.82 165	95.06 152	91.89 178	87.49 206	89.61 186

thres400		94.04 163	91.94 175	96.50 129	97.98 123	97.82 104	97.66 112	96.96 126	90.96 151	94.20 163	83.24 205	82.82 191	93.80 140	96.50 119	98.09 64	98.38 86	94.15 157

ACMH+	94.90 8	98.40 21	98.71 16	98.04 51	98.93 63	98.84 26	99.30 15	97.86 79	97.78 13	94.19 165	98.77 59	99.39 11	98.61 11	99.33 13	99.07 14	99.33 22	97.81 54

MSP-MVS		97.67 55	97.88 43	97.43 85	99.34 29	98.99 19	98.87 46	98.12 57	95.63 52	94.16 166	97.45 95	99.50 7	96.44 87	96.35 123	98.70 31	97.65 122	98.57 22

MVS_Test		95.34 138	94.88 139	95.89 143	96.93 171	96.84 147	96.66 157	97.08 122	90.06 164	94.02 167	97.61 91	96.64 136	93.59 144	92.73 181	94.02 161	97.03 149	96.24 118

baseline		94.07 161	94.50 147	93.57 180	96.34 182	93.40 183	95.56 184	92.39 194	92.07 141	94.00 168	98.24 79	97.51 119	89.19 181	91.75 187	92.72 174	93.96 182	95.79 132

thres600view7		94.34 156	92.31 172	96.70 119	98.19 107	98.12 79	97.85 105	97.45 104	91.49 144	93.98 169	84.27 203	82.02 193	94.24 134	97.04 103	98.76 29	98.49 77	94.47 153

thres200		93.98 165	91.90 176	96.40 133	97.66 143	98.12 79	97.20 138	97.45 104	90.16 162	93.82 170	83.08 206	83.74 189	93.80 140	97.04 103	97.48 83	98.49 77	93.70 163

MS-PatchMatch		94.84 147	94.76 141	94.94 167	96.38 181	94.69 179	95.90 175	94.03 192	92.49 135	93.81 171	95.79 131	96.38 141	94.54 127	94.70 154	94.85 149	94.97 178	94.43 154

PMMVS		91.67 180	91.47 179	91.91 194	89.43 213	88.61 208	94.99 195	85.67 206	87.50 186	93.80 172	94.42 158	94.88 156	90.71 168	92.26 184	92.96 172	96.83 156	89.65 185

CHOSEN 1792x2688		94.98 143	94.69 142	95.31 157	97.27 164	95.58 171	97.90 100	95.56 168	95.03 75	93.77 173	95.65 132	99.29 16	95.30 114	91.51 190	91.28 182	92.05 193	94.50 152

Anonymous20231206		95.69 131	95.68 121	95.70 148	98.32 95	96.95 141	97.37 128	96.65 142	93.33 122	93.61 174	98.70 64	98.03 104	91.04 163	95.07 151	94.59 155	97.20 141	93.09 170

IB-MVS	92.44 16	93.33 170	92.15 174	94.70 169	97.42 158	96.39 158	95.57 181	94.67 186	86.40 196	93.59 175	78.28 210	95.76 151	89.59 180	95.88 136	95.98 128	97.39 133	96.34 116
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
thres100view900		92.93 172	90.89 181	95.31 157	97.52 152	96.82 148	96.41 162	95.08 176	87.65 184	93.56 176	83.03 207	84.12 187	91.12 162	94.53 156	96.91 99	98.17 98	93.21 168

tfpn200view9		93.80 167	91.75 177	96.20 136	97.52 152	98.15 77	97.48 123	97.47 101	87.65 184	93.56 176	83.03 207	84.12 187	92.62 155	97.04 103	98.09 64	98.52 76	94.17 156

CDS-MVSNet		94.91 145	95.17 131	94.60 171	97.85 130	96.21 163	96.90 151	96.39 145	90.81 153	93.40 178	97.24 101	94.54 159	85.78 200	96.25 127	96.15 121	97.26 138	95.01 145
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+-dtu		94.34 156	93.26 163	95.62 151	97.82 136	95.97 167	95.86 176	99.01 13	86.88 190	93.39 179	90.83 192	95.46 152	90.61 169	94.46 160	94.68 153	97.01 150	94.51 151

EPP-MVSNet		97.29 78	96.88 90	97.76 70	98.70 76	99.10 13	98.92 41	98.36 37	95.12 73	93.36 180	97.39 97	91.00 178	97.65 47	98.72 36	98.91 21	99.58 7	97.92 51

tpmrst		87.60 200	84.13 207	91.66 196	95.65 194	89.73 206	93.77 203	94.74 184	88.85 172	93.35 181	95.60 133	72.37 212	87.40 192	81.24 210	78.19 207	85.02 211	82.90 209

dps		88.36 199	84.32 206	93.07 184	93.86 206	92.29 189	94.89 197	95.93 155	83.50 206	93.13 182	91.87 184	67.79 216	90.32 172	85.99 204	83.22 201	90.28 198	85.56 199

FMVSNet1		97.40 76	98.09 34	96.60 123	97.80 139	98.76 36	98.26 79	98.50 25	96.79 24	93.13 182	99.28 33	98.64 74	92.90 152	97.67 80	97.86 75	99.02 36	97.64 65

CostFormer		89.06 196	85.65 203	93.03 187	95.88 190	92.40 188	95.30 191	95.86 157	86.49 195	93.12 184	93.40 170	74.18 208	88.25 188	82.99 208	81.46 204	89.77 199	88.66 191

CVMVSNet		94.01 164	94.25 149	93.73 179	94.36 203	92.44 187	97.45 124	88.56 201	95.59 54	93.06 185	98.88 49	90.03 180	94.84 123	94.08 166	93.45 169	94.09 180	95.31 143

MVSTER		91.97 177	90.31 183	93.91 177	96.81 173	96.91 142	94.22 200	95.64 166	84.98 199	92.98 186	93.42 168	72.56 211	86.64 198	95.11 150	93.89 164	97.16 144	95.31 143

diffmvs		95.86 126	96.21 109	95.44 155	97.25 165	96.85 146	96.99 145	95.23 175	94.96 80	92.82 187	98.89 48	98.85 56	93.52 145	94.21 164	94.25 156	96.84 155	95.49 140

casdiffmvs		97.00 92	97.36 66	96.59 124	97.65 144	97.98 91	98.06 89	96.81 134	95.78 49	92.77 188	99.40 26	99.26 23	95.65 111	96.70 115	96.39 116	98.59 71	95.99 126

test20.03		96.08 120	96.80 95	95.25 161	99.19 38	97.58 113	97.24 137	97.56 94	94.95 81	91.91 189	98.58 67	98.03 104	87.88 190	97.43 90	96.94 98	97.69 119	94.05 159

baseline1		93.89 166	92.82 168	95.14 163	97.62 148	96.97 140	96.12 170	96.36 146	91.30 146	91.53 190	94.68 149	80.72 195	90.80 167	95.71 138	96.29 118	98.44 83	94.09 158

FMVSNet2		95.77 128	96.20 110	95.27 159	96.77 175	98.18 72	97.28 133	97.90 75	93.12 127	91.37 191	98.25 78	96.05 147	90.04 175	94.96 153	95.94 129	98.28 88	96.90 97

ADS-MVSNet		89.89 190	87.70 191	92.43 191	95.52 196	90.91 200	95.57 181	95.33 172	93.19 125	91.21 192	93.41 169	82.12 192	89.05 182	86.21 202	83.77 198	87.92 204	84.31 203

EPMVS		89.28 194	86.28 200	92.79 188	96.01 187	92.00 194	95.83 177	95.85 159	90.78 154	91.00 193	94.58 152	74.65 207	88.93 184	85.00 205	82.88 203	89.09 202	84.09 205

FC-MVSNet-test		97.54 63	98.26 27	96.70 119	98.87 65	97.79 107	98.49 68	98.56 23	96.04 39	90.39 194	99.65 8	98.67 71	95.15 117	99.23 16	99.07 14	98.73 64	97.39 81

GBi-Net		95.21 139	95.35 125	95.04 164	96.77 175	98.18 72	97.28 133	97.58 91	88.43 178	90.28 195	96.01 126	92.43 170	90.04 175	97.67 80	97.86 75	98.28 88	96.90 97

test1		95.21 139	95.35 125	95.04 164	96.77 175	98.18 72	97.28 133	97.58 91	88.43 178	90.28 195	96.01 126	92.43 170	90.04 175	97.67 80	97.86 75	98.28 88	96.90 97

FMVSNet3		94.06 162	93.85 156	94.31 176	95.46 199	97.80 106	96.34 164	97.58 91	88.43 178	90.28 195	96.01 126	92.43 170	88.67 187	91.82 186	93.96 162	97.53 124	96.50 113

IS_MVSNet		96.62 108	96.48 104	96.78 117	98.46 87	98.68 46	98.61 62	98.24 45	92.23 138	89.63 198	95.90 130	94.40 161	96.23 91	98.65 42	98.77 28	99.52 12	96.76 104

test-LLR		89.77 192	87.47 194	92.45 190	98.01 118	89.77 204	93.25 206	95.80 161	81.56 209	89.19 199	92.08 182	79.59 198	85.77 202	91.47 191	89.04 191	92.69 189	88.75 189

TESTMET0.1,1		88.60 198	87.47 194	89.93 202	94.23 205	89.77 204	93.25 206	84.47 208	81.56 209	89.19 199	92.08 182	79.59 198	85.77 202	91.47 191	89.04 191	92.69 189	88.75 189

Vis-MVSNet (Re-imp)		96.29 114	96.50 102	96.05 138	97.96 124	97.83 100	97.30 132	97.86 79	93.14 126	88.90 201	96.80 110	95.28 153	95.15 117	98.37 59	98.25 56	99.12 32	95.84 129

EMVS		86.63 204	84.48 205	89.15 204	95.51 197	83.66 212	90.19 209	86.14 205	91.78 143	88.68 202	93.83 165	81.97 194	89.05 182	92.76 180	76.09 210	85.31 210	71.28 212

testgi		94.81 148	96.05 114	93.35 182	99.06 57	96.87 145	97.57 118	96.70 139	95.77 50	88.60 203	93.19 172	98.87 55	81.21 208	97.03 106	96.64 108	96.97 152	93.99 161

N_pmnet		92.46 173	92.38 171	92.55 189	97.91 127	93.47 182	97.42 126	94.01 193	96.40 32	88.48 204	98.50 69	98.07 103	88.14 189	91.04 193	84.30 196	89.35 201	84.85 201

test-mter		89.16 195	88.14 189	90.37 201	94.79 201	91.05 199	93.60 205	85.26 207	81.65 208	88.32 205	92.22 180	79.35 200	87.03 195	92.28 182	90.12 186	93.19 185	90.29 183

FMVSNet5		89.65 193	87.60 193	92.04 193	95.63 195	96.61 150	94.82 198	94.75 183	80.11 212	87.72 206	77.73 211	73.81 209	83.81 206	95.64 139	96.08 126	95.49 175	93.21 168

E-PMN		86.94 202	85.10 204	89.09 205	95.77 192	83.54 213	89.89 210	86.55 203	92.18 139	87.34 207	94.02 161	83.42 190	89.63 179	93.32 173	77.11 209	85.33 209	72.09 211

MIMVSNet		93.68 168	93.96 152	93.35 182	97.82 136	96.08 165	96.34 164	98.46 30	91.28 148	86.67 208	94.95 144	94.87 157	84.39 205	94.53 156	94.65 154	96.45 165	91.34 177

TAMVS		92.46 173	93.34 161	91.44 197	97.03 169	93.84 181	94.68 199	90.60 199	90.44 158	85.31 209	97.14 105	93.03 168	85.78 200	94.34 161	93.67 165	95.22 176	90.93 179

new_pmnet		90.85 186	92.26 173	89.21 203	93.68 207	89.05 207	93.20 208	84.16 209	92.99 132	84.25 210	97.72 89	94.60 158	86.80 197	93.20 175	91.30 181	93.21 184	86.94 197

test0.0.03 1		91.17 184	91.50 178	90.80 200	98.01 118	95.46 172	94.22 200	95.80 161	86.55 194	81.75 211	90.83 192	87.93 182	78.48 209	94.51 159	94.11 160	96.50 163	91.08 178

tmp_tt				45.72 208	60.00 215	38.74 216	45.50 216	12.18 212	79.58 213	68.42 212	67.62 212	65.04 217	22.12 211	84.83 206	78.72 206	66.08 214

MVE	72.99 18	85.37 206	89.43 186	80.63 206	74.43 214	71.94 215	88.25 212	89.81 200	93.27 123	67.32 213	96.32 120	91.83 174	90.40 171	93.36 171	90.79 184	73.55 213	88.49 192
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX						72.99 214	80.14 214	37.34 211	83.46 207	60.13 214	84.40 202	85.48 184	86.93 196	87.22 200		79.61 212	87.32 196

PMMVS2		86.47 205	92.62 169	79.29 207	92.01 209	85.63 211	93.74 204	86.37 204	93.95 115	54.18 215	98.19 80	97.39 122	58.46 210	96.57 118	93.07 171	90.99 194	83.55 208

GG-mvs-BLEND		61.03 207	87.02 197	30.71 209	0.74 218	90.01 203	78.90 215	0.74 215	84.56 202	9.46 216	79.17 209	90.69 179	1.37 214	91.74 188	89.13 190	93.04 187	83.83 207

test123		4.41 209	5.71 211	2.88 210	1.28 217	2.21 217	3.09 219	1.65 214	6.35 215	4.98 217	8.53 214	3.88 221	3.46 212	5.79 213	5.71 211	2.85 216	7.50 214

testmvs		4.99 208	6.88 210	2.78 211	1.73 216	2.04 218	3.10 218	1.71 213	7.27 214	3.92 218	12.18 213	6.71 220	3.31 213	6.94 212	5.51 212	2.94 215	7.51 213

uanet_test		0.00 210	0.00 212	0.00 212	0.00 219	0.00 219	0.00 220	0.00 216	0.00 216	0.00 219	0.00 215	0.00 222	0.00 215	0.00 214	0.00 213	0.00 217	0.00 215

sosnet-low-res		0.00 210	0.00 212	0.00 212	0.00 219	0.00 219	0.00 220	0.00 216	0.00 216	0.00 219	0.00 215	0.00 222	0.00 215	0.00 214	0.00 213	0.00 217	0.00 215

sosnet		0.00 210	0.00 212	0.00 212	0.00 219	0.00 219	0.00 220	0.00 216	0.00 216	0.00 219	0.00 215	0.00 222	0.00 215	0.00 214	0.00 213	0.00 217	0.00 215

9.14												96.98 133

SR-MVS					99.33 31			98.40 33				98.90 51

Anonymous202405211			97.39 65		98.85 67	98.59 50	97.89 102	97.93 73	94.41 102		97.37 98	96.99 132	93.09 149	98.61 44	98.46 39	99.11 33	97.27 86

our_test_3					97.32 160	95.13 175	97.59 117

test_part1																	98.16 41

Patchmatch-RL test							17.42 217

mPP-MVS					99.58 6							98.98 43

NP-MVS									89.27 171

High-resolution multi-view benchmark