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	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

LCM-MVSNet		99.86 1	99.86 1	99.87 1	99.99 1	99.77 1	99.77 1	99.80 1	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 4

pmmvs6		99.07 4	99.24 4	98.56 44	99.81 3	96.38 56	98.87 9	99.30 9	99.01 15	99.63 9	99.66 4	99.27 2	99.68 103	97.75 41	99.89 33	99.62 31

Anonymous20231211		99.29 2	99.41 2	98.91 22	99.94 2	97.08 37	99.47 3	99.51 5	99.56 2	99.83 3	99.80 2	99.13 3	99.90 13	97.55 49	99.93 21	99.75 13

pcd1.5k->3k		41.47 329	44.19 330	33.29 342	99.65 11	0.00 360	0.00 351	99.07 34	0.00 355	0.00 356	0.00 357	99.04 4	0.00 358	0.00 355	99.96 11	99.87 2

XVG-OURS-SEG-HR		97.38 95	97.07 115	98.30 63	99.01 89	97.41 31	94.66 234	99.02 51	95.20 149	98.15 97	97.52 176	98.83 5	98.43 316	94.87 139	96.41 310	99.07 151

ACMH	93.61 9	98.44 25	98.76 16	97.51 108	99.43 37	93.54 147	98.23 34	99.05 38	97.40 79	99.37 19	99.08 46	98.79 6	99.47 181	97.74 42	99.71 63	99.50 50
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvs_tets		98.90 5	98.94 8	98.75 30	99.69 8	96.48 54	98.54 20	99.22 10	96.23 110	99.71 5	99.48 7	98.77 7	99.93 2	98.89 10	99.95 13	99.84 6

LTVRE_ROB	96.88 1	99.18 3	99.34 3	98.72 35	99.71 7	96.99 40	99.69 2	99.57 3	99.02 14	99.62 10	99.36 16	98.53 8	99.52 162	98.58 24	99.95 13	99.66 23
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
TransMVSNet (Re)		98.38 28	98.67 19	97.51 108	99.51 26	93.39 152	98.20 39	98.87 81	98.23 35	99.48 12	99.27 25	98.47 9	99.55 155	96.52 78	99.53 104	99.60 34

pm-mvs1		98.47 24	98.67 19	97.86 85	99.52 25	94.58 112	98.28 31	99.00 62	97.57 63	99.27 26	99.22 30	98.32 10	99.50 174	97.09 68	99.75 54	99.50 50

jajsoiax		98.77 11	98.79 15	98.74 32	99.66 10	96.48 54	98.45 25	99.12 22	95.83 125	99.67 7	99.37 14	98.25 11	99.92 4	98.77 14	99.94 19	99.82 7

ACMH+	93.58 10	98.23 35	98.31 37	97.98 80	99.39 42	95.22 92	97.55 81	99.20 13	98.21 36	99.25 27	98.51 82	98.21 12	99.40 209	94.79 144	99.72 59	99.32 106

HPM-MVS_fast		98.32 30	98.13 44	98.88 23	99.54 23	97.48 27	98.35 28	99.03 50	95.88 122	97.88 131	98.22 108	98.15 13	99.74 59	96.50 80	99.62 79	99.42 85

wuyk23d		93.25 252	95.20 185	87.40 333	96.07 304	95.38 85	97.04 107	94.97 285	95.33 142	99.70 6	98.11 123	98.14 14	91.94 350	77.76 339	99.68 71	74.89 350

wuykxyi23d		98.68 17	98.53 26	99.13 3	99.44 34	97.97 7	96.85 117	99.02 51	95.81 126	99.88 2	99.38 13	98.14 14	99.69 97	98.32 28	99.95 13	99.73 16

ACMM	93.33 11	98.05 42	97.79 59	98.85 24	99.15 67	97.55 23	96.68 123	98.83 95	95.21 148	98.36 76	98.13 120	98.13 16	99.62 127	96.04 92	99.54 102	99.39 93
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS		98.11 40	97.83 58	98.92 19	99.42 39	97.46 28	98.57 17	99.05 38	95.43 140	97.41 155	97.50 178	97.98 17	99.79 38	95.58 114	99.57 94	99.50 50

testgi		96.07 164	96.50 148	94.80 248	99.26 51	87.69 267	95.96 160	98.58 142	95.08 159	98.02 113	96.25 250	97.92 18	97.60 338	88.68 268	98.74 221	99.11 144

LPG-MVS_test		97.94 52	97.67 68	98.74 32	99.15 67	97.02 38	97.09 105	99.02 51	95.15 153	98.34 78	98.23 105	97.91 19	99.70 88	94.41 155	99.73 56	99.50 50

LGP-MVS_train				98.74 32	99.15 67	97.02 38		99.02 51	95.15 153	98.34 78	98.23 105	97.91 19	99.70 88	94.41 155	99.73 56	99.50 50

abl_6		98.42 26	98.19 41	99.09 4	99.16 64	98.10 5	97.73 69	99.11 23	97.76 50	98.62 56	98.27 103	97.88 21	99.80 37	95.67 105	99.50 111	99.38 95

SD-MVS		97.37 96	97.70 65	96.35 178	98.14 191	95.13 95	96.54 124	98.92 73	95.94 120	99.19 29	98.08 125	97.74 22	95.06 348	95.24 125	99.54 102	98.87 180

DeepC-MVS	95.41 4	97.82 67	97.70 65	98.16 69	98.78 104	95.72 73	96.23 143	99.02 51	93.92 197	98.62 56	98.99 49	97.69 23	99.62 127	96.18 87	99.87 36	99.15 133
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
nrg030		98.54 21	98.62 23	98.32 60	99.22 56	95.66 77	97.90 56	99.08 30	98.31 32	99.02 37	98.74 65	97.68 24	99.61 133	97.77 40	99.85 39	99.70 19

ANet_high		98.31 31	98.94 8	96.41 176	99.33 47	89.64 213	97.92 55	99.56 4	99.27 5	99.66 8	99.50 6	97.67 25	99.83 30	97.55 49	99.98 3	99.77 9

canonicalmvs		97.23 106	97.21 104	97.30 128	97.65 246	94.39 117	97.84 59	99.05 38	97.42 71	96.68 185	93.85 303	97.63 26	99.33 229	96.29 85	98.47 240	98.18 241

TranMVSNet+NR-MVSNet		98.33 29	98.30 39	98.43 50	99.07 81	95.87 69	96.73 121	99.05 38	98.67 21	98.84 45	98.45 86	97.58 27	99.88 19	96.45 82	99.86 38	99.54 45

cdsmvs_eth3d_5k		24.22 330	32.30 331	0.00 345	0.00 359	0.00 360	0.00 351	98.10 200	0.00 355	0.00 356	95.06 281	97.54 28	0.00 358	0.00 355	0.00 356	0.00 356

ACMP	92.54 13	97.47 90	97.10 112	98.55 45	99.04 85	96.70 47	96.24 142	98.89 77	93.71 207	97.97 118	97.75 158	97.44 29	99.63 121	93.22 186	99.70 66	99.32 106
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_djsdf		98.73 13	98.74 18	98.69 37	99.63 13	96.30 59	98.67 12	99.02 51	96.50 99	99.32 21	99.44 10	97.43 30	99.92 4	98.73 17	99.95 13	99.86 3

TDRefinement		98.90 5	98.86 11	99.02 8	99.54 23	98.06 6	99.34 5	99.44 7	98.85 19	99.00 40	99.20 31	97.42 31	99.59 143	97.21 62	99.76 50	99.40 90

anonymousdsp		98.72 16	98.63 21	98.99 10	99.62 14	97.29 34	98.65 15	99.19 14	95.62 131	99.35 20	99.37 14	97.38 32	99.90 13	98.59 23	99.91 27	99.77 9

PS-CasMVS		98.73 13	98.85 13	98.39 54	99.55 21	95.47 84	98.49 22	99.13 21	99.22 7	99.22 28	98.96 52	97.35 33	99.92 4	97.79 39	99.93 21	99.79 8

COLMAP_ROB	94.48 6	98.25 34	98.11 45	98.64 40	99.21 59	97.35 32	97.96 52	99.16 16	98.34 31	98.78 48	98.52 81	97.32 34	99.45 190	94.08 167	99.67 73	99.13 136
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
EG-PatchMatch MVS		97.69 76	97.79 59	97.40 123	99.06 82	93.52 149	95.96 160	98.97 69	94.55 177	98.82 46	98.76 63	97.31 35	99.29 236	97.20 64	99.44 130	99.38 95

XXY-MVS		97.54 86	97.70 65	97.07 139	99.46 32	92.21 170	97.22 95	99.00 62	94.93 164	98.58 61	98.92 56	97.31 35	99.41 206	94.44 153	99.43 139	99.59 35

PEN-MVS		98.75 12	98.85 13	98.44 49	99.58 18	95.67 76	98.45 25	99.15 19	99.33 4	99.30 24	99.00 48	97.27 37	99.92 4	97.64 44	99.92 24	99.75 13

DTE-MVSNet		98.79 10	98.86 11	98.59 42	99.55 21	96.12 63	98.48 24	99.10 25	99.36 3	99.29 25	99.06 47	97.27 37	99.93 2	97.71 43	99.91 27	99.70 19

MP-MVS-pluss		97.69 76	97.36 90	98.70 36	99.50 29	96.84 43	95.38 196	98.99 65	92.45 237	98.11 100	98.31 96	97.25 39	99.77 47	96.60 75	99.62 79	99.48 61
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_Plus		97.89 59	97.63 74	98.67 38	99.35 46	96.84 43	96.36 134	98.79 101	95.07 160	97.88 131	98.35 92	97.24 40	99.72 70	96.05 91	99.58 91	99.45 71

Effi-MVS+		96.19 161	96.01 162	96.71 157	97.43 261	92.19 173	96.12 148	99.10 25	95.45 138	93.33 300	94.71 287	97.23 41	99.56 151	93.21 187	97.54 285	98.37 219

PGM-MVS		97.88 60	97.52 83	98.96 13	99.20 60	97.62 18	97.09 105	99.06 36	95.45 138	97.55 144	97.94 141	97.11 42	99.78 39	94.77 146	99.46 125	99.48 61

APD-MVS_3200maxsize		98.13 39	97.90 54	98.79 28	98.79 103	97.31 33	97.55 81	98.92 73	97.72 55	98.25 88	98.13 120	97.10 43	99.75 54	95.44 117	99.24 175	99.32 106

OPM-MVS		97.54 86	97.25 96	98.41 51	99.11 77	96.61 50	95.24 208	98.46 150	94.58 176	98.10 103	98.07 126	97.09 44	99.39 215	95.16 130	99.44 130	99.21 124

HFP-MVS		97.94 52	97.64 72	98.83 25	99.15 67	97.50 25	97.59 78	98.84 87	96.05 113	97.49 148	97.54 173	97.07 45	99.70 88	95.61 111	99.46 125	99.30 110

#test#		97.62 80	97.22 103	98.83 25	99.15 67	97.50 25	96.81 119	98.84 87	94.25 188	97.49 148	97.54 173	97.07 45	99.70 88	94.37 158	99.46 125	99.30 110

SteuartSystems-ACMMP		98.02 44	97.76 62	98.79 28	99.43 37	97.21 36	97.15 96	98.90 75	96.58 98	98.08 106	97.87 148	97.02 47	99.76 48	95.25 124	99.59 89	99.40 90
Skip Steuart: Steuart Systems R&D Blog.
APDe-MVS		98.14 37	98.03 50	98.47 48	98.72 110	96.04 66	98.07 46	99.10 25	95.96 119	98.59 60	98.69 69	96.94 48	99.81 33	96.64 74	99.58 91	99.57 40

LCM-MVSNet-Re		97.33 100	97.33 91	97.32 127	98.13 194	93.79 138	96.99 109	99.65 2	96.74 94	99.47 13	98.93 55	96.91 49	99.84 28	90.11 246	99.06 194	98.32 226

VPA-MVSNet		98.27 32	98.46 29	97.70 94	99.06 82	93.80 137	97.76 64	99.00 62	98.40 29	99.07 35	98.98 50	96.89 50	99.75 54	97.19 65	99.79 47	99.55 44

ACMMP		98.05 42	97.75 63	98.93 18	99.23 55	97.60 19	98.09 45	98.96 70	95.75 128	97.91 126	98.06 129	96.89 50	99.76 48	95.32 122	99.57 94	99.43 83
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
PMVS	89.60 17	96.71 142	96.97 119	95.95 210	99.51 26	97.81 13	97.42 88	97.49 238	97.93 45	95.95 218	98.58 75	96.88 52	96.91 342	89.59 253	99.36 154	93.12 341
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
region2R		97.92 55	97.59 78	98.92 19	99.22 56	97.55 23	97.60 77	98.84 87	96.00 117	97.22 160	97.62 168	96.87 53	99.76 48	95.48 115	99.43 139	99.46 66

CP-MVS		97.92 55	97.56 81	98.99 10	98.99 90	97.82 12	97.93 54	98.96 70	96.11 112	96.89 180	97.45 181	96.85 54	99.78 39	95.19 127	99.63 78	99.38 95

test_0402		97.84 63	97.97 51	97.47 116	99.19 62	94.07 128	96.71 122	98.73 112	98.66 22	98.56 62	98.41 88	96.84 55	99.69 97	94.82 141	99.81 43	98.64 198

v52		98.85 8	99.01 5	98.37 55	99.61 15	95.53 82	99.01 7	99.04 45	98.48 26	99.31 22	99.41 11	96.82 56	99.87 21	99.44 2	99.95 13	99.70 19

V4		98.85 8	99.01 5	98.37 55	99.61 15	95.53 82	99.01 7	99.04 45	98.48 26	99.31 22	99.41 11	96.81 57	99.87 21	99.44 2	99.95 13	99.70 19

ACMMPR		97.95 50	97.62 76	98.94 15	99.20 60	97.56 22	97.59 78	98.83 95	96.05 113	97.46 153	97.63 167	96.77 58	99.76 48	95.61 111	99.46 125	99.49 58

Vis-MVSNet		98.27 32	98.34 35	98.07 73	99.33 47	95.21 94	98.04 48	99.46 6	97.32 82	97.82 140	99.11 43	96.75 59	99.86 23	97.84 36	99.36 154	99.15 133
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Fast-Effi-MVS+		95.49 182	95.07 189	96.75 155	97.67 245	92.82 159	94.22 249	98.60 139	91.61 249	93.42 297	92.90 314	96.73 60	99.70 88	92.60 193	97.89 263	97.74 264

test_part1								98.84 87				96.69 61			99.44 130	99.37 100

ESAPD		97.22 107	96.82 128	98.40 53	99.03 86	96.07 64	95.64 180	98.84 87	94.84 165	98.08 106	97.60 170	96.69 61	99.76 48	91.22 218	99.44 130	99.37 100

tfpnnormal		97.72 73	97.97 51	96.94 146	99.26 51	92.23 169	97.83 60	98.45 151	98.25 34	99.13 32	98.66 71	96.65 63	99.69 97	93.92 172	99.62 79	98.91 171

DeepPCF-MVS	94.58 5	96.90 124	96.43 149	98.31 62	97.48 255	97.23 35	92.56 303	98.60 139	92.84 231	98.54 63	97.40 184	96.64 64	98.78 292	94.40 157	99.41 148	98.93 168

MVS_111021_LR		96.82 133	96.55 142	97.62 100	98.27 164	95.34 87	93.81 271	98.33 170	94.59 175	96.56 189	96.63 230	96.61 65	98.73 296	94.80 143	99.34 159	98.78 189

Gipuma		98.07 41	98.31 37	97.36 125	99.76 5	96.28 60	98.51 21	99.10 25	98.76 20	96.79 182	99.34 20	96.61 65	98.82 288	96.38 83	99.50 111	96.98 287
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVS_111021_HR		96.73 139	96.54 144	97.27 129	98.35 156	93.66 144	93.42 284	98.36 165	94.74 170	96.58 187	96.76 223	96.54 67	98.99 268	94.87 139	99.27 173	99.15 133

v748		98.58 20	98.89 10	97.67 98	99.61 15	93.53 148	98.59 16	98.90 75	98.97 17	99.43 15	99.15 40	96.53 68	99.85 24	98.88 11	99.91 27	99.64 27

v7n		98.73 13	98.99 7	97.95 81	99.64 12	94.20 125	98.67 12	99.14 20	99.08 9	99.42 16	99.23 29	96.53 68	99.91 12	99.27 4	99.93 21	99.73 16

mPP-MVS		97.91 57	97.53 82	99.04 7	99.22 56	97.87 11	97.74 67	98.78 104	96.04 115	97.10 166	97.73 161	96.53 68	99.78 39	95.16 130	99.50 111	99.46 66

XVS		97.96 48	97.63 74	98.94 15	99.15 67	97.66 16	97.77 62	98.83 95	97.42 71	96.32 203	97.64 166	96.49 71	99.72 70	95.66 107	99.37 151	99.45 71

X-MVStestdata		92.86 255	90.83 289	98.94 15	99.15 67	97.66 16	97.77 62	98.83 95	97.42 71	96.32 203	36.50 352	96.49 71	99.72 70	95.66 107	99.37 151	99.45 71

UA-Net		98.88 7	98.76 16	99.22 2	99.11 77	97.89 10	99.47 3	99.32 8	99.08 9	97.87 136	99.67 3	96.47 73	99.92 4	97.88 34	99.98 3	99.85 4

xiu_mvs_v1_base_debu		95.62 176	95.96 165	94.60 256	98.01 202	88.42 246	93.99 262	98.21 185	92.98 224	95.91 219	94.53 289	96.39 74	99.72 70	95.43 119	98.19 248	95.64 320

xiu_mvs_v1_base		95.62 176	95.96 165	94.60 256	98.01 202	88.42 246	93.99 262	98.21 185	92.98 224	95.91 219	94.53 289	96.39 74	99.72 70	95.43 119	98.19 248	95.64 320

xiu_mvs_v1_base_debi		95.62 176	95.96 165	94.60 256	98.01 202	88.42 246	93.99 262	98.21 185	92.98 224	95.91 219	94.53 289	96.39 74	99.72 70	95.43 119	98.19 248	95.64 320

testing_2		97.43 91	97.71 64	96.60 162	98.91 97	90.85 194	96.01 153	98.54 143	94.78 169	98.78 48	98.96 52	96.35 77	99.54 157	97.25 60	99.82 42	99.40 90

MP-MVS		97.64 79	97.18 105	99.00 9	99.32 49	97.77 14	97.49 84	98.73 112	96.27 107	95.59 231	97.75 158	96.30 78	99.78 39	93.70 178	99.48 121	99.45 71

TinyColmap		96.00 167	96.34 152	94.96 242	97.90 213	87.91 262	94.13 257	98.49 148	94.41 181	98.16 95	97.76 155	96.29 79	98.68 303	90.52 238	99.42 142	98.30 229

Fast-Effi-MVS+-dtu		96.44 154	96.12 157	97.39 124	97.18 276	94.39 117	95.46 186	98.73 112	96.03 116	94.72 247	94.92 285	96.28 80	99.69 97	93.81 175	97.98 255	98.09 243

OMC-MVS		96.48 152	96.00 163	97.91 83	98.30 158	96.01 68	94.86 228	98.60 139	91.88 247	97.18 162	97.21 195	96.11 81	99.04 261	90.49 241	99.34 159	98.69 196

xiu_mvs_v2_base		94.22 227	94.63 206	92.99 298	97.32 270	84.84 301	92.12 310	97.84 215	91.96 244	94.17 266	93.43 304	96.07 82	99.71 80	91.27 215	97.48 288	94.42 330

CSCG		97.40 94	97.30 92	97.69 96	98.95 93	94.83 103	97.28 91	98.99 65	96.35 106	98.13 99	95.95 263	95.99 83	99.66 114	94.36 161	99.73 56	98.59 203

PHI-MVS		96.96 119	96.53 145	98.25 67	97.48 255	96.50 53	96.76 120	98.85 84	93.52 210	96.19 212	96.85 214	95.94 84	99.42 195	93.79 176	99.43 139	98.83 184

TSAR-MVS + MP.		97.42 92	97.23 102	98.00 79	99.38 43	95.00 98	97.63 73	98.20 188	93.00 223	98.16 95	98.06 129	95.89 85	99.72 70	95.67 105	99.10 188	99.28 117

XVG-ACMP-BASELINE		97.58 84	97.28 95	98.49 46	99.16 64	96.90 42	96.39 129	98.98 67	95.05 161	98.06 109	98.02 132	95.86 86	99.56 151	94.37 158	99.64 77	99.00 157

AllTest		97.20 108	96.92 123	98.06 74	99.08 79	96.16 61	97.14 98	99.16 16	94.35 185	97.78 141	98.07 126	95.84 87	99.12 251	91.41 212	99.42 142	98.91 171

TestCases				98.06 74	99.08 79	96.16 61		99.16 16	94.35 185	97.78 141	98.07 126	95.84 87	99.12 251	91.41 212	99.42 142	98.91 171

APD-MVS		97.00 111	96.53 145	98.41 51	98.55 135	96.31 58	96.32 137	98.77 105	92.96 229	97.44 154	97.58 172	95.84 87	99.74 59	91.96 200	99.35 157	99.19 126
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
pcd_1.5k_mvsjas		7.98 333	10.65 334	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	95.82 90	0.00 358	0.00 355	0.00 356	0.00 356

PS-MVSNAJss		98.53 22	98.63 21	98.21 68	99.68 9	94.82 104	98.10 44	99.21 11	96.91 87	99.75 4	99.45 9	95.82 90	99.92 4	98.80 13	99.96 11	99.89 1

PS-MVSNAJ		94.10 233	94.47 213	93.00 297	97.35 265	84.88 300	91.86 314	97.84 215	91.96 244	94.17 266	92.50 321	95.82 90	99.71 80	91.27 215	97.48 288	94.40 331

3Dnovator	96.53 2	97.61 81	97.64 72	97.50 111	97.74 237	93.65 145	98.49 22	98.88 79	96.86 91	97.11 165	98.55 79	95.82 90	99.73 64	95.94 98	99.42 142	99.13 136

MPTG		98.01 46	97.66 69	99.06 5	99.44 34	97.90 8	95.66 176	98.73 112	97.69 57	97.90 127	97.96 137	95.81 94	99.82 31	96.13 88	99.61 84	99.45 71

MTAPA		98.14 37	97.84 57	99.06 5	99.44 34	97.90 8	97.25 92	98.73 112	97.69 57	97.90 127	97.96 137	95.81 94	99.82 31	96.13 88	99.61 84	99.45 71

DP-MVS		97.87 61	97.89 55	97.81 88	98.62 126	94.82 104	97.13 99	98.79 101	98.98 16	98.74 51	98.49 83	95.80 96	99.49 176	95.04 137	99.44 130	99.11 144

LS3D		97.77 70	97.50 85	98.57 43	96.24 298	97.58 21	98.45 25	98.85 84	98.58 24	97.51 146	97.94 141	95.74 97	99.63 121	95.19 127	98.97 199	98.51 209

CNVR-MVS		96.92 122	96.55 142	98.03 78	98.00 205	95.54 80	94.87 227	98.17 193	94.60 173	96.38 197	97.05 202	95.67 98	99.36 224	95.12 134	99.08 190	99.19 126

CLD-MVS		95.47 185	95.07 189	96.69 159	98.27 164	92.53 163	91.36 321	98.67 127	91.22 253	95.78 225	94.12 301	95.65 99	98.98 270	90.81 228	99.72 59	98.57 204
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Regformer-2		97.41 93	97.24 98	97.93 82	97.21 274	94.72 107	94.85 229	98.27 180	97.74 51	98.11 100	97.50 178	95.58 100	99.69 97	96.57 77	99.31 166	99.37 100

ITE_SJBPF				97.85 86	98.64 121	96.66 48		98.51 147	95.63 130	97.22 160	97.30 192	95.52 101	98.55 311	90.97 223	98.90 206	98.34 225

Regformer-4		97.53 88	97.47 87	97.71 93	97.35 265	93.91 133	95.26 206	98.14 197	97.97 44	98.34 78	97.89 146	95.49 102	99.71 80	97.41 57	99.42 142	99.51 49

DeepC-MVS_fast	94.34 7	96.74 137	96.51 147	97.44 120	97.69 241	94.15 126	96.02 152	98.43 155	93.17 219	97.30 158	97.38 189	95.48 103	99.28 237	93.74 177	99.34 159	98.88 178
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
WR-MVS_H		98.65 18	98.62 23	98.75 30	99.51 26	96.61 50	98.55 19	99.17 15	99.05 12	99.17 31	98.79 60	95.47 104	99.89 17	97.95 32	99.91 27	99.75 13

FMVSNet1		97.95 50	98.08 46	97.56 103	99.14 75	93.67 141	98.23 34	98.66 129	97.41 78	99.00 40	99.19 32	95.47 104	99.73 64	95.83 101	99.76 50	99.30 110

MIMVSNet1		98.51 23	98.45 31	98.67 38	99.72 6	96.71 46	98.76 10	98.89 77	98.49 25	99.38 18	99.14 41	95.44 106	99.84 28	96.47 81	99.80 46	99.47 64

CP-MVSNet		98.42 26	98.46 29	98.30 63	99.46 32	95.22 92	98.27 33	98.84 87	99.05 12	99.01 38	98.65 73	95.37 107	99.90 13	97.57 48	99.91 27	99.77 9

Regformer-1		97.27 103	97.16 107	97.61 101	97.21 274	93.86 135	94.85 229	98.04 208	97.62 61	98.03 112	97.50 178	95.34 108	99.63 121	96.52 78	99.31 166	99.35 104

segment_acmp												95.34 108

CDPH-MVS		95.45 188	94.65 205	97.84 87	98.28 162	94.96 100	93.73 273	98.33 170	85.03 312	95.44 232	96.60 231	95.31 110	99.44 193	90.01 248	99.13 184	99.11 144

3Dnovator+	96.13 3	97.73 72	97.59 78	98.15 70	98.11 195	95.60 78	98.04 48	98.70 121	98.13 38	96.93 178	98.45 86	95.30 111	99.62 127	95.64 109	98.96 200	99.24 122

MVS_Test		96.27 157	96.79 132	94.73 251	96.94 284	86.63 284	96.18 145	98.33 170	94.94 162	96.07 215	98.28 101	95.25 112	99.26 240	97.21 62	97.90 262	98.30 229

XVG-OURS		97.12 109	96.74 133	98.26 65	98.99 90	97.45 29	93.82 270	99.05 38	95.19 150	98.32 81	97.70 164	95.22 113	98.41 317	94.27 163	98.13 251	98.93 168

MCST-MVS		96.24 158	95.80 170	97.56 103	98.75 106	94.13 127	94.66 234	98.17 193	90.17 262	96.21 211	96.10 257	95.14 114	99.43 194	94.13 166	98.85 215	99.13 136

EI-MVSNet-Vis-set		97.32 101	97.39 89	97.11 136	97.36 264	92.08 176	95.34 199	97.65 230	97.74 51	98.29 86	98.11 123	95.05 115	99.68 103	97.50 53	99.50 111	99.56 41

Regformer-3		97.25 105	97.29 93	97.11 136	97.35 265	92.32 167	95.26 206	97.62 235	97.67 59	98.17 94	97.89 146	95.05 115	99.56 151	97.16 66	99.42 142	99.46 66

EI-MVSNet-UG-set		97.32 101	97.40 88	97.09 138	97.34 268	92.01 178	95.33 200	97.65 230	97.74 51	98.30 85	98.14 119	95.04 117	99.69 97	97.55 49	99.52 108	99.58 36

DELS-MVS		96.17 162	96.23 155	95.99 206	97.55 253	90.04 206	92.38 307	98.52 145	94.13 193	96.55 192	97.06 201	94.99 118	99.58 145	95.62 110	99.28 171	98.37 219
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
ab-mvs		96.59 147	96.59 138	96.60 162	98.64 121	92.21 170	98.35 28	97.67 226	94.45 178	96.99 170	98.79 60	94.96 119	99.49 176	90.39 243	99.07 192	98.08 244

MSLP-MVS++		96.42 156	96.71 134	95.57 223	97.82 221	90.56 202	95.71 171	98.84 87	94.72 171	96.71 184	97.39 187	94.91 120	98.10 332	95.28 123	99.02 196	98.05 249

v13		98.02 44	98.52 27	96.51 169	99.02 88	90.14 204	98.07 46	99.09 29	98.10 40	99.13 32	99.35 18	94.84 121	99.74 59	99.12 5	99.98 3	99.65 24

QAPM		95.88 171	95.57 176	96.80 152	97.90 213	91.84 182	98.18 41	98.73 112	88.41 275	96.42 195	98.13 120	94.73 122	99.75 54	88.72 266	98.94 204	98.81 185

RPSCF		97.87 61	97.51 84	98.95 14	99.15 67	98.43 3	97.56 80	99.06 36	96.19 111	98.48 68	98.70 68	94.72 123	99.24 242	94.37 158	99.33 164	99.17 129

v12		97.97 47	98.47 28	96.46 173	98.98 92	90.01 208	97.97 51	99.08 30	98.00 43	99.11 34	99.34 20	94.70 124	99.73 64	99.07 6	99.98 3	99.64 27

DU-MVS		97.79 69	97.60 77	98.36 58	98.73 108	95.78 71	95.65 178	98.87 81	97.57 63	98.31 83	97.83 149	94.69 125	99.85 24	97.02 70	99.71 63	99.46 66

Baseline_NR-MVSNet		97.72 73	97.79 59	97.50 111	99.56 19	93.29 153	95.44 187	98.86 83	98.20 37	98.37 75	99.24 27	94.69 125	99.55 155	95.98 97	99.79 47	99.65 24

TEST9					97.84 219	95.23 89	93.62 277	98.39 161	86.81 293	93.78 279	95.99 258	94.68 127	99.52 162

UniMVSNet (Re)		97.83 64	97.65 70	98.35 59	98.80 102	95.86 70	95.92 164	99.04 45	97.51 68	98.22 90	97.81 153	94.68 127	99.78 39	97.14 67	99.75 54	99.41 87

agg_prior1		95.39 190	94.60 208	97.75 91	97.80 226	94.96 100	93.39 285	98.36 165	87.20 289	93.49 292	95.97 261	94.65 129	99.53 159	91.69 210	98.86 213	98.77 190

UniMVSNet_NR-MVSNet		97.83 64	97.65 70	98.37 55	98.72 110	95.78 71	95.66 176	99.02 51	98.11 39	98.31 83	97.69 165	94.65 129	99.85 24	97.02 70	99.71 63	99.48 61

VPNet		97.26 104	97.49 86	96.59 164	99.47 31	90.58 200	96.27 138	98.53 144	97.77 49	98.46 70	98.41 88	94.59 131	99.68 103	94.61 149	99.29 170	99.52 48

train_agg		95.46 186	94.66 204	97.88 84	97.84 219	95.23 89	93.62 277	98.39 161	87.04 291	93.78 279	95.99 258	94.58 132	99.52 162	91.76 207	98.90 206	98.89 174

test_8					97.81 222	95.07 97	93.54 280	98.38 163	87.04 291	93.71 283	95.96 262	94.58 132	99.52 162

API-MVS		95.09 203	95.01 192	95.31 231	96.61 290	94.02 130	96.83 118	97.18 249	95.60 132	95.79 224	94.33 298	94.54 134	98.37 323	85.70 301	98.52 236	93.52 338

V9		97.90 58	98.40 32	96.40 177	98.93 94	89.86 210	97.86 58	99.07 34	97.88 47	99.05 36	99.30 23	94.53 135	99.72 70	99.01 8	99.98 3	99.63 29

Test By Simon												94.51 136

MSDG		95.33 193	95.13 187	95.94 212	97.40 263	91.85 181	91.02 324	98.37 164	95.30 143	96.31 205	95.99 258	94.51 136	98.38 321	89.59 253	97.65 281	97.60 269

TSAR-MVS + GP.		96.47 153	96.12 157	97.49 114	97.74 237	95.23 89	94.15 255	96.90 259	93.26 213	98.04 111	96.70 226	94.41 138	98.89 280	94.77 146	99.14 182	98.37 219

NR-MVSNet		97.96 48	97.86 56	98.26 65	98.73 108	95.54 80	98.14 42	98.73 112	97.79 48	99.42 16	97.83 149	94.40 139	99.78 39	95.91 100	99.76 50	99.46 66

V14		97.83 64	98.33 36	96.35 178	98.88 100	89.72 211	97.75 65	99.05 38	97.74 51	99.01 38	99.27 25	94.35 140	99.71 80	98.95 9	99.97 8	99.62 31

AdaColmap		95.11 201	94.62 207	96.58 165	97.33 269	94.45 116	94.92 225	98.08 203	93.15 220	93.98 276	95.53 274	94.34 141	99.10 255	85.69 302	98.61 232	96.20 313

FC-MVSNet-test		98.16 36	98.37 33	97.56 103	99.49 30	93.10 156	98.35 28	99.21 11	98.43 28	98.89 44	98.83 59	94.30 142	99.81 33	97.87 35	99.91 27	99.77 9

v11		97.82 67	98.36 34	96.17 194	98.93 94	89.16 230	97.79 61	99.08 30	97.64 60	99.19 29	99.32 22	94.28 143	99.72 70	99.07 6	99.97 8	99.63 29

Effi-MVS+-dtu		96.81 134	96.09 159	98.99 10	96.90 286	98.69 2	96.42 128	98.09 201	95.86 123	95.15 238	95.54 273	94.26 144	99.81 33	94.06 168	98.51 238	98.47 211

mvs-test1		96.20 160	95.50 178	98.32 60	96.90 286	98.16 4	95.07 217	98.09 201	95.86 123	93.63 286	94.32 299	94.26 144	99.71 80	94.06 168	97.27 297	97.07 284

ambc				96.56 168	98.23 175	91.68 185	97.88 57	98.13 198		98.42 73	98.56 78	94.22 146	99.04 261	94.05 170	99.35 157	98.95 163

v15		97.77 70	98.26 40	96.30 183	98.81 101	89.59 218	97.62 74	99.04 45	97.59 62	98.97 42	99.24 27	94.19 147	99.70 88	98.88 11	99.97 8	99.61 33

test20.03		96.58 148	96.61 137	96.48 172	98.49 144	91.72 184	95.68 175	97.69 225	96.81 92	98.27 87	97.92 144	94.18 148	98.71 298	90.78 230	99.66 75	99.00 157

agg_prior3		95.30 195	94.46 216	97.80 89	97.80 226	95.00 98	93.63 276	98.34 169	86.33 297	93.40 299	95.84 265	94.15 149	99.50 174	91.76 207	98.90 206	98.89 174

HPM-MVS++		96.99 112	96.38 150	98.81 27	98.64 121	97.59 20	95.97 156	98.20 188	95.51 136	95.06 239	96.53 235	94.10 150	99.70 88	94.29 162	99.15 181	99.13 136

v17		97.70 75	98.17 42	96.28 186	98.77 105	89.59 218	97.62 74	99.01 60	97.54 65	98.72 53	99.18 35	94.06 151	99.68 103	98.74 16	99.92 24	99.58 36

v16		97.69 76	98.16 43	96.29 185	98.75 106	89.60 216	97.62 74	99.01 60	97.53 67	98.69 55	99.18 35	94.05 152	99.68 103	98.73 17	99.88 34	99.58 36

PM-MVS		97.36 99	97.10 112	98.14 71	98.91 97	96.77 45	96.20 144	98.63 136	93.82 204	98.54 63	98.33 94	93.98 153	99.05 260	95.99 96	99.45 129	98.61 202

OpenMVS	94.22 8	95.48 184	95.20 185	96.32 181	97.16 277	91.96 179	97.74 67	98.84 87	87.26 287	94.36 263	98.01 133	93.95 154	99.67 109	90.70 234	98.75 220	97.35 281

v18		97.60 82	98.06 48	96.23 187	98.68 120	89.46 221	97.48 85	98.98 67	97.33 81	98.60 59	99.13 42	93.86 155	99.67 109	98.62 21	99.87 36	99.56 41

v8		97.60 82	98.06 48	96.23 187	98.71 113	89.44 222	97.43 87	98.82 99	97.29 83	98.74 51	99.10 44	93.86 155	99.68 103	98.61 22	99.94 19	99.56 41

v6		96.97 116	97.24 98	96.15 195	98.71 113	89.44 222	95.97 156	98.33 170	95.25 145	97.89 129	98.15 116	93.86 155	99.61 133	97.51 52	99.50 111	99.42 85

v1neww		96.97 116	97.24 98	96.15 195	98.70 115	89.44 222	95.97 156	98.33 170	95.25 145	97.88 131	98.15 116	93.83 158	99.61 133	97.50 53	99.50 111	99.41 87

v7new		96.97 116	97.24 98	96.15 195	98.70 115	89.44 222	95.97 156	98.33 170	95.25 145	97.88 131	98.15 116	93.83 158	99.61 133	97.50 53	99.50 111	99.41 87

NCCC		96.52 150	95.99 164	98.10 72	97.81 222	95.68 75	95.00 223	98.20 188	95.39 141	95.40 234	96.36 246	93.81 160	99.45 190	93.55 181	98.42 241	99.17 129

TAPA-MVS	93.32 12	94.93 208	94.23 221	97.04 141	98.18 184	94.51 113	95.22 209	98.73 112	81.22 329	96.25 209	95.95 263	93.80 161	98.98 270	89.89 249	98.87 211	97.62 267
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
FIs		97.93 54	98.07 47	97.48 115	99.38 43	92.95 158	98.03 50	99.11 23	98.04 42	98.62 56	98.66 71	93.75 162	99.78 39	97.23 61	99.84 40	99.73 16

OurMVSNet-221017-0		98.61 19	98.61 25	98.63 41	99.77 4	96.35 57	99.17 6	99.05 38	98.05 41	99.61 11	99.52 5	93.72 163	99.88 19	98.72 20	99.88 34	99.65 24

test_prior3		95.91 169	95.39 181	97.46 117	97.79 231	94.26 123	93.33 288	98.42 158	94.21 190	94.02 273	96.25 250	93.64 164	99.34 226	91.90 201	98.96 200	98.79 187

test_prior2							93.33 288		94.21 190	94.02 273	96.25 250	93.64 164		91.90 201	98.96 200

旧先验1					97.80 226	93.87 134		97.75 220			97.04 203	93.57 166			98.68 227	98.72 194

v10		97.55 85	97.97 51	96.31 182	98.60 128	89.64 213	97.44 86	99.02 51	96.60 96	98.72 53	99.16 39	93.48 167	99.72 70	98.76 15	99.92 24	99.58 36

v7		96.93 120	97.17 106	96.23 187	98.59 130	89.64 213	95.96 160	98.66 129	94.41 181	97.87 136	98.38 91	93.47 168	99.64 118	97.93 33	99.24 175	99.43 83

v148		96.58 148	96.97 119	95.42 228	98.63 125	87.57 268	95.09 214	97.90 211	95.91 121	98.24 89	97.96 137	93.42 169	99.39 215	96.04 92	99.52 108	99.29 116

v1		96.86 126	97.14 109	96.04 202	98.55 135	89.06 233	95.44 187	98.33 170	95.14 155	97.94 121	98.18 114	93.39 170	99.61 133	97.61 45	99.69 67	99.44 79

v1141		96.86 126	97.14 109	96.04 202	98.55 135	89.06 233	95.44 187	98.33 170	95.14 155	97.93 124	98.19 110	93.36 171	99.62 127	97.61 45	99.69 67	99.44 79

divwei89l23v2f112		96.86 126	97.14 109	96.04 202	98.54 138	89.06 233	95.44 187	98.33 170	95.14 155	97.93 124	98.19 110	93.36 171	99.61 133	97.61 45	99.68 71	99.44 79

V42		97.04 110	97.16 107	96.68 160	98.59 130	91.05 191	96.33 136	98.36 165	94.60 173	97.99 114	98.30 99	93.32 173	99.62 127	97.40 58	99.53 104	99.38 95

new-patchmatchnet		95.67 175	96.58 139	92.94 299	97.48 255	80.21 326	92.96 294	98.19 192	94.83 167	98.82 46	98.79 60	93.31 174	99.51 172	95.83 101	99.04 195	99.12 141

test12				97.46 117	97.61 249	94.07 128		97.78 219		93.57 290		93.31 174	99.42 195		98.78 217	98.89 174

UGNet		96.81 134	96.56 141	97.58 102	96.64 289	93.84 136	97.75 65	97.12 252	96.47 102	93.62 287	98.88 58	93.22 176	99.53 159	95.61 111	99.69 67	99.36 103
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
pmmvs-eth3d		96.49 151	96.18 156	97.42 121	98.25 173	94.29 120	94.77 233	98.07 205	89.81 265	97.97 118	98.33 94	93.11 177	99.08 257	95.46 116	99.84 40	98.89 174

v1144		96.84 129	97.08 114	96.13 199	98.42 152	89.28 228	95.41 194	98.67 127	94.21 190	97.97 118	98.31 96	93.06 178	99.65 115	98.06 30	99.62 79	99.45 71

PVSNet_BlendedMVS		95.02 206	94.93 196	95.27 232	97.79 231	87.40 273	94.14 256	98.68 124	88.94 271	94.51 259	98.01 133	93.04 179	99.30 233	89.77 251	99.49 118	99.11 144

PVSNet_Blended		93.96 237	93.65 234	94.91 243	97.79 231	87.40 273	91.43 320	98.68 124	84.50 316	94.51 259	94.48 292	93.04 179	99.30 233	89.77 251	98.61 232	98.02 254

mvs_anonymous		95.36 192	96.07 161	93.21 292	96.29 297	81.56 321	94.60 236	97.66 228	93.30 212	96.95 177	98.91 57	93.03 181	99.38 220	96.60 75	97.30 296	98.69 196

v1192		96.83 132	97.06 116	96.15 195	98.28 162	89.29 227	95.36 197	98.77 105	93.73 206	98.11 100	98.34 93	93.02 182	99.67 109	98.35 26	99.58 91	99.50 50

F-COLMAP		95.30 195	94.38 218	98.05 77	98.64 121	96.04 66	95.61 184	98.66 129	89.00 270	93.22 301	96.40 245	92.90 183	99.35 225	87.45 290	97.53 286	98.77 190

WR-MVS		96.90 124	96.81 129	97.16 133	98.56 134	92.20 172	94.33 242	98.12 199	97.34 80	98.20 92	97.33 191	92.81 184	99.75 54	94.79 144	99.81 43	99.54 45

v1240		96.74 137	97.02 118	95.91 213	98.18 184	88.52 245	95.39 195	98.88 79	93.15 220	98.46 70	98.40 90	92.80 185	99.71 80	98.45 25	99.49 118	99.49 58

MVE	73.61 22	86.48 322	85.92 322	88.18 331	96.23 300	85.28 294	81.78 350	75.79 353	86.01 299	82.53 350	91.88 326	92.74 186	87.47 353	71.42 348	94.86 325	91.78 344
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DP-MVS Recon		95.55 179	95.13 187	96.80 152	98.51 142	93.99 132	94.60 236	98.69 122	90.20 261	95.78 225	96.21 253	92.73 187	98.98 270	90.58 237	98.86 213	97.42 274

CANet		95.86 172	95.65 174	96.49 171	96.41 296	90.82 196	94.36 241	98.41 160	94.94 162	92.62 312	96.73 224	92.68 188	99.71 80	95.12 134	99.60 87	98.94 165

v1921920		96.72 140	96.96 121	95.99 206	98.21 177	88.79 242	95.42 192	98.79 101	93.22 214	98.19 93	98.26 104	92.68 188	99.70 88	98.34 27	99.55 100	99.49 58

BH-untuned		94.69 216	94.75 203	94.52 261	97.95 212	87.53 269	94.07 259	97.01 255	93.99 195	97.10 166	95.65 269	92.65 190	98.95 275	87.60 287	96.74 305	97.09 283

LF4IMVS		96.07 164	95.63 175	97.36 125	98.19 181	95.55 79	95.44 187	98.82 99	92.29 239	95.70 229	96.55 233	92.63 191	98.69 300	91.75 209	99.33 164	97.85 259

v2v482		96.78 136	97.06 116	95.95 210	98.57 133	88.77 243	95.36 197	98.26 182	95.18 151	97.85 138	98.23 105	92.58 192	99.63 121	97.80 38	99.69 67	99.45 71

EI-MVSNet		96.63 146	96.93 122	95.74 218	97.26 272	88.13 253	95.29 204	97.65 230	96.99 84	97.94 121	98.19 110	92.55 193	99.58 145	96.91 72	99.56 96	99.50 50

IterMVS-LS		96.92 122	97.29 93	95.79 217	98.51 142	88.13 253	95.10 212	98.66 129	96.99 84	98.46 70	98.68 70	92.55 193	99.74 59	96.91 72	99.79 47	99.50 50
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VDD-MVS		97.37 96	97.25 96	97.74 92	98.69 119	94.50 115	97.04 107	95.61 282	98.59 23	98.51 65	98.72 66	92.54 195	99.58 145	96.02 94	99.49 118	99.12 141

MVS		90.02 299	89.20 306	92.47 305	94.71 324	86.90 280	95.86 165	96.74 264	64.72 350	90.62 326	92.77 316	92.54 195	98.39 319	79.30 332	95.56 322	92.12 343

v144192		96.69 143	96.90 124	96.03 205	98.25 173	88.92 236	95.49 185	98.77 105	93.05 222	98.09 104	98.29 100	92.51 197	99.70 88	98.11 29	99.56 96	99.47 64

testmv		95.51 180	95.33 182	96.05 201	98.23 175	89.51 220	93.50 282	98.63 136	94.25 188	98.22 90	97.73 161	92.51 197	99.47 181	85.22 307	99.72 59	99.17 129

原ACMM1				96.58 165	98.16 188	92.12 174		98.15 196	85.90 302	93.49 292	96.43 242	92.47 199	99.38 220	87.66 280	98.62 231	98.23 235

VNet		96.84 129	96.83 127	96.88 150	98.06 197	92.02 177	96.35 135	97.57 237	97.70 56	97.88 131	97.80 154	92.40 200	99.54 157	94.73 148	98.96 200	99.08 149

114514_t		93.96 237	93.22 242	96.19 192	99.06 82	90.97 193	95.99 154	98.94 72	73.88 348	93.43 296	96.93 210	92.38 201	99.37 223	89.09 260	99.28 171	98.25 234

CPTT-MVS		96.69 143	96.08 160	98.49 46	98.89 99	96.64 49	97.25 92	98.77 105	92.89 230	96.01 217	97.13 198	92.23 202	99.67 109	92.24 198	99.34 159	99.17 129

HSP-MVS		97.37 96	96.85 125	98.92 19	99.26 51	97.70 15	97.66 70	98.23 184	95.65 129	98.51 65	96.46 239	92.15 203	99.81 33	95.14 132	98.58 235	99.26 121

MAR-MVS		94.21 230	93.03 244	97.76 90	96.94 284	97.44 30	96.97 116	97.15 250	87.89 285	92.00 317	92.73 319	92.14 204	99.12 251	83.92 315	97.51 287	96.73 298
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
PVSNet_Blended_VisFu		95.95 168	95.80 170	96.42 175	99.28 50	90.62 199	95.31 202	99.08 30	88.40 276	96.97 176	98.17 115	92.11 205	99.78 39	93.64 179	99.21 177	98.86 181

BH-RMVSNet		94.56 222	94.44 217	94.91 243	97.57 250	87.44 272	93.78 272	96.26 268	93.69 208	96.41 196	96.50 238	92.10 206	99.00 267	85.96 299	97.71 275	98.31 227

新几何1				97.25 132	98.29 159	94.70 109		97.73 222	77.98 341	94.83 246	96.67 228	92.08 207	99.45 190	88.17 275	98.65 229	97.61 268

diffmvs		95.00 207	95.00 193	95.01 241	96.53 292	87.96 261	95.73 169	98.32 179	90.67 258	91.89 319	97.43 182	92.07 208	98.90 277	95.44 117	96.88 300	98.16 242

testdata				95.70 221	98.16 188	90.58 200		97.72 223	80.38 332	95.62 230	97.02 204	92.06 209	98.98 270	89.06 262	98.52 236	97.54 271

YYNet1		94.73 213	94.84 200	94.41 263	97.47 259	85.09 298	90.29 329	95.85 277	92.52 234	97.53 145	97.76 155	91.97 210	99.18 247	93.31 183	96.86 301	98.95 163

Anonymous20231206		95.27 197	95.06 191	95.88 214	98.72 110	89.37 226	95.70 172	97.85 214	88.00 283	96.98 171	97.62 168	91.95 211	99.34 226	89.21 258	99.53 104	98.94 165

MS-PatchMatch		94.83 211	94.91 197	94.57 259	96.81 288	87.10 279	94.23 248	97.34 243	88.74 273	97.14 164	97.11 199	91.94 212	98.23 328	92.99 191	97.92 260	98.37 219

1121		94.26 225	93.26 240	97.27 129	98.26 172	94.73 106	95.86 165	97.71 224	77.96 342	94.53 258	96.71 225	91.93 213	99.40 209	87.71 277	98.64 230	97.69 265

MDA-MVSNet_test_wron		94.73 213	94.83 201	94.42 262	97.48 255	85.15 296	90.28 330	95.87 275	92.52 234	97.48 151	97.76 155	91.92 214	99.17 249	93.32 182	96.80 304	98.94 165

HQP_MVS		96.66 145	96.33 153	97.68 97	98.70 115	94.29 120	96.50 126	98.75 109	96.36 104	96.16 213	96.77 221	91.91 215	99.46 186	92.59 194	99.20 178	99.28 117

plane_prior6					98.38 153	94.37 119						91.91 215

MVS_0304		96.22 159	95.94 168	97.04 141	97.07 280	92.54 162	94.19 251	99.04 45	95.17 152	93.74 282	96.92 211	91.77 217	99.73 64	95.76 103	99.81 43	98.85 183

MVP-Stereo		95.69 173	95.28 183	96.92 147	98.15 190	93.03 157	95.64 180	98.20 188	90.39 259	96.63 186	97.73 161	91.63 218	99.10 255	91.84 205	97.31 295	98.63 200
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_normal		95.51 180	95.46 179	95.68 222	97.97 207	89.12 232	93.73 273	95.86 276	91.98 243	97.17 163	96.94 208	91.55 219	99.42 195	95.21 126	98.73 224	98.51 209

no-one		94.84 210	94.76 202	95.09 238	98.29 159	87.49 270	91.82 315	97.49 238	88.21 279	97.84 139	98.75 64	91.51 220	99.27 238	88.96 263	99.99 2	98.52 208

DI_MVS_plusplus_test		95.46 186	95.43 180	95.55 224	98.05 198	88.84 240	94.18 252	95.75 278	91.92 246	97.32 157	96.94 208	91.44 221	99.39 215	94.81 142	98.48 239	98.43 215

PatchMatch-RL		94.61 220	93.81 232	97.02 144	98.19 181	95.72 73	93.66 275	97.23 246	88.17 280	94.94 243	95.62 271	91.43 222	98.57 308	87.36 291	97.68 278	96.76 297

MDA-MVSNet-bldmvs		95.69 173	95.67 173	95.74 218	98.48 146	88.76 244	92.84 295	97.25 245	96.00 117	97.59 143	97.95 140	91.38 223	99.46 186	93.16 188	96.35 311	98.99 160

PAPR		92.22 268	91.27 273	95.07 239	95.73 312	88.81 241	91.97 313	97.87 213	85.80 303	90.91 324	92.73 319	91.16 224	98.33 325	79.48 331	95.76 319	98.08 244

1314		92.38 265	92.30 256	92.64 304	95.42 318	85.15 296	95.86 165	96.97 257	85.40 309	90.62 326	93.06 312	91.12 225	97.80 336	86.74 295	95.49 323	94.97 328

PLC	91.02 16	94.05 236	92.90 246	97.51 108	98.00 205	95.12 96	94.25 246	98.25 183	86.17 298	91.48 322	95.25 277	91.01 226	99.19 246	85.02 309	96.69 306	98.22 236
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test222					98.17 186	93.24 155	92.74 300	97.61 236	75.17 346	94.65 249	96.69 227	90.96 227			98.66 228	97.66 266

USDC		94.56 222	94.57 211	94.55 260	97.78 235	86.43 286	92.75 298	98.65 135	85.96 300	96.91 179	97.93 143	90.82 228	98.74 295	90.71 233	99.59 89	98.47 211

PCF-MVS	89.43 18	92.12 271	90.64 292	96.57 167	97.80 226	93.48 150	89.88 335	98.45 151	74.46 347	96.04 216	95.68 268	90.71 229	99.31 231	73.73 343	99.01 198	96.91 291
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PAPM_NR		94.61 220	94.17 225	95.96 208	98.36 155	91.23 189	95.93 163	97.95 209	92.98 224	93.42 297	94.43 297	90.53 230	98.38 321	87.60 287	96.29 312	98.27 232

OpenMVS_ROB	91.80 14	93.64 244	93.05 243	95.42 228	97.31 271	91.21 190	95.08 216	96.68 266	81.56 326	96.88 181	96.41 243	90.44 231	99.25 241	85.39 306	97.67 279	95.80 318

HQP2-MVS												90.33 232

N_pmnet		95.18 199	94.23 221	98.06 74	97.85 215	96.55 52	92.49 304	91.63 318	89.34 267	98.09 104	97.41 183	90.33 232	99.06 259	91.58 211	99.31 166	98.56 205

HQP-MVS		95.17 200	94.58 210	96.92 147	97.85 215	92.47 164	94.26 243	98.43 155	93.18 216	92.86 305	95.08 279	90.33 232	99.23 244	90.51 239	98.74 221	99.05 154

CNLPA		95.04 204	94.47 213	96.75 155	97.81 222	95.25 88	94.12 258	97.89 212	94.41 181	94.57 256	95.69 267	90.30 235	98.35 324	86.72 296	98.76 219	96.64 301

PMMVS		92.39 264	91.08 277	96.30 183	93.12 343	92.81 160	90.58 328	95.96 273	79.17 337	91.85 320	92.27 322	90.29 236	98.66 305	89.85 250	96.68 307	97.43 273

TR-MVS		92.54 263	92.20 257	93.57 284	96.49 294	86.66 283	93.51 281	94.73 287	89.96 264	94.95 242	93.87 302	90.24 237	98.61 306	81.18 328	94.88 324	95.45 324

TAMVS		95.49 182	94.94 194	97.16 133	98.31 157	93.41 151	95.07 217	96.82 261	91.09 254	97.51 146	97.82 152	89.96 238	99.42 195	88.42 271	99.44 130	98.64 198

PMMVS2		93.66 243	94.07 227	92.45 306	97.57 250	80.67 325	86.46 342	96.00 271	93.99 195	97.10 166	97.38 189	89.90 239	97.82 335	88.76 265	99.47 123	98.86 181

BH-w/o		92.14 270	91.94 263	92.73 302	97.13 278	85.30 293	92.46 305	95.64 281	89.33 268	94.21 265	92.74 318	89.60 240	98.24 327	81.68 326	94.66 326	94.66 329

UnsupCasMVSNet_bld		94.72 215	94.26 220	96.08 200	98.62 126	90.54 203	93.38 286	98.05 207	90.30 260	97.02 169	96.80 219	89.54 241	99.16 250	88.44 270	96.18 313	98.56 205

MG-MVS		94.08 235	94.00 230	94.32 265	97.09 279	85.89 287	93.19 292	95.96 273	92.52 234	94.93 244	97.51 177	89.54 241	98.77 293	87.52 289	97.71 275	98.31 227

UnsupCasMVSNet_eth		95.91 169	95.73 172	96.44 174	98.48 146	91.52 187	95.31 202	98.45 151	95.76 127	97.48 151	97.54 173	89.53 243	98.69 300	94.43 154	94.61 327	99.13 136

GBi-Net		96.99 112	96.80 130	97.56 103	97.96 208	93.67 141	98.23 34	98.66 129	95.59 133	97.99 114	99.19 32	89.51 244	99.73 64	94.60 150	99.44 130	99.30 110

test1		96.99 112	96.80 130	97.56 103	97.96 208	93.67 141	98.23 34	98.66 129	95.59 133	97.99 114	99.19 32	89.51 244	99.73 64	94.60 150	99.44 130	99.30 110

FMVSNet2		96.72 140	96.67 136	96.87 151	97.96 208	91.88 180	97.15 96	98.06 206	95.59 133	98.50 67	98.62 74	89.51 244	99.65 115	94.99 138	99.60 87	99.07 151

pmmvs4		94.82 212	94.19 224	96.70 158	97.42 262	92.75 161	92.09 312	96.76 262	86.80 294	95.73 228	97.22 194	89.28 247	98.89 280	93.28 184	99.14 182	98.46 213

cascas		91.89 277	91.35 271	93.51 285	94.27 331	85.60 289	88.86 338	98.61 138	79.32 336	92.16 316	91.44 334	89.22 248	98.12 331	90.80 229	97.47 290	96.82 294

DSMNet-mixed		92.19 269	91.83 265	93.25 291	96.18 302	83.68 317	96.27 138	93.68 297	76.97 345	92.54 313	99.18 35	89.20 249	98.55 311	83.88 316	98.60 234	97.51 272

testus		90.90 295	90.51 294	92.06 310	96.07 304	79.45 328	88.99 336	98.44 154	85.46 307	94.15 268	90.77 338	89.12 250	98.01 334	73.66 344	97.95 256	98.71 195

CANet_DTU		94.65 218	94.21 223	95.96 208	95.90 307	89.68 212	93.92 266	97.83 217	93.19 215	90.12 333	95.64 270	88.52 251	99.57 150	93.27 185	99.47 123	98.62 201

EPP-MVSNet		96.84 129	96.58 139	97.65 99	99.18 63	93.78 139	98.68 11	96.34 267	97.91 46	97.30 158	98.06 129	88.46 252	99.85 24	93.85 174	99.40 149	99.32 106

SixPastTwentyTwo		97.49 89	97.57 80	97.26 131	99.56 19	92.33 166	98.28 31	96.97 257	98.30 33	99.45 14	99.35 18	88.43 253	99.89 17	98.01 31	99.76 50	99.54 45

IS-MVSNet		96.93 120	96.68 135	97.70 94	99.25 54	94.00 131	98.57 17	96.74 264	98.36 30	98.14 98	97.98 136	88.23 254	99.71 80	93.10 189	99.72 59	99.38 95

jason		94.39 224	94.04 228	95.41 230	98.29 159	87.85 264	92.74 300	96.75 263	85.38 310	95.29 235	96.15 254	88.21 255	99.65 115	94.24 164	99.34 159	98.74 192
jason: jason.
Patchmatch-test1		93.38 250	93.59 235	92.73 302	96.24 298	81.40 322	93.24 290	94.00 293	91.58 250	94.57 256	96.67 228	87.94 256	99.03 264	90.42 242	97.66 280	97.77 263

sss		94.22 227	93.72 233	95.74 218	97.71 240	89.95 209	93.84 269	96.98 256	88.38 278	93.75 281	95.74 266	87.94 256	98.89 280	91.02 221	98.10 252	98.37 219

IterMVS		95.42 189	95.83 169	94.20 268	97.52 254	83.78 316	92.41 306	97.47 242	95.49 137	98.06 109	98.49 83	87.94 256	99.58 145	96.02 94	99.02 196	99.23 123
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		94.10 233	93.41 238	96.18 193	99.16 64	90.04 206	92.15 309	98.68 124	79.90 334	96.22 210	97.83 149	87.92 259	99.42 195	89.18 259	99.65 76	99.08 149

VDDNet		96.98 115	96.84 126	97.41 122	99.40 41	93.26 154	97.94 53	95.31 284	99.26 6	98.39 74	99.18 35	87.85 260	99.62 127	95.13 133	99.09 189	99.35 104

pmmvs5		94.63 219	94.34 219	95.50 226	97.63 248	88.34 249	94.02 260	97.13 251	87.15 290	95.22 237	97.15 197	87.50 261	99.27 238	93.99 171	99.26 174	98.88 178

semantic-postprocess				94.85 247	97.68 242	85.53 290		97.63 234	96.99 84	98.36 76	98.54 80	87.44 262	99.75 54	97.07 69	99.08 190	99.27 120

PVSNet	86.72 19	91.10 290	90.97 286	91.49 313	97.56 252	78.04 334	87.17 340	94.60 289	84.65 314	92.34 314	92.20 323	87.37 263	98.47 314	85.17 308	97.69 277	97.96 256

Test4		95.39 190	95.24 184	95.82 216	98.07 196	89.60 216	94.40 240	98.49 148	91.39 252	97.40 156	96.32 248	87.32 264	99.41 206	95.09 136	98.71 226	98.44 214

MVSFormer		96.14 163	96.36 151	95.49 227	97.68 242	87.81 265	98.67 12	99.02 51	96.50 99	94.48 261	96.15 254	86.90 265	99.92 4	98.73 17	99.13 184	98.74 192

lupinMVS		93.77 239	93.28 239	95.24 233	97.68 242	87.81 265	92.12 310	96.05 270	84.52 315	94.48 261	95.06 281	86.90 265	99.63 121	93.62 180	99.13 184	98.27 232

WTY-MVS		93.55 246	93.00 245	95.19 234	97.81 222	87.86 263	93.89 267	96.00 271	89.02 269	94.07 271	95.44 275	86.27 267	99.33 229	87.69 279	96.82 302	98.39 218

CDS-MVSNet		94.88 209	94.12 226	97.14 135	97.64 247	93.57 146	93.96 265	97.06 254	90.05 263	96.30 206	96.55 233	86.10 268	99.47 181	90.10 247	99.31 166	98.40 216
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1112_ss		94.12 232	93.42 237	96.23 187	98.59 130	90.85 194	94.24 247	98.85 84	85.49 305	92.97 303	94.94 283	86.01 269	99.64 118	91.78 206	97.92 260	98.20 238

new_pmnet		92.34 266	91.69 267	94.32 265	96.23 300	89.16 230	92.27 308	92.88 307	84.39 318	95.29 235	96.35 247	85.66 270	96.74 345	84.53 312	97.56 284	97.05 285

alignmvs		96.01 166	95.52 177	97.50 111	97.77 236	94.71 108	96.07 149	96.84 260	97.48 69	96.78 183	94.28 300	85.50 271	99.40 209	96.22 86	98.73 224	98.40 216

lessismore_v0				97.05 140	99.36 45	92.12 174		84.07 351		98.77 50	98.98 50	85.36 272	99.74 59	97.34 59	99.37 151	99.30 110

test1235678		92.95 254	92.40 254	94.61 255	96.95 283	86.87 281	90.75 326	97.75 220	91.00 256	96.33 199	95.38 276	85.21 273	98.92 276	79.00 333	99.20 178	98.03 252

HY-MVS	91.43 15	92.58 258	91.81 266	94.90 245	96.49 294	88.87 238	97.31 89	94.62 288	85.92 301	90.50 330	96.84 215	85.05 274	99.40 209	83.77 318	95.78 318	96.43 310

EPNet		93.72 241	92.62 253	97.03 143	87.61 355	92.25 168	96.27 138	91.28 320	96.74 94	87.65 343	97.39 187	85.00 275	99.64 118	92.14 199	99.48 121	99.20 125
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Test_1112_low_res		93.53 247	92.86 247	95.54 225	98.60 128	88.86 239	92.75 298	98.69 122	82.66 323	92.65 310	96.92 211	84.75 276	99.56 151	90.94 224	97.76 264	98.19 239

MVS-HIRNet		88.40 313	90.20 299	82.99 337	97.01 281	60.04 355	93.11 293	85.61 349	84.45 317	88.72 339	99.09 45	84.72 277	98.23 328	82.52 321	96.59 308	90.69 348

K. test v3		96.44 154	96.28 154	96.95 145	99.41 40	91.53 186	97.65 71	90.31 331	98.89 18	98.93 43	99.36 16	84.57 278	99.92 4	97.81 37	99.56 96	99.39 93

Vis-MVSNet (Re-imp)		95.11 201	94.85 199	95.87 215	99.12 76	89.17 229	97.54 83	94.92 286	96.50 99	96.58 187	97.27 193	83.64 279	99.48 179	88.42 271	99.67 73	98.97 161

PVSNet_0	81.89 21	84.49 324	83.21 327	88.34 330	95.76 311	74.97 344	83.49 346	92.70 311	78.47 340	87.94 342	86.90 349	83.38 280	96.63 346	73.44 345	66.86 352	93.40 339

CMPMVS	73.10 23	92.74 257	91.39 269	96.77 154	93.57 340	94.67 110	94.21 250	97.67 226	80.36 333	93.61 288	96.60 231	82.85 281	97.35 339	84.86 310	98.78 217	98.29 231
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		94.25 226	94.47 213	93.60 283	98.14 191	82.60 319	97.24 94	92.72 310	85.08 311	98.48 68	98.94 54	82.59 282	98.76 294	97.47 56	99.53 104	99.44 79

LP		93.12 253	92.78 251	94.14 269	94.50 328	85.48 291	95.73 169	95.68 280	92.97 228	95.05 240	97.17 196	81.93 283	99.40 209	93.06 190	88.96 342	97.55 270

CVMVSNet		92.33 267	92.79 249	90.95 319	97.26 272	75.84 341	95.29 204	92.33 313	81.86 324	96.27 207	98.19 110	81.44 284	98.46 315	94.23 165	98.29 243	98.55 207

EPNet_dtu		91.39 289	90.75 290	93.31 289	90.48 353	82.61 318	94.80 231	92.88 307	93.39 211	81.74 351	94.90 286	81.36 285	99.11 254	88.28 273	98.87 211	98.21 237
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MIMVSNet		93.42 248	92.86 247	95.10 237	98.17 186	88.19 250	98.13 43	93.69 295	92.07 240	95.04 241	98.21 109	80.95 286	99.03 264	81.42 327	98.06 253	98.07 246

PAPM		87.64 320	85.84 323	93.04 295	96.54 291	84.99 299	88.42 339	95.57 283	79.52 335	83.82 348	93.05 313	80.57 287	98.41 317	62.29 351	92.79 333	95.71 319

HyFIR lowres test		93.72 241	92.65 252	96.91 149	98.93 94	91.81 183	91.23 323	98.52 145	82.69 322	96.46 194	96.52 237	80.38 288	99.90 13	90.36 244	98.79 216	99.03 155

FMVSNet3		95.26 198	94.94 194	96.22 191	96.53 292	90.06 205	95.99 154	97.66 228	94.11 194	97.99 114	97.91 145	80.22 289	99.63 121	94.60 150	99.44 130	98.96 162

RPMNet		94.22 227	94.03 229	94.78 249	95.44 316	88.15 251	96.18 145	93.73 294	97.43 70	94.10 269	98.49 83	79.40 290	99.39 215	95.69 104	95.81 315	96.81 295

LFMVS		95.32 194	94.88 198	96.62 161	98.03 199	91.47 188	97.65 71	90.72 326	99.11 8	97.89 129	98.31 96	79.20 291	99.48 179	93.91 173	99.12 187	98.93 168

ADS-MVSNet2		91.47 288	90.51 294	94.36 264	95.51 314	85.63 288	95.05 220	95.70 279	83.46 320	92.69 308	96.84 215	79.15 292	99.41 206	85.66 303	90.52 337	98.04 250

ADS-MVSNet		90.95 294	90.26 297	93.04 295	95.51 314	82.37 320	95.05 220	93.41 301	83.46 320	92.69 308	96.84 215	79.15 292	98.70 299	85.66 303	90.52 337	98.04 250

MDTV_nov1_ep13_2view						57.28 356	94.89 226		80.59 331	94.02 273		78.66 294		85.50 305		97.82 261

PatchmatchNet		91.98 273	91.87 264	92.30 308	94.60 326	79.71 327	95.12 211	93.59 300	89.52 266	93.61 288	97.02 204	77.94 295	99.18 247	90.84 227	94.57 328	98.01 255
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												77.80 296				98.06 247

CR-MVSNet		93.29 251	92.79 249	94.78 249	95.44 316	88.15 251	96.18 145	97.20 247	84.94 313	94.10 269	98.57 76	77.67 297	99.39 215	95.17 129	95.81 315	96.81 295

Patchmtry		95.03 205	94.59 209	96.33 180	94.83 323	90.82 196	96.38 133	97.20 247	96.59 97	97.49 148	98.57 76	77.67 297	99.38 220	92.95 192	99.62 79	98.80 186

tpmrst		90.31 297	90.61 293	89.41 326	94.06 335	72.37 348	95.06 219	93.69 295	88.01 282	92.32 315	96.86 213	77.45 299	98.82 288	91.04 220	87.01 345	97.04 286

sam_mvs												77.38 300

patchmatchnet-post											96.84 215	77.36 301	99.42 195

Patchmatch-RL test		94.66 217	94.49 212	95.19 234	98.54 138	88.91 237	92.57 302	98.74 111	91.46 251	98.32 81	97.75 158	77.31 302	98.81 290	96.06 90	99.61 84	97.85 259

tpmvs		90.79 296	90.87 287	90.57 322	92.75 347	76.30 339	95.79 168	93.64 298	91.04 255	91.91 318	96.26 249	77.19 303	98.86 286	89.38 256	89.85 340	96.56 304

test_post											10.87 355	76.83 304	99.07 258

Patchmatch-test		93.60 245	93.25 241	94.63 254	96.14 303	87.47 271	96.04 151	94.50 290	93.57 209	96.47 193	96.97 206	76.50 305	98.61 306	90.67 235	98.41 242	97.81 262

MDTV_nov1_ep13			91.28 272		94.31 330	73.51 345	94.80 231	93.16 304	86.75 295	93.45 295	97.40 184	76.37 306	98.55 311	88.85 264	96.43 309

EMVS		89.06 308	89.22 304	88.61 329	93.00 344	77.34 337	82.91 348	90.92 323	94.64 172	92.63 311	91.81 327	76.30 307	97.02 341	83.83 317	96.90 299	91.48 346

test_post1							94.98 224				10.37 356	76.21 308	99.04 261	89.47 255

GA-MVS		92.83 256	92.15 258	94.87 246	96.97 282	87.27 276	90.03 331	96.12 269	91.83 248	94.05 272	94.57 288	76.01 309	98.97 274	92.46 196	97.34 294	98.36 224

PatchT		93.75 240	93.57 236	94.29 267	95.05 321	87.32 275	96.05 150	92.98 305	97.54 65	94.25 264	98.72 66	75.79 310	99.24 242	95.92 99	95.81 315	96.32 311

E-PMN		89.52 306	89.78 301	88.73 328	93.14 342	77.61 336	83.26 347	92.02 314	94.82 168	93.71 283	93.11 307	75.31 311	96.81 343	85.81 300	96.81 303	91.77 345

DeepMVS_CX				77.17 339	90.94 352	85.28 294		74.08 356	52.51 351	80.87 352	88.03 347	75.25 312	70.63 354	59.23 352	84.94 347	75.62 349

CHOSEN 280x420		89.98 301	89.19 307	92.37 307	95.60 313	81.13 323	86.22 343	97.09 253	81.44 328	87.44 344	93.15 306	73.99 313	99.47 181	88.69 267	99.07 192	96.52 305

thres200		91.00 292	90.42 296	92.77 301	97.47 259	83.98 315	94.01 261	91.18 322	95.12 158	95.44 232	91.21 336	73.93 314	99.31 231	77.76 339	97.63 283	95.01 327

test-LLR		89.97 302	89.90 300	90.16 323	94.24 332	74.98 342	89.89 332	89.06 337	92.02 241	89.97 334	90.77 338	73.92 315	98.57 308	91.88 203	97.36 292	96.92 289

test0.0.03 1		90.11 298	89.21 305	92.83 300	93.89 336	86.87 281	91.74 316	88.74 339	92.02 241	94.71 248	91.14 337	73.92 315	94.48 349	83.75 319	92.94 331	97.16 282

tpm cat1		88.01 316	87.33 316	90.05 325	94.48 329	76.28 340	94.47 239	94.35 292	73.84 349	89.26 337	95.61 272	73.64 317	98.30 326	84.13 313	86.20 346	95.57 323

tfpn200view9		91.55 287	91.00 278	93.21 292	98.02 200	84.35 312	95.70 172	90.79 324	96.26 108	95.90 222	92.13 324	73.62 318	99.42 195	78.85 335	97.74 265	95.85 316

view600		92.56 259	92.11 259	93.91 274	98.45 148	84.76 303	97.10 101	90.23 332	97.42 71	96.98 171	94.48 292	73.62 318	99.60 139	82.49 322	98.28 244	97.36 275

view800		92.56 259	92.11 259	93.91 274	98.45 148	84.76 303	97.10 101	90.23 332	97.42 71	96.98 171	94.48 292	73.62 318	99.60 139	82.49 322	98.28 244	97.36 275

conf0.05thres1000		92.56 259	92.11 259	93.91 274	98.45 148	84.76 303	97.10 101	90.23 332	97.42 71	96.98 171	94.48 292	73.62 318	99.60 139	82.49 322	98.28 244	97.36 275

tfpn		92.56 259	92.11 259	93.91 274	98.45 148	84.76 303	97.10 101	90.23 332	97.42 71	96.98 171	94.48 292	73.62 318	99.60 139	82.49 322	98.28 244	97.36 275

thres400		91.68 286	91.00 278	93.71 281	98.02 200	84.35 312	95.70 172	90.79 324	96.26 108	95.90 222	92.13 324	73.62 318	99.42 195	78.85 335	97.74 265	97.36 275

tfpn111		91.92 274	91.39 269	93.49 286	98.21 177	84.50 308	96.39 129	90.39 327	96.87 88	96.33 199	93.08 309	73.44 324	99.51 172	79.87 330	97.94 259	96.46 306

conf200view11		91.81 279	91.26 274	93.46 287	98.21 177	84.50 308	96.39 129	90.39 327	96.87 88	96.33 199	93.08 309	73.44 324	99.42 195	78.85 335	97.74 265	96.46 306

thres100view900		91.76 281	91.26 274	93.26 290	98.21 177	84.50 308	96.39 129	90.39 327	96.87 88	96.33 199	93.08 309	73.44 324	99.42 195	78.85 335	97.74 265	95.85 316

thres600view7		92.03 272	91.43 268	93.82 279	98.19 181	84.61 307	96.27 138	90.39 327	96.81 92	96.37 198	93.11 307	73.44 324	99.49 176	80.32 329	97.95 256	97.36 275

MVSTER		94.21 230	93.93 231	95.05 240	95.83 309	86.46 285	95.18 210	97.65 230	92.41 238	97.94 121	98.00 135	72.39 328	99.58 145	96.36 84	99.56 96	99.12 141

PatchFormer-LS_test		89.62 305	89.12 308	91.11 318	93.62 338	78.42 331	94.57 238	93.62 299	88.39 277	90.54 329	88.40 346	72.33 329	99.03 264	92.41 197	88.20 343	95.89 315

JIA-IIPM		91.79 280	90.69 291	95.11 236	93.80 337	90.98 192	94.16 254	91.78 317	96.38 103	90.30 332	99.30 23	72.02 330	98.90 277	88.28 273	90.17 339	95.45 324

tpm		91.08 291	90.85 288	91.75 312	95.33 319	78.09 332	95.03 222	91.27 321	88.75 272	93.53 291	97.40 184	71.24 331	99.30 233	91.25 217	93.87 329	97.87 258

CostFormer		89.75 304	89.25 303	91.26 316	94.69 325	78.00 335	95.32 201	91.98 315	81.50 327	90.55 328	96.96 207	71.06 332	98.89 280	88.59 269	92.63 334	96.87 292

FPMVS		89.92 303	88.63 310	93.82 279	98.37 154	96.94 41	91.58 317	93.34 302	88.00 283	90.32 331	97.10 200	70.87 333	91.13 351	71.91 347	96.16 314	93.39 340

EPMVS		89.26 307	88.55 311	91.39 314	92.36 348	79.11 329	95.65 178	79.86 352	88.60 274	93.12 302	96.53 235	70.73 334	98.10 332	90.75 231	89.32 341	96.98 287

test12356		87.98 317	88.41 312	86.69 335	95.84 308	63.49 352	87.15 341	97.32 244	87.21 288	91.78 321	93.36 305	70.66 335	98.39 319	74.70 342	97.64 282	98.19 239

tmp_tt		57.23 328	62.50 329	41.44 341	34.77 356	49.21 357	83.93 345	60.22 358	15.31 352	71.11 353	79.37 351	70.09 336	44.86 355	64.76 350	82.93 350	30.25 352

conf0.01		91.90 275	90.98 280	94.67 252	98.27 164	88.03 255	96.98 110	88.58 340	93.90 198	94.64 250	91.45 328	69.62 337	99.52 162	87.62 281	97.74 265	96.46 306

conf0.002		91.90 275	90.98 280	94.67 252	98.27 164	88.03 255	96.98 110	88.58 340	93.90 198	94.64 250	91.45 328	69.62 337	99.52 162	87.62 281	97.74 265	96.46 306

thresconf0.02		91.72 282	90.98 280	93.97 270	98.27 164	88.03 255	96.98 110	88.58 340	93.90 198	94.64 250	91.45 328	69.62 337	99.52 162	87.62 281	97.74 265	94.35 332

tfpn_n400		91.72 282	90.98 280	93.97 270	98.27 164	88.03 255	96.98 110	88.58 340	93.90 198	94.64 250	91.45 328	69.62 337	99.52 162	87.62 281	97.74 265	94.35 332

tfpnconf		91.72 282	90.98 280	93.97 270	98.27 164	88.03 255	96.98 110	88.58 340	93.90 198	94.64 250	91.45 328	69.62 337	99.52 162	87.62 281	97.74 265	94.35 332

tfpnview11		91.72 282	90.98 280	93.97 270	98.27 164	88.03 255	96.98 110	88.58 340	93.90 198	94.64 250	91.45 328	69.62 337	99.52 162	87.62 281	97.74 265	94.35 332

dp		88.08 315	88.05 313	88.16 332	92.85 345	68.81 350	94.17 253	92.88 307	85.47 306	91.38 323	96.14 256	68.87 343	98.81 290	86.88 294	83.80 349	96.87 292

tfpn1000		91.88 278	91.20 276	93.89 278	97.96 208	87.13 278	97.13 99	88.16 347	94.41 181	94.87 245	92.77 316	68.34 344	99.47 181	89.24 257	97.95 256	95.06 326

tfpn_ndepth		90.98 293	90.24 298	93.20 294	97.72 239	87.18 277	96.52 125	88.20 346	92.63 233	93.69 285	90.70 341	68.22 345	99.42 195	86.98 293	97.47 290	93.00 342

tpm2		88.47 311	87.69 314	90.79 320	94.98 322	77.34 337	95.09 214	91.83 316	77.51 344	89.40 336	96.41 243	67.83 346	98.73 296	83.58 320	92.60 335	96.29 312

pmmvs3		90.00 300	88.90 309	93.32 288	94.20 334	85.34 292	91.25 322	92.56 312	78.59 339	93.82 278	95.17 278	67.36 347	98.69 300	89.08 261	98.03 254	95.92 314

tpmp4_e23		88.46 312	87.54 315	91.22 317	94.56 327	78.08 333	95.63 183	93.17 303	79.08 338	85.85 346	96.80 219	65.86 348	98.85 287	84.10 314	92.85 332	96.72 299

FMVSNet5		93.39 249	92.35 255	96.50 170	95.83 309	90.81 198	97.31 89	98.27 180	92.74 232	96.27 207	98.28 101	62.23 349	99.67 109	90.86 226	99.36 154	99.03 155

DWT-MVSNet_test		87.92 318	86.77 320	91.39 314	93.18 341	78.62 330	95.10 212	91.42 319	85.58 304	88.00 341	88.73 345	60.60 350	98.90 277	90.60 236	87.70 344	96.65 300

IB-MVS	85.98 20	88.63 310	86.95 319	93.68 282	95.12 320	84.82 302	90.85 325	90.17 336	87.55 286	88.48 340	91.34 335	58.01 351	99.59 143	87.24 292	93.80 330	96.63 303
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
gg-mvs-nofinetune		88.28 314	86.96 318	92.23 309	92.84 346	84.44 311	98.19 40	74.60 354	99.08 9	87.01 345	99.47 8	56.93 352	98.23 328	78.91 334	95.61 321	94.01 336

GG-mvs-BLEND				90.60 321	91.00 351	84.21 314	98.23 34	72.63 357		82.76 349	84.11 350	56.14 353	96.79 344	72.20 346	92.09 336	90.78 347

TESTMET0.1,1		87.20 321	86.57 321	89.07 327	93.62 338	72.84 347	89.89 332	87.01 348	85.46 307	89.12 338	90.20 343	56.00 354	97.72 337	90.91 225	96.92 298	96.64 301

test-mter		87.92 318	87.17 317	90.16 323	94.24 332	74.98 342	89.89 332	89.06 337	86.44 296	89.97 334	90.77 338	54.96 355	98.57 308	91.88 203	97.36 292	96.92 289

test2356		85.45 323	83.26 326	92.01 311	91.12 350	80.76 324	85.16 344	92.90 306	83.90 319	90.63 325	87.71 348	53.10 356	97.24 340	69.20 349	95.65 320	98.03 252

PNet_i23d		83.82 325	83.39 325	85.10 336	96.07 304	65.16 351	81.87 349	94.37 291	90.87 257	93.92 277	92.89 315	52.80 357	96.44 347	77.52 341	70.22 351	93.70 337

testpf		82.70 326	84.35 324	77.74 338	88.97 354	73.23 346	93.85 268	84.33 350	88.10 281	85.06 347	90.42 342	52.62 358	91.05 352	91.00 222	84.82 348	68.93 351

1111		88.78 309	89.39 302	86.96 334	98.53 140	62.84 353	91.49 318	97.48 240	94.45 178	96.56 189	96.45 240	43.83 359	98.87 284	86.33 297	99.40 149	99.18 128

.test1245		73.49 327	79.27 328	56.15 340	98.53 140	62.84 353	91.49 318	97.48 240	94.45 178	96.56 189	96.45 240	43.83 359	98.87 284	86.33 297	8.32 354	6.75 354

test123		12.59 331	15.49 332	3.87 343	6.07 357	2.55 358	90.75 326	2.59 360	2.52 353	5.20 355	13.02 354	4.96 361	1.85 357	5.20 353	9.09 353	7.23 353

testmvs		12.33 332	15.23 333	3.64 344	5.77 358	2.23 359	88.99 336	3.62 359	2.30 354	5.29 354	13.09 353	4.52 362	1.95 356	5.16 354	8.32 354	6.75 354

sosnet-low-res		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

sosnet		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

uncertanet		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

Regformer		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

ab-mvs-re		7.91 334	10.55 335	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	94.94 283	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

uanet		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

GSMVS																98.06 247

test_part3							95.64 180		94.84 165		97.60 170		99.76 48	91.22 218

test_part2					99.03 86	96.07 64				98.08 106

MTGPA								98.73 112

MTMP								74.60 354

gm-plane-assit					91.79 349	71.40 349			81.67 325		90.11 344		98.99 268	84.86 310

test9_res														91.29 214	98.89 210	99.00 157

agg_prior2														90.34 245	98.90 206	99.10 148

agg_prior					97.80 226	94.96 100		98.36 165		93.49 292			99.53 159

test_prior4						95.38 85	93.61 279

test_prior				97.46 117	97.79 231	94.26 123		98.42 158					99.34 226			98.79 187

旧先验2							93.35 287		77.95 343	95.77 227			98.67 304	90.74 232

新几何2							93.43 283

无先验							93.20 291	97.91 210	80.78 330				99.40 209	87.71 277		97.94 257

原ACMM2							92.82 296

testdata2													99.46 186	87.84 276

testdata1							92.77 297		93.78 205

plane_prior7					98.70 115	94.67 110

plane_prior5								98.75 109					99.46 186	92.59 194	99.20 178	99.28 117

plane_prior4											96.77 221

plane_prior3						94.51 113			95.29 144	96.16 213

plane_prior2							96.50 126		96.36 104

plane_prior1					98.49 144

plane_prior						94.29 120	95.42 192		94.31 187						98.93 205

n2								0.00 361

nn								0.00 361

door-mid								98.17 193

test11								98.08 203

door								97.81 218

HQP5-MVS						92.47 164

HQP-NCC					97.85 215		94.26 243		93.18 216	92.86 305

ACMP_Plane					97.85 215		94.26 243		93.18 216	92.86 305

BP-MVS														90.51 239

HQP4-MVS										92.87 304			99.23 244			99.06 153

HQP3-MVS								98.43 155							98.74 221

NP-MVS					98.14 191	93.72 140					95.08 279

ACMMP++_ref															99.52 108

ACMMP++															99.55 100

High-resolution multi-view benchmark