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		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 2	99.98 1	99.99 1	99.96 1	99.77 1	100.00 1	99.81 1	100.00 1	99.85 7

ANet_high		99.57 7	99.67 5	99.28 79	99.89 6	98.09 127	99.14 40	99.93 1	99.82 3	99.93 2	99.81 3	99.17 12	99.94 23	99.31 16	100.00 1	99.82 9

PS-MVSNAJss		99.46 12	99.49 10	99.35 69	99.90 4	98.15 123	99.20 32	99.65 18	99.48 24	99.92 3	99.71 12	98.07 64	99.96 8	99.53 9	100.00 1	99.93 1

mvs_tets		99.63 5	99.67 5	99.49 48	99.88 7	98.61 87	99.34 13	99.71 10	99.27 43	99.90 4	99.74 8	99.68 2	99.97 3	99.55 8	99.99 5	99.88 3

wuyk23d		96.06 273	97.62 185	91.38 344	98.65 264	98.57 91	98.85 64	96.95 322	96.86 222	99.90 4	99.16 86	99.18 11	98.40 357	89.23 342	99.77 90	77.18 361

jajsoiax		99.58 6	99.61 7	99.48 50	99.87 10	98.61 87	99.28 27	99.66 17	99.09 65	99.89 6	99.68 14	99.53 4	99.97 3	99.50 10	99.99 5	99.87 4

UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 14	99.34 14	99.69 4	99.58 26	99.90 2	99.86 7	99.78 5	99.58 3	99.95 15	99.00 33	99.95 16	99.78 14

pmmvs6		99.67 3	99.70 3	99.60 13	99.90 4	99.27 20	99.53 7	99.76 7	99.64 12	99.84 8	99.83 2	99.50 5	99.87 83	99.36 14	99.92 34	99.64 39

Anonymous20231211		99.27 25	99.27 24	99.26 85	99.29 122	98.18 120	99.49 8	99.51 55	99.70 8	99.80 9	99.68 14	96.84 149	99.83 136	99.21 23	99.91 40	99.77 16

OurMVSNet-221017-0		99.37 21	99.31 22	99.53 36	99.91 3	98.98 61	99.63 6	99.58 26	99.44 29	99.78 10	99.76 6	96.39 176	99.92 35	99.44 13	99.92 34	99.68 31

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 24	99.85 13	99.11 55	99.90 1	99.78 4	99.63 14	99.78 10	99.67 16	99.48 6	99.81 159	99.30 17	99.97 11	99.77 16
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)		99.44 13	99.47 12	99.36 64	99.80 17	98.58 90	99.27 29	99.57 33	99.39 32	99.75 12	99.62 21	99.17 12	99.83 136	99.06 30	99.62 153	99.66 34

NR-MVSNet		98.95 47	98.82 49	99.36 64	99.16 154	98.72 81	99.22 31	99.20 168	99.10 62	99.72 13	98.76 181	96.38 178	99.86 91	98.00 90	99.82 65	99.50 100

MIMVSNet1		99.38 20	99.32 21	99.55 26	99.86 11	99.19 34	99.41 10	99.59 24	99.59 20	99.71 14	99.57 27	97.12 134	99.90 49	99.21 23	99.87 52	99.54 83

test_djsdf		99.52 9	99.51 9	99.53 36	99.86 11	98.74 76	99.39 11	99.56 40	99.11 56	99.70 15	99.73 10	99.00 15	99.97 3	99.26 18	99.98 9	99.89 2

SixPastTwentyTwo		98.75 71	98.62 73	99.16 97	99.83 15	97.96 148	99.28 27	98.20 290	99.37 34	99.70 15	99.65 19	92.65 272	99.93 28	99.04 31	99.84 56	99.60 49

new-patchmatchnet		98.35 132	98.74 56	97.18 277	99.24 129	92.23 320	96.42 268	99.48 67	98.30 111	99.69 17	99.53 33	97.44 116	99.82 146	98.84 42	99.77 90	99.49 104

LCM-MVSNet-Re		98.64 91	98.48 95	99.11 104	98.85 220	98.51 97	98.49 94	99.83 3	98.37 105	99.69 17	99.46 43	98.21 56	99.92 35	94.13 277	99.30 228	98.91 256

v7n		99.53 8	99.57 8	99.41 60	99.88 7	98.54 95	99.45 9	99.61 22	99.66 11	99.68 19	99.66 17	98.44 39	99.95 15	99.73 2	99.96 14	99.75 22

SED-MVS		98.91 51	98.72 59	99.49 48	99.49 84	99.17 36	98.10 130	99.31 130	98.03 132	99.66 20	99.02 115	98.36 43	99.88 67	96.91 147	99.62 153	99.41 141

test_241102_ONE					99.49 84	99.17 36		99.31 130	97.98 134	99.66 20	98.90 146	98.36 43	99.48 309

anonymousdsp		99.51 10	99.47 12	99.62 6	99.88 7	99.08 59	99.34 13	99.69 13	98.93 79	99.65 22	99.72 11	98.93 19	99.95 15	99.11 27	100.00 1	99.82 9

pm-mvs1		99.44 13	99.48 11	99.33 74	99.80 17	98.63 84	99.29 23	99.63 19	99.30 41	99.65 22	99.60 25	99.16 14	99.82 146	99.07 29	99.83 62	99.56 71

ACMH	96.65 7	99.25 27	99.24 26	99.26 85	99.72 29	98.38 104	99.07 46	99.55 44	98.30 111	99.65 22	99.45 47	99.22 9	99.76 206	98.44 65	99.77 90	99.64 39
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_part1		97.91 167	97.46 197	99.27 82	98.80 233	98.18 120	99.07 46	99.36 106	99.75 5	99.63 25	99.49 39	82.20 340	99.89 58	98.87 40	99.95 16	99.74 24

SD-MVS		98.40 127	98.68 66	97.54 262	98.96 196	97.99 139	97.88 156	99.36 106	98.20 123	99.63 25	99.04 111	98.76 23	95.33 363	96.56 183	99.74 103	99.31 184
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
DIV-MVS_2432*1600		99.25 27	99.18 28	99.44 56	99.63 48	99.06 60	98.69 73	99.54 48	99.31 39	99.62 27	99.53 33	97.36 121	99.86 91	99.24 22	99.71 117	99.39 150

PEN-MVS		99.41 17	99.34 19	99.62 6	99.73 24	99.14 48	99.29 23	99.54 48	99.62 17	99.56 28	99.42 49	98.16 60	99.96 8	98.78 44	99.93 25	99.77 16

DTE-MVSNet		99.43 15	99.35 17	99.66 4	99.71 30	99.30 16	99.31 18	99.51 55	99.64 12	99.56 28	99.46 43	98.23 52	99.97 3	98.78 44	99.93 25	99.72 25

Anonymous20240529		98.93 49	98.87 44	99.12 102	99.19 143	98.22 117	99.01 50	98.99 223	99.25 44	99.54 30	99.37 54	97.04 137	99.80 168	97.89 93	99.52 189	99.35 170

EU-MVSNet		97.66 191	98.50 90	95.13 325	99.63 48	85.84 352	98.35 109	98.21 289	98.23 119	99.54 30	99.46 43	95.02 223	99.68 245	98.24 74	99.87 52	99.87 4

DeepC-MVS	97.60 4	98.97 44	98.93 42	99.10 106	99.35 115	97.98 143	98.01 145	99.46 75	97.56 165	99.54 30	99.50 36	98.97 16	99.84 122	98.06 85	99.92 34	99.49 104
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TDRefinement		99.42 16	99.38 15	99.55 26	99.76 22	99.33 15	99.68 5	99.71 10	99.38 33	99.53 33	99.61 23	98.64 28	99.80 168	98.24 74	99.84 56	99.52 93

ACMH+	96.62 9	99.08 34	99.00 39	99.33 74	99.71 30	98.83 70	98.60 79	99.58 26	99.11 56	99.53 33	99.18 80	98.81 22	99.67 248	96.71 171	99.77 90	99.50 100

v8		99.01 37	99.16 30	98.57 184	99.47 94	96.31 228	98.90 59	99.47 73	99.03 68	99.52 35	99.57 27	96.93 145	99.81 159	99.60 4	99.98 9	99.60 49

VPA-MVSNet		99.30 24	99.30 23	99.28 79	99.49 84	98.36 106	99.00 52	99.45 78	99.63 14	99.52 35	99.44 48	98.25 50	99.88 67	99.09 28	99.84 56	99.62 44

K. test v3		98.00 162	97.66 181	99.03 123	99.79 19	97.56 179	99.19 36	92.47 354	99.62 17	99.52 35	99.66 17	89.61 290	99.96 8	99.25 20	99.81 69	99.56 71

tfpnnormal		98.90 53	98.90 43	98.91 138	99.67 40	97.82 162	99.00 52	99.44 81	99.45 28	99.51 38	99.24 72	98.20 57	99.86 91	95.92 220	99.69 128	99.04 233

WR-MVS_H		99.33 23	99.22 27	99.65 5	99.71 30	99.24 23	99.32 15	99.55 44	99.46 27	99.50 39	99.34 60	97.30 123	99.93 28	98.90 37	99.93 25	99.77 16

v10		98.97 44	99.11 33	98.55 189	99.44 100	96.21 230	98.90 59	99.55 44	98.73 88	99.48 40	99.60 25	96.63 165	99.83 136	99.70 3	99.99 5	99.61 48

DP-MVS		98.93 49	98.81 51	99.28 79	99.21 136	98.45 101	98.46 99	99.33 123	99.63 14	99.48 40	99.15 90	97.23 131	99.75 213	97.17 128	99.66 144	99.63 43

N_pmnet		97.63 194	97.17 213	98.99 129	99.27 124	97.86 156	95.98 284	93.41 351	95.25 272	99.47 42	98.90 146	95.63 206	99.85 105	96.91 147	99.73 106	99.27 194

nrg030		99.40 18	99.35 17	99.54 29	99.58 51	99.13 51	98.98 55	99.48 67	99.68 9	99.46 43	99.26 69	98.62 29	99.73 221	99.17 26	99.92 34	99.76 20

PS-CasMVS		99.40 18	99.33 20	99.62 6	99.71 30	99.10 56	99.29 23	99.53 51	99.53 23	99.46 43	99.41 51	98.23 52	99.95 15	98.89 39	99.95 16	99.81 11

v1240		98.55 108	98.62 73	98.32 211	99.22 134	95.58 243	97.51 197	99.45 78	97.16 209	99.45 45	99.24 72	96.12 185	99.85 105	99.60 4	99.88 49	99.55 79

DPE-MVS		98.59 102	98.26 128	99.57 18	99.27 124	99.15 45	97.01 232	99.39 96	97.67 154	99.44 46	98.99 125	97.53 105	99.89 58	95.40 244	99.68 133	99.66 34
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
FMVSNet1		99.17 30	99.17 29	99.17 94	99.55 65	98.24 112	99.20 32	99.44 81	99.21 45	99.43 47	99.55 29	97.82 83	99.86 91	98.42 67	99.89 48	99.41 141

pmmvs-eth3d		98.47 119	98.34 119	98.86 145	99.30 121	97.76 167	97.16 227	99.28 148	95.54 263	99.42 48	99.19 78	97.27 126	99.63 266	97.89 93	99.97 11	99.20 207

IU-MVS					99.49 84	99.15 45		98.87 239	92.97 309	99.41 49				96.76 164	99.62 153	99.66 34

IterMVS-SCA-FT		97.85 179	98.18 137	96.87 291	99.27 124	91.16 335	95.53 306	99.25 157	99.10 62	99.41 49	99.35 58	93.10 263	99.96 8	98.65 53	99.94 21	99.49 104

test20.03		98.78 66	98.77 55	98.78 158	99.46 95	97.20 200	97.78 165	99.24 162	99.04 67	99.41 49	98.90 146	97.65 93	99.76 206	97.70 107	99.79 82	99.39 150

FC-MVSNet-test		99.27 25	99.25 25	99.34 72	99.77 20	98.37 105	99.30 22	99.57 33	99.61 19	99.40 52	99.50 36	97.12 134	99.85 105	99.02 32	99.94 21	99.80 12

EG-PatchMatch MVS		98.99 39	99.01 38	98.94 134	99.50 77	97.47 183	98.04 139	99.59 24	98.15 128	99.40 52	99.36 57	98.58 32	99.76 206	98.78 44	99.68 133	99.59 55

v1921920		98.54 111	98.60 78	98.38 207	99.20 140	95.76 242	97.56 191	99.36 106	97.23 204	99.38 54	99.17 84	96.02 188	99.84 122	99.57 6	99.90 44	99.54 83

IterMVS-LS		98.55 108	98.70 64	98.09 226	99.48 92	94.73 267	97.22 220	99.39 96	98.97 74	99.38 54	99.31 64	96.00 190	99.93 28	98.58 55	99.97 11	99.60 49
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
lessismore_v0				98.97 130	99.73 24	97.53 181		86.71 364		99.37 56	99.52 35	89.93 288	99.92 35	98.99 34	99.72 113	99.44 131

XXY-MVS		99.14 32	99.15 32	99.10 106	99.76 22	97.74 170	98.85 64	99.62 20	98.48 102	99.37 56	99.49 39	98.75 24	99.86 91	98.20 77	99.80 77	99.71 26

TranMVSNet+NR-MVSNet		99.17 30	99.07 36	99.46 55	99.37 110	98.87 67	98.39 105	99.42 90	99.42 30	99.36 58	99.06 101	98.38 42	99.95 15	98.34 71	99.90 44	99.57 66

APDe-MVS		98.99 39	98.79 52	99.60 13	99.21 136	99.15 45	98.87 61	99.48 67	97.57 163	99.35 59	99.24 72	97.83 80	99.89 58	97.88 96	99.70 122	99.75 22

casdiffmvs		98.95 47	99.00 39	98.81 151	99.38 108	97.33 189	97.82 163	99.57 33	99.17 53	99.35 59	99.17 84	98.35 46	99.69 236	98.46 64	99.73 106	99.41 141

PM-MVS		98.82 59	98.72 59	99.12 102	99.64 46	98.54 95	97.98 148	99.68 14	97.62 158	99.34 61	99.18 80	97.54 103	99.77 199	97.79 99	99.74 103	99.04 233

Anonymous20240521		98.69 81	98.87 44	98.16 224	99.77 20	95.11 261	99.08 44	99.44 81	99.34 37	99.33 62	99.55 29	94.10 250	99.94 23	99.25 20	99.96 14	99.42 138

v1192		98.60 99	98.66 69	98.41 204	99.27 124	95.88 237	97.52 195	99.36 106	97.41 182	99.33 62	99.20 77	96.37 179	99.82 146	99.57 6	99.92 34	99.55 79

CP-MVSNet		99.21 29	99.09 34	99.56 24	99.65 43	98.96 65	99.13 41	99.34 118	99.42 30	99.33 62	99.26 69	97.01 141	99.94 23	98.74 49	99.93 25	99.79 13

IterMVS		97.73 186	98.11 147	96.57 298	99.24 129	90.28 336	95.52 308	99.21 166	98.86 82	99.33 62	99.33 62	93.11 262	99.94 23	98.49 62	99.94 21	99.48 112
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DeepPCF-MVS	96.93 5	98.32 134	98.01 156	99.23 90	98.39 287	98.97 62	95.03 320	99.18 177	96.88 221	99.33 62	98.78 177	98.16 60	99.28 335	96.74 166	99.62 153	99.44 131

COLMAP_ROB	96.50 10	98.99 39	98.85 47	99.41 60	99.58 51	99.10 56	98.74 68	99.56 40	99.09 65	99.33 62	99.19 78	98.40 41	99.72 229	95.98 218	99.76 99	99.42 138
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v144192		98.54 111	98.57 82	98.45 201	99.21 136	95.98 234	97.63 182	99.36 106	97.15 211	99.32 68	99.18 80	95.84 201	99.84 122	99.50 10	99.91 40	99.54 83

v148		98.45 121	98.60 78	98.00 235	99.44 100	94.98 262	97.44 204	99.06 203	98.30 111	99.32 68	98.97 131	96.65 164	99.62 268	98.37 69	99.85 54	99.39 150

MSP-MVS		98.40 127	98.00 157	99.61 9	99.57 55	99.25 22	98.57 83	99.35 112	97.55 166	99.31 70	97.71 285	94.61 236	99.88 67	96.14 213	99.19 246	99.70 29
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
VPNet		98.87 55	98.83 48	99.01 127	99.70 36	97.62 178	98.43 102	99.35 112	99.47 26	99.28 71	99.05 108	96.72 161	99.82 146	98.09 83	99.36 217	99.59 55

v2v482		98.56 104	98.62 73	98.37 208	99.42 105	95.81 240	97.58 189	99.16 186	97.90 141	99.28 71	99.01 122	95.98 194	99.79 181	99.33 15	99.90 44	99.51 96

ambc				98.24 219	98.82 228	95.97 235	98.62 77	99.00 222		99.27 73	99.21 75	96.99 142	99.50 305	96.55 186	99.50 199	99.26 197

Patchmatch-RL test		97.26 220	97.02 221	97.99 236	99.52 72	95.53 245	96.13 281	99.71 10	97.47 172	99.27 73	99.16 86	84.30 327	99.62 268	97.89 93	99.77 90	98.81 267

v1144		98.60 99	98.66 69	98.41 204	99.36 111	95.90 236	97.58 189	99.34 118	97.51 168	99.27 73	99.15 90	96.34 181	99.80 168	99.47 12	99.93 25	99.51 96

Vis-MVSNet		99.34 22	99.36 16	99.27 82	99.73 24	98.26 110	99.17 37	99.78 4	99.11 56	99.27 73	99.48 41	98.82 21	99.95 15	98.94 35	99.93 25	99.59 55
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_241102_TWO								99.30 139	98.03 132	99.26 77	99.02 115	97.51 108	99.88 67	96.91 147	99.60 162	99.66 34

test0726					99.50 77	99.21 26	98.17 124	99.35 112	97.97 135	99.26 77	99.06 101	97.61 98

V42		98.78 66	98.78 53	98.76 161	99.44 100	97.04 207	98.27 113	99.19 173	97.87 143	99.25 79	99.16 86	96.84 149	99.78 193	99.21 23	99.84 56	99.46 122

TSAR-MVS + MP.		98.63 93	98.49 93	99.06 118	99.64 46	97.90 153	98.51 92	98.94 226	96.96 217	99.24 80	98.89 154	97.83 80	99.81 159	96.88 154	99.49 200	99.48 112
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
FIs		99.14 32	99.09 34	99.29 77	99.70 36	98.28 109	99.13 41	99.52 54	99.48 24	99.24 80	99.41 51	96.79 155	99.82 146	98.69 52	99.88 49	99.76 20

abl_6		98.99 39	98.78 53	99.61 9	99.45 98	99.46 3	98.60 79	99.50 57	98.59 96	99.24 80	99.04 111	98.54 34	99.89 58	96.45 193	99.62 153	99.50 100

TSAR-MVS + GP.		98.18 150	97.98 158	98.77 160	98.71 245	97.88 154	96.32 273	98.66 269	96.33 240	99.23 83	98.51 221	97.48 114	99.40 319	97.16 129	99.46 204	99.02 236

ppachtmachnet_test		97.50 200	97.74 174	96.78 296	98.70 249	91.23 334	94.55 335	99.05 207	96.36 239	99.21 84	98.79 176	96.39 176	99.78 193	96.74 166	99.82 65	99.34 172

Baseline_NR-MVSNet		98.98 43	98.86 46	99.36 64	99.82 16	98.55 92	97.47 201	99.57 33	99.37 34	99.21 84	99.61 23	96.76 158	99.83 136	98.06 85	99.83 62	99.71 26

EI-MVSNet-UG-set		98.69 81	98.71 61	98.62 176	99.10 166	96.37 225	97.23 217	98.87 239	99.20 48	99.19 86	98.99 125	97.30 123	99.85 105	98.77 47	99.79 82	99.65 38

testgi		98.32 134	98.39 112	98.13 225	99.57 55	95.54 244	97.78 165	99.49 65	97.37 186	99.19 86	97.65 290	98.96 17	99.49 306	96.50 190	98.99 274	99.34 172

baseline		98.96 46	99.02 37	98.76 161	99.38 108	97.26 194	98.49 94	99.50 57	98.86 82	99.19 86	99.06 101	98.23 52	99.69 236	98.71 51	99.76 99	99.33 178

FMVSNet2		98.49 117	98.40 109	98.75 163	98.90 209	97.14 206	98.61 78	99.13 193	98.59 96	99.19 86	99.28 65	94.14 246	99.82 146	97.97 91	99.80 77	99.29 191

EI-MVSNet-Vis-set		98.68 85	98.70 64	98.63 174	99.09 169	96.40 224	97.23 217	98.86 244	99.20 48	99.18 90	98.97 131	97.29 125	99.85 105	98.72 50	99.78 86	99.64 39

Regformer-4		98.73 74	98.68 66	98.89 141	99.02 185	97.22 197	97.17 225	99.06 203	99.21 45	99.17 91	98.85 162	97.45 115	99.86 91	98.48 63	99.70 122	99.60 49

TAMVS		98.24 145	98.05 153	98.80 153	99.07 173	97.18 202	97.88 156	98.81 252	96.66 230	99.17 91	99.21 75	94.81 231	99.77 199	96.96 145	99.88 49	99.44 131

UniMVSNet (Re)		98.87 55	98.71 61	99.35 69	99.24 129	98.73 79	97.73 173	99.38 98	98.93 79	99.12 93	98.73 184	96.77 156	99.86 91	98.63 54	99.80 77	99.46 122

RRT_test8_iter05		95.24 291	95.13 291	95.57 318	97.32 337	87.02 349	97.99 146	99.41 91	98.06 131	99.12 93	99.05 108	66.85 367	99.85 105	98.93 36	99.47 203	99.84 8

Anonymous202405211		97.90 168	97.50 191	99.08 110	98.90 209	98.25 111	98.53 87	96.16 332	98.87 81	99.11 95	98.86 159	90.40 286	99.78 193	97.36 120	99.31 225	99.19 212

VDD-MVS		98.56 104	98.39 112	99.07 113	99.13 161	98.07 133	98.59 81	97.01 320	99.59 20	99.11 95	99.27 67	94.82 229	99.79 181	98.34 71	99.63 150	99.34 172

XVG-OURS-SEG-HR		98.49 117	98.28 126	99.14 100	99.49 84	98.83 70	96.54 259	99.48 67	97.32 191	99.11 95	98.61 212	99.33 8	99.30 332	96.23 206	98.38 300	99.28 192

Regformer-3		98.61 96	98.61 76	98.63 174	99.02 185	96.53 222	97.17 225	98.84 246	99.13 55	99.10 98	98.85 162	97.24 130	99.79 181	98.41 68	99.70 122	99.57 66

LPG-MVS_test		98.71 76	98.46 99	99.47 53	99.57 55	98.97 62	98.23 116	99.48 67	96.60 231	99.10 98	99.06 101	98.71 26	99.83 136	95.58 240	99.78 86	99.62 44

LGP-MVS_train				99.47 53	99.57 55	98.97 62		99.48 67	96.60 231	99.10 98	99.06 101	98.71 26	99.83 136	95.58 240	99.78 86	99.62 44

DVP-MVS		98.77 68	98.52 86	99.52 41	99.50 77	99.21 26	98.02 142	98.84 246	97.97 135	99.08 101	99.02 115	97.61 98	99.88 67	96.99 141	99.63 150	99.48 112
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									98.17 126	99.08 101	99.02 115	97.89 77	99.88 67	97.07 136	99.71 117	99.70 29

RRT_MVS		97.07 235	96.57 250	98.58 181	95.89 359	96.33 226	97.36 208	98.77 258	97.85 145	99.08 101	99.12 94	82.30 337	99.96 8	98.82 43	99.90 44	99.45 126

EI-MVSNet		98.40 127	98.51 88	98.04 233	99.10 166	94.73 267	97.20 221	98.87 239	98.97 74	99.06 104	99.02 115	96.00 190	99.80 168	98.58 55	99.82 65	99.60 49

UniMVSNet_NR-MVSNet		98.86 57	98.68 66	99.40 62	99.17 152	98.74 76	97.68 177	99.40 94	99.14 54	99.06 104	98.59 214	96.71 162	99.93 28	98.57 57	99.77 90	99.53 89

DU-MVS		98.82 59	98.63 72	99.39 63	99.16 154	98.74 76	97.54 193	99.25 157	98.84 84	99.06 104	98.76 181	96.76 158	99.93 28	98.57 57	99.77 90	99.50 100

MVSTER		96.86 248	96.55 252	97.79 243	97.91 313	94.21 279	97.56 191	98.87 239	97.49 171	99.06 104	99.05 108	80.72 342	99.80 168	98.44 65	99.82 65	99.37 160

TinyColmap		97.89 170	97.98 158	97.60 255	98.86 218	94.35 276	96.21 278	99.44 81	97.45 179	99.06 104	98.88 155	97.99 73	99.28 335	94.38 270	99.58 170	99.18 214

test_part2					99.36 111	99.10 56				99.05 109

XVG-OURS		98.53 113	98.34 119	99.11 104	99.50 77	98.82 72	95.97 285	99.50 57	97.30 193	99.05 109	98.98 129	99.35 7	99.32 329	95.72 231	99.68 133	99.18 214

our_test_3		97.39 211	97.73 176	96.34 302	98.70 249	89.78 338	94.61 333	98.97 225	96.50 234	99.04 111	98.85 162	95.98 194	99.84 122	97.26 125	99.67 139	99.41 141

UA-Net		99.47 11	99.40 14	99.70 2	99.49 84	99.29 17	99.80 3	99.72 9	99.82 3	99.04 111	99.81 3	98.05 67	99.96 8	98.85 41	99.99 5	99.86 6

ACMM	96.08 12	98.91 51	98.73 57	99.48 50	99.55 65	99.14 48	98.07 133	99.37 102	97.62 158	99.04 111	98.96 134	98.84 20	99.79 181	97.43 117	99.65 145	99.49 104
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
APD-MVS_3200maxsize		98.84 58	98.61 76	99.53 36	99.19 143	99.27 20	98.49 94	99.33 123	98.64 90	99.03 114	98.98 129	97.89 77	99.85 105	96.54 187	99.42 208	99.46 122

bset_n11_16_dypcd		96.99 244	96.56 251	98.27 217	99.00 188	95.25 253	92.18 357	94.05 349	98.75 87	99.01 115	98.38 237	88.98 295	99.93 28	98.77 47	99.92 34	99.64 39

Regformer-2		98.60 99	98.46 99	99.02 126	98.85 220	97.71 172	96.91 241	99.09 199	98.98 73	99.01 115	98.64 203	97.37 120	99.84 122	97.75 106	99.57 174	99.52 93

HyFIR lowres test		97.19 227	96.60 248	98.96 131	99.62 50	97.28 193	95.17 316	99.50 57	94.21 293	99.01 115	98.32 245	86.61 306	99.99 2	97.10 135	99.84 56	99.60 49

CVMVSNet		96.25 270	97.21 212	93.38 341	99.10 166	80.56 365	97.20 221	98.19 292	96.94 218	99.00 118	99.02 115	89.50 292	99.80 168	96.36 200	99.59 164	99.78 14

Regformer-1		98.55 108	98.44 103	98.87 143	98.85 220	97.29 191	96.91 241	98.99 223	98.97 74	98.99 119	98.64 203	97.26 129	99.81 159	97.79 99	99.57 174	99.51 96

PVSNet_Blended_VisFu		98.17 152	98.15 143	98.22 220	99.73 24	95.15 258	97.36 208	99.68 14	94.45 288	98.99 119	99.27 67	96.87 148	99.94 23	97.13 133	99.91 40	99.57 66

SMA-MVS		98.40 127	98.03 155	99.51 45	99.16 154	99.21 26	98.05 137	99.22 165	94.16 295	98.98 121	99.10 98	97.52 107	99.79 181	96.45 193	99.64 147	99.53 89
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
XVG-ACMP-BASELINE		98.56 104	98.34 119	99.22 91	99.54 68	98.59 89	97.71 174	99.46 75	97.25 198	98.98 121	98.99 125	97.54 103	99.84 122	95.88 221	99.74 103	99.23 202

IS-MVSNet		98.19 149	97.90 165	99.08 110	99.57 55	97.97 144	99.31 18	98.32 285	99.01 70	98.98 121	99.03 114	91.59 280	99.79 181	95.49 242	99.80 77	99.48 112

MP-MVS-pluss		98.57 103	98.23 132	99.60 13	99.69 38	99.35 11	97.16 227	99.38 98	94.87 279	98.97 124	98.99 125	98.01 69	99.88 67	97.29 123	99.70 122	99.58 61
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
VDDNet		98.21 147	97.95 160	99.01 127	99.58 51	97.74 170	99.01 50	97.29 316	99.67 10	98.97 124	99.50 36	90.45 285	99.80 168	97.88 96	99.20 242	99.48 112

USDC		97.41 210	97.40 198	97.44 268	98.94 199	93.67 299	95.17 316	99.53 51	94.03 298	98.97 124	99.10 98	95.29 217	99.34 326	95.84 227	99.73 106	99.30 187

SR-MVS-dyc-post		98.81 61	98.55 83	99.57 18	99.20 140	99.38 5	98.48 97	99.30 139	98.64 90	98.95 127	98.96 134	97.49 112	99.86 91	96.56 183	99.39 212	99.45 126

RE-MVS-def			98.58 81		99.20 140	99.38 5	98.48 97	99.30 139	98.64 90	98.95 127	98.96 134	97.75 87		96.56 183	99.39 212	99.45 126

GBi-Net		98.65 89	98.47 97	99.17 94	98.90 209	98.24 112	99.20 32	99.44 81	98.59 96	98.95 127	99.55 29	94.14 246	99.86 91	97.77 101	99.69 128	99.41 141

test1		98.65 89	98.47 97	99.17 94	98.90 209	98.24 112	99.20 32	99.44 81	98.59 96	98.95 127	99.55 29	94.14 246	99.86 91	97.77 101	99.69 128	99.41 141

FMVSNet3		97.50 200	97.24 210	98.29 215	98.08 305	95.83 239	97.86 159	98.91 233	97.89 142	98.95 127	98.95 138	87.06 303	99.81 159	97.77 101	99.69 128	99.23 202

test_0402		98.76 69	98.71 61	98.93 135	99.56 62	98.14 125	98.45 101	99.34 118	99.28 42	98.95 127	98.91 143	98.34 47	99.79 181	95.63 237	99.91 40	98.86 261

HPM-MVS_fast		99.01 37	98.82 49	99.57 18	99.71 30	99.35 11	99.00 52	99.50 57	97.33 189	98.94 133	98.86 159	98.75 24	99.82 146	97.53 113	99.71 117	99.56 71

Anonymous20231206		98.21 147	98.21 133	98.20 221	99.51 74	95.43 250	98.13 125	99.32 125	96.16 246	98.93 134	98.82 171	96.00 190	99.83 136	97.32 122	99.73 106	99.36 166

YYNet1		97.60 195	97.67 178	97.39 271	99.04 180	93.04 307	95.27 313	98.38 284	97.25 198	98.92 135	98.95 138	95.48 214	99.73 221	96.99 141	98.74 285	99.41 141

GeoE		99.05 35	98.99 41	99.25 87	99.44 100	98.35 107	98.73 70	99.56 40	98.42 104	98.91 136	98.81 173	98.94 18	99.91 45	98.35 70	99.73 106	99.49 104

test1172		98.76 69	98.49 93	99.57 18	99.18 150	99.37 8	98.39 105	99.31 130	98.43 103	98.90 137	98.88 155	97.49 112	99.86 91	96.43 195	99.37 216	99.48 112

SteuartSystems-ACMMP		98.79 63	98.54 84	99.54 29	99.73 24	99.16 40	98.23 116	99.31 130	97.92 139	98.90 137	98.90 146	98.00 70	99.88 67	96.15 212	99.72 113	99.58 61
Skip Steuart: Steuart Systems R&D Blog.
RPSCF		98.62 95	98.36 116	99.42 57	99.65 43	99.42 4	98.55 85	99.57 33	97.72 152	98.90 137	99.26 69	96.12 185	99.52 300	95.72 231	99.71 117	99.32 180

D2MVS		97.84 180	97.84 169	97.83 241	99.14 159	94.74 266	96.94 236	98.88 237	95.84 257	98.89 140	98.96 134	94.40 241	99.69 236	97.55 110	99.95 16	99.05 229

zzz-MVS		98.79 63	98.52 86	99.61 9	99.67 40	99.36 9	97.33 210	99.20 168	98.83 85	98.89 140	98.90 146	96.98 143	99.92 35	97.16 129	99.70 122	99.56 71

MTAPA		98.88 54	98.64 71	99.61 9	99.67 40	99.36 9	98.43 102	99.20 168	98.83 85	98.89 140	98.90 146	96.98 143	99.92 35	97.16 129	99.70 122	99.56 71

WR-MVS		98.40 127	98.19 136	99.03 123	99.00 188	97.65 175	96.85 244	98.94 226	98.57 100	98.89 140	98.50 224	95.60 207	99.85 105	97.54 112	99.85 54	99.59 55

SR-MVS		98.71 76	98.43 105	99.57 18	99.18 150	99.35 11	98.36 108	99.29 146	98.29 114	98.88 144	98.85 162	97.53 105	99.87 83	96.14 213	99.31 225	99.48 112

AllTest		98.44 122	98.20 134	99.16 97	99.50 77	98.55 92	98.25 115	99.58 26	96.80 223	98.88 144	99.06 101	97.65 93	99.57 285	94.45 264	99.61 160	99.37 160

TestCases				99.16 97	99.50 77	98.55 92		99.58 26	96.80 223	98.88 144	99.06 101	97.65 93	99.57 285	94.45 264	99.61 160	99.37 160

MDA-MVSNet_test_wron		97.60 195	97.66 181	97.41 270	99.04 180	93.09 303	95.27 313	98.42 281	97.26 197	98.88 144	98.95 138	95.43 215	99.73 221	97.02 138	98.72 287	99.41 141

VNet		98.42 124	98.30 124	98.79 155	98.79 235	97.29 191	98.23 116	98.66 269	99.31 39	98.85 148	98.80 174	94.80 232	99.78 193	98.13 79	99.13 256	99.31 184

CSCG		98.68 85	98.50 90	99.20 92	99.45 98	98.63 84	98.56 84	99.57 33	97.87 143	98.85 148	98.04 266	97.66 92	99.84 122	96.72 169	99.81 69	99.13 222

CHOSEN 1792x2688		97.49 202	97.14 217	98.54 192	99.68 39	96.09 233	96.50 263	99.62 20	91.58 326	98.84 150	98.97 131	92.36 274	99.88 67	96.76 164	99.95 16	99.67 33

xxxxxxxxxxxxxcwj		98.44 122	98.24 130	99.06 118	99.11 162	97.97 144	96.53 260	99.54 48	98.24 117	98.83 151	98.90 146	97.80 84	99.82 146	95.68 234	99.52 189	99.38 157

SF-MVS		98.53 113	98.27 127	99.32 76	99.31 118	98.75 75	98.19 120	99.41 91	96.77 225	98.83 151	98.90 146	97.80 84	99.82 146	95.68 234	99.52 189	99.38 157

mvs_anonymous		97.83 182	98.16 141	96.87 291	98.18 299	91.89 322	97.31 212	98.90 234	97.37 186	98.83 151	99.46 43	96.28 182	99.79 181	98.90 37	98.16 308	98.95 247

MDA-MVSNet-bldmvs		97.94 166	97.91 164	98.06 231	99.44 100	94.96 263	96.63 257	99.15 192	98.35 106	98.83 151	99.11 96	94.31 243	99.85 105	96.60 177	98.72 287	99.37 160

PMMVS2		98.07 157	98.08 151	98.04 233	99.41 106	94.59 273	94.59 334	99.40 94	97.50 169	98.82 155	98.83 168	96.83 151	99.84 122	97.50 115	99.81 69	99.71 26

ACMMP		98.75 71	98.50 90	99.52 41	99.56 62	99.16 40	98.87 61	99.37 102	97.16 209	98.82 155	99.01 122	97.71 89	99.87 83	96.29 204	99.69 128	99.54 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
ACMP	95.32 15	98.41 125	98.09 148	99.36 64	99.51 74	98.79 74	97.68 177	99.38 98	95.76 260	98.81 157	98.82 171	98.36 43	99.82 146	94.75 254	99.77 90	99.48 112
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMMP_NAP		98.75 71	98.48 95	99.57 18	99.58 51	99.29 17	97.82 163	99.25 157	96.94 218	98.78 158	99.12 94	98.02 68	99.84 122	97.13 133	99.67 139	99.59 55

LFMVS		97.20 226	96.72 239	98.64 171	98.72 242	96.95 211	98.93 58	94.14 348	99.74 7	98.78 158	99.01 122	84.45 324	99.73 221	97.44 116	99.27 232	99.25 198

Patchmtry		97.35 213	96.97 224	98.50 197	97.31 338	96.47 223	98.18 121	98.92 231	98.95 78	98.78 158	99.37 54	85.44 318	99.85 105	95.96 219	99.83 62	99.17 218

cl_fuxian		97.36 212	97.37 201	97.31 272	98.09 304	93.25 302	95.01 321	99.16 186	97.05 213	98.77 161	98.72 186	92.88 268	99.64 263	96.93 146	99.76 99	99.05 229

UnsupCasMVSNet_eth		97.89 170	97.60 187	98.75 163	99.31 118	97.17 203	97.62 183	99.35 112	98.72 89	98.76 162	98.68 193	92.57 273	99.74 217	97.76 105	95.60 349	99.34 172

OPM-MVS		98.56 104	98.32 123	99.25 87	99.41 106	98.73 79	97.13 229	99.18 177	97.10 212	98.75 163	98.92 142	98.18 58	99.65 261	96.68 173	99.56 179	99.37 160

DeepC-MVS_fast	96.85 6	98.30 136	98.15 143	98.75 163	98.61 265	97.23 195	97.76 170	99.09 199	97.31 192	98.75 163	98.66 198	97.56 102	99.64 263	96.10 215	99.55 181	99.39 150
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
miper_lstm_enhance		97.18 228	97.16 214	97.25 276	98.16 300	92.85 309	95.15 318	99.31 130	97.25 198	98.74 165	98.78 177	90.07 287	99.78 193	97.19 127	99.80 77	99.11 225

APD-MVS		98.10 154	97.67 178	99.42 57	99.11 162	98.93 66	97.76 170	99.28 148	94.97 276	98.72 166	98.77 179	97.04 137	99.85 105	93.79 288	99.54 182	99.49 104
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
miper_ehance_all_eth		97.06 236	97.03 220	97.16 280	97.83 316	93.06 304	94.66 330	99.09 199	95.99 253	98.69 167	98.45 230	92.73 271	99.61 274	96.79 160	99.03 267	98.82 264

PGM-MVS		98.66 88	98.37 115	99.55 26	99.53 70	99.18 35	98.23 116	99.49 65	97.01 216	98.69 167	98.88 155	98.00 70	99.89 58	95.87 224	99.59 164	99.58 61

GST-MVS		98.61 96	98.30 124	99.52 41	99.51 74	99.20 32	98.26 114	99.25 157	97.44 180	98.67 169	98.39 235	97.68 90	99.85 105	96.00 216	99.51 192	99.52 93

tttt0517		95.64 283	94.98 294	97.64 253	99.36 111	93.81 295	98.72 71	90.47 360	98.08 130	98.67 169	98.34 242	73.88 359	99.92 35	97.77 101	99.51 192	99.20 207

OpenMVS_ROB	95.38 14	95.84 279	95.18 290	97.81 242	98.41 286	97.15 205	97.37 207	98.62 272	83.86 356	98.65 171	98.37 239	94.29 244	99.68 245	88.41 344	98.62 295	96.60 346

MS-PatchMatch		97.68 189	97.75 173	97.45 267	98.23 297	93.78 296	97.29 213	98.84 246	96.10 248	98.64 172	98.65 200	96.04 187	99.36 324	96.84 158	99.14 253	99.20 207

cl-mvsnet____		97.02 240	96.83 234	97.58 257	97.82 317	94.04 283	94.66 330	99.16 186	97.04 214	98.63 173	98.71 187	88.68 298	99.69 236	97.00 139	99.81 69	99.00 240

cl-mvsnet1		97.02 240	96.84 233	97.58 257	97.82 317	94.03 284	94.66 330	99.16 186	97.04 214	98.63 173	98.71 187	88.69 297	99.69 236	97.00 139	99.81 69	99.01 237

pmmvs5		97.64 192	97.49 192	98.08 229	99.14 159	95.12 260	96.70 254	99.05 207	93.77 301	98.62 175	98.83 168	93.23 259	99.75 213	98.33 73	99.76 99	99.36 166

ab-mvs		98.41 125	98.36 116	98.59 180	99.19 143	97.23 195	99.32 15	98.81 252	97.66 155	98.62 175	99.40 53	96.82 152	99.80 168	95.88 221	99.51 192	98.75 277

pmmvs4		97.58 197	97.28 207	98.51 195	98.84 223	96.93 212	95.40 312	98.52 277	93.60 303	98.61 177	98.65 200	95.10 222	99.60 275	96.97 144	99.79 82	98.99 241

HPM-MVS		98.79 63	98.53 85	99.59 17	99.65 43	99.29 17	99.16 38	99.43 87	96.74 226	98.61 177	98.38 237	98.62 29	99.87 83	96.47 191	99.67 139	99.59 55
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CL-MVSNet_2432*1600		97.44 208	97.22 211	98.08 229	98.57 272	95.78 241	94.30 340	98.79 255	96.58 233	98.60 179	98.19 254	94.74 235	99.64 263	96.41 197	98.84 281	98.82 264

Gipuma		99.03 36	99.16 30	98.64 171	99.94 2	98.51 97	99.32 15	99.75 8	99.58 22	98.60 179	99.62 21	98.22 55	99.51 304	97.70 107	99.73 106	97.89 314
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CDS-MVSNet		97.69 188	97.35 203	98.69 167	98.73 240	97.02 209	96.92 240	98.75 262	95.89 256	98.59 181	98.67 195	92.08 278	99.74 217	96.72 169	99.81 69	99.32 180
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EPP-MVSNet		98.30 136	98.04 154	99.07 113	99.56 62	97.83 159	99.29 23	98.07 296	99.03 68	98.59 181	99.13 93	92.16 276	99.90 49	96.87 155	99.68 133	99.49 104

hse-mvs3		97.77 185	97.33 206	99.10 106	99.21 136	97.84 158	98.35 109	98.57 274	99.11 56	98.58 183	99.02 115	88.65 299	99.96 8	98.11 80	96.34 342	99.49 104

hse-mvs2		97.46 205	97.07 218	98.64 171	98.73 240	97.33 189	97.45 203	97.64 309	99.11 56	98.58 183	97.98 269	88.65 299	99.79 181	98.11 80	97.39 326	98.81 267

HFP-MVS		98.71 76	98.44 103	99.51 45	99.49 84	99.16 40	98.52 88	99.31 130	97.47 172	98.58 183	98.50 224	97.97 74	99.85 105	96.57 180	99.59 164	99.53 89

#test#		98.50 116	98.16 141	99.51 45	99.49 84	99.16 40	98.03 140	99.31 130	96.30 243	98.58 183	98.50 224	97.97 74	99.85 105	95.68 234	99.59 164	99.53 89

eth_miper_zixun_eth		97.23 224	97.25 208	97.17 278	98.00 309	92.77 311	94.71 327	99.18 177	97.27 196	98.56 187	98.74 183	91.89 279	99.69 236	97.06 137	99.81 69	99.05 229

ACMMPR		98.70 79	98.42 107	99.54 29	99.52 72	99.14 48	98.52 88	99.31 130	97.47 172	98.56 187	98.54 218	97.75 87	99.88 67	96.57 180	99.59 164	99.58 61

new_pmnet		96.99 244	96.76 237	97.67 249	98.72 242	94.89 264	95.95 289	98.20 290	92.62 315	98.55 189	98.54 218	94.88 228	99.52 300	93.96 281	99.44 207	98.59 289

3Dnovator	98.27 2	98.81 61	98.73 57	99.05 120	98.76 236	97.81 164	99.25 30	99.30 139	98.57 100	98.55 189	99.33 62	97.95 76	99.90 49	97.16 129	99.67 139	99.44 131

9.14			97.78 171		99.07 173		97.53 194	99.32 125	95.53 265	98.54 191	98.70 190	97.58 100	99.76 206	94.32 271	99.46 204

diffmvs		98.22 146	98.24 130	98.17 223	99.00 188	95.44 249	96.38 270	99.58 26	97.79 149	98.53 192	98.50 224	96.76 158	99.74 217	97.95 92	99.64 147	99.34 172

OMC-MVS		97.88 172	97.49 192	99.04 122	98.89 214	98.63 84	96.94 236	99.25 157	95.02 274	98.53 192	98.51 221	97.27 126	99.47 311	93.50 296	99.51 192	99.01 237

jason		97.45 207	97.35 203	97.76 245	99.24 129	93.93 289	95.86 293	98.42 281	94.24 292	98.50 194	98.13 256	94.82 229	99.91 45	97.22 126	99.73 106	99.43 135
jason: jason.
MVP-Stereo		98.08 156	97.92 163	98.57 184	98.96 196	96.79 215	97.90 155	99.18 177	96.41 238	98.46 195	98.95 138	95.93 197	99.60 275	96.51 189	98.98 276	99.31 184
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
DELS-MVS		98.27 140	98.20 134	98.48 198	98.86 218	96.70 219	95.60 304	99.20 168	97.73 151	98.45 196	98.71 187	97.50 109	99.82 146	98.21 76	99.59 164	98.93 252
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
region2R		98.69 81	98.40 109	99.54 29	99.53 70	99.17 36	98.52 88	99.31 130	97.46 177	98.44 197	98.51 221	97.83 80	99.88 67	96.46 192	99.58 170	99.58 61

BH-untuned		96.83 249	96.75 238	97.08 281	98.74 239	93.33 301	96.71 253	98.26 287	96.72 227	98.44 197	97.37 308	95.20 219	99.47 311	91.89 320	97.43 325	98.44 295

LS3D		98.63 93	98.38 114	99.36 64	97.25 339	99.38 5	99.12 43	99.32 125	99.21 45	98.44 197	98.88 155	97.31 122	99.80 168	96.58 178	99.34 221	98.92 253

ETH3D-3000-0.1		98.03 158	97.62 185	99.29 77	99.11 162	98.80 73	97.47 201	99.32 125	95.54 263	98.43 200	98.62 209	96.61 166	99.77 199	93.95 282	99.49 200	99.30 187

xiu_mvs_v1_base_debu		97.86 174	98.17 138	96.92 288	98.98 193	93.91 290	96.45 265	99.17 183	97.85 145	98.41 201	97.14 316	98.47 36	99.92 35	98.02 87	99.05 263	96.92 340

xiu_mvs_v1_base		97.86 174	98.17 138	96.92 288	98.98 193	93.91 290	96.45 265	99.17 183	97.85 145	98.41 201	97.14 316	98.47 36	99.92 35	98.02 87	99.05 263	96.92 340

xiu_mvs_v1_base_debi		97.86 174	98.17 138	96.92 288	98.98 193	93.91 290	96.45 265	99.17 183	97.85 145	98.41 201	97.14 316	98.47 36	99.92 35	98.02 87	99.05 263	96.92 340

Patchmatch-test		96.55 260	96.34 258	97.17 278	98.35 288	93.06 304	98.40 104	97.79 302	97.33 189	98.41 201	98.67 195	83.68 331	99.69 236	95.16 246	99.31 225	98.77 275

baseline1		95.96 276	95.44 281	97.52 264	98.51 278	93.99 287	98.39 105	96.09 334	98.21 120	98.40 205	97.76 283	86.88 304	99.63 266	95.42 243	89.27 361	98.95 247

MSDG		97.71 187	97.52 190	98.28 216	98.91 208	96.82 214	94.42 337	99.37 102	97.65 156	98.37 206	98.29 247	97.40 118	99.33 328	94.09 278	99.22 239	98.68 286

miper_enhance_ethall		96.01 274	95.74 269	96.81 295	96.41 353	92.27 319	93.69 349	98.89 236	91.14 333	98.30 207	97.35 310	90.58 284	99.58 284	96.31 202	99.03 267	98.60 287

CP-MVS		98.70 79	98.42 107	99.52 41	99.36 111	99.12 53	98.72 71	99.36 106	97.54 167	98.30 207	98.40 233	97.86 79	99.89 58	96.53 188	99.72 113	99.56 71

UnsupCasMVSNet_bld		97.30 217	96.92 227	98.45 201	99.28 123	96.78 218	96.20 279	99.27 151	95.42 268	98.28 209	98.30 246	93.16 261	99.71 230	94.99 249	97.37 327	98.87 260

ITE_SJBPF				98.87 143	99.22 134	98.48 99		99.35 112	97.50 169	98.28 209	98.60 213	97.64 96	99.35 325	93.86 286	99.27 232	98.79 273

thisisatest0530		95.27 290	94.45 300	97.74 247	99.19 143	94.37 275	97.86 159	90.20 361	97.17 208	98.22 211	97.65 290	73.53 360	99.90 49	96.90 152	99.35 219	98.95 247

test_yl		96.69 254	96.29 260	97.90 237	98.28 292	95.24 254	97.29 213	97.36 312	98.21 120	98.17 212	97.86 276	86.27 308	99.55 291	94.87 252	98.32 301	98.89 257

DCV-MVSNet		96.69 254	96.29 260	97.90 237	98.28 292	95.24 254	97.29 213	97.36 312	98.21 120	98.17 212	97.86 276	86.27 308	99.55 291	94.87 252	98.32 301	98.89 257

MVSFormer		98.26 142	98.43 105	97.77 244	98.88 215	93.89 293	99.39 11	99.56 40	99.11 56	98.16 214	98.13 256	93.81 253	99.97 3	99.26 18	99.57 174	99.43 135

lupinMVS		97.06 236	96.86 231	97.65 251	98.88 215	93.89 293	95.48 309	97.97 299	93.53 304	98.16 214	97.58 294	93.81 253	99.91 45	96.77 163	99.57 174	99.17 218

Vis-MVSNet (Re-imp)		97.46 205	97.16 214	98.34 210	99.55 65	96.10 231	98.94 57	98.44 280	98.32 110	98.16 214	98.62 209	88.76 296	99.73 221	93.88 285	99.79 82	99.18 214

TAPA-MVS	96.21 11	96.63 258	95.95 266	98.65 169	98.93 201	98.09 127	96.93 238	99.28 148	83.58 357	98.13 217	97.78 281	96.13 184	99.40 319	93.52 294	99.29 230	98.45 294
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
testtj		97.79 184	97.25 208	99.42 57	99.03 183	98.85 68	97.78 165	99.18 177	95.83 258	98.12 218	98.50 224	95.50 212	99.86 91	92.23 318	99.07 262	99.54 83

ZNCC-MVS		98.68 85	98.40 109	99.54 29	99.57 55	99.21 26	98.46 99	99.29 146	97.28 195	98.11 219	98.39 235	98.00 70	99.87 83	96.86 157	99.64 147	99.55 79

MVS_111021_LR		98.30 136	98.12 146	98.83 148	99.16 154	98.03 137	96.09 282	99.30 139	97.58 162	98.10 220	98.24 249	98.25 50	99.34 326	96.69 172	99.65 145	99.12 223

mPP-MVS		98.64 91	98.34 119	99.54 29	99.54 68	99.17 36	98.63 76	99.24 162	97.47 172	98.09 221	98.68 193	97.62 97	99.89 58	96.22 207	99.62 153	99.57 66

3Dnovator+	97.89 3	98.69 81	98.51 88	99.24 89	98.81 231	98.40 102	99.02 49	99.19 173	98.99 71	98.07 222	99.28 65	97.11 136	99.84 122	96.84 158	99.32 223	99.47 120

PHI-MVS		98.29 139	97.95 160	99.34 72	98.44 284	99.16 40	98.12 127	99.38 98	96.01 252	98.06 223	98.43 231	97.80 84	99.67 248	95.69 233	99.58 170	99.20 207

CLD-MVS		97.49 202	97.16 214	98.48 198	99.07 173	97.03 208	94.71 327	99.21 166	94.46 286	98.06 223	97.16 314	97.57 101	99.48 309	94.46 263	99.78 86	98.95 247
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ZD-MVS					99.01 187	98.84 69		99.07 202	94.10 296	98.05 225	98.12 259	96.36 180	99.86 91	92.70 312	99.19 246

MVS_Test		98.18 150	98.36 116	97.67 249	98.48 280	94.73 267	98.18 121	99.02 216	97.69 153	98.04 226	99.11 96	97.22 132	99.56 288	98.57 57	98.90 280	98.71 280

FMVSNet5		96.01 274	95.20 289	98.41 204	97.53 329	96.10 231	98.74 68	99.50 57	97.22 207	98.03 227	99.04 111	69.80 362	99.88 67	97.27 124	99.71 117	99.25 198

MVS_111021_HR		98.25 144	98.08 151	98.75 163	99.09 169	97.46 184	95.97 285	99.27 151	97.60 161	97.99 228	98.25 248	98.15 62	99.38 323	96.87 155	99.57 174	99.42 138

MCST-MVS		98.00 162	97.63 184	99.10 106	99.24 129	98.17 122	96.89 243	98.73 265	95.66 261	97.92 229	97.70 287	97.17 133	99.66 256	96.18 211	99.23 238	99.47 120

MG-MVS		96.77 252	96.61 247	97.26 275	98.31 291	93.06 304	95.93 290	98.12 295	96.45 237	97.92 229	98.73 184	93.77 255	99.39 321	91.19 332	99.04 266	99.33 178

MSLP-MVS++		98.02 160	98.14 145	97.64 253	98.58 270	95.19 257	97.48 199	99.23 164	97.47 172	97.90 231	98.62 209	97.04 137	98.81 354	97.55 110	99.41 209	98.94 251

cl-mvsnet2		95.79 280	95.39 284	96.98 285	96.77 347	92.79 310	94.40 338	98.53 276	94.59 283	97.89 232	98.17 255	82.82 336	99.24 337	96.37 198	99.03 267	98.92 253

BH-RMVSNet		96.83 249	96.58 249	97.58 257	98.47 281	94.05 282	96.67 255	97.36 312	96.70 229	97.87 233	97.98 269	95.14 221	99.44 316	90.47 338	98.58 297	99.25 198

MIMVSNet		96.62 259	96.25 263	97.71 248	99.04 180	94.66 270	99.16 38	96.92 324	97.23 204	97.87 233	99.10 98	86.11 312	99.65 261	91.65 323	99.21 241	98.82 264

LF4IMVS		97.90 168	97.69 177	98.52 193	99.17 152	97.66 174	97.19 224	99.47 73	96.31 242	97.85 235	98.20 253	96.71 162	99.52 300	94.62 258	99.72 113	98.38 298

CPTT-MVS		97.84 180	97.36 202	99.27 82	99.31 118	98.46 100	98.29 111	99.27 151	94.90 278	97.83 236	98.37 239	94.90 225	99.84 122	93.85 287	99.54 182	99.51 96

CMPMVS	75.91 23	96.29 268	95.44 281	98.84 147	96.25 355	98.69 82	97.02 231	99.12 195	88.90 345	97.83 236	98.86 159	89.51 291	98.90 352	91.92 319	99.51 192	98.92 253
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
E-PMN		94.17 307	94.37 302	93.58 338	96.86 344	85.71 354	90.11 359	97.07 319	98.17 126	97.82 238	97.19 312	84.62 323	98.94 350	89.77 340	97.68 321	96.09 353

CDPH-MVS		97.26 220	96.66 245	99.07 113	99.00 188	98.15 123	96.03 283	99.01 219	91.21 332	97.79 239	97.85 278	96.89 147	99.69 236	92.75 310	99.38 215	99.39 150

HQP_MVS		97.99 165	97.67 178	98.93 135	99.19 143	97.65 175	97.77 168	99.27 151	98.20 123	97.79 239	97.98 269	94.90 225	99.70 232	94.42 266	99.51 192	99.45 126

plane_prior3						97.78 166			97.41 182	97.79 239

MDTV_nov1_ep13_2view						74.92 367	97.69 176		90.06 341	97.75 242		85.78 314		93.52 294		98.69 283

pmmvs3		95.03 295	94.40 301	96.93 287	97.70 323	92.53 314	95.08 319	97.71 305	88.57 347	97.71 243	98.08 264	79.39 349	99.82 146	96.19 209	99.11 260	98.43 296

DP-MVS Recon		97.33 215	96.92 227	98.57 184	99.09 169	97.99 139	96.79 247	99.35 112	93.18 307	97.71 243	98.07 265	95.00 224	99.31 330	93.97 280	99.13 256	98.42 297

QAPM		97.31 216	96.81 235	98.82 149	98.80 233	97.49 182	99.06 48	99.19 173	90.22 338	97.69 245	99.16 86	96.91 146	99.90 49	90.89 336	99.41 209	99.07 227

SCA		96.41 266	96.66 245	95.67 315	98.24 295	88.35 343	95.85 295	96.88 325	96.11 247	97.67 246	98.67 195	93.10 263	99.85 105	94.16 272	99.22 239	98.81 267

ETH3D cwj APD-0.16		97.55 198	97.00 222	99.19 93	98.51 278	98.64 83	96.85 244	99.13 193	94.19 294	97.65 247	98.40 233	95.78 202	99.81 159	93.37 299	99.16 249	99.12 223

Effi-MVS+-dtu		98.26 142	97.90 165	99.35 69	98.02 307	99.49 2	98.02 142	99.16 186	98.29 114	97.64 248	97.99 268	96.44 174	99.95 15	96.66 174	98.93 279	98.60 287

CNVR-MVS		98.17 152	97.87 167	99.07 113	98.67 258	98.24 112	97.01 232	98.93 228	97.25 198	97.62 249	98.34 242	97.27 126	99.57 285	96.42 196	99.33 222	99.39 150

PVSNet_BlendedMVS		97.55 198	97.53 189	97.60 255	98.92 205	93.77 297	96.64 256	99.43 87	94.49 284	97.62 249	99.18 80	96.82 152	99.67 248	94.73 255	99.93 25	99.36 166

PVSNet_Blended		96.88 247	96.68 242	97.47 266	98.92 205	93.77 297	94.71 327	99.43 87	90.98 334	97.62 249	97.36 309	96.82 152	99.67 248	94.73 255	99.56 179	98.98 242

alignmvs		97.35 213	96.88 230	98.78 158	98.54 275	98.09 127	97.71 174	97.69 306	99.20 48	97.59 252	95.90 336	88.12 302	99.55 291	98.18 78	98.96 277	98.70 282

MP-MVS		98.46 120	98.09 148	99.54 29	99.57 55	99.22 25	98.50 93	99.19 173	97.61 160	97.58 253	98.66 198	97.40 118	99.88 67	94.72 257	99.60 162	99.54 83
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DSMNet-mixed		97.42 209	97.60 187	96.87 291	99.15 158	91.46 326	98.54 86	99.12 195	92.87 312	97.58 253	99.63 20	96.21 183	99.90 49	95.74 230	99.54 182	99.27 194

test0.0.03 1		94.51 300	93.69 309	96.99 284	96.05 356	93.61 300	94.97 322	93.49 350	96.17 244	97.57 255	94.88 352	82.30 337	99.01 349	93.60 292	94.17 357	98.37 300

CS-MVS		98.61 96	98.60 78	98.65 169	98.82 228	98.21 118	98.79 67	99.77 6	98.34 107	97.55 256	97.69 288	98.27 49	99.87 83	98.52 61	99.62 153	97.88 316

PCF-MVS	92.86 18	94.36 302	93.00 319	98.42 203	98.70 249	97.56 179	93.16 352	99.11 197	79.59 360	97.55 256	97.43 304	92.19 275	99.73 221	79.85 360	99.45 206	97.97 313
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
XVS		98.72 75	98.45 101	99.53 36	99.46 95	99.21 26	98.65 74	99.34 118	98.62 94	97.54 258	98.63 207	97.50 109	99.83 136	96.79 160	99.53 186	99.56 71

X-MVStestdata		94.32 303	92.59 321	99.53 36	99.46 95	99.21 26	98.65 74	99.34 118	98.62 94	97.54 258	45.85 363	97.50 109	99.83 136	96.79 160	99.53 186	99.56 71

旧先验2							95.76 297		88.56 348	97.52 260			99.66 256	94.48 262

PMVS	91.26 20	97.86 174	97.94 162	97.65 251	99.71 30	97.94 151	98.52 88	98.68 268	98.99 71	97.52 260	99.35 58	97.41 117	98.18 358	91.59 325	99.67 139	96.82 343
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ETV-MVS		98.03 158	97.86 168	98.56 188	98.69 253	98.07 133	97.51 197	99.50 57	98.10 129	97.50 262	95.51 342	98.41 40	99.88 67	96.27 205	99.24 237	97.71 328

PS-MVSNAJ		97.08 234	97.39 199	96.16 309	98.56 273	92.46 315	95.24 315	98.85 245	97.25 198	97.49 263	95.99 334	98.07 64	99.90 49	96.37 198	98.67 292	96.12 352

xiu_mvs_v2_base		97.16 230	97.49 192	96.17 307	98.54 275	92.46 315	95.45 310	98.84 246	97.25 198	97.48 264	96.49 325	98.31 48	99.90 49	96.34 201	98.68 291	96.15 351

canonicalmvs		98.34 133	98.26 128	98.58 181	98.46 282	97.82 162	98.96 56	99.46 75	99.19 52	97.46 265	95.46 344	98.59 31	99.46 313	98.08 84	98.71 289	98.46 292

testdata				98.09 226	98.93 201	95.40 251		98.80 254	90.08 340	97.45 266	98.37 239	95.26 218	99.70 232	93.58 293	98.95 278	99.17 218

thres600view7		94.45 301	93.83 307	96.29 303	99.06 177	91.53 325	97.99 146	94.24 346	98.34 107	97.44 267	95.01 348	79.84 345	99.67 248	84.33 352	98.23 303	97.66 329

EMVS		93.83 313	94.02 305	93.23 342	96.83 346	84.96 355	89.77 360	96.32 331	97.92 139	97.43 268	96.36 331	86.17 310	98.93 351	87.68 346	97.73 320	95.81 354

thres100view900		94.19 306	93.67 310	95.75 314	99.06 177	91.35 329	98.03 140	94.24 346	98.33 109	97.40 269	94.98 350	79.84 345	99.62 268	83.05 354	98.08 313	96.29 347

Fast-Effi-MVS+-dtu		98.27 140	98.09 148	98.81 151	98.43 285	98.11 126	97.61 185	99.50 57	98.64 90	97.39 270	97.52 298	98.12 63	99.95 15	96.90 152	98.71 289	98.38 298

API-MVS		97.04 239	96.91 229	97.42 269	97.88 314	98.23 116	98.18 121	98.50 278	97.57 163	97.39 270	96.75 321	96.77 156	99.15 344	90.16 339	99.02 270	94.88 357

PatchMatch-RL		97.24 223	96.78 236	98.61 178	99.03 183	97.83 159	96.36 271	99.06 203	93.49 306	97.36 272	97.78 281	95.75 203	99.49 306	93.44 297	98.77 284	98.52 290

sss		97.21 225	96.93 225	98.06 231	98.83 225	95.22 256	96.75 251	98.48 279	94.49 284	97.27 273	97.90 275	92.77 270	99.80 168	96.57 180	99.32 223	99.16 221

KD-MVS_2432*1600		92.87 322	91.99 326	95.51 320	91.37 364	89.27 339	94.07 342	98.14 293	95.42 268	97.25 274	96.44 328	67.86 364	99.24 337	91.28 329	96.08 346	98.02 310

miper_refine_blended		92.87 322	91.99 326	95.51 320	91.37 364	89.27 339	94.07 342	98.14 293	95.42 268	97.25 274	96.44 328	67.86 364	99.24 337	91.28 329	96.08 346	98.02 310

WTY-MVS		96.67 256	96.27 262	97.87 239	98.81 231	94.61 272	96.77 249	97.92 301	94.94 277	97.12 276	97.74 284	91.11 282	99.82 146	93.89 284	98.15 309	99.18 214

tfpn200view9		94.03 310	93.44 312	95.78 313	98.93 201	91.44 327	97.60 186	94.29 344	97.94 137	97.10 277	94.31 356	79.67 347	99.62 268	83.05 354	98.08 313	96.29 347

thres400		94.14 308	93.44 312	96.24 305	98.93 201	91.44 327	97.60 186	94.29 344	97.94 137	97.10 277	94.31 356	79.67 347	99.62 268	83.05 354	98.08 313	97.66 329

ETH3 D test6400		96.46 265	95.59 276	99.08 110	98.88 215	98.21 118	96.53 260	99.18 177	88.87 346	97.08 279	97.79 280	93.64 258	99.77 199	88.92 343	99.40 211	99.28 192

PatchmatchNet		95.58 284	95.67 273	95.30 324	97.34 336	87.32 347	97.65 181	96.65 327	95.30 271	97.07 280	98.69 191	84.77 321	99.75 213	94.97 250	98.64 293	98.83 263
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNLPA		97.17 229	96.71 240	98.55 189	98.56 273	98.05 136	96.33 272	98.93 228	96.91 220	97.06 281	97.39 306	94.38 242	99.45 315	91.66 322	99.18 248	98.14 306

NCCC		97.86 174	97.47 196	99.05 120	98.61 265	98.07 133	96.98 234	98.90 234	97.63 157	97.04 282	97.93 274	95.99 193	99.66 256	95.31 245	98.82 283	99.43 135

TR-MVS		95.55 285	95.12 292	96.86 294	97.54 328	93.94 288	96.49 264	96.53 329	94.36 291	97.03 283	96.61 323	94.26 245	99.16 343	86.91 348	96.31 343	97.47 336

MDTV_nov1_ep13			95.22 288		97.06 342	83.20 361	97.74 172	96.16 332	94.37 290	96.99 284	98.83 168	83.95 329	99.53 296	93.90 283	97.95 317

CANet		97.87 173	97.76 172	98.19 222	97.75 319	95.51 246	96.76 250	99.05 207	97.74 150	96.93 285	98.21 252	95.59 208	99.89 58	97.86 98	99.93 25	99.19 212

EPMVS		93.72 315	93.27 314	95.09 326	96.04 357	87.76 345	98.13 125	85.01 365	94.69 282	96.92 286	98.64 203	78.47 355	99.31 330	95.04 247	96.46 341	98.20 303

AdaColmap		97.14 231	96.71 240	98.46 200	98.34 289	97.80 165	96.95 235	98.93 228	95.58 262	96.92 286	97.66 289	95.87 200	99.53 296	90.97 333	99.14 253	98.04 309

thisisatest0515		94.12 309	93.16 316	96.97 286	98.60 267	92.90 308	93.77 348	90.61 359	94.10 296	96.91 288	95.87 337	74.99 358	99.80 168	94.52 261	99.12 259	98.20 303

CR-MVSNet		96.28 269	95.95 266	97.28 274	97.71 321	94.22 277	98.11 128	98.92 231	92.31 318	96.91 288	99.37 54	85.44 318	99.81 159	97.39 119	97.36 329	97.81 321

RPMNet		97.02 240	96.93 225	97.30 273	97.71 321	94.22 277	98.11 128	99.30 139	99.37 34	96.91 288	99.34 60	86.72 305	99.87 83	97.53 113	97.36 329	97.81 321

HPM-MVS++		98.10 154	97.64 183	99.48 50	99.09 169	99.13 51	97.52 195	98.75 262	97.46 177	96.90 291	97.83 279	96.01 189	99.84 122	95.82 228	99.35 219	99.46 122

PatchT		96.65 257	96.35 257	97.54 262	97.40 334	95.32 252	97.98 148	96.64 328	99.33 38	96.89 292	99.42 49	84.32 326	99.81 159	97.69 109	97.49 322	97.48 335

1112_ss		97.29 219	96.86 231	98.58 181	99.34 117	96.32 227	96.75 251	99.58 26	93.14 308	96.89 292	97.48 301	92.11 277	99.86 91	96.91 147	99.54 182	99.57 66

test222					98.92 205	96.93 212	95.54 305	98.78 257	85.72 354	96.86 294	98.11 260	94.43 239			99.10 261	99.23 202

thres200		93.72 315	93.14 317	95.46 322	98.66 263	91.29 331	96.61 258	94.63 342	97.39 184	96.83 295	93.71 359	79.88 344	99.56 288	82.40 357	98.13 310	95.54 356

UGNet		98.53 113	98.45 101	98.79 155	97.94 311	96.96 210	99.08 44	98.54 275	99.10 62	96.82 296	99.47 42	96.55 168	99.84 122	98.56 60	99.94 21	99.55 79
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
Test_1112_low_res		96.99 244	96.55 252	98.31 213	99.35 115	95.47 248	95.84 296	99.53 51	91.51 328	96.80 297	98.48 229	91.36 281	99.83 136	96.58 178	99.53 186	99.62 44

新几何1				98.91 138	98.94 199	97.76 167		98.76 259	87.58 351	96.75 298	98.10 261	94.80 232	99.78 193	92.73 311	99.00 273	99.20 207

Effi-MVS+		98.02 160	97.82 170	98.62 176	98.53 277	97.19 201	97.33 210	99.68 14	97.30 193	96.68 299	97.46 303	98.56 33	99.80 168	96.63 176	98.20 305	98.86 261

GA-MVS		95.86 278	95.32 286	97.49 265	98.60 267	94.15 281	93.83 347	97.93 300	95.49 266	96.68 299	97.42 305	83.21 332	99.30 332	96.22 207	98.55 298	99.01 237

EIA-MVS		98.00 162	97.74 174	98.80 153	98.72 242	98.09 127	98.05 137	99.60 23	97.39 184	96.63 301	95.55 341	97.68 90	99.80 168	96.73 168	99.27 232	98.52 290

F-COLMAP		97.30 217	96.68 242	99.14 100	99.19 143	98.39 103	97.27 216	99.30 139	92.93 310	96.62 302	98.00 267	95.73 204	99.68 245	92.62 313	98.46 299	99.35 170

PAPM_NR		96.82 251	96.32 259	98.30 214	99.07 173	96.69 220	97.48 199	98.76 259	95.81 259	96.61 303	96.47 327	94.12 249	99.17 342	90.82 337	97.78 319	99.06 228

1121		96.73 253	96.00 264	98.91 138	98.95 198	97.76 167	98.07 133	98.73 265	87.65 350	96.54 304	98.13 256	94.52 238	99.73 221	92.38 316	99.02 270	99.24 201

test12				98.93 135	98.58 270	97.83 159		98.66 269		96.53 305		95.51 211	99.69 236		99.13 256	99.27 194

BH-w/o		95.13 293	94.89 297	95.86 311	98.20 298	91.31 330	95.65 302	97.37 311	93.64 302	96.52 306	95.70 339	93.04 266	99.02 347	88.10 345	95.82 348	97.24 338

ADS-MVSNet2		95.43 288	94.98 294	96.76 297	98.14 301	91.74 323	97.92 152	97.76 303	90.23 336	96.51 307	98.91 143	85.61 315	99.85 105	92.88 305	96.90 335	98.69 283

ADS-MVSNet		95.24 291	94.93 296	96.18 306	98.14 301	90.10 337	97.92 152	97.32 315	90.23 336	96.51 307	98.91 143	85.61 315	99.74 217	92.88 305	96.90 335	98.69 283

114514_t		96.50 263	95.77 268	98.69 167	99.48 92	97.43 186	97.84 161	99.55 44	81.42 359	96.51 307	98.58 215	95.53 209	99.67 248	93.41 298	99.58 170	98.98 242

PVSNet	93.40 17	95.67 282	95.70 271	95.57 318	98.83 225	88.57 341	92.50 354	97.72 304	92.69 314	96.49 310	96.44 328	93.72 256	99.43 317	93.61 291	99.28 231	98.71 280

mvs-test1		97.83 182	97.48 195	98.89 141	98.02 307	99.20 32	97.20 221	99.16 186	98.29 114	96.46 311	97.17 313	96.44 174	99.92 35	96.66 174	97.90 318	97.54 334

DPM-MVS		96.32 267	95.59 276	98.51 195	98.76 236	97.21 199	94.54 336	98.26 287	91.94 322	96.37 312	97.25 311	93.06 265	99.43 317	91.42 328	98.74 285	98.89 257

tpmrst		95.07 294	95.46 279	93.91 335	97.11 341	84.36 359	97.62 183	96.96 321	94.98 275	96.35 313	98.80 174	85.46 317	99.59 279	95.60 238	96.23 344	97.79 324

OpenMVS	96.65 7	97.09 233	96.68 242	98.32 211	98.32 290	97.16 204	98.86 63	99.37 102	89.48 342	96.29 314	99.15 90	96.56 167	99.90 49	92.90 304	99.20 242	97.89 314

Fast-Effi-MVS+		97.67 190	97.38 200	98.57 184	98.71 245	97.43 186	97.23 217	99.45 78	94.82 280	96.13 315	96.51 324	98.52 35	99.91 45	96.19 209	98.83 282	98.37 300

test_prior3		97.48 204	97.00 222	98.95 132	98.69 253	97.95 149	95.74 299	99.03 212	96.48 235	96.11 316	97.63 292	95.92 198	99.59 279	94.16 272	99.20 242	99.30 187

test_prior2							95.74 299		96.48 235	96.11 316	97.63 292	95.92 198		94.16 272	99.20 242

dp		93.47 317	93.59 311	93.13 343	96.64 348	81.62 364	97.66 179	96.42 330	92.80 313	96.11 316	98.64 203	78.55 354	99.59 279	93.31 300	92.18 360	98.16 305

原ACMM1				98.35 209	98.90 209	96.25 229		98.83 251	92.48 316	96.07 319	98.10 261	95.39 216	99.71 230	92.61 314	98.99 274	99.08 226

PMMVS		96.51 261	95.98 265	98.09 226	97.53 329	95.84 238	94.92 323	98.84 246	91.58 326	96.05 320	95.58 340	95.68 205	99.66 256	95.59 239	98.09 312	98.76 276

tpm		94.67 299	94.34 303	95.66 316	97.68 325	88.42 342	97.88 156	94.90 340	94.46 286	96.03 321	98.56 217	78.66 351	99.79 181	95.88 221	95.01 352	98.78 274

TEST9					98.71 245	98.08 131	95.96 287	99.03 212	91.40 329	95.85 322	97.53 296	96.52 169	99.76 206

train_agg		97.10 232	96.45 255	99.07 113	98.71 245	98.08 131	95.96 287	99.03 212	91.64 324	95.85 322	97.53 296	96.47 172	99.76 206	93.67 290	99.16 249	99.36 166

test_8					98.67 258	98.01 138	95.91 292	99.02 216	91.64 324	95.79 324	97.50 299	96.47 172	99.76 206

agg_prior1		97.06 236	96.40 256	99.03 123	98.68 256	97.99 139	95.76 297	99.01 219	91.73 323	95.59 325	97.50 299	96.49 171	99.77 199	93.71 289	99.14 253	99.34 172

agg_prior					98.68 256	97.99 139		99.01 219		95.59 325			99.77 199

PLC	94.65 16	96.51 261	95.73 270	98.85 146	98.75 238	97.91 152	96.42 268	99.06 203	90.94 335	95.59 325	97.38 307	94.41 240	99.59 279	90.93 334	98.04 316	99.05 229
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
HQP4-MVS										95.56 328			99.54 294			99.32 180

HQP-NCC					98.67 258		96.29 274		96.05 249	95.55 329

ACMP_Plane					98.67 258		96.29 274		96.05 249	95.55 329

HQP-MVS		97.00 243	96.49 254	98.55 189	98.67 258	96.79 215	96.29 274	99.04 210	96.05 249	95.55 329	96.84 319	93.84 251	99.54 294	92.82 307	99.26 235	99.32 180

MAR-MVS		96.47 264	95.70 271	98.79 155	97.92 312	99.12 53	98.28 112	98.60 273	92.16 321	95.54 332	96.17 332	94.77 234	99.52 300	89.62 341	98.23 303	97.72 327
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
AUN-MVS		96.24 271	95.45 280	98.60 179	98.70 249	97.22 197	97.38 206	97.65 307	95.95 254	95.53 333	97.96 273	82.11 341	99.79 181	96.31 202	97.44 324	98.80 272

tpmvs		95.02 296	95.25 287	94.33 331	96.39 354	85.87 351	98.08 132	96.83 326	95.46 267	95.51 334	98.69 191	85.91 313	99.53 296	94.16 272	96.23 344	97.58 332

MVS-HIRNet		94.32 303	95.62 274	90.42 345	98.46 282	75.36 366	96.29 274	89.13 363	95.25 272	95.38 335	99.75 7	92.88 268	99.19 341	94.07 279	99.39 212	96.72 345

PAPR		95.29 289	94.47 299	97.75 246	97.50 333	95.14 259	94.89 324	98.71 267	91.39 330	95.35 336	95.48 343	94.57 237	99.14 345	84.95 351	97.37 327	98.97 246

HY-MVS	95.94 13	95.90 277	95.35 285	97.55 261	97.95 310	94.79 265	98.81 66	96.94 323	92.28 319	95.17 337	98.57 216	89.90 289	99.75 213	91.20 331	97.33 331	98.10 307

CANet_DTU		97.26 220	97.06 219	97.84 240	97.57 326	94.65 271	96.19 280	98.79 255	97.23 204	95.14 338	98.24 249	93.22 260	99.84 122	97.34 121	99.84 56	99.04 233

cascas		94.79 298	94.33 304	96.15 310	96.02 358	92.36 318	92.34 356	99.26 156	85.34 355	95.08 339	94.96 351	92.96 267	98.53 356	94.41 269	98.59 296	97.56 333

CostFormer		93.97 311	93.78 308	94.51 330	97.53 329	85.83 353	97.98 148	95.96 335	89.29 344	94.99 340	98.63 207	78.63 352	99.62 268	94.54 260	96.50 340	98.09 308

CHOSEN 280x420		95.51 287	95.47 278	95.65 317	98.25 294	88.27 344	93.25 351	98.88 237	93.53 304	94.65 341	97.15 315	86.17 310	99.93 28	97.41 118	99.93 25	98.73 279

JIA-IIPM		95.52 286	95.03 293	97.00 283	96.85 345	94.03 284	96.93 238	95.82 336	99.20 48	94.63 342	99.71 12	83.09 333	99.60 275	94.42 266	94.64 353	97.36 337

MVS		93.19 320	92.09 324	96.50 300	96.91 343	94.03 284	98.07 133	98.06 297	68.01 361	94.56 343	96.48 326	95.96 196	99.30 332	83.84 353	96.89 337	96.17 349

1314		95.74 281	95.60 275	96.17 307	97.53 329	92.75 312	98.07 133	98.31 286	91.22 331	94.25 344	96.68 322	95.53 209	99.03 346	91.64 324	97.18 332	96.74 344

tpm cat1		93.29 319	93.13 318	93.75 336	97.39 335	84.74 356	97.39 205	97.65 307	83.39 358	94.16 345	98.41 232	82.86 335	99.39 321	91.56 326	95.35 351	97.14 339

test-LLR		93.90 312	93.85 306	94.04 333	96.53 349	84.62 357	94.05 344	92.39 355	96.17 244	94.12 346	95.07 346	82.30 337	99.67 248	95.87 224	98.18 306	97.82 319

test-mter		92.33 327	91.76 330	94.04 333	96.53 349	84.62 357	94.05 344	92.39 355	94.00 299	94.12 346	95.07 346	65.63 370	99.67 248	95.87 224	98.18 306	97.82 319

tpm2		93.09 321	92.58 322	94.62 329	97.56 327	86.53 350	97.66 179	95.79 337	86.15 353	94.07 348	98.23 251	75.95 356	99.53 296	90.91 335	96.86 338	97.81 321

TESTMET0.1,1		92.19 329	91.77 329	93.46 339	96.48 351	82.80 362	94.05 344	91.52 358	94.45 288	94.00 349	94.88 352	66.65 368	99.56 288	95.78 229	98.11 311	98.02 310

PVSNet_0	89.98 21	91.15 331	90.30 334	93.70 337	97.72 320	84.34 360	90.24 358	97.42 310	90.20 339	93.79 350	93.09 360	90.90 283	98.89 353	86.57 349	72.76 363	97.87 317

FPMVS		93.44 318	92.23 323	97.08 281	99.25 128	97.86 156	95.61 303	97.16 318	92.90 311	93.76 351	98.65 200	75.94 357	95.66 361	79.30 361	97.49 322	97.73 326

MVS_0304		97.64 192	97.35 203	98.52 193	97.87 315	96.69 220	98.59 81	98.05 298	97.44 180	93.74 352	98.85 162	93.69 257	99.88 67	98.11 80	99.81 69	98.98 242

EPNet		96.14 272	95.44 281	98.25 218	90.76 366	95.50 247	97.92 152	94.65 341	98.97 74	92.98 353	98.85 162	89.12 294	99.87 83	95.99 217	99.68 133	99.39 150
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DWT-MVSNet_test		92.75 324	92.05 325	94.85 327	96.48 351	87.21 348	97.83 162	94.99 339	92.22 320	92.72 354	94.11 358	70.75 361	99.46 313	95.01 248	94.33 356	97.87 317

baseline2		93.73 314	92.83 320	96.42 301	97.70 323	91.28 332	96.84 246	89.77 362	93.96 300	92.44 355	95.93 335	79.14 350	99.77 199	92.94 303	96.76 339	98.21 302

IB-MVS	91.63 19	92.24 328	90.90 332	96.27 304	97.22 340	91.24 333	94.36 339	93.33 352	92.37 317	92.24 356	94.58 355	66.20 369	99.89 58	93.16 302	94.63 354	97.66 329
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		92.37 326	91.20 331	95.85 312	95.80 360	92.38 317	99.31 18	81.84 367	99.75 5	91.83 357	99.74 8	68.29 363	99.02 347	87.15 347	97.12 333	96.16 350

DeepMVS_CX				93.44 340	98.24 295	94.21 279		94.34 343	64.28 362	91.34 358	94.87 354	89.45 293	92.77 364	77.54 362	93.14 358	93.35 359

PAPM		91.88 330	90.34 333	96.51 299	98.06 306	92.56 313	92.44 355	97.17 317	86.35 352	90.38 359	96.01 333	86.61 306	99.21 340	70.65 363	95.43 350	97.75 325

ET-MVSNet_ETH3D		94.30 305	93.21 315	97.58 257	98.14 301	94.47 274	94.78 326	93.24 353	94.72 281	89.56 360	95.87 337	78.57 353	99.81 159	96.91 147	97.11 334	98.46 292

EPNet_dtu		94.93 297	94.78 298	95.38 323	93.58 363	87.68 346	96.78 248	95.69 338	97.35 188	89.14 361	98.09 263	88.15 301	99.49 306	94.95 251	99.30 228	98.98 242
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GG-mvs-BLEND				94.76 328	94.54 362	92.13 321	99.31 18	80.47 368		88.73 362	91.01 362	67.59 366	98.16 359	82.30 358	94.53 355	93.98 358

tmp_tt		78.77 333	78.73 336	78.90 347	58.45 368	74.76 368	94.20 341	78.26 369	39.16 363	86.71 363	92.82 361	80.50 343	75.19 365	86.16 350	92.29 359	86.74 360

MVE	83.40 22	92.50 325	91.92 328	94.25 332	98.83 225	91.64 324	92.71 353	83.52 366	95.92 255	86.46 364	95.46 344	95.20 219	95.40 362	80.51 359	98.64 293	95.73 355
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		79.78 332	79.50 335	80.62 346	80.21 367	45.76 369	70.82 361	98.41 283	31.08 364	80.89 365	97.71 285	84.85 320	97.37 360	91.51 327	80.03 362	98.75 277

testmvs		17.12 335	20.53 338	6.87 349	12.05 369	4.20 371	93.62 350	6.73 370	4.62 366	10.41 366	24.33 364	8.28 372	3.56 367	9.69 365	15.07 364	12.86 363

test123		17.04 336	20.11 339	7.82 348	10.25 370	4.91 370	94.80 325	4.47 371	4.93 365	10.00 367	24.28 365	9.69 371	3.64 366	10.14 364	12.43 365	14.92 362

uanet_test		0.00 339	0.00 342	0.00 350	0.00 371	0.00 372	0.00 362	0.00 372	0.00 367	0.00 368	0.00 368	0.00 373	0.00 368	0.00 366	0.00 366	0.00 364

cdsmvs_eth3d_5k		24.66 334	32.88 337	0.00 350	0.00 371	0.00 372	0.00 362	99.10 198	0.00 367	0.00 368	97.58 294	99.21 10	0.00 368	0.00 366	0.00 366	0.00 364

pcd_1.5k_mvsjas		8.17 337	10.90 340	0.00 350	0.00 371	0.00 372	0.00 362	0.00 372	0.00 367	0.00 368	0.00 368	98.07 64	0.00 368	0.00 366	0.00 366	0.00 364

sosnet-low-res		0.00 339	0.00 342	0.00 350	0.00 371	0.00 372	0.00 362	0.00 372	0.00 367	0.00 368	0.00 368	0.00 373	0.00 368	0.00 366	0.00 366	0.00 364

sosnet		0.00 339	0.00 342	0.00 350	0.00 371	0.00 372	0.00 362	0.00 372	0.00 367	0.00 368	0.00 368	0.00 373	0.00 368	0.00 366	0.00 366	0.00 364

uncertanet		0.00 339	0.00 342	0.00 350	0.00 371	0.00 372	0.00 362	0.00 372	0.00 367	0.00 368	0.00 368	0.00 373	0.00 368	0.00 366	0.00 366	0.00 364

Regformer		0.00 339	0.00 342	0.00 350	0.00 371	0.00 372	0.00 362	0.00 372	0.00 367	0.00 368	0.00 368	0.00 373	0.00 368	0.00 366	0.00 366	0.00 364

ab-mvs-re		8.12 338	10.83 341	0.00 350	0.00 371	0.00 372	0.00 362	0.00 372	0.00 367	0.00 368	97.48 301	0.00 373	0.00 368	0.00 366	0.00 366	0.00 364

uanet		0.00 339	0.00 342	0.00 350	0.00 371	0.00 372	0.00 362	0.00 372	0.00 367	0.00 368	0.00 368	0.00 373	0.00 368	0.00 366	0.00 366	0.00 364

OPU-MVS				98.82 149	98.59 269	98.30 108	98.10 130				98.52 220	98.18 58	98.75 355	94.62 258	99.48 202	99.41 141

save fliter					99.11 162	97.97 144	96.53 260	99.02 216	98.24 117

test_0728_SECOND				99.60 13	99.50 77	99.23 24	98.02 142	99.32 125					99.88 67	96.99 141	99.63 150	99.68 31

GSMVS																98.81 267

sam_mvs1												84.74 322				98.81 267

sam_mvs												84.29 328

MTGPA								99.20 168

test_post1							97.59 188				20.48 367	83.07 334	99.66 256	94.16 272

test_post											21.25 366	83.86 330	99.70 232

patchmatchnet-post											98.77 179	84.37 325	99.85 105

MTMP							97.93 151	91.91 357

gm-plane-assit					94.83 361	81.97 363			88.07 349		94.99 349		99.60 275	91.76 321

test9_res														93.28 301	99.15 252	99.38 157

agg_prior2														92.50 315	99.16 249	99.37 160

test_prior4						97.97 144	95.86 293

test_prior				98.95 132	98.69 253	97.95 149		99.03 212					99.59 279			99.30 187

新几何2							95.93 290

旧先验1					98.82 228	97.45 185		98.76 259			98.34 242	95.50 212			99.01 272	99.23 202

无先验							95.74 299	98.74 264	89.38 343				99.73 221	92.38 316		99.22 206

原ACMM2							95.53 306

testdata2													99.79 181	92.80 309

segment_acmp												97.02 140

testdata1							95.44 311		96.32 241

plane_prior7					99.19 143	97.87 155

plane_prior6					98.99 192	97.70 173						94.90 225

plane_prior5								99.27 151					99.70 232	94.42 266	99.51 192	99.45 126

plane_prior4											97.98 269

plane_prior2							97.77 168		98.20 123

plane_prior1					99.05 179

plane_prior						97.65 175	97.07 230		96.72 227						99.36 217

n2								0.00 372

nn								0.00 372

door-mid								99.57 33

test11								98.87 239

door								99.41 91

HQP5-MVS						96.79 215

BP-MVS														92.82 307

HQP3-MVS								99.04 210							99.26 235

HQP2-MVS												93.84 251

NP-MVS					98.84 223	97.39 188					96.84 319

ACMMP++_ref															99.77 90

ACMMP++															99.68 133

Test By Simon												96.52 169

High-resolution multi-view benchmark