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

pmmvs6		99.67 3	99.70 3	99.60 13	99.90 4	99.27 20	99.53 7	99.76 6	99.64 12	99.84 8	99.83 2	99.50 5	99.87 82	99.36 14	99.92 34	99.64 39

UA-Net		99.47 11	99.40 14	99.70 2	99.49 84	99.29 17	99.80 3	99.72 8	99.82 3	99.04 111	99.81 3	98.05 66	99.96 8	98.85 41	99.99 5	99.86 6

ANet_high		99.57 7	99.67 5	99.28 79	99.89 6	98.09 125	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

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

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	96.39 175	99.92 35	99.44 13	99.92 34	99.68 31

MVS-HIRNet		94.32 302	95.62 273	90.42 344	98.46 281	75.36 365	96.29 273	89.13 361	95.25 271	95.38 334	99.75 7	92.88 267	99.19 340	94.07 278	99.39 210	96.72 343

gg-mvs-nofinetune		92.37 325	91.20 330	95.85 311	95.80 359	92.38 316	99.31 18	81.84 365	99.75 5	91.83 356	99.74 8	68.29 361	99.02 346	87.15 345	97.12 332	96.16 348

mvs_tets		99.63 5	99.67 5	99.49 48	99.88 7	98.61 87	99.34 13	99.71 9	99.27 43	99.90 4	99.74 8	99.68 2	99.97 3	99.55 8	99.99 5	99.88 3

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

anonymousdsp		99.51 10	99.47 12	99.62 6	99.88 7	99.08 59	99.34 13	99.69 12	98.93 79	99.65 22	99.72 11	98.93 18	99.95 15	99.11 27	100.00 1	99.82 9

PS-MVSNAJss		99.46 12	99.49 10	99.35 69	99.90 4	98.15 121	99.20 32	99.65 17	99.48 24	99.92 3	99.71 12	98.07 63	99.96 8	99.53 9	100.00 1	99.93 1

JIA-IIPM		95.52 285	95.03 292	97.00 282	96.85 344	94.03 283	96.93 237	95.82 334	99.20 48	94.63 341	99.71 12	83.09 331	99.60 274	94.42 265	94.64 352	97.36 335

Anonymous20231211		99.27 25	99.27 24	99.26 85	99.29 121	98.18 118	99.49 8	99.51 54	99.70 8	99.80 9	99.68 14	96.84 148	99.83 135	99.21 23	99.91 40	99.77 16

jajsoiax		99.58 6	99.61 7	99.48 50	99.87 10	98.61 87	99.28 27	99.66 16	99.09 65	99.89 6	99.68 14	99.53 4	99.97 3	99.50 10	99.99 5	99.87 4

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	99.81 158	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
v7n		99.53 8	99.57 8	99.41 60	99.88 7	98.54 95	99.45 9	99.61 21	99.66 11	99.68 19	99.66 17	98.44 38	99.95 15	99.73 2	99.96 14	99.75 22

K. test v3		98.00 160	97.66 179	99.03 122	99.79 19	97.56 178	99.19 36	92.47 352	99.62 17	99.52 35	99.66 17	89.61 289	99.96 8	99.25 20	99.81 69	99.56 71

SixPastTwentyTwo		98.75 70	98.62 72	99.16 96	99.83 15	97.96 147	99.28 27	98.20 288	99.37 34	99.70 15	99.65 19	92.65 271	99.93 28	99.04 31	99.84 56	99.60 49

DSMNet-mixed		97.42 208	97.60 185	96.87 290	99.15 157	91.46 325	98.54 84	99.12 194	92.87 311	97.58 252	99.63 20	96.21 182	99.90 48	95.74 229	99.54 180	99.27 193

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	99.83 135	99.06 30	99.62 152	99.66 34

Gipuma		99.03 35	99.16 30	98.64 169	99.94 2	98.51 97	99.32 15	99.75 7	99.58 22	98.60 178	99.62 21	98.22 54	99.51 303	97.70 105	99.73 106	97.89 312
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
Baseline_NR-MVSNet		98.98 42	98.86 45	99.36 64	99.82 16	98.55 92	97.47 200	99.57 33	99.37 34	99.21 84	99.61 23	96.76 157	99.83 135	98.06 83	99.83 62	99.71 26

TDRefinement		99.42 16	99.38 15	99.55 26	99.76 22	99.33 15	99.68 5	99.71 9	99.38 33	99.53 33	99.61 23	98.64 27	99.80 167	98.24 72	99.84 56	99.52 93

pm-mvs1		99.44 13	99.48 11	99.33 74	99.80 17	98.63 84	99.29 23	99.63 18	99.30 41	99.65 22	99.60 25	99.16 14	99.82 145	99.07 29	99.83 62	99.56 71

v10		98.97 43	99.11 33	98.55 187	99.44 100	96.21 229	98.90 59	99.55 43	98.73 88	99.48 40	99.60 25	96.63 164	99.83 135	99.70 3	99.99 5	99.61 48

v8		99.01 36	99.16 30	98.57 182	99.47 94	96.31 227	98.90 59	99.47 72	99.03 68	99.52 35	99.57 27	96.93 144	99.81 158	99.60 4	99.98 9	99.60 49

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	97.12 133	99.90 48	99.21 23	99.87 52	99.54 83

Anonymous20240521		98.69 80	98.87 43	98.16 223	99.77 20	95.11 260	99.08 44	99.44 80	99.34 37	99.33 62	99.55 29	94.10 249	99.94 23	99.25 20	99.96 14	99.42 137

GBi-Net		98.65 88	98.47 95	99.17 93	98.90 208	98.24 111	99.20 32	99.44 80	98.59 96	98.95 127	99.55 29	94.14 245	99.86 89	97.77 99	99.69 127	99.41 140

test1		98.65 88	98.47 95	99.17 93	98.90 208	98.24 111	99.20 32	99.44 80	98.59 96	98.95 127	99.55 29	94.14 245	99.86 89	97.77 99	99.69 127	99.41 140

FMVSNet1		99.17 30	99.17 29	99.17 93	99.55 65	98.24 111	99.20 32	99.44 80	99.21 45	99.43 47	99.55 29	97.82 82	99.86 89	98.42 66	99.89 48	99.41 140

DIV-MVS_2432*1600		99.25 27	99.18 28	99.44 56	99.63 48	99.06 60	98.69 71	99.54 47	99.31 39	99.62 27	99.53 33	97.36 120	99.86 89	99.24 22	99.71 116	99.39 149

new-patchmatchnet		98.35 130	98.74 55	97.18 276	99.24 128	92.23 319	96.42 267	99.48 66	98.30 109	99.69 17	99.53 33	97.44 115	99.82 145	98.84 42	99.77 90	99.49 104

lessismore_v0				98.97 129	99.73 24	97.53 180		86.71 362		99.37 56	99.52 35	89.93 287	99.92 35	98.99 34	99.72 112	99.44 130

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	97.12 133	99.85 103	99.02 32	99.94 21	99.80 12

VDDNet		98.21 145	97.95 158	99.01 126	99.58 51	97.74 169	99.01 50	97.29 314	99.67 10	98.97 124	99.50 36	90.45 284	99.80 167	97.88 94	99.20 240	99.48 111

DeepC-MVS	97.60 4	98.97 43	98.93 41	99.10 105	99.35 114	97.98 142	98.01 144	99.46 74	97.56 163	99.54 30	99.50 36	98.97 16	99.84 120	98.06 83	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
test_part1		97.91 165	97.46 196	99.27 82	98.80 231	98.18 118	99.07 46	99.36 105	99.75 5	99.63 25	99.49 39	82.20 338	99.89 57	98.87 40	99.95 16	99.74 24

XXY-MVS		99.14 32	99.15 32	99.10 105	99.76 22	97.74 169	98.85 64	99.62 19	98.48 102	99.37 56	99.49 39	98.75 23	99.86 89	98.20 75	99.80 77	99.71 26

Vis-MVSNet		99.34 22	99.36 16	99.27 82	99.73 24	98.26 109	99.17 37	99.78 4	99.11 56	99.27 73	99.48 41	98.82 20	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
UGNet		98.53 111	98.45 99	98.79 154	97.94 310	96.96 209	99.08 44	98.54 274	99.10 62	96.82 294	99.47 42	96.55 167	99.84 120	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
EU-MVSNet		97.66 190	98.50 88	95.13 324	99.63 48	85.84 351	98.35 107	98.21 287	98.23 117	99.54 30	99.46 43	95.02 222	99.68 244	98.24 72	99.87 52	99.87 4

LCM-MVSNet-Re		98.64 90	98.48 93	99.11 103	98.85 219	98.51 97	98.49 92	99.83 3	98.37 104	99.69 17	99.46 43	98.21 55	99.92 35	94.13 276	99.30 226	98.91 255

mvs_anonymous		97.83 180	98.16 139	96.87 290	98.18 298	91.89 321	97.31 211	98.90 233	97.37 184	98.83 150	99.46 43	96.28 181	99.79 180	98.90 37	98.16 307	98.95 246

DTE-MVSNet		99.43 15	99.35 17	99.66 4	99.71 30	99.30 16	99.31 18	99.51 54	99.64 12	99.56 28	99.46 43	98.23 51	99.97 3	98.78 44	99.93 25	99.72 25

ACMH	96.65 7	99.25 27	99.24 26	99.26 85	99.72 29	98.38 104	99.07 46	99.55 43	98.30 109	99.65 22	99.45 47	99.22 9	99.76 205	98.44 64	99.77 90	99.64 39
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
VPA-MVSNet		99.30 24	99.30 23	99.28 79	99.49 84	98.36 106	99.00 52	99.45 77	99.63 14	99.52 35	99.44 48	98.25 49	99.88 66	99.09 28	99.84 56	99.62 44

PEN-MVS		99.41 17	99.34 19	99.62 6	99.73 24	99.14 48	99.29 23	99.54 47	99.62 17	99.56 28	99.42 49	98.16 59	99.96 8	98.78 44	99.93 25	99.77 16

PatchT		96.65 256	96.35 256	97.54 261	97.40 333	95.32 251	97.98 147	96.64 326	99.33 38	96.89 290	99.42 49	84.32 324	99.81 158	97.69 107	97.49 321	97.48 333

FIs		99.14 32	99.09 34	99.29 77	99.70 36	98.28 108	99.13 41	99.52 53	99.48 24	99.24 80	99.41 51	96.79 154	99.82 145	98.69 52	99.88 49	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 50	99.53 23	99.46 43	99.41 51	98.23 51	99.95 15	98.89 39	99.95 16	99.81 11

ab-mvs		98.41 123	98.36 114	98.59 178	99.19 142	97.23 194	99.32 15	98.81 251	97.66 153	98.62 174	99.40 53	96.82 151	99.80 167	95.88 220	99.51 190	98.75 276

Anonymous20240529		98.93 48	98.87 43	99.12 101	99.19 142	98.22 116	99.01 50	98.99 222	99.25 44	99.54 30	99.37 54	97.04 136	99.80 167	97.89 91	99.52 187	99.35 169

CR-MVSNet		96.28 268	95.95 265	97.28 273	97.71 320	94.22 276	98.11 127	98.92 230	92.31 317	96.91 286	99.37 54	85.44 317	99.81 158	97.39 117	97.36 328	97.81 318

Patchmtry		97.35 212	96.97 223	98.50 196	97.31 337	96.47 222	98.18 120	98.92 230	98.95 78	98.78 157	99.37 54	85.44 317	99.85 103	95.96 218	99.83 62	99.17 217

EG-PatchMatch MVS		98.99 38	99.01 38	98.94 133	99.50 77	97.47 182	98.04 138	99.59 24	98.15 126	99.40 52	99.36 57	98.58 31	99.76 205	98.78 44	99.68 132	99.59 55

IterMVS-SCA-FT		97.85 177	98.18 135	96.87 290	99.27 123	91.16 334	95.53 305	99.25 156	99.10 62	99.41 49	99.35 58	93.10 262	99.96 8	98.65 53	99.94 21	99.49 104

PMVS	91.26 20	97.86 172	97.94 160	97.65 250	99.71 30	97.94 150	98.52 86	98.68 267	98.99 71	97.52 258	99.35 58	97.41 116	98.18 357	91.59 324	99.67 138	96.82 341
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
WR-MVS_H		99.33 23	99.22 27	99.65 5	99.71 30	99.24 23	99.32 15	99.55 43	99.46 27	99.50 39	99.34 60	97.30 122	99.93 28	98.90 37	99.93 25	99.77 16

RPMNet		97.02 239	96.93 224	97.30 272	97.71 320	94.22 276	98.11 127	99.30 138	99.37 34	96.91 286	99.34 60	86.72 304	99.87 82	97.53 111	97.36 328	97.81 318

IterMVS		97.73 185	98.11 145	96.57 297	99.24 128	90.28 335	95.52 307	99.21 165	98.86 82	99.33 62	99.33 62	93.11 261	99.94 23	98.49 61	99.94 21	99.48 111
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
3Dnovator	98.27 2	98.81 60	98.73 56	99.05 119	98.76 234	97.81 163	99.25 30	99.30 138	98.57 100	98.55 188	99.33 62	97.95 75	99.90 48	97.16 127	99.67 138	99.44 130

IterMVS-LS		98.55 106	98.70 63	98.09 225	99.48 92	94.73 266	97.22 219	99.39 95	98.97 74	99.38 54	99.31 64	96.00 189	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.
FMVSNet2		98.49 115	98.40 107	98.75 162	98.90 208	97.14 205	98.61 76	99.13 192	98.59 96	99.19 86	99.28 65	94.14 245	99.82 145	97.97 89	99.80 77	99.29 190

3Dnovator+	97.89 3	98.69 80	98.51 86	99.24 88	98.81 229	98.40 102	99.02 49	99.19 172	98.99 71	98.07 221	99.28 65	97.11 135	99.84 120	96.84 156	99.32 221	99.47 119

VDD-MVS		98.56 102	98.39 110	99.07 112	99.13 160	98.07 131	98.59 79	97.01 318	99.59 20	99.11 95	99.27 67	94.82 228	99.79 180	98.34 69	99.63 149	99.34 171

PVSNet_Blended_VisFu		98.17 150	98.15 141	98.22 219	99.73 24	95.15 257	97.36 207	99.68 13	94.45 287	98.99 119	99.27 67	96.87 147	99.94 23	97.13 131	99.91 40	99.57 66

nrg030		99.40 18	99.35 17	99.54 29	99.58 51	99.13 51	98.98 55	99.48 66	99.68 9	99.46 43	99.26 69	98.62 28	99.73 220	99.17 26	99.92 34	99.76 20

CP-MVSNet		99.21 29	99.09 34	99.56 24	99.65 43	98.96 65	99.13 41	99.34 117	99.42 30	99.33 62	99.26 69	97.01 140	99.94 23	98.74 49	99.93 25	99.79 13

RPSCF		98.62 94	98.36 114	99.42 57	99.65 43	99.42 4	98.55 83	99.57 33	97.72 150	98.90 136	99.26 69	96.12 184	99.52 299	95.72 230	99.71 116	99.32 179

tfpnnormal		98.90 52	98.90 42	98.91 137	99.67 40	97.82 161	99.00 52	99.44 80	99.45 28	99.51 38	99.24 72	98.20 56	99.86 89	95.92 219	99.69 127	99.04 232

v1240		98.55 106	98.62 72	98.32 210	99.22 133	95.58 242	97.51 196	99.45 77	97.16 207	99.45 45	99.24 72	96.12 184	99.85 103	99.60 4	99.88 49	99.55 79

APDe-MVS		98.99 38	98.79 51	99.60 13	99.21 135	99.15 45	98.87 61	99.48 66	97.57 161	99.35 59	99.24 72	97.83 79	99.89 57	97.88 94	99.70 121	99.75 22

ambc				98.24 218	98.82 227	95.97 234	98.62 75	99.00 221		99.27 73	99.21 75	96.99 141	99.50 304	96.55 184	99.50 197	99.26 196

TAMVS		98.24 143	98.05 151	98.80 152	99.07 172	97.18 201	97.88 155	98.81 251	96.66 229	99.17 91	99.21 75	94.81 230	99.77 198	96.96 143	99.88 49	99.44 130

v1192		98.60 97	98.66 68	98.41 203	99.27 123	95.88 236	97.52 194	99.36 105	97.41 180	99.33 62	99.20 77	96.37 178	99.82 145	99.57 6	99.92 34	99.55 79

pmmvs-eth3d		98.47 117	98.34 117	98.86 144	99.30 120	97.76 166	97.16 226	99.28 147	95.54 262	99.42 48	99.19 78	97.27 125	99.63 265	97.89 91	99.97 11	99.20 206

COLMAP_ROB	96.50 10	98.99 38	98.85 46	99.41 60	99.58 51	99.10 56	98.74 67	99.56 40	99.09 65	99.33 62	99.19 78	98.40 40	99.72 228	95.98 217	99.76 99	99.42 137
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v144192		98.54 109	98.57 80	98.45 200	99.21 135	95.98 233	97.63 181	99.36 105	97.15 209	99.32 68	99.18 80	95.84 200	99.84 120	99.50 10	99.91 40	99.54 83

PM-MVS		98.82 58	98.72 58	99.12 101	99.64 46	98.54 95	97.98 147	99.68 13	97.62 156	99.34 61	99.18 80	97.54 102	99.77 198	97.79 97	99.74 103	99.04 232

PVSNet_BlendedMVS		97.55 197	97.53 188	97.60 254	98.92 204	93.77 296	96.64 255	99.43 86	94.49 283	97.62 248	99.18 80	96.82 151	99.67 247	94.73 254	99.93 25	99.36 165

ACMH+	96.62 9	99.08 34	99.00 39	99.33 74	99.71 30	98.83 70	98.60 77	99.58 26	99.11 56	99.53 33	99.18 80	98.81 21	99.67 247	96.71 169	99.77 90	99.50 100

v1921920		98.54 109	98.60 77	98.38 206	99.20 139	95.76 241	97.56 190	99.36 105	97.23 202	99.38 54	99.17 84	96.02 187	99.84 120	99.57 6	99.90 44	99.54 83

casdiffmvs		98.95 46	99.00 39	98.81 150	99.38 107	97.33 188	97.82 162	99.57 33	99.17 53	99.35 59	99.17 84	98.35 45	99.69 235	98.46 63	99.73 106	99.41 140

Patchmatch-RL test		97.26 219	97.02 220	97.99 235	99.52 72	95.53 244	96.13 280	99.71 9	97.47 170	99.27 73	99.16 86	84.30 325	99.62 267	97.89 91	99.77 90	98.81 266

V42		98.78 65	98.78 52	98.76 160	99.44 100	97.04 206	98.27 111	99.19 172	97.87 141	99.25 79	99.16 86	96.84 148	99.78 192	99.21 23	99.84 56	99.46 121

QAPM		97.31 215	96.81 234	98.82 148	98.80 231	97.49 181	99.06 48	99.19 172	90.22 337	97.69 244	99.16 86	96.91 145	99.90 48	90.89 334	99.41 207	99.07 226

wuyk23d		96.06 272	97.62 183	91.38 343	98.65 263	98.57 91	98.85 64	96.95 320	96.86 221	99.90 4	99.16 86	99.18 11	98.40 356	89.23 340	99.77 90	77.18 359

v1144		98.60 97	98.66 68	98.41 203	99.36 110	95.90 235	97.58 188	99.34 117	97.51 166	99.27 73	99.15 90	96.34 180	99.80 167	99.47 12	99.93 25	99.51 96

DP-MVS		98.93 48	98.81 50	99.28 79	99.21 135	98.45 101	98.46 97	99.33 122	99.63 14	99.48 40	99.15 90	97.23 130	99.75 212	97.17 126	99.66 143	99.63 43

OpenMVS	96.65 7	97.09 232	96.68 241	98.32 210	98.32 289	97.16 203	98.86 63	99.37 101	89.48 341	96.29 312	99.15 90	96.56 166	99.90 48	92.90 303	99.20 240	97.89 312

EPP-MVSNet		98.30 134	98.04 152	99.07 112	99.56 62	97.83 158	99.29 23	98.07 294	99.03 68	98.59 180	99.13 93	92.16 275	99.90 48	96.87 153	99.68 132	99.49 104

ACMMP_NAP		98.75 70	98.48 93	99.57 18	99.58 51	99.29 17	97.82 162	99.25 156	96.94 217	98.78 157	99.12 94	98.02 67	99.84 120	97.13 131	99.67 138	99.59 55

RRT_MVS		97.07 234	96.57 249	98.58 179	95.89 358	96.33 225	97.36 207	98.77 257	97.85 143	99.08 101	99.12 94	82.30 335	99.96 8	98.82 43	99.90 44	99.45 125

MVS_Test		98.18 148	98.36 114	97.67 248	98.48 279	94.73 266	98.18 120	99.02 215	97.69 151	98.04 225	99.11 96	97.22 131	99.56 287	98.57 57	98.90 279	98.71 278

MDA-MVSNet-bldmvs		97.94 164	97.91 162	98.06 230	99.44 100	94.96 262	96.63 256	99.15 191	98.35 105	98.83 150	99.11 96	94.31 242	99.85 103	96.60 175	98.72 286	99.37 159

SMA-MVS		98.40 125	98.03 153	99.51 45	99.16 153	99.21 26	98.05 136	99.22 164	94.16 294	98.98 121	99.10 98	97.52 106	99.79 180	96.45 191	99.64 146	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
MIMVSNet		96.62 258	96.25 262	97.71 247	99.04 179	94.66 269	99.16 38	96.92 322	97.23 202	97.87 232	99.10 98	86.11 311	99.65 260	91.65 322	99.21 239	98.82 263

USDC		97.41 209	97.40 197	97.44 267	98.94 198	93.67 298	95.17 315	99.53 50	94.03 297	98.97 124	99.10 98	95.29 216	99.34 325	95.84 226	99.73 106	99.30 186

test0726					99.50 77	99.21 26	98.17 123	99.35 111	97.97 133	99.26 77	99.06 101	97.61 97

AllTest		98.44 120	98.20 132	99.16 96	99.50 77	98.55 92	98.25 113	99.58 26	96.80 222	98.88 143	99.06 101	97.65 92	99.57 284	94.45 263	99.61 158	99.37 159

TestCases				99.16 96	99.50 77	98.55 92		99.58 26	96.80 222	98.88 143	99.06 101	97.65 92	99.57 284	94.45 263	99.61 158	99.37 159

TranMVSNet+NR-MVSNet		99.17 30	99.07 36	99.46 55	99.37 109	98.87 67	98.39 103	99.42 89	99.42 30	99.36 58	99.06 101	98.38 41	99.95 15	98.34 69	99.90 44	99.57 66

LPG-MVS_test		98.71 75	98.46 97	99.47 53	99.57 55	98.97 62	98.23 114	99.48 66	96.60 230	99.10 98	99.06 101	98.71 25	99.83 135	95.58 239	99.78 86	99.62 44

LGP-MVS_train				99.47 53	99.57 55	98.97 62		99.48 66	96.60 230	99.10 98	99.06 101	98.71 25	99.83 135	95.58 239	99.78 86	99.62 44

baseline		98.96 45	99.02 37	98.76 160	99.38 107	97.26 193	98.49 92	99.50 56	98.86 82	99.19 86	99.06 101	98.23 51	99.69 235	98.71 51	99.76 99	99.33 177

VPNet		98.87 54	98.83 47	99.01 126	99.70 36	97.62 177	98.43 100	99.35 111	99.47 26	99.28 71	99.05 108	96.72 160	99.82 145	98.09 81	99.36 215	99.59 55

RRT_test8_iter05		95.24 290	95.13 290	95.57 317	97.32 336	87.02 348	97.99 145	99.41 90	98.06 129	99.12 93	99.05 108	66.85 365	99.85 103	98.93 36	99.47 201	99.84 8

MVSTER		96.86 247	96.55 251	97.79 242	97.91 312	94.21 278	97.56 190	98.87 238	97.49 169	99.06 104	99.05 108	80.72 340	99.80 167	98.44 64	99.82 65	99.37 159

SD-MVS		98.40 125	98.68 65	97.54 261	98.96 195	97.99 138	97.88 155	99.36 105	98.20 121	99.63 25	99.04 111	98.76 22	95.33 361	96.56 181	99.74 103	99.31 183
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
abl_6		98.99 38	98.78 52	99.61 9	99.45 98	99.46 3	98.60 77	99.50 56	98.59 96	99.24 80	99.04 111	98.54 33	99.89 57	96.45 191	99.62 152	99.50 100

FMVSNet5		96.01 273	95.20 288	98.41 203	97.53 328	96.10 230	98.74 67	99.50 56	97.22 205	98.03 226	99.04 111	69.80 360	99.88 66	97.27 122	99.71 116	99.25 197

IS-MVSNet		98.19 147	97.90 163	99.08 109	99.57 55	97.97 143	99.31 18	98.32 283	99.01 70	98.98 121	99.03 114	91.59 279	99.79 180	95.49 241	99.80 77	99.48 111

hse-mvs3		97.77 184	97.33 205	99.10 105	99.21 135	97.84 157	98.35 107	98.57 273	99.11 56	98.58 182	99.02 115	88.65 298	99.96 8	98.11 78	96.34 341	99.49 104

SED-MVS		98.91 50	98.72 58	99.49 48	99.49 84	99.17 36	98.10 129	99.31 129	98.03 130	99.66 20	99.02 115	98.36 42	99.88 66	96.91 145	99.62 152	99.41 140

test_241102_TWO								99.30 138	98.03 130	99.26 77	99.02 115	97.51 107	99.88 66	96.91 145	99.60 160	99.66 34

DVP-MVS		98.77 67	98.52 84	99.52 41	99.50 77	99.21 26	98.02 141	98.84 245	97.97 133	99.08 101	99.02 115	97.61 97	99.88 66	96.99 139	99.63 149	99.48 111
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									98.17 124	99.08 101	99.02 115	97.89 76	99.88 66	97.07 134	99.71 116	99.70 29

EI-MVSNet		98.40 125	98.51 86	98.04 232	99.10 165	94.73 266	97.20 220	98.87 238	98.97 74	99.06 104	99.02 115	96.00 189	99.80 167	98.58 55	99.82 65	99.60 49

CVMVSNet		96.25 269	97.21 211	93.38 340	99.10 165	80.56 364	97.20 220	98.19 290	96.94 217	99.00 118	99.02 115	89.50 291	99.80 167	96.36 198	99.59 162	99.78 14

LFMVS		97.20 225	96.72 238	98.64 169	98.72 241	96.95 210	98.93 58	94.14 346	99.74 7	98.78 157	99.01 122	84.45 322	99.73 220	97.44 114	99.27 230	99.25 197

v2v482		98.56 102	98.62 72	98.37 207	99.42 104	95.81 239	97.58 188	99.16 185	97.90 139	99.28 71	99.01 122	95.98 193	99.79 180	99.33 15	99.90 44	99.51 96

ACMMP		98.75 70	98.50 88	99.52 41	99.56 62	99.16 40	98.87 61	99.37 101	97.16 207	98.82 154	99.01 122	97.71 88	99.87 82	96.29 203	99.69 127	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
DPE-MVS		98.59 100	98.26 126	99.57 18	99.27 123	99.15 45	97.01 231	99.39 95	97.67 152	99.44 46	98.99 125	97.53 104	99.89 57	95.40 243	99.68 132	99.66 34
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MP-MVS-pluss		98.57 101	98.23 130	99.60 13	99.69 38	99.35 11	97.16 226	99.38 97	94.87 278	98.97 124	98.99 125	98.01 68	99.88 66	97.29 121	99.70 121	99.58 61
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
EI-MVSNet-UG-set		98.69 80	98.71 60	98.62 174	99.10 165	96.37 224	97.23 216	98.87 238	99.20 48	99.19 86	98.99 125	97.30 122	99.85 103	98.77 47	99.79 82	99.65 38

XVG-ACMP-BASELINE		98.56 102	98.34 117	99.22 90	99.54 68	98.59 89	97.71 173	99.46 74	97.25 196	98.98 121	98.99 125	97.54 102	99.84 120	95.88 220	99.74 103	99.23 201

APD-MVS_3200maxsize		98.84 57	98.61 75	99.53 36	99.19 142	99.27 20	98.49 92	99.33 122	98.64 90	99.03 114	98.98 129	97.89 76	99.85 103	96.54 185	99.42 206	99.46 121

XVG-OURS		98.53 111	98.34 117	99.11 103	99.50 77	98.82 72	95.97 284	99.50 56	97.30 191	99.05 109	98.98 129	99.35 7	99.32 328	95.72 230	99.68 132	99.18 213

v148		98.45 119	98.60 77	98.00 234	99.44 100	94.98 261	97.44 203	99.06 202	98.30 109	99.32 68	98.97 131	96.65 163	99.62 267	98.37 68	99.85 54	99.39 149

EI-MVSNet-Vis-set		98.68 84	98.70 63	98.63 172	99.09 168	96.40 223	97.23 216	98.86 243	99.20 48	99.18 90	98.97 131	97.29 124	99.85 103	98.72 50	99.78 86	99.64 39

CHOSEN 1792x2688		97.49 201	97.14 216	98.54 190	99.68 39	96.09 232	96.50 262	99.62 19	91.58 325	98.84 149	98.97 131	92.36 273	99.88 66	96.76 162	99.95 16	99.67 33

SR-MVS-dyc-post		98.81 60	98.55 81	99.57 18	99.20 139	99.38 5	98.48 95	99.30 138	98.64 90	98.95 127	98.96 134	97.49 111	99.86 89	96.56 181	99.39 210	99.45 125

RE-MVS-def			98.58 79		99.20 139	99.38 5	98.48 95	99.30 138	98.64 90	98.95 127	98.96 134	97.75 86		96.56 181	99.39 210	99.45 125

D2MVS		97.84 178	97.84 167	97.83 240	99.14 158	94.74 265	96.94 235	98.88 236	95.84 256	98.89 139	98.96 134	94.40 240	99.69 235	97.55 108	99.95 16	99.05 228

ACMM	96.08 12	98.91 50	98.73 56	99.48 50	99.55 65	99.14 48	98.07 132	99.37 101	97.62 156	99.04 111	98.96 134	98.84 19	99.79 180	97.43 115	99.65 144	99.49 104
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVP-Stereo		98.08 154	97.92 161	98.57 182	98.96 195	96.79 214	97.90 154	99.18 176	96.41 237	98.46 194	98.95 138	95.93 196	99.60 274	96.51 187	98.98 275	99.31 183
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
YYNet1		97.60 194	97.67 176	97.39 270	99.04 179	93.04 306	95.27 312	98.38 282	97.25 196	98.92 135	98.95 138	95.48 213	99.73 220	96.99 139	98.74 284	99.41 140

MDA-MVSNet_test_wron		97.60 194	97.66 179	97.41 269	99.04 179	93.09 302	95.27 312	98.42 280	97.26 195	98.88 143	98.95 138	95.43 214	99.73 220	97.02 136	98.72 286	99.41 140

FMVSNet3		97.50 199	97.24 209	98.29 214	98.08 304	95.83 238	97.86 158	98.91 232	97.89 140	98.95 127	98.95 138	87.06 302	99.81 158	97.77 99	99.69 127	99.23 201

OPM-MVS		98.56 102	98.32 121	99.25 87	99.41 105	98.73 79	97.13 228	99.18 176	97.10 210	98.75 162	98.92 142	98.18 57	99.65 260	96.68 171	99.56 177	99.37 159

ADS-MVSNet2		95.43 287	94.98 293	96.76 296	98.14 300	91.74 322	97.92 151	97.76 301	90.23 335	96.51 305	98.91 143	85.61 314	99.85 103	92.88 304	96.90 334	98.69 281

ADS-MVSNet		95.24 290	94.93 295	96.18 305	98.14 300	90.10 336	97.92 151	97.32 313	90.23 335	96.51 305	98.91 143	85.61 314	99.74 216	92.88 304	96.90 334	98.69 281

test_0402		98.76 68	98.71 60	98.93 134	99.56 62	98.14 123	98.45 99	99.34 117	99.28 42	98.95 127	98.91 143	98.34 46	99.79 180	95.63 236	99.91 40	98.86 260

test_241102_ONE					99.49 84	99.17 36		99.31 129	97.98 132	99.66 20	98.90 146	98.36 42	99.48 308

xxxxxxxxxxxxxcwj		98.44 120	98.24 128	99.06 117	99.11 161	97.97 143	96.53 259	99.54 47	98.24 115	98.83 150	98.90 146	97.80 83	99.82 145	95.68 233	99.52 187	99.38 156

SF-MVS		98.53 111	98.27 125	99.32 76	99.31 117	98.75 75	98.19 119	99.41 90	96.77 224	98.83 150	98.90 146	97.80 83	99.82 145	95.68 233	99.52 187	99.38 156

zzz-MVS		98.79 62	98.52 84	99.61 9	99.67 40	99.36 9	97.33 209	99.20 167	98.83 85	98.89 139	98.90 146	96.98 142	99.92 35	97.16 127	99.70 121	99.56 71

MTAPA		98.88 53	98.64 70	99.61 9	99.67 40	99.36 9	98.43 100	99.20 167	98.83 85	98.89 139	98.90 146	96.98 142	99.92 35	97.16 127	99.70 121	99.56 71

test20.03		98.78 65	98.77 54	98.78 157	99.46 95	97.20 199	97.78 164	99.24 161	99.04 67	99.41 49	98.90 146	97.65 92	99.76 205	97.70 105	99.79 82	99.39 149

SteuartSystems-ACMMP		98.79 62	98.54 82	99.54 29	99.73 24	99.16 40	98.23 114	99.31 129	97.92 137	98.90 136	98.90 146	98.00 69	99.88 66	96.15 211	99.72 112	99.58 61
Skip Steuart: Steuart Systems R&D Blog.
N_pmnet		97.63 193	97.17 212	98.99 128	99.27 123	97.86 155	95.98 283	93.41 349	95.25 271	99.47 42	98.90 146	95.63 205	99.85 103	96.91 145	99.73 106	99.27 193

TSAR-MVS + MP.		98.63 92	98.49 91	99.06 117	99.64 46	97.90 152	98.51 90	98.94 225	96.96 216	99.24 80	98.89 154	97.83 79	99.81 158	96.88 152	99.49 198	99.48 111
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test1172		98.76 68	98.49 91	99.57 18	99.18 149	99.37 8	98.39 103	99.31 129	98.43 103	98.90 136	98.88 155	97.49 111	99.86 89	96.43 193	99.37 214	99.48 111

PGM-MVS		98.66 87	98.37 113	99.55 26	99.53 70	99.18 35	98.23 114	99.49 64	97.01 215	98.69 166	98.88 155	98.00 69	99.89 57	95.87 223	99.59 162	99.58 61

TinyColmap		97.89 168	97.98 156	97.60 254	98.86 217	94.35 275	96.21 277	99.44 80	97.45 177	99.06 104	98.88 155	97.99 72	99.28 334	94.38 269	99.58 168	99.18 213

LS3D		98.63 92	98.38 112	99.36 64	97.25 338	99.38 5	99.12 43	99.32 124	99.21 45	98.44 196	98.88 155	97.31 121	99.80 167	96.58 176	99.34 219	98.92 252

Anonymous202405211		97.90 166	97.50 190	99.08 109	98.90 208	98.25 110	98.53 85	96.16 330	98.87 81	99.11 95	98.86 159	90.40 285	99.78 192	97.36 118	99.31 223	99.19 211

HPM-MVS_fast		99.01 36	98.82 48	99.57 18	99.71 30	99.35 11	99.00 52	99.50 56	97.33 187	98.94 133	98.86 159	98.75 23	99.82 145	97.53 111	99.71 116	99.56 71

CMPMVS	75.91 23	96.29 267	95.44 280	98.84 146	96.25 354	98.69 82	97.02 230	99.12 194	88.90 344	97.83 235	98.86 159	89.51 290	98.90 351	91.92 318	99.51 190	98.92 252
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SR-MVS		98.71 75	98.43 103	99.57 18	99.18 149	99.35 11	98.36 106	99.29 145	98.29 112	98.88 143	98.85 162	97.53 104	99.87 82	96.14 212	99.31 223	99.48 111

our_test_3		97.39 210	97.73 174	96.34 301	98.70 248	89.78 337	94.61 332	98.97 224	96.50 233	99.04 111	98.85 162	95.98 193	99.84 120	97.26 123	99.67 138	99.41 140

MVS_0304		97.64 191	97.35 202	98.52 191	97.87 314	96.69 219	98.59 79	98.05 296	97.44 178	93.74 351	98.85 162	93.69 256	99.88 66	98.11 78	99.81 69	98.98 241

Regformer-3		98.61 95	98.61 75	98.63 172	99.02 184	96.53 221	97.17 224	98.84 245	99.13 55	99.10 98	98.85 162	97.24 129	99.79 180	98.41 67	99.70 121	99.57 66

Regformer-4		98.73 73	98.68 65	98.89 140	99.02 184	97.22 196	97.17 224	99.06 202	99.21 45	99.17 91	98.85 162	97.45 114	99.86 89	98.48 62	99.70 121	99.60 49

EPNet		96.14 271	95.44 280	98.25 217	90.76 365	95.50 246	97.92 151	94.65 339	98.97 74	92.98 352	98.85 162	89.12 293	99.87 82	95.99 216	99.68 132	99.39 149
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs5		97.64 191	97.49 191	98.08 228	99.14 158	95.12 259	96.70 253	99.05 206	93.77 300	98.62 174	98.83 168	93.23 258	99.75 212	98.33 71	99.76 99	99.36 165

PMMVS2		98.07 155	98.08 149	98.04 232	99.41 105	94.59 272	94.59 333	99.40 93	97.50 167	98.82 154	98.83 168	96.83 150	99.84 120	97.50 113	99.81 69	99.71 26

MDTV_nov1_ep13			95.22 287		97.06 341	83.20 360	97.74 171	96.16 330	94.37 289	96.99 282	98.83 168	83.95 327	99.53 295	93.90 282	97.95 316

Anonymous20231206		98.21 145	98.21 131	98.20 220	99.51 74	95.43 249	98.13 124	99.32 124	96.16 245	98.93 134	98.82 171	96.00 189	99.83 135	97.32 120	99.73 106	99.36 165

ACMP	95.32 15	98.41 123	98.09 146	99.36 64	99.51 74	98.79 74	97.68 176	99.38 97	95.76 259	98.81 156	98.82 171	98.36 42	99.82 145	94.75 253	99.77 90	99.48 111
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
VNet		98.42 122	98.30 122	98.79 154	98.79 233	97.29 190	98.23 114	98.66 268	99.31 39	98.85 147	98.80 173	94.80 231	99.78 192	98.13 77	99.13 255	99.31 183

tpmrst		95.07 293	95.46 278	93.91 334	97.11 340	84.36 358	97.62 182	96.96 319	94.98 274	96.35 311	98.80 173	85.46 316	99.59 278	95.60 237	96.23 343	97.79 321

ppachtmachnet_test		97.50 199	97.74 172	96.78 295	98.70 248	91.23 333	94.55 334	99.05 206	96.36 238	99.21 84	98.79 175	96.39 175	99.78 192	96.74 164	99.82 65	99.34 171

miper_lstm_enhance		97.18 227	97.16 213	97.25 275	98.16 299	92.85 308	95.15 317	99.31 129	97.25 196	98.74 164	98.78 176	90.07 286	99.78 192	97.19 125	99.80 77	99.11 224

DeepPCF-MVS	96.93 5	98.32 132	98.01 154	99.23 89	98.39 286	98.97 62	95.03 319	99.18 176	96.88 220	99.33 62	98.78 176	98.16 59	99.28 334	96.74 164	99.62 152	99.44 130

patchmatchnet-post											98.77 178	84.37 323	99.85 103

APD-MVS		98.10 152	97.67 176	99.42 57	99.11 161	98.93 66	97.76 169	99.28 147	94.97 275	98.72 165	98.77 178	97.04 136	99.85 103	93.79 287	99.54 180	99.49 104
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DU-MVS		98.82 58	98.63 71	99.39 63	99.16 153	98.74 76	97.54 192	99.25 156	98.84 84	99.06 104	98.76 180	96.76 157	99.93 28	98.57 57	99.77 90	99.50 100

NR-MVSNet		98.95 46	98.82 48	99.36 64	99.16 153	98.72 81	99.22 31	99.20 167	99.10 62	99.72 13	98.76 180	96.38 177	99.86 89	98.00 88	99.82 65	99.50 100

eth_miper_zixun_eth		97.23 223	97.25 207	97.17 277	98.00 308	92.77 310	94.71 326	99.18 176	97.27 194	98.56 186	98.74 182	91.89 278	99.69 235	97.06 135	99.81 69	99.05 228

UniMVSNet (Re)		98.87 54	98.71 60	99.35 69	99.24 128	98.73 79	97.73 172	99.38 97	98.93 79	99.12 93	98.73 183	96.77 155	99.86 89	98.63 54	99.80 77	99.46 121

MG-MVS		96.77 251	96.61 246	97.26 274	98.31 290	93.06 303	95.93 289	98.12 293	96.45 236	97.92 228	98.73 183	93.77 254	99.39 320	91.19 330	99.04 265	99.33 177

cl_fuxian		97.36 211	97.37 200	97.31 271	98.09 303	93.25 301	95.01 320	99.16 185	97.05 212	98.77 160	98.72 185	92.88 267	99.64 262	96.93 144	99.76 99	99.05 228

cl-mvsnet_		97.02 239	96.83 233	97.58 256	97.82 316	94.04 282	94.66 329	99.16 185	97.04 213	98.63 172	98.71 186	88.68 297	99.69 235	97.00 137	99.81 69	99.00 239

cl-mvsnet1		97.02 239	96.84 232	97.58 256	97.82 316	94.03 283	94.66 329	99.16 185	97.04 213	98.63 172	98.71 186	88.69 296	99.69 235	97.00 137	99.81 69	99.01 236

DELS-MVS		98.27 138	98.20 132	98.48 197	98.86 217	96.70 218	95.60 303	99.20 167	97.73 149	98.45 195	98.71 186	97.50 108	99.82 145	98.21 74	99.59 162	98.93 251
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
9.14			97.78 169		99.07 172		97.53 193	99.32 124	95.53 264	98.54 190	98.70 189	97.58 99	99.76 205	94.32 270	99.46 202

tpmvs		95.02 295	95.25 286	94.33 330	96.39 353	85.87 350	98.08 131	96.83 324	95.46 266	95.51 333	98.69 190	85.91 312	99.53 295	94.16 271	96.23 343	97.58 330

PatchmatchNet		95.58 283	95.67 272	95.30 323	97.34 335	87.32 346	97.65 180	96.65 325	95.30 270	97.07 278	98.69 190	84.77 319	99.75 212	94.97 249	98.64 292	98.83 262
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
mPP-MVS		98.64 90	98.34 117	99.54 29	99.54 68	99.17 36	98.63 74	99.24 161	97.47 170	98.09 220	98.68 192	97.62 96	99.89 57	96.22 206	99.62 152	99.57 66

UnsupCasMVSNet_eth		97.89 168	97.60 185	98.75 162	99.31 117	97.17 202	97.62 182	99.35 111	98.72 89	98.76 161	98.68 192	92.57 272	99.74 216	97.76 103	95.60 348	99.34 171

SCA		96.41 265	96.66 244	95.67 314	98.24 294	88.35 342	95.85 294	96.88 323	96.11 246	97.67 245	98.67 194	93.10 262	99.85 103	94.16 271	99.22 237	98.81 266

Patchmatch-test		96.55 259	96.34 257	97.17 277	98.35 287	93.06 303	98.40 102	97.79 300	97.33 187	98.41 200	98.67 194	83.68 329	99.69 235	95.16 245	99.31 223	98.77 274

CDS-MVSNet		97.69 187	97.35 202	98.69 166	98.73 239	97.02 208	96.92 239	98.75 261	95.89 255	98.59 180	98.67 194	92.08 277	99.74 216	96.72 167	99.81 69	99.32 179
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MP-MVS		98.46 118	98.09 146	99.54 29	99.57 55	99.22 25	98.50 91	99.19 172	97.61 158	97.58 252	98.66 197	97.40 117	99.88 66	94.72 256	99.60 160	99.54 83
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DeepC-MVS_fast	96.85 6	98.30 134	98.15 141	98.75 162	98.61 264	97.23 194	97.76 169	99.09 198	97.31 190	98.75 162	98.66 197	97.56 101	99.64 262	96.10 214	99.55 179	99.39 149
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MS-PatchMatch		97.68 188	97.75 171	97.45 266	98.23 296	93.78 295	97.29 212	98.84 245	96.10 247	98.64 171	98.65 199	96.04 186	99.36 323	96.84 156	99.14 252	99.20 206

pmmvs4		97.58 196	97.28 206	98.51 194	98.84 222	96.93 211	95.40 311	98.52 276	93.60 302	98.61 176	98.65 199	95.10 221	99.60 274	96.97 142	99.79 82	98.99 240

FPMVS		93.44 317	92.23 322	97.08 280	99.25 127	97.86 155	95.61 302	97.16 316	92.90 310	93.76 350	98.65 199	75.94 355	95.66 359	79.30 359	97.49 321	97.73 323

Regformer-1		98.55 106	98.44 101	98.87 142	98.85 219	97.29 190	96.91 240	98.99 222	98.97 74	98.99 119	98.64 202	97.26 128	99.81 158	97.79 97	99.57 172	99.51 96

Regformer-2		98.60 97	98.46 97	99.02 125	98.85 219	97.71 171	96.91 240	99.09 198	98.98 73	99.01 115	98.64 202	97.37 119	99.84 120	97.75 104	99.57 172	99.52 93

dp		93.47 316	93.59 310	93.13 342	96.64 347	81.62 363	97.66 178	96.42 328	92.80 312	96.11 314	98.64 202	78.55 352	99.59 278	93.31 299	92.18 359	98.16 303

EPMVS		93.72 314	93.27 313	95.09 325	96.04 356	87.76 344	98.13 124	85.01 363	94.69 281	96.92 284	98.64 202	78.47 353	99.31 329	95.04 246	96.46 340	98.20 301

XVS		98.72 74	98.45 99	99.53 36	99.46 95	99.21 26	98.65 72	99.34 117	98.62 94	97.54 256	98.63 206	97.50 108	99.83 135	96.79 158	99.53 184	99.56 71

CostFormer		93.97 310	93.78 307	94.51 329	97.53 328	85.83 352	97.98 147	95.96 333	89.29 343	94.99 339	98.63 206	78.63 350	99.62 267	94.54 259	96.50 339	98.09 306

ETH3D-3000-0.1		98.03 156	97.62 183	99.29 77	99.11 161	98.80 73	97.47 200	99.32 124	95.54 262	98.43 199	98.62 208	96.61 165	99.77 198	93.95 281	99.49 198	99.30 186

MSLP-MVS++		98.02 158	98.14 143	97.64 252	98.58 269	95.19 256	97.48 198	99.23 163	97.47 170	97.90 230	98.62 208	97.04 136	98.81 353	97.55 108	99.41 207	98.94 250

Vis-MVSNet (Re-imp)		97.46 204	97.16 213	98.34 209	99.55 65	96.10 230	98.94 57	98.44 279	98.32 108	98.16 213	98.62 208	88.76 295	99.73 220	93.88 284	99.79 82	99.18 213

XVG-OURS-SEG-HR		98.49 115	98.28 124	99.14 99	99.49 84	98.83 70	96.54 258	99.48 66	97.32 189	99.11 95	98.61 211	99.33 8	99.30 331	96.23 205	98.38 299	99.28 191

ITE_SJBPF				98.87 142	99.22 133	98.48 99		99.35 111	97.50 167	98.28 208	98.60 212	97.64 95	99.35 324	93.86 285	99.27 230	98.79 272

UniMVSNet_NR-MVSNet		98.86 56	98.68 65	99.40 62	99.17 151	98.74 76	97.68 176	99.40 93	99.14 54	99.06 104	98.59 213	96.71 161	99.93 28	98.57 57	99.77 90	99.53 89

114514_t		96.50 262	95.77 267	98.69 166	99.48 92	97.43 185	97.84 160	99.55 43	81.42 358	96.51 305	98.58 214	95.53 208	99.67 247	93.41 297	99.58 168	98.98 241

HY-MVS	95.94 13	95.90 276	95.35 284	97.55 260	97.95 309	94.79 264	98.81 66	96.94 321	92.28 318	95.17 336	98.57 215	89.90 288	99.75 212	91.20 329	97.33 330	98.10 305

tpm		94.67 298	94.34 302	95.66 315	97.68 324	88.42 341	97.88 155	94.90 338	94.46 285	96.03 319	98.56 216	78.66 349	99.79 180	95.88 220	95.01 351	98.78 273

ACMMPR		98.70 78	98.42 105	99.54 29	99.52 72	99.14 48	98.52 86	99.31 129	97.47 170	98.56 186	98.54 217	97.75 86	99.88 66	96.57 178	99.59 162	99.58 61

new_pmnet		96.99 243	96.76 236	97.67 248	98.72 241	94.89 263	95.95 288	98.20 288	92.62 314	98.55 188	98.54 217	94.88 227	99.52 299	93.96 280	99.44 205	98.59 287

OPU-MVS				98.82 148	98.59 268	98.30 107	98.10 129				98.52 219	98.18 57	98.75 354	94.62 257	99.48 200	99.41 140

region2R		98.69 80	98.40 107	99.54 29	99.53 70	99.17 36	98.52 86	99.31 129	97.46 175	98.44 196	98.51 220	97.83 79	99.88 66	96.46 190	99.58 168	99.58 61

TSAR-MVS + GP.		98.18 148	97.98 156	98.77 159	98.71 244	97.88 153	96.32 272	98.66 268	96.33 239	99.23 83	98.51 220	97.48 113	99.40 318	97.16 127	99.46 202	99.02 235

OMC-MVS		97.88 170	97.49 191	99.04 121	98.89 213	98.63 84	96.94 235	99.25 156	95.02 273	98.53 191	98.51 220	97.27 125	99.47 310	93.50 295	99.51 190	99.01 236

testtj		97.79 183	97.25 207	99.42 57	99.03 182	98.85 68	97.78 164	99.18 176	95.83 257	98.12 217	98.50 223	95.50 211	99.86 89	92.23 317	99.07 261	99.54 83

HFP-MVS		98.71 75	98.44 101	99.51 45	99.49 84	99.16 40	98.52 86	99.31 129	97.47 170	98.58 182	98.50 223	97.97 73	99.85 103	96.57 178	99.59 162	99.53 89

#test#		98.50 114	98.16 139	99.51 45	99.49 84	99.16 40	98.03 139	99.31 129	96.30 242	98.58 182	98.50 223	97.97 73	99.85 103	95.68 233	99.59 162	99.53 89

diffmvs		98.22 144	98.24 128	98.17 222	99.00 187	95.44 248	96.38 269	99.58 26	97.79 147	98.53 191	98.50 223	96.76 157	99.74 216	97.95 90	99.64 146	99.34 171

WR-MVS		98.40 125	98.19 134	99.03 122	99.00 187	97.65 174	96.85 243	98.94 225	98.57 100	98.89 139	98.50 223	95.60 206	99.85 103	97.54 110	99.85 54	99.59 55

Test_1112_low_res		96.99 243	96.55 251	98.31 212	99.35 114	95.47 247	95.84 295	99.53 50	91.51 327	96.80 295	98.48 228	91.36 280	99.83 135	96.58 176	99.53 184	99.62 44

miper_ehance_all_eth		97.06 235	97.03 219	97.16 279	97.83 315	93.06 303	94.66 329	99.09 198	95.99 252	98.69 166	98.45 229	92.73 270	99.61 273	96.79 158	99.03 266	98.82 263

PHI-MVS		98.29 137	97.95 158	99.34 72	98.44 283	99.16 40	98.12 126	99.38 97	96.01 251	98.06 222	98.43 230	97.80 83	99.67 247	95.69 232	99.58 168	99.20 206

tpm cat1		93.29 318	93.13 317	93.75 335	97.39 334	84.74 355	97.39 204	97.65 305	83.39 357	94.16 344	98.41 231	82.86 333	99.39 320	91.56 325	95.35 350	97.14 337

ETH3D cwj APD-0.16		97.55 197	97.00 221	99.19 92	98.51 277	98.64 83	96.85 243	99.13 192	94.19 293	97.65 246	98.40 232	95.78 201	99.81 158	93.37 298	99.16 248	99.12 222

CP-MVS		98.70 78	98.42 105	99.52 41	99.36 110	99.12 53	98.72 69	99.36 105	97.54 165	98.30 206	98.40 232	97.86 78	99.89 57	96.53 186	99.72 112	99.56 71

ZNCC-MVS		98.68 84	98.40 107	99.54 29	99.57 55	99.21 26	98.46 97	99.29 145	97.28 193	98.11 218	98.39 234	98.00 69	99.87 82	96.86 155	99.64 146	99.55 79

GST-MVS		98.61 95	98.30 122	99.52 41	99.51 74	99.20 32	98.26 112	99.25 156	97.44 178	98.67 168	98.39 234	97.68 89	99.85 103	96.00 215	99.51 190	99.52 93

bset_n11_16_dypcd		96.99 243	96.56 250	98.27 216	99.00 187	95.25 252	92.18 356	94.05 347	98.75 87	99.01 115	98.38 236	88.98 294	99.93 28	98.77 47	99.92 34	99.64 39

HPM-MVS		98.79 62	98.53 83	99.59 17	99.65 43	99.29 17	99.16 38	99.43 86	96.74 225	98.61 176	98.38 236	98.62 28	99.87 82	96.47 189	99.67 138	99.59 55
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testdata				98.09 225	98.93 200	95.40 250		98.80 253	90.08 339	97.45 264	98.37 238	95.26 217	99.70 231	93.58 292	98.95 277	99.17 217

CPTT-MVS		97.84 178	97.36 201	99.27 82	99.31 117	98.46 100	98.29 109	99.27 150	94.90 277	97.83 235	98.37 238	94.90 224	99.84 120	93.85 286	99.54 180	99.51 96

OpenMVS_ROB	95.38 14	95.84 278	95.18 289	97.81 241	98.41 285	97.15 204	97.37 206	98.62 271	83.86 355	98.65 170	98.37 238	94.29 243	99.68 244	88.41 342	98.62 294	96.60 344

tttt0517		95.64 282	94.98 293	97.64 252	99.36 110	93.81 294	98.72 69	90.47 358	98.08 128	98.67 168	98.34 241	73.88 357	99.92 35	97.77 99	99.51 190	99.20 206

旧先验1					98.82 227	97.45 184		98.76 258			98.34 241	95.50 211			99.01 271	99.23 201

CNVR-MVS		98.17 150	97.87 165	99.07 112	98.67 257	98.24 111	97.01 231	98.93 227	97.25 196	97.62 248	98.34 241	97.27 125	99.57 284	96.42 194	99.33 220	99.39 149

HyFIR lowres test		97.19 226	96.60 247	98.96 130	99.62 50	97.28 192	95.17 315	99.50 56	94.21 292	99.01 115	98.32 244	86.61 305	99.99 2	97.10 133	99.84 56	99.60 49

UnsupCasMVSNet_bld		97.30 216	96.92 226	98.45 200	99.28 122	96.78 217	96.20 278	99.27 150	95.42 267	98.28 208	98.30 245	93.16 260	99.71 229	94.99 248	97.37 326	98.87 259

MSDG		97.71 186	97.52 189	98.28 215	98.91 207	96.82 213	94.42 336	99.37 101	97.65 154	98.37 205	98.29 246	97.40 117	99.33 327	94.09 277	99.22 237	98.68 284

MVS_111021_HR		98.25 142	98.08 149	98.75 162	99.09 168	97.46 183	95.97 284	99.27 150	97.60 159	97.99 227	98.25 247	98.15 61	99.38 322	96.87 153	99.57 172	99.42 137

CANet_DTU		97.26 219	97.06 218	97.84 239	97.57 325	94.65 270	96.19 279	98.79 254	97.23 202	95.14 337	98.24 248	93.22 259	99.84 120	97.34 119	99.84 56	99.04 232

MVS_111021_LR		98.30 134	98.12 144	98.83 147	99.16 153	98.03 136	96.09 281	99.30 138	97.58 160	98.10 219	98.24 248	98.25 49	99.34 325	96.69 170	99.65 144	99.12 222

tpm2		93.09 320	92.58 321	94.62 328	97.56 326	86.53 349	97.66 178	95.79 335	86.15 352	94.07 347	98.23 250	75.95 354	99.53 295	90.91 333	96.86 337	97.81 318

CANet		97.87 171	97.76 170	98.19 221	97.75 318	95.51 245	96.76 249	99.05 206	97.74 148	96.93 283	98.21 251	95.59 207	99.89 57	97.86 96	99.93 25	99.19 211

LF4IMVS		97.90 166	97.69 175	98.52 191	99.17 151	97.66 173	97.19 223	99.47 72	96.31 241	97.85 234	98.20 252	96.71 161	99.52 299	94.62 257	99.72 112	98.38 296

CL-MVSNet_2432*1600		97.44 207	97.22 210	98.08 228	98.57 271	95.78 240	94.30 339	98.79 254	96.58 232	98.60 178	98.19 253	94.74 234	99.64 262	96.41 195	98.84 280	98.82 263

cl-mvsnet2		95.79 279	95.39 283	96.98 284	96.77 346	92.79 309	94.40 337	98.53 275	94.59 282	97.89 231	98.17 254	82.82 334	99.24 336	96.37 196	99.03 266	98.92 252

1121		96.73 252	96.00 263	98.91 137	98.95 197	97.76 166	98.07 132	98.73 264	87.65 349	96.54 302	98.13 255	94.52 237	99.73 220	92.38 315	99.02 269	99.24 200

MVSFormer		98.26 140	98.43 103	97.77 243	98.88 214	93.89 292	99.39 11	99.56 40	99.11 56	98.16 213	98.13 255	93.81 252	99.97 3	99.26 18	99.57 172	99.43 134

jason		97.45 206	97.35 202	97.76 244	99.24 128	93.93 288	95.86 292	98.42 280	94.24 291	98.50 193	98.13 255	94.82 228	99.91 45	97.22 124	99.73 106	99.43 134
jason: jason.
ZD-MVS					99.01 186	98.84 69		99.07 201	94.10 295	98.05 224	98.12 258	96.36 179	99.86 89	92.70 311	99.19 244

test222					98.92 204	96.93 211	95.54 304	98.78 256	85.72 353	96.86 292	98.11 259	94.43 238			99.10 260	99.23 201

新几何1				98.91 137	98.94 198	97.76 166		98.76 258	87.58 350	96.75 296	98.10 260	94.80 231	99.78 192	92.73 310	99.00 272	99.20 206

原ACMM1				98.35 208	98.90 208	96.25 228		98.83 250	92.48 315	96.07 317	98.10 260	95.39 215	99.71 229	92.61 313	98.99 273	99.08 225

EPNet_dtu		94.93 296	94.78 297	95.38 322	93.58 362	87.68 345	96.78 247	95.69 336	97.35 186	89.14 360	98.09 262	88.15 300	99.49 305	94.95 250	99.30 226	98.98 241
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs3		95.03 294	94.40 300	96.93 286	97.70 322	92.53 313	95.08 318	97.71 303	88.57 346	97.71 242	98.08 263	79.39 347	99.82 145	96.19 208	99.11 259	98.43 294

DP-MVS Recon		97.33 214	96.92 226	98.57 182	99.09 168	97.99 138	96.79 246	99.35 111	93.18 306	97.71 242	98.07 264	95.00 223	99.31 329	93.97 279	99.13 255	98.42 295

CSCG		98.68 84	98.50 88	99.20 91	99.45 98	98.63 84	98.56 82	99.57 33	97.87 141	98.85 147	98.04 265	97.66 91	99.84 120	96.72 167	99.81 69	99.13 221

F-COLMAP		97.30 216	96.68 241	99.14 99	99.19 142	98.39 103	97.27 215	99.30 138	92.93 309	96.62 300	98.00 266	95.73 203	99.68 244	92.62 312	98.46 298	99.35 169

Effi-MVS+-dtu		98.26 140	97.90 163	99.35 69	98.02 306	99.49 2	98.02 141	99.16 185	98.29 112	97.64 247	97.99 267	96.44 173	99.95 15	96.66 172	98.93 278	98.60 285

hse-mvs2		97.46 204	97.07 217	98.64 169	98.73 239	97.33 188	97.45 202	97.64 307	99.11 56	98.58 182	97.98 268	88.65 298	99.79 180	98.11 78	97.39 325	98.81 266

HQP_MVS		97.99 163	97.67 176	98.93 134	99.19 142	97.65 174	97.77 167	99.27 150	98.20 121	97.79 238	97.98 268	94.90 224	99.70 231	94.42 265	99.51 190	99.45 125

plane_prior4											97.98 268

BH-RMVSNet		96.83 248	96.58 248	97.58 256	98.47 280	94.05 281	96.67 254	97.36 310	96.70 228	97.87 232	97.98 268	95.14 220	99.44 315	90.47 336	98.58 296	99.25 197

AUN-MVS		96.24 270	95.45 279	98.60 177	98.70 248	97.22 196	97.38 205	97.65 305	95.95 253	95.53 332	97.96 272	82.11 339	99.79 180	96.31 200	97.44 323	98.80 271

NCCC		97.86 172	97.47 195	99.05 119	98.61 264	98.07 131	96.98 233	98.90 233	97.63 155	97.04 280	97.93 273	95.99 192	99.66 255	95.31 244	98.82 282	99.43 134

sss		97.21 224	96.93 224	98.06 230	98.83 224	95.22 255	96.75 250	98.48 278	94.49 283	97.27 271	97.90 274	92.77 269	99.80 167	96.57 178	99.32 221	99.16 220

test_yl		96.69 253	96.29 259	97.90 236	98.28 291	95.24 253	97.29 212	97.36 310	98.21 118	98.17 211	97.86 275	86.27 307	99.55 290	94.87 251	98.32 300	98.89 256

DCV-MVSNet		96.69 253	96.29 259	97.90 236	98.28 291	95.24 253	97.29 212	97.36 310	98.21 118	98.17 211	97.86 275	86.27 307	99.55 290	94.87 251	98.32 300	98.89 256

CDPH-MVS		97.26 219	96.66 244	99.07 112	99.00 187	98.15 121	96.03 282	99.01 218	91.21 331	97.79 238	97.85 277	96.89 146	99.69 235	92.75 309	99.38 213	99.39 149

HPM-MVS++		98.10 152	97.64 181	99.48 50	99.09 168	99.13 51	97.52 194	98.75 261	97.46 175	96.90 289	97.83 278	96.01 188	99.84 120	95.82 227	99.35 217	99.46 121

ETH3 D test6400		96.46 264	95.59 275	99.08 109	98.88 214	98.21 117	96.53 259	99.18 176	88.87 345	97.08 277	97.79 279	93.64 257	99.77 198	88.92 341	99.40 209	99.28 191

PatchMatch-RL		97.24 222	96.78 235	98.61 176	99.03 182	97.83 158	96.36 270	99.06 202	93.49 305	97.36 270	97.78 280	95.75 202	99.49 305	93.44 296	98.77 283	98.52 288

TAPA-MVS	96.21 11	96.63 257	95.95 265	98.65 168	98.93 200	98.09 125	96.93 237	99.28 147	83.58 356	98.13 216	97.78 280	96.13 183	99.40 318	93.52 293	99.29 228	98.45 292
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
baseline1		95.96 275	95.44 280	97.52 263	98.51 277	93.99 286	98.39 103	96.09 332	98.21 118	98.40 204	97.76 282	86.88 303	99.63 265	95.42 242	89.27 360	98.95 246

WTY-MVS		96.67 255	96.27 261	97.87 238	98.81 229	94.61 271	96.77 248	97.92 299	94.94 276	97.12 274	97.74 283	91.11 281	99.82 145	93.89 283	98.15 308	99.18 213

MSP-MVS		98.40 125	98.00 155	99.61 9	99.57 55	99.25 22	98.57 81	99.35 111	97.55 164	99.31 70	97.71 284	94.61 235	99.88 66	96.14 212	99.19 244	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
MCST-MVS		98.00 160	97.63 182	99.10 105	99.24 128	98.17 120	96.89 242	98.73 264	95.66 260	97.92 228	97.70 285	97.17 132	99.66 255	96.18 210	99.23 236	99.47 119

AdaColmap		97.14 230	96.71 239	98.46 199	98.34 288	97.80 164	96.95 234	98.93 227	95.58 261	96.92 284	97.66 286	95.87 199	99.53 295	90.97 331	99.14 252	98.04 307

thisisatest0530		95.27 289	94.45 299	97.74 246	99.19 142	94.37 274	97.86 158	90.20 359	97.17 206	98.22 210	97.65 287	73.53 358	99.90 48	96.90 150	99.35 217	98.95 246

testgi		98.32 132	98.39 110	98.13 224	99.57 55	95.54 243	97.78 164	99.49 64	97.37 184	99.19 86	97.65 287	98.96 17	99.49 305	96.50 188	98.99 273	99.34 171

test_prior3		97.48 203	97.00 221	98.95 131	98.69 252	97.95 148	95.74 298	99.03 211	96.48 234	96.11 314	97.63 289	95.92 197	99.59 278	94.16 271	99.20 240	99.30 186

test_prior2							95.74 298		96.48 234	96.11 314	97.63 289	95.92 197		94.16 271	99.20 240

cdsmvs_eth3d_5k		24.66 332	32.88 335	0.00 348	0.00 369	0.00 370	0.00 360	99.10 197	0.00 365	0.00 366	97.58 291	99.21 10	0.00 366	0.00 364	0.00 364	0.00 362

lupinMVS		97.06 235	96.86 230	97.65 250	98.88 214	93.89 292	95.48 308	97.97 297	93.53 303	98.16 213	97.58 291	93.81 252	99.91 45	96.77 161	99.57 172	99.17 217

TEST9					98.71 244	98.08 129	95.96 286	99.03 211	91.40 328	95.85 321	97.53 293	96.52 168	99.76 205

train_agg		97.10 231	96.45 254	99.07 112	98.71 244	98.08 129	95.96 286	99.03 211	91.64 323	95.85 321	97.53 293	96.47 171	99.76 205	93.67 289	99.16 248	99.36 165

Fast-Effi-MVS+-dtu		98.27 138	98.09 146	98.81 150	98.43 284	98.11 124	97.61 184	99.50 56	98.64 90	97.39 268	97.52 295	98.12 62	99.95 15	96.90 150	98.71 288	98.38 296

test_8					98.67 257	98.01 137	95.91 291	99.02 215	91.64 323	95.79 323	97.50 296	96.47 171	99.76 205

agg_prior1		97.06 235	96.40 255	99.03 122	98.68 255	97.99 138	95.76 296	99.01 218	91.73 322	95.59 324	97.50 296	96.49 170	99.77 198	93.71 288	99.14 252	99.34 171

1112_ss		97.29 218	96.86 230	98.58 179	99.34 116	96.32 226	96.75 250	99.58 26	93.14 307	96.89 290	97.48 298	92.11 276	99.86 89	96.91 145	99.54 180	99.57 66

ab-mvs-re		8.12 336	10.83 339	0.00 348	0.00 369	0.00 370	0.00 360	0.00 370	0.00 365	0.00 366	97.48 298	0.00 371	0.00 366	0.00 364	0.00 364	0.00 362

Effi-MVS+		98.02 158	97.82 168	98.62 174	98.53 276	97.19 200	97.33 209	99.68 13	97.30 191	96.68 297	97.46 300	98.56 32	99.80 167	96.63 174	98.20 304	98.86 260

PCF-MVS	92.86 18	94.36 301	93.00 318	98.42 202	98.70 248	97.56 178	93.16 351	99.11 196	79.59 359	97.55 255	97.43 301	92.19 274	99.73 220	79.85 358	99.45 204	97.97 311
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
GA-MVS		95.86 277	95.32 285	97.49 264	98.60 266	94.15 280	93.83 346	97.93 298	95.49 265	96.68 297	97.42 302	83.21 330	99.30 331	96.22 206	98.55 297	99.01 236

CNLPA		97.17 228	96.71 239	98.55 187	98.56 272	98.05 134	96.33 271	98.93 227	96.91 219	97.06 279	97.39 303	94.38 241	99.45 314	91.66 321	99.18 246	98.14 304

PLC	94.65 16	96.51 260	95.73 269	98.85 145	98.75 237	97.91 151	96.42 267	99.06 202	90.94 334	95.59 324	97.38 304	94.41 239	99.59 278	90.93 332	98.04 315	99.05 228
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 248	96.75 237	97.08 280	98.74 238	93.33 300	96.71 252	98.26 285	96.72 226	98.44 196	97.37 305	95.20 218	99.47 310	91.89 319	97.43 324	98.44 293

PVSNet_Blended		96.88 246	96.68 241	97.47 265	98.92 204	93.77 296	94.71 326	99.43 86	90.98 333	97.62 248	97.36 306	96.82 151	99.67 247	94.73 254	99.56 177	98.98 241

miper_enhance_ethall		96.01 273	95.74 268	96.81 294	96.41 352	92.27 318	93.69 348	98.89 235	91.14 332	98.30 206	97.35 307	90.58 283	99.58 283	96.31 200	99.03 266	98.60 285

DPM-MVS		96.32 266	95.59 275	98.51 194	98.76 234	97.21 198	94.54 335	98.26 285	91.94 321	96.37 310	97.25 308	93.06 264	99.43 316	91.42 326	98.74 284	98.89 256

E-PMN		94.17 306	94.37 301	93.58 337	96.86 343	85.71 353	90.11 358	97.07 317	98.17 124	97.82 237	97.19 309	84.62 321	98.94 349	89.77 338	97.68 320	96.09 351

mvs-test1		97.83 180	97.48 194	98.89 140	98.02 306	99.20 32	97.20 220	99.16 185	98.29 112	96.46 309	97.17 310	96.44 173	99.92 35	96.66 172	97.90 317	97.54 332

CLD-MVS		97.49 201	97.16 213	98.48 197	99.07 172	97.03 207	94.71 326	99.21 165	94.46 285	98.06 222	97.16 311	97.57 100	99.48 308	94.46 262	99.78 86	98.95 246
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CHOSEN 280x420		95.51 286	95.47 277	95.65 316	98.25 293	88.27 343	93.25 350	98.88 236	93.53 303	94.65 340	97.15 312	86.17 309	99.93 28	97.41 116	99.93 25	98.73 277

xiu_mvs_v1_base_debu		97.86 172	98.17 136	96.92 287	98.98 192	93.91 289	96.45 264	99.17 182	97.85 143	98.41 200	97.14 313	98.47 35	99.92 35	98.02 85	99.05 262	96.92 338

xiu_mvs_v1_base		97.86 172	98.17 136	96.92 287	98.98 192	93.91 289	96.45 264	99.17 182	97.85 143	98.41 200	97.14 313	98.47 35	99.92 35	98.02 85	99.05 262	96.92 338

xiu_mvs_v1_base_debi		97.86 172	98.17 136	96.92 287	98.98 192	93.91 289	96.45 264	99.17 182	97.85 143	98.41 200	97.14 313	98.47 35	99.92 35	98.02 85	99.05 262	96.92 338

NP-MVS					98.84 222	97.39 187					96.84 316

HQP-MVS		97.00 242	96.49 253	98.55 187	98.67 257	96.79 214	96.29 273	99.04 209	96.05 248	95.55 328	96.84 316	93.84 250	99.54 293	92.82 306	99.26 233	99.32 179

API-MVS		97.04 238	96.91 228	97.42 268	97.88 313	98.23 115	98.18 120	98.50 277	97.57 161	97.39 268	96.75 318	96.77 155	99.15 343	90.16 337	99.02 269	94.88 355

1314		95.74 280	95.60 274	96.17 306	97.53 328	92.75 311	98.07 132	98.31 284	91.22 330	94.25 343	96.68 319	95.53 208	99.03 345	91.64 323	97.18 331	96.74 342

TR-MVS		95.55 284	95.12 291	96.86 293	97.54 327	93.94 287	96.49 263	96.53 327	94.36 290	97.03 281	96.61 320	94.26 244	99.16 342	86.91 346	96.31 342	97.47 334

Fast-Effi-MVS+		97.67 189	97.38 199	98.57 182	98.71 244	97.43 185	97.23 216	99.45 77	94.82 279	96.13 313	96.51 321	98.52 34	99.91 45	96.19 208	98.83 281	98.37 298

xiu_mvs_v2_base		97.16 229	97.49 191	96.17 306	98.54 274	92.46 314	95.45 309	98.84 245	97.25 196	97.48 262	96.49 322	98.31 47	99.90 48	96.34 199	98.68 290	96.15 349

MVS		93.19 319	92.09 323	96.50 299	96.91 342	94.03 283	98.07 132	98.06 295	68.01 360	94.56 342	96.48 323	95.96 195	99.30 331	83.84 351	96.89 336	96.17 347

PAPM_NR		96.82 250	96.32 258	98.30 213	99.07 172	96.69 219	97.48 198	98.76 258	95.81 258	96.61 301	96.47 324	94.12 248	99.17 341	90.82 335	97.78 318	99.06 227

KD-MVS_2432*1600		92.87 321	91.99 325	95.51 319	91.37 363	89.27 338	94.07 341	98.14 291	95.42 267	97.25 272	96.44 325	67.86 362	99.24 336	91.28 327	96.08 345	98.02 308

miper_refine_blended		92.87 321	91.99 325	95.51 319	91.37 363	89.27 338	94.07 341	98.14 291	95.42 267	97.25 272	96.44 325	67.86 362	99.24 336	91.28 327	96.08 345	98.02 308

PVSNet	93.40 17	95.67 281	95.70 270	95.57 317	98.83 224	88.57 340	92.50 353	97.72 302	92.69 313	96.49 308	96.44 325	93.72 255	99.43 316	93.61 290	99.28 229	98.71 278

EMVS		93.83 312	94.02 304	93.23 341	96.83 345	84.96 354	89.77 359	96.32 329	97.92 137	97.43 266	96.36 328	86.17 309	98.93 350	87.68 344	97.73 319	95.81 352

MAR-MVS		96.47 263	95.70 270	98.79 154	97.92 311	99.12 53	98.28 110	98.60 272	92.16 320	95.54 331	96.17 329	94.77 233	99.52 299	89.62 339	98.23 302	97.72 324
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
PAPM		91.88 329	90.34 332	96.51 298	98.06 305	92.56 312	92.44 354	97.17 315	86.35 351	90.38 358	96.01 330	86.61 305	99.21 339	70.65 361	95.43 349	97.75 322

PS-MVSNAJ		97.08 233	97.39 198	96.16 308	98.56 272	92.46 314	95.24 314	98.85 244	97.25 196	97.49 261	95.99 331	98.07 63	99.90 48	96.37 196	98.67 291	96.12 350

baseline2		93.73 313	92.83 319	96.42 300	97.70 322	91.28 331	96.84 245	89.77 360	93.96 299	92.44 354	95.93 332	79.14 348	99.77 198	92.94 302	96.76 338	98.21 300

alignmvs		97.35 212	96.88 229	98.78 157	98.54 274	98.09 125	97.71 173	97.69 304	99.20 48	97.59 251	95.90 333	88.12 301	99.55 290	98.18 76	98.96 276	98.70 280

ET-MVSNet_ETH3D		94.30 304	93.21 314	97.58 256	98.14 300	94.47 273	94.78 325	93.24 351	94.72 280	89.56 359	95.87 334	78.57 351	99.81 158	96.91 145	97.11 333	98.46 290

thisisatest0515		94.12 308	93.16 315	96.97 285	98.60 266	92.90 307	93.77 347	90.61 357	94.10 295	96.91 286	95.87 334	74.99 356	99.80 167	94.52 260	99.12 258	98.20 301

BH-w/o		95.13 292	94.89 296	95.86 310	98.20 297	91.31 329	95.65 301	97.37 309	93.64 301	96.52 304	95.70 336	93.04 265	99.02 346	88.10 343	95.82 347	97.24 336

PMMVS		96.51 260	95.98 264	98.09 225	97.53 328	95.84 237	94.92 322	98.84 245	91.58 325	96.05 318	95.58 337	95.68 204	99.66 255	95.59 238	98.09 311	98.76 275

EIA-MVS		98.00 160	97.74 172	98.80 152	98.72 241	98.09 125	98.05 136	99.60 23	97.39 182	96.63 299	95.55 338	97.68 89	99.80 167	96.73 166	99.27 230	98.52 288

ETV-MVS		98.03 156	97.86 166	98.56 186	98.69 252	98.07 131	97.51 196	99.50 56	98.10 127	97.50 260	95.51 339	98.41 39	99.88 66	96.27 204	99.24 235	97.71 325

PAPR		95.29 288	94.47 298	97.75 245	97.50 332	95.14 258	94.89 323	98.71 266	91.39 329	95.35 335	95.48 340	94.57 236	99.14 344	84.95 349	97.37 326	98.97 245

canonicalmvs		98.34 131	98.26 126	98.58 179	98.46 281	97.82 161	98.96 56	99.46 74	99.19 52	97.46 263	95.46 341	98.59 30	99.46 312	98.08 82	98.71 288	98.46 290

MVE	83.40 22	92.50 324	91.92 327	94.25 331	98.83 224	91.64 323	92.71 352	83.52 364	95.92 254	86.46 363	95.46 341	95.20 218	95.40 360	80.51 357	98.64 292	95.73 353
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test-LLR		93.90 311	93.85 305	94.04 332	96.53 348	84.62 356	94.05 343	92.39 353	96.17 243	94.12 345	95.07 343	82.30 335	99.67 247	95.87 223	98.18 305	97.82 316

test-mter		92.33 326	91.76 329	94.04 332	96.53 348	84.62 356	94.05 343	92.39 353	94.00 298	94.12 345	95.07 343	65.63 368	99.67 247	95.87 223	98.18 305	97.82 316

thres600view7		94.45 300	93.83 306	96.29 302	99.06 176	91.53 324	97.99 145	94.24 344	98.34 106	97.44 265	95.01 345	79.84 343	99.67 247	84.33 350	98.23 302	97.66 327

gm-plane-assit					94.83 360	81.97 362			88.07 348		94.99 346		99.60 274	91.76 320

thres100view900		94.19 305	93.67 309	95.75 313	99.06 176	91.35 328	98.03 139	94.24 344	98.33 107	97.40 267	94.98 347	79.84 343	99.62 267	83.05 352	98.08 312	96.29 345

cascas		94.79 297	94.33 303	96.15 309	96.02 357	92.36 317	92.34 355	99.26 155	85.34 354	95.08 338	94.96 348	92.96 266	98.53 355	94.41 268	98.59 295	97.56 331

TESTMET0.1,1		92.19 328	91.77 328	93.46 338	96.48 350	82.80 361	94.05 343	91.52 356	94.45 287	94.00 348	94.88 349	66.65 366	99.56 287	95.78 228	98.11 310	98.02 308

test0.0.03 1		94.51 299	93.69 308	96.99 283	96.05 355	93.61 299	94.97 321	93.49 348	96.17 243	97.57 254	94.88 349	82.30 335	99.01 348	93.60 291	94.17 356	98.37 298

CS-MVS		97.82 182	97.59 187	98.52 191	98.76 234	98.04 135	98.20 118	99.61 21	97.10 210	96.02 320	94.87 351	98.27 48	99.84 120	96.31 200	99.17 247	97.69 326

DeepMVS_CX				93.44 339	98.24 294	94.21 278		94.34 341	64.28 361	91.34 357	94.87 351	89.45 292	92.77 362	77.54 360	93.14 357	93.35 357

IB-MVS	91.63 19	92.24 327	90.90 331	96.27 303	97.22 339	91.24 332	94.36 338	93.33 350	92.37 316	92.24 355	94.58 353	66.20 367	99.89 57	93.16 301	94.63 353	97.66 327
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
tfpn200view9		94.03 309	93.44 311	95.78 312	98.93 200	91.44 326	97.60 185	94.29 342	97.94 135	97.10 275	94.31 354	79.67 345	99.62 267	83.05 352	98.08 312	96.29 345

thres400		94.14 307	93.44 311	96.24 304	98.93 200	91.44 326	97.60 185	94.29 342	97.94 135	97.10 275	94.31 354	79.67 345	99.62 267	83.05 352	98.08 312	97.66 327

DWT-MVSNet_test		92.75 323	92.05 324	94.85 326	96.48 350	87.21 347	97.83 161	94.99 337	92.22 319	92.72 353	94.11 356	70.75 359	99.46 312	95.01 247	94.33 355	97.87 314

thres200		93.72 314	93.14 316	95.46 321	98.66 262	91.29 330	96.61 257	94.63 340	97.39 182	96.83 293	93.71 357	79.88 342	99.56 287	82.40 355	98.13 309	95.54 354

PVSNet_0	89.98 21	91.15 330	90.30 333	93.70 336	97.72 319	84.34 359	90.24 357	97.42 308	90.20 338	93.79 349	93.09 358	90.90 282	98.89 352	86.57 347	72.76 361	97.87 314

tmp_tt		78.77 331	78.73 334	78.90 345	58.45 366	74.76 367	94.20 340	78.26 367	39.16 362	86.71 362	92.82 359	80.50 341	75.19 363	86.16 348	92.29 358	86.74 358

GG-mvs-BLEND				94.76 327	94.54 361	92.13 320	99.31 18	80.47 366		88.73 361	91.01 360	67.59 364	98.16 358	82.30 356	94.53 354	93.98 356

X-MVStestdata		94.32 302	92.59 320	99.53 36	99.46 95	99.21 26	98.65 72	99.34 117	98.62 94	97.54 256	45.85 361	97.50 108	99.83 135	96.79 158	99.53 184	99.56 71

testmvs		17.12 333	20.53 336	6.87 347	12.05 367	4.20 369	93.62 349	6.73 368	4.62 364	10.41 364	24.33 362	8.28 370	3.56 365	9.69 363	15.07 362	12.86 361

test123		17.04 334	20.11 337	7.82 346	10.25 368	4.91 368	94.80 324	4.47 369	4.93 363	10.00 365	24.28 363	9.69 369	3.64 364	10.14 362	12.43 363	14.92 360

test_post											21.25 364	83.86 328	99.70 231

test_post1							97.59 187				20.48 365	83.07 332	99.66 255	94.16 271

uanet_test		0.00 337	0.00 340	0.00 348	0.00 369	0.00 370	0.00 360	0.00 370	0.00 365	0.00 366	0.00 366	0.00 371	0.00 366	0.00 364	0.00 364	0.00 362

pcd_1.5k_mvsjas		8.17 335	10.90 338	0.00 348	0.00 369	0.00 370	0.00 360	0.00 370	0.00 365	0.00 366	0.00 366	98.07 63	0.00 366	0.00 364	0.00 364	0.00 362

sosnet-low-res		0.00 337	0.00 340	0.00 348	0.00 369	0.00 370	0.00 360	0.00 370	0.00 365	0.00 366	0.00 366	0.00 371	0.00 366	0.00 364	0.00 364	0.00 362

sosnet		0.00 337	0.00 340	0.00 348	0.00 369	0.00 370	0.00 360	0.00 370	0.00 365	0.00 366	0.00 366	0.00 371	0.00 366	0.00 364	0.00 364	0.00 362

uncertanet		0.00 337	0.00 340	0.00 348	0.00 369	0.00 370	0.00 360	0.00 370	0.00 365	0.00 366	0.00 366	0.00 371	0.00 366	0.00 364	0.00 364	0.00 362

Regformer		0.00 337	0.00 340	0.00 348	0.00 369	0.00 370	0.00 360	0.00 370	0.00 365	0.00 366	0.00 366	0.00 371	0.00 366	0.00 364	0.00 364	0.00 362

uanet		0.00 337	0.00 340	0.00 348	0.00 369	0.00 370	0.00 360	0.00 370	0.00 365	0.00 366	0.00 366	0.00 371	0.00 366	0.00 364	0.00 364	0.00 362

IU-MVS					99.49 84	99.15 45		98.87 238	92.97 308	99.41 49				96.76 162	99.62 152	99.66 34

save fliter					99.11 161	97.97 143	96.53 259	99.02 215	98.24 115

test_0728_SECOND				99.60 13	99.50 77	99.23 24	98.02 141	99.32 124					99.88 66	96.99 139	99.63 149	99.68 31

GSMVS																98.81 266

test_part2					99.36 110	99.10 56				99.05 109

sam_mvs1												84.74 320				98.81 266

sam_mvs												84.29 326

MTGPA								99.20 167

MTMP							97.93 150	91.91 355

test9_res														93.28 300	99.15 251	99.38 156

agg_prior2														92.50 314	99.16 248	99.37 159

agg_prior					98.68 255	97.99 138		99.01 218		95.59 324			99.77 198

test_prior4						97.97 143	95.86 292

test_prior				98.95 131	98.69 252	97.95 148		99.03 211					99.59 278			99.30 186

旧先验2							95.76 296		88.56 347	97.52 258			99.66 255	94.48 261

新几何2							95.93 289

无先验							95.74 298	98.74 263	89.38 342				99.73 220	92.38 315		99.22 205

原ACMM2							95.53 305

testdata2													99.79 180	92.80 308

segment_acmp												97.02 139

testdata1							95.44 310		96.32 240

test12				98.93 134	98.58 269	97.83 158		98.66 268		96.53 303		95.51 210	99.69 235		99.13 255	99.27 193

plane_prior7					99.19 142	97.87 154

plane_prior6					98.99 191	97.70 172						94.90 224

plane_prior5								99.27 150					99.70 231	94.42 265	99.51 190	99.45 125

plane_prior3						97.78 165			97.41 180	97.79 238

plane_prior2							97.77 167		98.20 121

plane_prior1					99.05 178

plane_prior						97.65 174	97.07 229		96.72 226						99.36 215

n2								0.00 370

nn								0.00 370

door-mid								99.57 33

test11								98.87 238

door								99.41 90

HQP5-MVS						96.79 214

HQP-NCC					98.67 257		96.29 273		96.05 248	95.55 328

ACMP_Plane					98.67 257		96.29 273		96.05 248	95.55 328

BP-MVS														92.82 306

HQP4-MVS										95.56 327			99.54 293			99.32 179

HQP3-MVS								99.04 209							99.26 233

HQP2-MVS												93.84 250

MDTV_nov1_ep13_2view						74.92 366	97.69 175		90.06 340	97.75 241		85.78 313		93.52 293		98.69 281

ACMMP++_ref															99.77 90

ACMMP++															99.68 132

Test By Simon												96.52 168

High-resolution multi-view benchmark