High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

LCM-MVSNet		99.86 1	99.86 1	99.87 1	99.99 1	99.77 1	99.77 1	99.80 1	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 3

UA-Net		98.88 7	98.76 13	99.22 2	99.11 82	97.89 13	99.47 3	99.32 9	99.08 10	97.87 135	99.67 2	96.47 85	99.92 4	97.88 23	99.98 2	99.85 3

pmmvs6		99.07 4	99.24 4	98.56 49	99.81 2	96.38 61	98.87 7	99.30 10	99.01 16	99.63 9	99.66 3	99.27 2	99.68 119	97.75 30	99.89 22	99.62 25

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 43	99.77 3	96.34 63	99.18 5	99.20 15	99.67 2	99.73 3	99.65 4	99.15 3	99.86 20	97.22 45	99.92 14	99.77 8

OurMVSNet-221017-0		98.61 16	98.61 23	98.63 45	99.77 3	96.35 62	99.17 6	99.05 42	98.05 40	99.61 11	99.52 5	93.72 176	99.88 18	98.72 9	99.88 23	99.65 23

ANet_high		98.31 28	98.94 6	96.41 200	99.33 43	89.64 245	97.92 52	99.56 5	99.27 6	99.66 8	99.50 6	97.67 25	99.83 28	97.55 36	99.98 2	99.77 8

mvs_tets		98.90 5	98.94 6	98.75 33	99.69 8	96.48 59	98.54 18	99.22 12	96.23 108	99.71 4	99.48 7	98.77 6	99.93 2	98.89 3	99.95 5	99.84 5

gg-mvs-nofinetune		88.28 325	86.96 330	92.23 325	92.84 359	84.44 327	98.19 38	74.60 367	99.08 10	87.01 359	99.47 8	56.93 367	98.23 343	78.91 351	95.61 334	94.01 349

PS-MVSNAJss		98.53 19	98.63 19	98.21 75	99.68 9	94.82 122	98.10 42	99.21 13	96.91 82	99.75 2	99.45 9	95.82 105	99.92 4	98.80 4	99.96 4	99.89 1

test_djsdf		98.73 11	98.74 16	98.69 40	99.63 12	96.30 65	98.67 11	99.02 51	96.50 96	99.32 20	99.44 10	97.43 31	99.92 4	98.73 7	99.95 5	99.86 2

Anonymous20231211		98.55 17	98.76 13	97.94 93	98.79 106	94.37 140	98.84 8	99.15 23	99.37 3	99.67 6	99.43 11	95.61 117	99.72 82	98.12 16	99.86 25	99.73 15

anonymousdsp		98.72 14	98.63 19	98.99 13	99.62 13	97.29 37	98.65 14	99.19 17	95.62 141	99.35 19	99.37 12	97.38 33	99.90 13	98.59 11	99.91 17	99.77 8

jajsoiax		98.77 9	98.79 12	98.74 35	99.66 10	96.48 59	98.45 23	99.12 27	95.83 133	99.67 6	99.37 12	98.25 10	99.92 4	98.77 5	99.94 8	99.82 6

K. test v3		96.44 154	96.28 155	96.95 166	99.41 35	91.53 217	97.65 68	90.31 352	98.89 18	98.93 38	99.36 14	84.57 292	99.92 4	97.81 26	99.56 85	99.39 83

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 38	99.71 7	96.99 44	99.69 2	99.57 4	99.02 15	99.62 10	99.36 14	98.53 7	99.52 176	98.58 12	99.95 5	99.66 22
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
SixPastTwentyTwo		97.49 90	97.57 79	97.26 151	99.56 15	92.33 197	98.28 29	96.97 274	98.30 33	99.45 14	99.35 16	88.43 263	99.89 16	98.01 20	99.76 39	99.54 36

Gipuma		98.07 40	98.31 29	97.36 145	99.76 5	96.28 66	98.51 19	99.10 30	98.76 22	96.79 194	99.34 17	96.61 74	98.82 299	96.38 72	99.50 109	96.98 306
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
JIA-IIPM		91.79 295	90.69 304	95.11 254	93.80 349	90.98 225	94.16 257	91.78 339	96.38 100	90.30 344	99.30 18	72.02 349	98.90 292	88.28 302	90.17 354	95.45 341

TransMVSNet (Re)		98.38 25	98.67 17	97.51 124	99.51 22	93.39 178	98.20 37	98.87 85	98.23 35	99.48 12	99.27 19	98.47 8	99.55 167	96.52 67	99.53 97	99.60 26

Baseline_NR-MVSNet		97.72 74	97.79 53	97.50 127	99.56 15	93.29 179	95.44 188	98.86 87	98.20 37	98.37 73	99.24 20	94.69 145	99.55 167	95.98 91	99.79 35	99.65 23

v7n		98.73 11	98.99 5	97.95 92	99.64 11	94.20 148	98.67 11	99.14 25	99.08 10	99.42 15	99.23 21	96.53 80	99.91 12	99.27 2	99.93 10	99.73 15

pm-mvs1		98.47 21	98.67 17	97.86 99	99.52 21	94.58 132	98.28 29	99.00 59	97.57 60	99.27 24	99.22 22	98.32 9	99.50 181	97.09 54	99.75 43	99.50 43

TDRefinement		98.90 5	98.86 8	99.02 9	99.54 19	98.06 7	99.34 4	99.44 7	98.85 19	99.00 36	99.20 23	97.42 32	99.59 154	97.21 47	99.76 39	99.40 81

GBi-Net		96.99 116	96.80 128	97.56 119	97.96 202	93.67 168	98.23 32	98.66 146	95.59 143	97.99 119	99.19 24	89.51 254	99.73 78	94.60 162	99.44 127	99.30 102

test1		96.99 116	96.80 128	97.56 119	97.96 202	93.67 168	98.23 32	98.66 146	95.59 143	97.99 119	99.19 24	89.51 254	99.73 78	94.60 162	99.44 127	99.30 102

FMVSNet1		97.95 49	98.08 35	97.56 119	99.14 80	93.67 168	98.23 32	98.66 146	97.41 70	99.00 36	99.19 24	95.47 122	99.73 78	95.83 97	99.76 39	99.30 102

VDDNet		96.98 119	96.84 125	97.41 141	99.40 36	93.26 180	97.94 49	95.31 309	99.26 7	98.39 72	99.18 27	87.85 272	99.62 144	95.13 141	99.09 202	99.35 93

DSMNet-mixed		92.19 289	91.83 286	93.25 303	96.18 309	83.68 333	96.27 139	93.68 321	76.97 358	92.54 328	99.18 27	89.20 259	98.55 326	83.88 339	98.60 255	97.51 294

v10		97.55 85	97.97 41	96.31 204	98.60 131	89.64 245	97.44 83	99.02 51	96.60 90	98.72 49	99.16 29	93.48 180	99.72 82	98.76 6	99.92 14	99.58 28

MIMVSNet1		98.51 20	98.45 26	98.67 41	99.72 6	96.71 50	98.76 9	98.89 78	98.49 27	99.38 17	99.14 30	95.44 124	99.84 25	96.47 70	99.80 33	99.47 59

Vis-MVSNet		98.27 29	98.34 28	98.07 83	99.33 43	95.21 113	98.04 45	99.46 6	97.32 73	97.82 140	99.11 31	96.75 68	99.86 20	97.84 25	99.36 153	99.15 133
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v8		97.60 82	98.06 38	96.23 207	98.71 117	89.44 249	97.43 85	98.82 111	97.29 75	98.74 47	99.10 32	93.86 170	99.68 119	98.61 10	99.94 8	99.56 33

MVS-HIRNet		88.40 324	90.20 310	82.99 346	97.01 284	60.04 368	93.11 295	85.61 363	84.45 332	88.72 352	99.09 33	84.72 291	98.23 343	82.52 344	96.59 321	90.69 360

ACMH	93.61 9	98.44 22	98.76 13	97.51 124	99.43 32	93.54 174	98.23 32	99.05 42	97.40 71	99.37 18	99.08 34	98.79 5	99.47 188	97.74 31	99.71 51	99.50 43
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_part1		96.77 135	96.53 144	97.47 132	98.04 192	92.92 188	97.93 50	98.85 91	98.83 20	99.30 21	99.07 35	79.25 312	99.79 38	97.59 34	99.93 10	99.69 20

DTE-MVSNet		98.79 8	98.86 8	98.59 47	99.55 17	96.12 70	98.48 22	99.10 30	99.36 4	99.29 23	99.06 36	97.27 38	99.93 2	97.71 32	99.91 17	99.70 18

Anonymous20240521		97.07 113	97.51 83	95.76 228	99.35 41	88.18 271	97.78 58	98.40 177	97.11 77	98.34 78	99.04 37	89.58 250	99.79 38	98.09 18	99.93 10	99.30 102

PEN-MVS		98.75 10	98.85 10	98.44 55	99.58 14	95.67 87	98.45 23	99.15 23	99.33 5	99.30 21	99.00 38	97.27 38	99.92 4	97.64 33	99.92 14	99.75 13

DeepC-MVS	95.41 4	97.82 67	97.70 60	98.16 76	98.78 108	95.72 82	96.23 144	99.02 51	93.92 204	98.62 51	98.99 39	97.69 23	99.62 144	96.18 78	99.87 24	99.15 133
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
VPA-MVSNet		98.27 29	98.46 24	97.70 110	99.06 87	93.80 163	97.76 62	99.00 59	98.40 29	99.07 33	98.98 40	96.89 60	99.75 65	97.19 50	99.79 35	99.55 35

lessismore_v0				97.05 162	99.36 40	92.12 205		84.07 364		98.77 46	98.98 40	85.36 286	99.74 72	97.34 43	99.37 150	99.30 102

PS-CasMVS		98.73 11	98.85 10	98.39 59	99.55 17	95.47 98	98.49 20	99.13 26	99.22 8	99.22 27	98.96 42	97.35 34	99.92 4	97.79 28	99.93 10	99.79 7

EU-MVSNet		94.25 244	94.47 230	93.60 296	98.14 185	82.60 336	97.24 94	92.72 332	85.08 324	98.48 63	98.94 43	82.59 300	98.76 306	97.47 39	99.53 97	99.44 76

LCM-MVSNet-Re		97.33 103	97.33 95	97.32 147	98.13 188	93.79 164	96.99 108	99.65 2	96.74 87	99.47 13	98.93 44	96.91 59	99.84 25	90.11 275	99.06 208	98.32 241

XXY-MVS		97.54 86	97.70 60	97.07 161	99.46 28	92.21 201	97.22 95	99.00 59	94.93 171	98.58 56	98.92 45	97.31 36	99.41 210	94.44 169	99.43 135	99.59 27

mvs_anonymous		95.36 197	96.07 166	93.21 305	96.29 302	81.56 341	94.60 240	97.66 245	93.30 220	96.95 188	98.91 46	93.03 190	99.38 220	96.60 63	97.30 307	98.69 211

DIV-MVS_2432*1600		97.86 63	98.07 36	97.25 152	99.22 57	92.81 190	97.55 75	98.94 73	97.10 78	98.85 40	98.88 47	95.03 136	99.67 124	97.39 42	99.65 61	99.26 115

UGNet		96.81 132	96.56 140	97.58 118	96.64 294	93.84 162	97.75 63	97.12 268	96.47 99	93.62 301	98.88 47	93.22 185	99.53 172	95.61 107	99.69 55	99.36 91
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
Anonymous20240529		97.96 46	98.04 39	97.71 108	98.69 121	94.28 145	97.86 55	98.31 190	98.79 21	99.23 26	98.86 49	95.76 112	99.61 151	95.49 111	99.36 153	99.23 122

FC-MVSNet-test		98.16 33	98.37 27	97.56 119	99.49 26	93.10 184	98.35 26	99.21 13	98.43 28	98.89 39	98.83 50	94.30 160	99.81 31	97.87 24	99.91 17	99.77 8

new-patchmatchnet		95.67 183	96.58 138	92.94 313	97.48 255	80.21 346	92.96 296	98.19 205	94.83 173	98.82 42	98.79 51	93.31 183	99.51 180	95.83 97	99.04 209	99.12 144

WR-MVS_H		98.65 15	98.62 21	98.75 33	99.51 22	96.61 55	98.55 17	99.17 18	99.05 13	99.17 29	98.79 51	95.47 122	99.89 16	97.95 21	99.91 17	99.75 13

ab-mvs		96.59 147	96.59 137	96.60 186	98.64 123	92.21 201	98.35 26	97.67 243	94.45 185	96.99 184	98.79 51	94.96 139	99.49 182	90.39 272	99.07 205	98.08 260

EG-PatchMatch MVS		97.69 76	97.79 53	97.40 142	99.06 87	93.52 175	95.96 160	98.97 69	94.55 184	98.82 42	98.76 54	97.31 36	99.29 244	97.20 49	99.44 127	99.38 85

nrg030		98.54 18	98.62 21	98.32 64	99.22 57	95.66 88	97.90 53	99.08 36	98.31 32	99.02 34	98.74 55	97.68 24	99.61 151	97.77 29	99.85 27	99.70 18

VDD-MVS		97.37 100	97.25 100	97.74 106	98.69 121	94.50 136	97.04 105	95.61 303	98.59 25	98.51 60	98.72 56	92.54 204	99.58 156	96.02 87	99.49 113	99.12 144

PatchT		93.75 259	93.57 255	94.29 288	95.05 334	87.32 291	96.05 152	92.98 328	97.54 63	94.25 280	98.72 56	75.79 333	99.24 252	95.92 93	95.81 329	96.32 328

RPSCF		97.87 61	97.51 83	98.95 17	99.15 72	98.43 3	97.56 74	99.06 40	96.19 109	98.48 63	98.70 58	94.72 144	99.24 252	94.37 174	99.33 168	99.17 129

APDe-MVS		98.14 34	98.03 40	98.47 54	98.72 114	96.04 73	98.07 44	99.10 30	95.96 122	98.59 55	98.69 59	96.94 55	99.81 31	96.64 62	99.58 78	99.57 32

IterMVS-LS		96.92 122	97.29 97	95.79 227	98.51 141	88.13 274	95.10 213	98.66 146	96.99 79	98.46 66	98.68 60	92.55 202	99.74 72	96.91 60	99.79 35	99.50 43
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tfpnnormal		97.72 74	97.97 41	96.94 167	99.26 48	92.23 200	97.83 57	98.45 167	98.25 34	99.13 30	98.66 61	96.65 71	99.69 113	93.92 195	99.62 65	98.91 181

FIs		97.93 54	98.07 36	97.48 131	99.38 38	92.95 187	98.03 47	99.11 28	98.04 41	98.62 51	98.66 61	93.75 175	99.78 42	97.23 44	99.84 28	99.73 15

CP-MVSNet		98.42 23	98.46 24	98.30 67	99.46 28	95.22 111	98.27 31	98.84 96	99.05 13	99.01 35	98.65 63	95.37 125	99.90 13	97.57 35	99.91 17	99.77 8

FMVSNet2		96.72 139	96.67 135	96.87 172	97.96 202	91.88 211	97.15 97	98.06 222	95.59 143	98.50 62	98.62 64	89.51 254	99.65 131	94.99 149	99.60 74	99.07 155

PMVS	89.60 17	96.71 141	96.97 118	95.95 220	99.51 22	97.81 16	97.42 86	97.49 255	97.93 43	95.95 235	98.58 65	96.88 62	96.91 355	89.59 283	99.36 153	93.12 354
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CR-MVSNet		93.29 272	92.79 270	94.78 270	95.44 328	88.15 272	96.18 146	97.20 263	84.94 328	94.10 284	98.57 66	77.67 320	99.39 217	95.17 134	95.81 329	96.81 317

Patchmtry		95.03 213	94.59 225	96.33 202	94.83 336	90.82 228	96.38 134	97.20 263	96.59 91	97.49 151	98.57 66	77.67 320	99.38 220	92.95 218	99.62 65	98.80 197

ambc				96.56 191	98.23 172	91.68 216	97.88 54	98.13 212		98.42 69	98.56 68	94.22 163	99.04 278	94.05 190	99.35 158	98.95 170

3Dnovator	96.53 2	97.61 81	97.64 70	97.50 127	97.74 236	93.65 172	98.49 20	98.88 83	96.86 84	97.11 173	98.55 69	95.82 105	99.73 78	95.94 92	99.42 138	99.13 139

IterMVS-SCA-FT		95.86 178	96.19 159	94.85 266	97.68 240	85.53 311	92.42 308	97.63 251	96.99 79	98.36 75	98.54 70	87.94 267	99.75 65	97.07 56	99.08 203	99.27 114

COLMAP_ROB	94.48 6	98.25 31	98.11 34	98.64 44	99.21 64	97.35 35	97.96 48	99.16 19	98.34 31	98.78 44	98.52 71	97.32 35	99.45 195	94.08 186	99.67 58	99.13 139
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	93.58 10	98.23 32	98.31 29	97.98 91	99.39 37	95.22 111	97.55 75	99.20 15	98.21 36	99.25 25	98.51 72	98.21 11	99.40 212	94.79 155	99.72 48	99.32 96

RPMNet		94.68 230	94.60 223	94.90 263	95.44 328	88.15 272	96.18 146	98.86 87	97.43 66	94.10 284	98.49 73	79.40 311	99.76 58	95.69 100	95.81 329	96.81 317

IterMVS		95.42 195	95.83 175	94.20 289	97.52 253	83.78 332	92.41 309	97.47 258	95.49 147	98.06 113	98.49 73	87.94 267	99.58 156	96.02 87	99.02 210	99.23 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		97.87 61	97.89 46	97.81 102	98.62 128	94.82 122	97.13 100	98.79 113	98.98 17	98.74 47	98.49 73	95.80 111	99.49 182	95.04 145	99.44 127	99.11 148

TranMVSNet+NR-MVSNet		98.33 26	98.30 31	98.43 56	99.07 86	95.87 78	96.73 122	99.05 42	98.67 23	98.84 41	98.45 76	97.58 28	99.88 18	96.45 71	99.86 25	99.54 36

3Dnovator+	96.13 3	97.73 73	97.59 77	98.15 79	98.11 190	95.60 90	98.04 45	98.70 136	98.13 38	96.93 189	98.45 76	95.30 129	99.62 144	95.64 105	98.96 214	99.24 121

VPNet		97.26 107	97.49 86	96.59 187	99.47 27	90.58 233	96.27 139	98.53 160	97.77 46	98.46 66	98.41 78	94.59 151	99.68 119	94.61 161	99.29 176	99.52 40

test_0402		97.84 64	97.97 41	97.47 132	99.19 67	94.07 151	96.71 123	98.73 126	98.66 24	98.56 57	98.41 78	96.84 65	99.69 113	94.82 153	99.81 30	98.64 214

v1240		96.74 136	97.02 117	95.91 223	98.18 178	88.52 264	95.39 194	98.88 83	93.15 229	98.46 66	98.40 80	92.80 194	99.71 96	98.45 13	99.49 113	99.49 51

SMA-MVS		97.48 91	97.11 109	98.60 46	98.83 102	96.67 52	96.74 118	98.73 126	91.61 257	98.48 63	98.36 81	96.53 80	99.68 119	95.17 134	99.54 94	99.45 66
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
ACMMP_NAP		97.89 59	97.63 72	98.67 41	99.35 41	96.84 47	96.36 135	98.79 113	95.07 164	97.88 132	98.35 82	97.24 42	99.72 82	96.05 84	99.58 78	99.45 66

v1192		96.83 130	97.06 114	96.15 212	98.28 164	89.29 251	95.36 196	98.77 118	93.73 208	98.11 105	98.34 83	93.02 191	99.67 124	98.35 14	99.58 78	99.50 43

pmmvs-eth3d		96.49 151	96.18 160	97.42 140	98.25 169	94.29 142	94.77 235	98.07 221	89.81 278	97.97 123	98.33 84	93.11 186	99.08 274	95.46 117	99.84 28	98.89 185

PM-MVS		97.36 102	97.10 110	98.14 80	98.91 98	96.77 49	96.20 145	98.63 152	93.82 206	98.54 58	98.33 84	93.98 168	99.05 277	95.99 90	99.45 126	98.61 219

test0726					99.24 52	95.51 94	96.89 111	98.89 78	95.92 125	98.64 50	98.31 86	97.06 50

MP-MVS-pluss		97.69 76	97.36 93	98.70 39	99.50 25	96.84 47	95.38 195	98.99 62	92.45 246	98.11 105	98.31 86	97.25 41	99.77 53	96.60 63	99.62 65	99.48 56
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
v1144		96.84 127	97.08 112	96.13 213	98.42 153	89.28 252	95.41 192	98.67 144	94.21 194	97.97 123	98.31 86	93.06 187	99.65 131	98.06 19	99.62 65	99.45 66

LFMVS		95.32 199	94.88 208	96.62 185	98.03 193	91.47 219	97.65 68	90.72 349	99.11 9	97.89 131	98.31 86	79.20 313	99.48 185	93.91 196	99.12 198	98.93 176

V42		97.04 114	97.16 107	96.68 184	98.59 133	91.05 223	96.33 137	98.36 182	94.60 180	97.99 119	98.30 90	93.32 182	99.62 144	97.40 41	99.53 97	99.38 85

casdiffmvs		97.50 89	97.81 52	96.56 191	98.51 141	91.04 224	95.83 169	99.09 35	97.23 76	98.33 82	98.30 90	97.03 52	99.37 223	96.58 65	99.38 149	99.28 110

v144192		96.69 142	96.90 124	96.03 215	98.25 169	88.92 256	95.49 186	98.77 118	93.05 231	98.09 109	98.29 92	92.51 206	99.70 105	98.11 17	99.56 85	99.47 59

DVP-MVS		97.78 70	97.65 67	98.16 76	99.24 52	95.51 94	96.74 118	98.23 196	95.92 125	98.40 70	98.28 93	97.06 50	99.71 96	95.48 114	99.52 102	99.26 115
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									96.62 89	98.40 70	98.28 93	97.10 45	99.71 96	95.70 99	99.62 65	99.58 28

MVS_Test		96.27 159	96.79 130	94.73 272	96.94 289	86.63 300	96.18 146	98.33 187	94.94 169	96.07 231	98.28 93	95.25 130	99.26 249	97.21 47	97.90 280	98.30 245

FMVSNet5		93.39 269	92.35 280	96.50 193	95.83 319	90.81 230	97.31 89	98.27 191	92.74 242	96.27 222	98.28 93	62.23 363	99.67 124	90.86 252	99.36 153	99.03 161

abl_6		98.42 23	98.19 32	99.09 3	99.16 69	98.10 5	97.73 66	99.11 28	97.76 49	98.62 51	98.27 97	97.88 19	99.80 37	95.67 101	99.50 109	99.38 85

v1921920		96.72 139	96.96 120	95.99 216	98.21 173	88.79 261	95.42 190	98.79 113	93.22 223	98.19 97	98.26 98	92.68 197	99.70 105	98.34 15	99.55 91	99.49 51

SED-MVS		97.94 51	97.90 44	98.07 83	99.22 57	95.35 103	96.79 115	98.83 103	96.11 112	99.08 31	98.24 99	97.87 20	99.72 82	95.44 118	99.51 107	99.14 136

test_241102_TWO								98.83 103	96.11 112	98.62 51	98.24 99	96.92 58	99.72 82	95.44 118	99.49 113	99.49 51

v2v482		96.78 134	97.06 114	95.95 220	98.57 135	88.77 262	95.36 196	98.26 193	95.18 159	97.85 137	98.23 101	92.58 201	99.63 136	97.80 27	99.69 55	99.45 66

LPG-MVS_test		97.94 51	97.67 64	98.74 35	99.15 72	97.02 42	97.09 102	99.02 51	95.15 160	98.34 78	98.23 101	97.91 17	99.70 105	94.41 171	99.73 45	99.50 43

LGP-MVS_train				98.74 35	99.15 72	97.02 42		99.02 51	95.15 160	98.34 78	98.23 101	97.91 17	99.70 105	94.41 171	99.73 45	99.50 43

HPM-MVS_fast		98.32 27	98.13 33	98.88 24	99.54 19	97.48 30	98.35 26	99.03 49	95.88 128	97.88 132	98.22 104	98.15 12	99.74 72	96.50 69	99.62 65	99.42 78

MIMVSNet		93.42 268	92.86 267	95.10 255	98.17 180	88.19 270	98.13 41	93.69 319	92.07 249	95.04 262	98.21 105	80.95 307	99.03 281	81.42 346	98.06 274	98.07 262

hse-mvs3		96.29 158	95.63 182	98.26 69	98.50 144	96.11 71	96.90 110	97.09 269	96.58 92	97.21 166	98.19 106	84.14 293	99.78 42	95.89 95	96.17 327	98.89 185

EI-MVSNet		96.63 146	96.93 121	95.74 229	97.26 274	88.13 274	95.29 203	97.65 247	96.99 79	97.94 126	98.19 106	92.55 202	99.58 156	96.91 60	99.56 85	99.50 43

CVMVSNet		92.33 287	92.79 270	90.95 331	97.26 274	75.84 359	95.29 203	92.33 335	81.86 338	96.27 222	98.19 106	81.44 303	98.46 331	94.23 181	98.29 266	98.55 224

PVSNet_Blended_VisFu		95.95 174	95.80 176	96.42 198	99.28 47	90.62 232	95.31 201	99.08 36	88.40 292	96.97 187	98.17 109	92.11 213	99.78 42	93.64 204	99.21 183	98.86 192

EI-MVSNet-UG-set		97.32 104	97.40 90	97.09 160	97.34 269	92.01 209	95.33 199	97.65 247	97.74 50	98.30 87	98.14 110	95.04 135	99.69 113	97.55 36	99.52 102	99.58 28

test_241102_ONE					99.22 57	95.35 103		98.83 103	96.04 117	99.08 31	98.13 111	97.87 20	99.33 233

APD-MVS_3200maxsize		98.13 37	97.90 44	98.79 31	98.79 106	97.31 36	97.55 75	98.92 75	97.72 53	98.25 90	98.13 111	97.10 45	99.75 65	95.44 118	99.24 182	99.32 96

QAPM		95.88 177	95.57 185	96.80 176	97.90 208	91.84 213	98.18 39	98.73 126	88.41 291	96.42 213	98.13 111	94.73 143	99.75 65	88.72 295	98.94 219	98.81 196

ACMM	93.33 11	98.05 41	97.79 53	98.85 25	99.15 72	97.55 26	96.68 124	98.83 103	95.21 156	98.36 75	98.13 111	98.13 14	99.62 144	96.04 85	99.54 94	99.39 83
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EI-MVSNet-Vis-set		97.32 104	97.39 91	97.11 158	97.36 264	92.08 207	95.34 198	97.65 247	97.74 50	98.29 88	98.11 115	95.05 133	99.68 119	97.50 38	99.50 109	99.56 33

wuyk23d		93.25 273	95.20 192	87.40 345	96.07 314	95.38 100	97.04 105	94.97 310	95.33 152	99.70 5	98.11 115	98.14 13	91.94 362	77.76 355	99.68 57	74.89 362

DPE-MVS		97.64 78	97.35 94	98.50 51	98.85 101	96.18 67	95.21 210	98.99 62	95.84 132	98.78 44	98.08 117	96.84 65	99.81 31	93.98 193	99.57 81	99.52 40
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SD-MVS		97.37 100	97.70 60	96.35 201	98.14 185	95.13 114	96.54 127	98.92 75	95.94 124	99.19 28	98.08 117	97.74 22	95.06 360	95.24 130	99.54 94	98.87 191
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
SR-MVS-dyc-post		98.14 34	97.84 49	99.02 9	98.81 103	98.05 8	97.55 75	98.86 87	97.77 46	98.20 94	98.07 119	96.60 76	99.76 58	95.49 111	99.20 184	99.26 115

RE-MVS-def			97.88 47		98.81 103	98.05 8	97.55 75	98.86 87	97.77 46	98.20 94	98.07 119	96.94 55		95.49 111	99.20 184	99.26 115

OPM-MVS		97.54 86	97.25 100	98.41 57	99.11 82	96.61 55	95.24 208	98.46 166	94.58 183	98.10 108	98.07 119	97.09 47	99.39 217	95.16 136	99.44 127	99.21 124

AllTest		97.20 111	96.92 122	98.06 85	99.08 84	96.16 68	97.14 99	99.16 19	94.35 189	97.78 141	98.07 119	95.84 102	99.12 267	91.41 239	99.42 138	98.91 181

TestCases				98.06 85	99.08 84	96.16 68		99.16 19	94.35 189	97.78 141	98.07 119	95.84 102	99.12 267	91.41 239	99.42 138	98.91 181

TSAR-MVS + MP.		97.42 95	97.23 103	98.00 90	99.38 38	95.00 117	97.63 70	98.20 200	93.00 233	98.16 99	98.06 124	95.89 100	99.72 82	95.67 101	99.10 201	99.28 110
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EPP-MVSNet		96.84 127	96.58 138	97.65 114	99.18 68	93.78 165	98.68 10	96.34 287	97.91 44	97.30 162	98.06 124	88.46 262	99.85 22	93.85 197	99.40 145	99.32 96

ACMMP		98.05 41	97.75 59	98.93 21	99.23 54	97.60 22	98.09 43	98.96 70	95.75 137	97.91 128	98.06 124	96.89 60	99.76 58	95.32 125	99.57 81	99.43 77
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
Anonymous202405211		96.34 157	95.98 170	97.43 139	98.25 169	93.85 161	96.74 118	94.41 316	97.72 53	98.37 73	98.03 127	87.15 276	99.53 172	94.06 187	99.07 205	98.92 180

XVG-ACMP-BASELINE		97.58 84	97.28 99	98.49 52	99.16 69	96.90 46	96.39 132	98.98 65	95.05 165	98.06 113	98.02 128	95.86 101	99.56 163	94.37 174	99.64 63	99.00 164

baseline		97.44 94	97.78 56	96.43 197	98.52 140	90.75 231	96.84 112	99.03 49	96.51 95	97.86 136	98.02 128	96.67 70	99.36 225	97.09 54	99.47 119	99.19 126

PVSNet_BlendedMVS		95.02 214	94.93 205	95.27 247	97.79 228	87.40 289	94.14 260	98.68 141	88.94 286	94.51 274	98.01 130	93.04 188	99.30 240	89.77 281	99.49 113	99.11 148

OpenMVS	94.22 8	95.48 191	95.20 192	96.32 203	97.16 280	91.96 210	97.74 64	98.84 96	87.26 301	94.36 278	98.01 130	93.95 169	99.67 124	90.70 262	98.75 240	97.35 300

MVSTER		94.21 247	93.93 250	95.05 257	95.83 319	86.46 301	95.18 211	97.65 247	92.41 247	97.94 126	98.00 132	72.39 348	99.58 156	96.36 73	99.56 85	99.12 144

IS-MVSNet		96.93 121	96.68 134	97.70 110	99.25 51	94.00 154	98.57 15	96.74 283	98.36 30	98.14 103	97.98 133	88.23 265	99.71 96	93.10 215	99.72 48	99.38 85

test1172		98.08 39	97.76 57	99.05 6	98.78 108	98.07 6	97.41 87	98.85 91	97.57 60	98.15 101	97.96 134	96.60 76	99.76 58	95.30 126	99.18 188	99.33 95

zzz-MVS		98.01 44	97.66 65	99.06 4	99.44 30	97.90 11	95.66 177	98.73 126	97.69 56	97.90 129	97.96 134	95.81 109	99.82 29	96.13 79	99.61 71	99.45 66

MTAPA		98.14 34	97.84 49	99.06 4	99.44 30	97.90 11	97.25 92	98.73 126	97.69 56	97.90 129	97.96 134	95.81 109	99.82 29	96.13 79	99.61 71	99.45 66

v148		96.58 148	96.97 118	95.42 243	98.63 127	87.57 285	95.09 215	97.90 228	95.91 127	98.24 92	97.96 134	93.42 181	99.39 217	96.04 85	99.52 102	99.29 109

MDA-MVSNet-bldmvs		95.69 181	95.67 180	95.74 229	98.48 147	88.76 263	92.84 297	97.25 261	96.00 120	97.59 144	97.95 138	91.38 227	99.46 191	93.16 214	96.35 324	98.99 167

PGM-MVS		97.88 60	97.52 82	98.96 16	99.20 65	97.62 21	97.09 102	99.06 40	95.45 148	97.55 145	97.94 139	97.11 44	99.78 42	94.77 158	99.46 122	99.48 56

LS3D		97.77 71	97.50 85	98.57 48	96.24 304	97.58 24	98.45 23	98.85 91	98.58 26	97.51 148	97.94 139	95.74 113	99.63 136	95.19 132	98.97 213	98.51 225

USDC		94.56 236	94.57 228	94.55 280	97.78 232	86.43 303	92.75 300	98.65 151	85.96 312	96.91 191	97.93 141	90.82 233	98.74 307	90.71 261	99.59 76	98.47 228

test20.03		96.58 148	96.61 136	96.48 195	98.49 145	91.72 215	95.68 176	97.69 242	96.81 85	98.27 89	97.92 142	94.18 164	98.71 310	90.78 256	99.66 60	99.00 164

FMVSNet3		95.26 203	94.94 203	96.22 209	96.53 297	90.06 237	95.99 157	97.66 245	94.11 198	97.99 119	97.91 143	80.22 310	99.63 136	94.60 162	99.44 127	98.96 169

Regformer-3		97.25 108	97.29 97	97.11 158	97.35 265	92.32 198	95.26 205	97.62 252	97.67 58	98.17 98	97.89 144	95.05 133	99.56 163	97.16 51	99.42 138	99.46 61

Regformer-4		97.53 88	97.47 88	97.71 108	97.35 265	93.91 156	95.26 205	98.14 210	97.97 42	98.34 78	97.89 144	95.49 120	99.71 96	97.41 40	99.42 138	99.51 42

xxxxxxxxxxxxxcwj		97.24 109	97.03 116	97.89 96	98.48 147	94.71 126	94.53 243	99.07 39	95.02 167	97.83 138	97.88 146	96.44 87	99.72 82	94.59 166	99.39 147	99.25 119

SF-MVS		97.60 82	97.39 91	98.22 74	98.93 96	95.69 84	97.05 104	99.10 30	95.32 153	97.83 138	97.88 146	96.44 87	99.72 82	94.59 166	99.39 147	99.25 119

SteuartSystems-ACMMP		98.02 43	97.76 57	98.79 31	99.43 32	97.21 41	97.15 97	98.90 77	96.58 92	98.08 111	97.87 148	97.02 53	99.76 58	95.25 129	99.59 76	99.40 81
Skip Steuart: Steuart Systems R&D Blog.
SR-MVS		98.00 45	97.66 65	99.01 11	98.77 110	97.93 10	97.38 88	98.83 103	97.32 73	98.06 113	97.85 149	96.65 71	99.77 53	95.00 148	99.11 199	99.32 96

RRT_MVS		94.90 216	94.07 243	97.39 143	93.18 353	93.21 182	95.26 205	97.49 255	93.94 203	98.25 90	97.85 149	72.96 347	99.84 25	97.90 22	99.78 38	99.14 136

DU-MVS		97.79 69	97.60 76	98.36 61	98.73 112	95.78 80	95.65 180	98.87 85	97.57 60	98.31 85	97.83 151	94.69 145	99.85 22	97.02 57	99.71 51	99.46 61

NR-MVSNet		97.96 46	97.86 48	98.26 69	98.73 112	95.54 92	98.14 40	98.73 126	97.79 45	99.42 15	97.83 151	94.40 158	99.78 42	95.91 94	99.76 39	99.46 61

CHOSEN 1792x2688		94.10 251	93.41 258	96.18 211	99.16 69	90.04 238	92.15 312	98.68 141	79.90 348	96.22 225	97.83 151	87.92 271	99.42 201	89.18 289	99.65 61	99.08 153

TAMVS		95.49 189	94.94 203	97.16 155	98.31 159	93.41 177	95.07 218	96.82 279	91.09 266	97.51 148	97.82 154	89.96 246	99.42 201	88.42 300	99.44 127	98.64 214

UniMVSNet (Re)		97.83 65	97.65 67	98.35 63	98.80 105	95.86 79	95.92 164	99.04 48	97.51 64	98.22 93	97.81 155	94.68 147	99.78 42	97.14 52	99.75 43	99.41 80

VNet		96.84 127	96.83 126	96.88 171	98.06 191	92.02 208	96.35 136	97.57 254	97.70 55	97.88 132	97.80 156	92.40 208	99.54 170	94.73 160	98.96 214	99.08 153

YYNet1		94.73 223	94.84 210	94.41 284	97.47 259	85.09 320	90.29 340	95.85 298	92.52 243	97.53 146	97.76 157	91.97 217	99.18 258	93.31 209	96.86 313	98.95 170

MDA-MVSNet_test_wron		94.73 223	94.83 212	94.42 283	97.48 255	85.15 318	90.28 341	95.87 297	92.52 243	97.48 154	97.76 157	91.92 221	99.17 262	93.32 208	96.80 316	98.94 172

TinyColmap		96.00 172	96.34 153	94.96 260	97.90 208	87.91 277	94.13 261	98.49 164	94.41 186	98.16 99	97.76 157	96.29 94	98.68 315	90.52 268	99.42 138	98.30 245

Patchmatch-RL test		94.66 231	94.49 229	95.19 252	98.54 138	88.91 257	92.57 304	98.74 124	91.46 260	98.32 83	97.75 160	77.31 325	98.81 301	96.06 82	99.61 71	97.85 280

MP-MVS		97.64 78	97.18 106	99.00 12	99.32 45	97.77 17	97.49 81	98.73 126	96.27 105	95.59 249	97.75 160	96.30 93	99.78 42	93.70 203	99.48 117	99.45 66
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ACMP	92.54 13	97.47 92	97.10 110	98.55 50	99.04 90	96.70 51	96.24 143	98.89 78	93.71 209	97.97 123	97.75 160	97.44 30	99.63 136	93.22 212	99.70 54	99.32 96
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MVP-Stereo		95.69 181	95.28 191	96.92 168	98.15 184	93.03 185	95.64 182	98.20 200	90.39 272	96.63 204	97.73 163	91.63 225	99.10 272	91.84 232	97.31 306	98.63 216
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
mPP-MVS		97.91 58	97.53 81	99.04 7	99.22 57	97.87 14	97.74 64	98.78 117	96.04 117	97.10 174	97.73 163	96.53 80	99.78 42	95.16 136	99.50 109	99.46 61

RRT_test8_iter05		92.46 283	92.52 279	92.29 324	95.33 331	77.43 354	95.73 171	98.55 159	94.41 186	97.46 157	97.72 165	57.44 366	99.74 72	96.92 59	99.14 191	99.69 20

MVS_0304		95.50 188	95.05 201	96.84 174	96.28 303	93.12 183	97.00 107	96.16 289	95.03 166	89.22 350	97.70 166	90.16 245	99.48 185	94.51 168	99.34 161	97.93 277

XVG-OURS		97.12 112	96.74 131	98.26 69	98.99 93	97.45 32	93.82 273	99.05 42	95.19 158	98.32 83	97.70 166	95.22 131	98.41 333	94.27 179	98.13 271	98.93 176

UniMVSNet_NR-MVSNet		97.83 65	97.65 67	98.37 60	98.72 114	95.78 80	95.66 177	99.02 51	98.11 39	98.31 85	97.69 168	94.65 149	99.85 22	97.02 57	99.71 51	99.48 56

D2MVS		95.18 205	95.17 194	95.21 250	97.76 234	87.76 283	94.15 258	97.94 226	89.77 279	96.99 184	97.68 169	87.45 274	99.14 265	95.03 147	99.81 30	98.74 205

XVS		97.96 46	97.63 72	98.94 18	99.15 72	97.66 19	97.77 60	98.83 103	97.42 67	96.32 218	97.64 170	96.49 83	99.72 82	95.66 103	99.37 150	99.45 66

ACMMPR		97.95 49	97.62 74	98.94 18	99.20 65	97.56 25	97.59 72	98.83 103	96.05 115	97.46 157	97.63 171	96.77 67	99.76 58	95.61 107	99.46 122	99.49 51

Anonymous20231206		95.27 202	95.06 200	95.88 224	98.72 114	89.37 250	95.70 173	97.85 231	88.00 297	96.98 186	97.62 172	91.95 218	99.34 230	89.21 288	99.53 97	98.94 172

region2R		97.92 55	97.59 77	98.92 22	99.22 57	97.55 26	97.60 71	98.84 96	96.00 120	97.22 164	97.62 172	96.87 63	99.76 58	95.48 114	99.43 135	99.46 61

GeoE		97.75 72	97.70 60	97.89 96	98.88 100	94.53 133	97.10 101	98.98 65	95.75 137	97.62 143	97.59 174	97.61 27	99.77 53	96.34 74	99.44 127	99.36 91

ppachtmachnet_test		94.49 239	94.84 210	93.46 299	96.16 310	82.10 338	90.59 337	97.48 257	90.53 271	97.01 183	97.59 174	91.01 230	99.36 225	93.97 194	99.18 188	98.94 172

APD-MVS		97.00 115	96.53 144	98.41 57	98.55 137	96.31 64	96.32 138	98.77 118	92.96 238	97.44 159	97.58 176	95.84 102	99.74 72	91.96 226	99.35 158	99.19 126
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HFP-MVS		97.94 51	97.64 70	98.83 26	99.15 72	97.50 28	97.59 72	98.84 96	96.05 115	97.49 151	97.54 177	97.07 48	99.70 105	95.61 107	99.46 122	99.30 102

#test#		97.62 80	97.22 104	98.83 26	99.15 72	97.50 28	96.81 114	98.84 96	94.25 193	97.49 151	97.54 177	97.07 48	99.70 105	94.37 174	99.46 122	99.30 102

UnsupCasMVSNet_eth		95.91 175	95.73 179	96.44 196	98.48 147	91.52 218	95.31 201	98.45 167	95.76 135	97.48 154	97.54 177	89.53 253	98.69 312	94.43 170	94.61 342	99.13 139

XVG-OURS-SEG-HR		97.38 98	97.07 113	98.30 67	99.01 92	97.41 34	94.66 238	99.02 51	95.20 157	98.15 101	97.52 180	98.83 4	98.43 332	94.87 151	96.41 323	99.07 155

MG-MVS		94.08 253	94.00 246	94.32 286	97.09 282	85.89 308	93.19 294	95.96 295	92.52 243	94.93 265	97.51 181	89.54 251	98.77 304	87.52 313	97.71 288	98.31 243

Regformer-1		97.27 106	97.16 107	97.61 117	97.21 277	93.86 160	94.85 231	98.04 224	97.62 59	98.03 117	97.50 182	95.34 126	99.63 136	96.52 67	99.31 172	99.35 93

Regformer-2		97.41 96	97.24 102	97.93 94	97.21 277	94.72 125	94.85 231	98.27 191	97.74 50	98.11 105	97.50 182	95.58 118	99.69 113	96.57 66	99.31 172	99.37 90

HPM-MVS		98.11 38	97.83 51	98.92 22	99.42 34	97.46 31	98.57 15	99.05 42	95.43 150	97.41 160	97.50 182	97.98 15	99.79 38	95.58 110	99.57 81	99.50 43
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
9.14			96.69 133		98.53 139		96.02 155	98.98 65	93.23 222	97.18 168	97.46 185	96.47 85	99.62 144	92.99 216	99.32 170

CP-MVS		97.92 55	97.56 80	98.99 13	98.99 93	97.82 15	97.93 50	98.96 70	96.11 112	96.89 192	97.45 186	96.85 64	99.78 42	95.19 132	99.63 64	99.38 85

ZNCC-MVS		97.92 55	97.62 74	98.83 26	99.32 45	97.24 39	97.45 82	98.84 96	95.76 135	96.93 189	97.43 187	97.26 40	99.79 38	96.06 82	99.53 97	99.45 66

N_pmnet		95.18 205	94.23 237	98.06 85	97.85 210	96.55 57	92.49 306	91.63 340	89.34 281	98.09 109	97.41 188	90.33 239	99.06 276	91.58 237	99.31 172	98.56 222

GST-MVS		97.82 67	97.49 86	98.81 29	99.23 54	97.25 38	97.16 96	98.79 113	95.96 122	97.53 146	97.40 189	96.93 57	99.77 53	95.04 145	99.35 158	99.42 78

tpm		91.08 303	90.85 301	91.75 326	95.33 331	78.09 350	95.03 223	91.27 344	88.75 288	93.53 305	97.40 189	71.24 350	99.30 240	91.25 244	93.87 345	97.87 279

MDTV_nov1_ep13			91.28 293		94.31 341	73.51 363	94.80 233	93.16 326	86.75 308	93.45 309	97.40 189	76.37 329	98.55 326	88.85 293	96.43 322

DeepPCF-MVS	94.58 5	96.90 124	96.43 150	98.31 66	97.48 255	97.23 40	92.56 305	98.60 154	92.84 241	98.54 58	97.40 189	96.64 73	98.78 303	94.40 173	99.41 144	98.93 176

MSLP-MVS++		96.42 156	96.71 132	95.57 235	97.82 217	90.56 235	95.71 172	98.84 96	94.72 176	96.71 200	97.39 193	94.91 141	98.10 347	95.28 127	99.02 210	98.05 269

EPNet		93.72 260	92.62 277	97.03 164	87.61 368	92.25 199	96.27 139	91.28 343	96.74 87	87.65 356	97.39 193	85.00 288	99.64 134	92.14 225	99.48 117	99.20 125
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PMMVS2		93.66 263	94.07 243	92.45 321	97.57 248	80.67 345	86.46 356	96.00 293	93.99 201	97.10 174	97.38 195	89.90 247	97.82 349	88.76 294	99.47 119	98.86 192

DeepC-MVS_fast	94.34 7	96.74 136	96.51 147	97.44 138	97.69 239	94.15 149	96.02 155	98.43 170	93.17 228	97.30 162	97.38 195	95.48 121	99.28 246	93.74 200	99.34 161	98.88 189
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		94.81 221	94.80 213	94.85 266	96.16 310	86.45 302	91.14 331	98.20 200	93.49 213	97.03 181	97.37 197	84.97 289	99.26 249	95.28 127	99.56 85	98.83 194

OPU-MVS				97.64 115	98.01 196	95.27 106	96.79 115				97.35 198	96.97 54	98.51 329	91.21 245	99.25 181	99.14 136

cl-mvsnet1		94.73 223	94.64 219	95.01 258	95.86 317	87.00 295	91.33 325	98.08 217	93.34 218	97.10 174	97.34 199	84.02 295	99.31 237	95.15 138	99.55 91	98.72 208

cl-mvsnet____		94.73 223	94.64 219	95.01 258	95.85 318	87.00 295	91.33 325	98.08 217	93.34 218	97.10 174	97.33 200	84.01 296	99.30 240	95.14 139	99.56 85	98.71 210

WR-MVS		96.90 124	96.81 127	97.16 155	98.56 136	92.20 203	94.33 247	98.12 213	97.34 72	98.20 94	97.33 200	92.81 193	99.75 65	94.79 155	99.81 30	99.54 36

ETH3D-3000-0.1		96.89 126	96.46 149	98.16 76	98.62 128	95.69 84	95.96 160	98.98 65	93.36 217	97.04 180	97.31 202	94.93 140	99.63 136	92.60 219	99.34 161	99.17 129

ITE_SJBPF				97.85 100	98.64 123	96.66 53		98.51 163	95.63 140	97.22 164	97.30 203	95.52 119	98.55 326	90.97 249	98.90 223	98.34 240

Vis-MVSNet (Re-imp)		95.11 208	94.85 209	95.87 225	99.12 81	89.17 253	97.54 80	94.92 311	96.50 96	96.58 205	97.27 204	83.64 297	99.48 185	88.42 300	99.67 58	98.97 168

cl_fuxian		95.20 204	95.32 189	94.83 268	96.19 308	86.43 303	91.83 318	98.35 186	93.47 214	97.36 161	97.26 205	88.69 260	99.28 246	95.41 124	99.36 153	98.78 200

eth_miper_zixun_eth		94.89 217	94.93 205	94.75 271	95.99 315	86.12 306	91.35 324	98.49 164	93.40 215	97.12 172	97.25 206	86.87 279	99.35 228	95.08 144	98.82 234	98.78 200

pmmvs4		94.82 220	94.19 240	96.70 182	97.42 262	92.75 192	92.09 315	96.76 281	86.80 307	95.73 246	97.22 207	89.28 257	98.89 294	93.28 210	99.14 191	98.46 230

OMC-MVS		96.48 152	96.00 168	97.91 95	98.30 161	96.01 76	94.86 230	98.60 154	91.88 254	97.18 168	97.21 208	96.11 96	99.04 278	90.49 271	99.34 161	98.69 211

pmmvs5		94.63 233	94.34 235	95.50 239	97.63 246	88.34 268	94.02 264	97.13 267	87.15 303	95.22 256	97.15 209	87.50 273	99.27 248	93.99 192	99.26 180	98.88 189

testtj		96.69 142	96.13 161	98.36 61	98.46 151	96.02 75	96.44 130	98.70 136	94.26 192	96.79 194	97.13 210	94.07 166	99.75 65	90.53 267	98.80 235	99.31 101

our_test_3		94.20 249	94.58 226	93.07 307	96.16 310	81.20 343	90.42 339	96.84 277	90.72 269	97.14 170	97.13 210	90.47 237	99.11 270	94.04 191	98.25 267	98.91 181

CPTT-MVS		96.69 142	96.08 165	98.49 52	98.89 99	96.64 54	97.25 92	98.77 118	92.89 240	96.01 234	97.13 210	92.23 210	99.67 124	92.24 224	99.34 161	99.17 129

MS-PatchMatch		94.83 219	94.91 207	94.57 279	96.81 293	87.10 294	94.23 253	97.34 260	88.74 289	97.14 170	97.11 213	91.94 219	98.23 343	92.99 216	97.92 278	98.37 234

FPMVS		89.92 314	88.63 321	93.82 292	98.37 156	96.94 45	91.58 320	93.34 325	88.00 297	90.32 343	97.10 214	70.87 353	91.13 363	71.91 361	96.16 328	93.39 353

ETH3D cwj APD-0.16		96.23 161	95.61 184	98.09 82	97.91 206	95.65 89	94.94 226	98.74 124	91.31 263	96.02 233	97.08 215	94.05 167	99.69 113	91.51 238	98.94 219	98.93 176

ZD-MVS					98.43 152	95.94 77		98.56 158	90.72 269	96.66 202	97.07 216	95.02 137	99.74 72	91.08 246	98.93 221

DELS-MVS		96.17 164	96.23 157	95.99 216	97.55 252	90.04 238	92.38 310	98.52 161	94.13 197	96.55 209	97.06 217	94.99 138	99.58 156	95.62 106	99.28 177	98.37 234
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
CNVR-MVS		96.92 122	96.55 141	98.03 89	98.00 200	95.54 92	94.87 229	98.17 206	94.60 180	96.38 215	97.05 218	95.67 115	99.36 225	95.12 142	99.08 203	99.19 126

旧先验1					97.80 222	93.87 159		97.75 238			97.04 219	93.57 179			98.68 245	98.72 208

testdata				95.70 232	98.16 182	90.58 233		97.72 240	80.38 346	95.62 248	97.02 220	92.06 216	98.98 286	89.06 292	98.52 257	97.54 293

PatchmatchNet		91.98 293	91.87 285	92.30 323	94.60 339	79.71 347	95.12 212	93.59 323	89.52 280	93.61 302	97.02 220	77.94 318	99.18 258	90.84 253	94.57 344	98.01 273
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		93.38 270	93.52 256	92.96 312	96.24 304	81.40 342	93.24 292	94.00 318	91.58 259	94.57 271	96.97 222	87.94 267	99.42 201	89.47 285	97.66 293	98.06 266

Patchmatch-test		93.60 265	93.25 261	94.63 274	96.14 313	87.47 287	96.04 153	94.50 315	93.57 211	96.47 211	96.97 222	76.50 328	98.61 320	90.67 263	98.41 262	97.81 284

CostFormer		89.75 315	89.25 314	91.26 330	94.69 338	78.00 352	95.32 200	91.98 337	81.50 341	90.55 341	96.96 224	71.06 352	98.89 294	88.59 298	92.63 349	96.87 311

diffmvs		96.04 169	96.23 157	95.46 242	97.35 265	88.03 276	93.42 285	99.08 36	94.09 199	96.66 202	96.93 225	93.85 171	99.29 244	96.01 89	98.67 246	99.06 157

114514_t		93.96 255	93.22 262	96.19 210	99.06 87	90.97 226	95.99 157	98.94 73	73.88 361	93.43 310	96.93 225	92.38 209	99.37 223	89.09 290	99.28 177	98.25 251

Test_1112_low_res		93.53 267	92.86 267	95.54 238	98.60 131	88.86 259	92.75 300	98.69 139	82.66 337	92.65 324	96.92 227	84.75 290	99.56 163	90.94 250	97.76 284	98.19 256

tpmrst		90.31 308	90.61 306	89.41 338	94.06 347	72.37 365	95.06 220	93.69 319	88.01 296	92.32 331	96.86 228	77.45 322	98.82 299	91.04 247	87.01 359	97.04 305

PHI-MVS		96.96 120	96.53 144	98.25 72	97.48 255	96.50 58	96.76 117	98.85 91	93.52 212	96.19 227	96.85 229	95.94 99	99.42 201	93.79 199	99.43 135	98.83 194

tttt0517		93.31 271	92.56 278	95.57 235	98.71 117	87.86 278	97.44 83	87.17 360	95.79 134	97.47 156	96.84 230	64.12 361	99.81 31	96.20 77	99.32 170	99.02 163

patchmatchnet-post											96.84 230	77.36 324	99.42 201

ADS-MVSNet2		91.47 299	90.51 307	94.36 285	95.51 326	85.63 309	95.05 221	95.70 299	83.46 334	92.69 322	96.84 230	79.15 314	99.41 210	85.66 326	90.52 352	98.04 270

ADS-MVSNet		90.95 305	90.26 309	93.04 308	95.51 326	82.37 337	95.05 221	93.41 324	83.46 334	92.69 322	96.84 230	79.15 314	98.70 311	85.66 326	90.52 352	98.04 270

HY-MVS	91.43 15	92.58 281	91.81 287	94.90 263	96.49 298	88.87 258	97.31 89	94.62 313	85.92 313	90.50 342	96.84 230	85.05 287	99.40 212	83.77 341	95.78 332	96.43 327

UnsupCasMVSNet_bld		94.72 227	94.26 236	96.08 214	98.62 128	90.54 236	93.38 288	98.05 223	90.30 273	97.02 182	96.80 235	89.54 251	99.16 263	88.44 299	96.18 326	98.56 222

HQP_MVS		96.66 145	96.33 154	97.68 113	98.70 119	94.29 142	96.50 128	98.75 122	96.36 101	96.16 228	96.77 236	91.91 222	99.46 191	92.59 221	99.20 184	99.28 110

plane_prior4											96.77 236

MVS_111021_HR		96.73 138	96.54 143	97.27 149	98.35 158	93.66 171	93.42 285	98.36 182	94.74 175	96.58 205	96.76 238	96.54 78	98.99 284	94.87 151	99.27 179	99.15 133

CANet		95.86 178	95.65 181	96.49 194	96.41 300	90.82 228	94.36 246	98.41 175	94.94 169	92.62 327	96.73 239	92.68 197	99.71 96	95.12 142	99.60 74	98.94 172

1121		94.26 243	93.26 260	97.27 149	98.26 168	94.73 124	95.86 165	97.71 241	77.96 355	94.53 273	96.71 240	91.93 220	99.40 212	87.71 306	98.64 251	97.69 288

TSAR-MVS + GP.		96.47 153	96.12 162	97.49 130	97.74 236	95.23 108	94.15 258	96.90 276	93.26 221	98.04 116	96.70 241	94.41 157	98.89 294	94.77 158	99.14 191	98.37 234

test222					98.17 180	93.24 181	92.74 302	97.61 253	75.17 359	94.65 270	96.69 242	90.96 232			98.66 248	97.66 289

新几何1				97.25 152	98.29 162	94.70 129		97.73 239	77.98 354	94.83 266	96.67 243	92.08 215	99.45 195	88.17 304	98.65 250	97.61 291

miper_ehance_all_eth		94.69 228	94.70 216	94.64 273	95.77 321	86.22 305	91.32 327	98.24 195	91.67 256	97.05 179	96.65 244	88.39 264	99.22 256	94.88 150	98.34 263	98.49 227

MVS_111021_LR		96.82 131	96.55 141	97.62 116	98.27 166	95.34 105	93.81 275	98.33 187	94.59 182	96.56 207	96.63 245	96.61 74	98.73 308	94.80 154	99.34 161	98.78 200

CDPH-MVS		95.45 194	94.65 218	97.84 101	98.28 164	94.96 118	93.73 277	98.33 187	85.03 326	95.44 251	96.60 246	95.31 128	99.44 198	90.01 277	99.13 195	99.11 148

CMPMVS	73.10 23	92.74 279	91.39 291	96.77 178	93.57 352	94.67 130	94.21 255	97.67 243	80.36 347	93.61 302	96.60 246	82.85 299	97.35 353	84.86 334	98.78 237	98.29 248
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CDS-MVSNet		94.88 218	94.12 242	97.14 157	97.64 245	93.57 173	93.96 269	97.06 271	90.05 276	96.30 221	96.55 248	86.10 281	99.47 188	90.10 276	99.31 172	98.40 231
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
LF4IMVS		96.07 167	95.63 182	97.36 145	98.19 175	95.55 91	95.44 188	98.82 111	92.29 248	95.70 247	96.55 248	92.63 200	98.69 312	91.75 235	99.33 168	97.85 280

HPM-MVS++		96.99 116	96.38 151	98.81 29	98.64 123	97.59 23	95.97 159	98.20 200	95.51 146	95.06 259	96.53 250	94.10 165	99.70 105	94.29 178	99.15 190	99.13 139

EPMVS		89.26 318	88.55 322	91.39 328	92.36 361	79.11 348	95.65 180	79.86 365	88.60 290	93.12 315	96.53 250	70.73 354	98.10 347	90.75 257	89.32 356	96.98 306

HyFIR lowres test		93.72 260	92.65 275	96.91 170	98.93 96	91.81 214	91.23 329	98.52 161	82.69 336	96.46 212	96.52 252	80.38 309	99.90 13	90.36 273	98.79 236	99.03 161

BH-RMVSNet		94.56 236	94.44 233	94.91 261	97.57 248	87.44 288	93.78 276	96.26 288	93.69 210	96.41 214	96.50 253	92.10 214	99.00 282	85.96 322	97.71 288	98.31 243

DROMVSNet		97.38 98	97.44 89	97.20 154	98.31 159	93.89 157	97.78 58	99.59 3	96.36 101	95.16 257	96.49 254	96.54 78	99.78 42	97.14 52	99.57 81	97.94 275

MSP-MVS		97.45 93	96.92 122	99.03 8	99.26 48	97.70 18	97.66 67	98.89 78	95.65 139	98.51 60	96.46 255	92.15 211	99.81 31	95.14 139	98.58 256	99.58 28
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
原ACMM1				96.58 188	98.16 182	92.12 205		98.15 209	85.90 314	93.49 306	96.43 256	92.47 207	99.38 220	87.66 309	98.62 252	98.23 252

tpm2		88.47 323	87.69 327	90.79 332	94.98 335	77.34 355	95.09 215	91.83 338	77.51 357	89.40 348	96.41 257	67.83 358	98.73 308	83.58 343	92.60 350	96.29 329

OpenMVS_ROB	91.80 14	93.64 264	93.05 263	95.42 243	97.31 273	91.21 221	95.08 217	96.68 285	81.56 340	96.88 193	96.41 257	90.44 238	99.25 251	85.39 329	97.67 292	95.80 335

CL-MVSNet_2432*1600		95.04 211	94.79 214	95.82 226	97.51 254	89.79 243	91.14 331	96.82 279	93.05 231	96.72 199	96.40 259	90.82 233	99.16 263	91.95 227	98.66 248	98.50 226

F-COLMAP		95.30 200	94.38 234	98.05 88	98.64 123	96.04 73	95.61 183	98.66 146	89.00 285	93.22 314	96.40 259	92.90 192	99.35 228	87.45 314	97.53 298	98.77 203

bset_n11_16_dypcd		94.53 238	93.95 249	96.25 206	97.56 250	89.85 242	88.52 353	91.32 342	94.90 172	97.51 148	96.38 261	82.34 301	99.78 42	97.22 45	99.80 33	99.12 144

NCCC		96.52 150	95.99 169	98.10 81	97.81 218	95.68 86	95.00 224	98.20 200	95.39 151	95.40 253	96.36 262	93.81 172	99.45 195	93.55 206	98.42 261	99.17 129

new_pmnet		92.34 286	91.69 289	94.32 286	96.23 306	89.16 254	92.27 311	92.88 329	84.39 333	95.29 254	96.35 263	85.66 284	96.74 358	84.53 336	97.56 296	97.05 304

cl-mvsnet2		93.25 273	92.84 269	94.46 282	94.30 342	86.00 307	91.09 333	96.64 286	90.74 268	95.79 241	96.31 264	78.24 317	98.77 304	94.15 184	98.34 263	98.62 217

tpmvs		90.79 306	90.87 300	90.57 334	92.75 360	76.30 357	95.79 170	93.64 322	91.04 267	91.91 334	96.26 265	77.19 326	98.86 298	89.38 287	89.85 355	96.56 325

test_prior3		95.91 175	95.39 188	97.46 135	97.79 228	94.26 146	93.33 290	98.42 173	94.21 194	94.02 288	96.25 266	93.64 177	99.34 230	91.90 228	98.96 214	98.79 198

test_prior2							93.33 290		94.21 194	94.02 288	96.25 266	93.64 177		91.90 228	98.96 214

testgi		96.07 167	96.50 148	94.80 269	99.26 48	87.69 284	95.96 160	98.58 157	95.08 163	98.02 118	96.25 266	97.92 16	97.60 352	88.68 297	98.74 241	99.11 148

DP-MVS Recon		95.55 187	95.13 195	96.80 176	98.51 141	93.99 155	94.60 240	98.69 139	90.20 274	95.78 243	96.21 269	92.73 196	98.98 286	90.58 266	98.86 229	97.42 297

hse-mvs2		95.77 180	95.09 197	97.79 103	97.84 214	95.51 94	95.66 177	95.43 308	96.58 92	97.21 166	96.16 270	84.14 293	99.54 170	95.89 95	96.92 310	98.32 241

MVSFormer		96.14 165	96.36 152	95.49 240	97.68 240	87.81 281	98.67 11	99.02 51	96.50 96	94.48 276	96.15 271	86.90 277	99.92 4	98.73 7	99.13 195	98.74 205

jason		94.39 242	94.04 245	95.41 245	98.29 162	87.85 280	92.74 302	96.75 282	85.38 323	95.29 254	96.15 271	88.21 266	99.65 131	94.24 180	99.34 161	98.74 205
jason: jason.
test_yl		94.40 240	94.00 246	95.59 233	96.95 287	89.52 247	94.75 236	95.55 305	96.18 110	96.79 194	96.14 273	81.09 305	99.18 258	90.75 257	97.77 282	98.07 262

DCV-MVSNet		94.40 240	94.00 246	95.59 233	96.95 287	89.52 247	94.75 236	95.55 305	96.18 110	96.79 194	96.14 273	81.09 305	99.18 258	90.75 257	97.77 282	98.07 262

dp		88.08 326	88.05 324	88.16 344	92.85 358	68.81 367	94.17 256	92.88 329	85.47 319	91.38 337	96.14 273	68.87 357	98.81 301	86.88 317	83.80 362	96.87 311

AUN-MVS		93.95 257	92.69 274	97.74 106	97.80 222	95.38 100	95.57 184	95.46 307	91.26 264	92.64 325	96.10 276	74.67 336	99.55 167	93.72 202	96.97 309	98.30 245

MCST-MVS		96.24 160	95.80 176	97.56 119	98.75 111	94.13 150	94.66 238	98.17 206	90.17 275	96.21 226	96.10 276	95.14 132	99.43 200	94.13 185	98.85 231	99.13 139

TEST9					97.84 214	95.23 108	93.62 279	98.39 178	86.81 306	93.78 293	95.99 278	94.68 147	99.52 176

train_agg		95.46 193	94.66 217	97.88 98	97.84 214	95.23 108	93.62 279	98.39 178	87.04 304	93.78 293	95.99 278	94.58 152	99.52 176	91.76 234	98.90 223	98.89 185

MSDG		95.33 198	95.13 195	95.94 222	97.40 263	91.85 212	91.02 334	98.37 181	95.30 154	96.31 220	95.99 278	94.51 155	98.38 336	89.59 283	97.65 294	97.60 292

agg_prior1		95.39 196	94.60 223	97.75 105	97.80 222	94.96 118	93.39 287	98.36 182	87.20 302	93.49 306	95.97 281	94.65 149	99.53 172	91.69 236	98.86 229	98.77 203

test_8					97.81 218	95.07 116	93.54 282	98.38 180	87.04 304	93.71 297	95.96 282	94.58 152	99.52 176

CSCG		97.40 97	97.30 96	97.69 112	98.95 95	94.83 121	97.28 91	98.99 62	96.35 104	98.13 104	95.95 283	95.99 98	99.66 130	94.36 177	99.73 45	98.59 220

TAPA-MVS	93.32 12	94.93 215	94.23 237	97.04 163	98.18 178	94.51 134	95.22 209	98.73 126	81.22 343	96.25 224	95.95 283	93.80 173	98.98 286	89.89 279	98.87 227	97.62 290
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ETH3 D test6400		94.77 222	93.87 251	97.47 132	98.12 189	93.73 166	94.56 242	98.70 136	85.45 321	94.70 269	95.93 285	91.77 224	99.63 136	86.45 320	99.14 191	99.05 159

baseline1		93.14 275	92.64 276	94.62 275	97.34 269	87.20 293	96.67 125	93.02 327	94.71 177	96.51 210	95.83 286	81.64 302	98.60 322	90.00 278	88.06 357	98.07 262

sss		94.22 245	93.72 253	95.74 229	97.71 238	89.95 240	93.84 272	96.98 273	88.38 293	93.75 296	95.74 287	87.94 267	98.89 294	91.02 248	98.10 272	98.37 234

CNLPA		95.04 211	94.47 230	96.75 179	97.81 218	95.25 107	94.12 262	97.89 229	94.41 186	94.57 271	95.69 288	90.30 242	98.35 339	86.72 319	98.76 239	96.64 322

PCF-MVS	89.43 18	92.12 291	90.64 305	96.57 190	97.80 222	93.48 176	89.88 347	98.45 167	74.46 360	96.04 232	95.68 289	90.71 235	99.31 237	73.73 358	99.01 212	96.91 310
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
BH-untuned		94.69 228	94.75 215	94.52 281	97.95 205	87.53 286	94.07 263	97.01 272	93.99 201	97.10 174	95.65 290	92.65 199	98.95 291	87.60 310	96.74 317	97.09 302

CANet_DTU		94.65 232	94.21 239	95.96 218	95.90 316	89.68 244	93.92 270	97.83 235	93.19 224	90.12 345	95.64 291	88.52 261	99.57 162	93.27 211	99.47 119	98.62 217

PatchMatch-RL		94.61 234	93.81 252	97.02 165	98.19 175	95.72 82	93.66 278	97.23 262	88.17 295	94.94 264	95.62 292	91.43 226	98.57 323	87.36 315	97.68 291	96.76 319

tpm cat1		88.01 327	87.33 328	90.05 337	94.48 340	76.28 358	94.47 245	94.35 317	73.84 362	89.26 349	95.61 293	73.64 341	98.30 341	84.13 337	86.20 360	95.57 340

Effi-MVS+-dtu		96.81 132	96.09 164	98.99 13	96.90 291	98.69 2	96.42 131	98.09 215	95.86 130	95.15 258	95.54 294	94.26 161	99.81 31	94.06 187	98.51 259	98.47 228

AdaColmap		95.11 208	94.62 222	96.58 188	97.33 271	94.45 137	94.92 227	98.08 217	93.15 229	93.98 291	95.53 295	94.34 159	99.10 272	85.69 325	98.61 253	96.20 330

thisisatest0530		92.71 280	91.76 288	95.56 237	98.42 153	88.23 269	96.03 154	87.35 359	94.04 200	96.56 207	95.47 296	64.03 362	99.77 53	94.78 157	99.11 199	98.68 213

WTY-MVS		93.55 266	93.00 265	95.19 252	97.81 218	87.86 278	93.89 271	96.00 293	89.02 284	94.07 286	95.44 297	86.27 280	99.33 233	87.69 308	96.82 314	98.39 233

PLC	91.02 16	94.05 254	92.90 266	97.51 124	98.00 200	95.12 115	94.25 251	98.25 194	86.17 310	91.48 336	95.25 298	91.01 230	99.19 257	85.02 333	96.69 318	98.22 253
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
pmmvs3		90.00 311	88.90 320	93.32 300	94.20 346	85.34 313	91.25 328	92.56 334	78.59 352	93.82 292	95.17 299	67.36 359	98.69 312	89.08 291	98.03 275	95.92 332

CS-MVS		95.98 173	96.24 156	95.20 251	97.26 274	89.88 241	95.84 168	99.39 8	93.89 205	94.28 279	95.15 300	94.81 142	99.62 144	96.11 81	99.40 145	96.10 331

NP-MVS					98.14 185	93.72 167					95.08 301

HQP-MVS		95.17 207	94.58 226	96.92 168	97.85 210	92.47 195	94.26 248	98.43 170	93.18 225	92.86 319	95.08 301	90.33 239	99.23 254	90.51 269	98.74 241	99.05 159

cdsmvs_eth3d_5k		24.22 336	32.30 339	0.00 352	0.00 373	0.00 374	0.00 364	98.10 214	0.00 369	0.00 370	95.06 303	97.54 29	0.00 370	0.00 368	0.00 368	0.00 366

lupinMVS		93.77 258	93.28 259	95.24 249	97.68 240	87.81 281	92.12 313	96.05 291	84.52 330	94.48 276	95.06 303	86.90 277	99.63 136	93.62 205	99.13 195	98.27 249

1112_ss		94.12 250	93.42 257	96.23 207	98.59 133	90.85 227	94.24 252	98.85 91	85.49 318	92.97 317	94.94 305	86.01 282	99.64 134	91.78 233	97.92 278	98.20 255

ab-mvs-re		7.91 340	10.55 343	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	94.94 305	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

Fast-Effi-MVS+-dtu		96.44 154	96.12 162	97.39 143	97.18 279	94.39 138	95.46 187	98.73 126	96.03 119	94.72 267	94.92 307	96.28 95	99.69 113	93.81 198	97.98 276	98.09 259

EPNet_dtu		91.39 300	90.75 303	93.31 301	90.48 365	82.61 335	94.80 233	92.88 329	93.39 216	81.74 364	94.90 308	81.36 304	99.11 270	88.28 302	98.87 227	98.21 254
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DPM-MVS		93.68 262	92.77 273	96.42 198	97.91 206	92.54 193	91.17 330	97.47 258	84.99 327	93.08 316	94.74 309	89.90 247	99.00 282	87.54 312	98.09 273	97.72 286

Effi-MVS+		96.19 163	96.01 167	96.71 181	97.43 261	92.19 204	96.12 149	99.10 30	95.45 148	93.33 313	94.71 310	97.23 43	99.56 163	93.21 213	97.54 297	98.37 234

GA-MVS		92.83 278	92.15 283	94.87 265	96.97 285	87.27 292	90.03 342	96.12 290	91.83 255	94.05 287	94.57 311	76.01 332	98.97 290	92.46 223	97.34 305	98.36 239

miper_enhance_ethall		93.14 275	92.78 272	94.20 289	93.65 350	85.29 315	89.97 343	97.85 231	85.05 325	96.15 230	94.56 312	85.74 283	99.14 265	93.74 200	98.34 263	98.17 258

xiu_mvs_v1_base_debu		95.62 184	95.96 171	94.60 276	98.01 196	88.42 265	93.99 266	98.21 197	92.98 234	95.91 236	94.53 313	96.39 89	99.72 82	95.43 121	98.19 268	95.64 337

xiu_mvs_v1_base		95.62 184	95.96 171	94.60 276	98.01 196	88.42 265	93.99 266	98.21 197	92.98 234	95.91 236	94.53 313	96.39 89	99.72 82	95.43 121	98.19 268	95.64 337

xiu_mvs_v1_base_debi		95.62 184	95.96 171	94.60 276	98.01 196	88.42 265	93.99 266	98.21 197	92.98 234	95.91 236	94.53 313	96.39 89	99.72 82	95.43 121	98.19 268	95.64 337

PVSNet_Blended		93.96 255	93.65 254	94.91 261	97.79 228	87.40 289	91.43 322	98.68 141	84.50 331	94.51 274	94.48 316	93.04 188	99.30 240	89.77 281	98.61 253	98.02 272

PAPM_NR		94.61 234	94.17 241	95.96 218	98.36 157	91.23 220	95.93 163	97.95 225	92.98 234	93.42 311	94.43 317	90.53 236	98.38 336	87.60 310	96.29 325	98.27 249

API-MVS		95.09 210	95.01 202	95.31 246	96.61 295	94.02 153	96.83 113	97.18 265	95.60 142	95.79 241	94.33 318	94.54 154	98.37 338	85.70 324	98.52 257	93.52 351

mvs-test1		96.20 162	95.50 187	98.32 64	96.90 291	98.16 4	95.07 218	98.09 215	95.86 130	93.63 300	94.32 319	94.26 161	99.71 96	94.06 187	97.27 308	97.07 303

alignmvs		96.01 171	95.52 186	97.50 127	97.77 233	94.71 126	96.07 151	96.84 277	97.48 65	96.78 198	94.28 320	85.50 285	99.40 212	96.22 76	98.73 244	98.40 231

CLD-MVS		95.47 192	95.07 198	96.69 183	98.27 166	92.53 194	91.36 323	98.67 144	91.22 265	95.78 243	94.12 321	95.65 116	98.98 286	90.81 254	99.72 48	98.57 221
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
TR-MVS		92.54 282	92.20 282	93.57 297	96.49 298	86.66 299	93.51 283	94.73 312	89.96 277	94.95 263	93.87 322	90.24 244	98.61 320	81.18 347	94.88 339	95.45 341

canonicalmvs		97.23 110	97.21 105	97.30 148	97.65 244	94.39 138	97.84 56	99.05 42	97.42 67	96.68 201	93.85 323	97.63 26	99.33 233	96.29 75	98.47 260	98.18 257

xiu_mvs_v2_base		94.22 245	94.63 221	92.99 311	97.32 272	84.84 323	92.12 313	97.84 233	91.96 252	94.17 282	93.43 324	96.07 97	99.71 96	91.27 242	97.48 300	94.42 347

CS-MVS-test		95.30 200	95.31 190	95.27 247	96.97 285	91.13 222	95.52 185	99.28 11	92.94 239	92.37 329	93.42 325	93.77 174	99.61 151	94.60 162	98.96 214	95.07 343

CHOSEN 280x420		89.98 312	89.19 318	92.37 322	95.60 325	81.13 344	86.22 357	97.09 269	81.44 342	87.44 357	93.15 326	73.99 337	99.47 188	88.69 296	99.07 205	96.52 326

KD-MVS_2432*1600		88.93 320	87.74 325	92.49 318	88.04 366	81.99 339	89.63 349	95.62 301	91.35 261	95.06 259	93.11 327	56.58 368	98.63 318	85.19 330	95.07 337	96.85 313

miper_refine_blended		88.93 320	87.74 325	92.49 318	88.04 366	81.99 339	89.63 349	95.62 301	91.35 261	95.06 259	93.11 327	56.58 368	98.63 318	85.19 330	95.07 337	96.85 313

thres600view7		92.03 292	91.43 290	93.82 292	98.19 175	84.61 325	96.27 139	90.39 350	96.81 85	96.37 216	93.11 327	73.44 345	99.49 182	80.32 348	97.95 277	97.36 298

E-PMN		89.52 317	89.78 312	88.73 340	93.14 355	77.61 353	83.26 360	92.02 336	94.82 174	93.71 297	93.11 327	75.31 334	96.81 356	85.81 323	96.81 315	91.77 357

thres100view900		91.76 296	91.26 295	93.26 302	98.21 173	84.50 326	96.39 132	90.39 350	96.87 83	96.33 217	93.08 331	73.44 345	99.42 201	78.85 352	97.74 285	95.85 333

1314		92.38 285	92.30 281	92.64 317	95.42 330	85.15 318	95.86 165	96.97 274	85.40 322	90.62 339	93.06 332	91.12 229	97.80 350	86.74 318	95.49 336	94.97 345

PAPM		87.64 330	85.84 335	93.04 308	96.54 296	84.99 321	88.42 354	95.57 304	79.52 349	83.82 361	93.05 333	80.57 308	98.41 333	62.29 364	92.79 348	95.71 336

Fast-Effi-MVS+		95.49 189	95.07 198	96.75 179	97.67 243	92.82 189	94.22 254	98.60 154	91.61 257	93.42 311	92.90 334	96.73 69	99.70 105	92.60 219	97.89 281	97.74 285

ET-MVSNet_ETH3D		91.12 301	89.67 313	95.47 241	96.41 300	89.15 255	91.54 321	90.23 353	89.07 283	86.78 360	92.84 335	69.39 356	99.44 198	94.16 183	96.61 320	97.82 282

MVS		90.02 310	89.20 317	92.47 320	94.71 337	86.90 297	95.86 165	96.74 283	64.72 363	90.62 339	92.77 336	92.54 204	98.39 335	79.30 350	95.56 335	92.12 355

BH-w/o		92.14 290	91.94 284	92.73 316	97.13 281	85.30 314	92.46 307	95.64 300	89.33 282	94.21 281	92.74 337	89.60 249	98.24 342	81.68 345	94.66 341	94.66 346

PAPR		92.22 288	91.27 294	95.07 256	95.73 323	88.81 260	91.97 316	97.87 230	85.80 315	90.91 338	92.73 338	91.16 228	98.33 340	79.48 349	95.76 333	98.08 260

MAR-MVS		94.21 247	93.03 264	97.76 104	96.94 289	97.44 33	96.97 109	97.15 266	87.89 299	92.00 333	92.73 338	92.14 212	99.12 267	83.92 338	97.51 299	96.73 320
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
baseline2		89.65 316	88.44 323	93.25 303	95.62 324	82.71 334	93.82 273	85.94 362	88.89 287	87.35 358	92.54 340	71.23 351	99.33 233	86.01 321	94.60 343	97.72 286

PS-MVSNAJ		94.10 251	94.47 230	93.00 310	97.35 265	84.88 322	91.86 317	97.84 233	91.96 252	94.17 282	92.50 341	95.82 105	99.71 96	91.27 242	97.48 300	94.40 348

PMMVS		92.39 284	91.08 296	96.30 205	93.12 356	92.81 190	90.58 338	95.96 295	79.17 351	91.85 335	92.27 342	90.29 243	98.66 317	89.85 280	96.68 319	97.43 296

PVSNet	86.72 19	91.10 302	90.97 299	91.49 327	97.56 250	78.04 351	87.17 355	94.60 314	84.65 329	92.34 330	92.20 343	87.37 275	98.47 330	85.17 332	97.69 290	97.96 274

tfpn200view9		91.55 298	91.00 297	93.21 305	98.02 194	84.35 328	95.70 173	90.79 347	96.26 106	95.90 239	92.13 344	73.62 342	99.42 201	78.85 352	97.74 285	95.85 333

thres400		91.68 297	91.00 297	93.71 294	98.02 194	84.35 328	95.70 173	90.79 347	96.26 106	95.90 239	92.13 344	73.62 342	99.42 201	78.85 352	97.74 285	97.36 298

MVE	73.61 22	86.48 332	85.92 334	88.18 343	96.23 306	85.28 316	81.78 362	75.79 366	86.01 311	82.53 363	91.88 346	92.74 195	87.47 365	71.42 362	94.86 340	91.78 356
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		89.06 319	89.22 315	88.61 341	93.00 357	77.34 355	82.91 361	90.92 346	94.64 179	92.63 326	91.81 347	76.30 330	97.02 354	83.83 340	96.90 312	91.48 358

thisisatest0515		90.43 307	89.18 319	94.17 291	97.07 283	85.44 312	89.75 348	87.58 358	88.28 294	93.69 299	91.72 348	65.27 360	99.58 156	90.59 265	98.67 246	97.50 295

test_method		66.88 334	66.13 337	69.11 348	62.68 369	25.73 371	49.76 363	96.04 292	14.32 366	64.27 367	91.69 349	73.45 344	88.05 364	76.06 357	66.94 364	93.54 350

EIA-MVS		96.04 169	95.77 178	96.85 173	97.80 222	92.98 186	96.12 149	99.16 19	94.65 178	93.77 295	91.69 349	95.68 114	99.67 124	94.18 182	98.85 231	97.91 278

cascas		91.89 294	91.35 292	93.51 298	94.27 343	85.60 310	88.86 352	98.61 153	79.32 350	92.16 332	91.44 351	89.22 258	98.12 346	90.80 255	97.47 302	96.82 316

IB-MVS	85.98 20	88.63 322	86.95 331	93.68 295	95.12 333	84.82 324	90.85 335	90.17 354	87.55 300	88.48 353	91.34 352	58.01 365	99.59 154	87.24 316	93.80 346	96.63 324
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
thres200		91.00 304	90.42 308	92.77 315	97.47 259	83.98 331	94.01 265	91.18 345	95.12 162	95.44 251	91.21 353	73.93 338	99.31 237	77.76 355	97.63 295	95.01 344

test0.0.03 1		90.11 309	89.21 316	92.83 314	93.89 348	86.87 298	91.74 319	88.74 357	92.02 250	94.71 268	91.14 354	73.92 339	94.48 361	83.75 342	92.94 347	97.16 301

ETV-MVS		96.13 166	95.90 174	96.82 175	97.76 234	93.89 157	95.40 193	98.95 72	95.87 129	95.58 250	91.00 355	96.36 92	99.72 82	93.36 207	98.83 233	96.85 313

test-LLR		89.97 313	89.90 311	90.16 335	94.24 344	74.98 360	89.89 344	89.06 355	92.02 250	89.97 346	90.77 356	73.92 339	98.57 323	91.88 230	97.36 303	96.92 308

test-mter		87.92 328	87.17 329	90.16 335	94.24 344	74.98 360	89.89 344	89.06 355	86.44 309	89.97 346	90.77 356	54.96 372	98.57 323	91.88 230	97.36 303	96.92 308

TESTMET0.1,1		87.20 331	86.57 333	89.07 339	93.62 351	72.84 364	89.89 344	87.01 361	85.46 320	89.12 351	90.20 358	56.00 371	97.72 351	90.91 251	96.92 310	96.64 322

gm-plane-assit					91.79 362	71.40 366			81.67 339		90.11 359		98.99 284	84.86 334

DWT-MVSNet_test		87.92 328	86.77 332	91.39 328	93.18 353	78.62 349	95.10 213	91.42 341	85.58 317	88.00 354	88.73 360	60.60 364	98.90 292	90.60 264	87.70 358	96.65 321

DeepMVS_CX				77.17 347	90.94 364	85.28 316		74.08 369	52.51 364	80.87 365	88.03 361	75.25 335	70.63 366	59.23 365	84.94 361	75.62 361

PVSNet_0	81.89 21	84.49 333	83.21 336	88.34 342	95.76 322	74.97 362	83.49 359	92.70 333	78.47 353	87.94 355	86.90 362	83.38 298	96.63 359	73.44 359	66.86 365	93.40 352

GG-mvs-BLEND				90.60 333	91.00 363	84.21 330	98.23 32	72.63 370		82.76 362	84.11 363	56.14 370	96.79 357	72.20 360	92.09 351	90.78 359

tmp_tt		57.23 335	62.50 338	41.44 349	34.77 370	49.21 370	83.93 358	60.22 371	15.31 365	71.11 366	79.37 364	70.09 355	44.86 367	64.76 363	82.93 363	30.25 363

X-MVStestdata		92.86 277	90.83 302	98.94 18	99.15 72	97.66 19	97.77 60	98.83 103	97.42 67	96.32 218	36.50 365	96.49 83	99.72 82	95.66 103	99.37 150	99.45 66

testmvs		12.33 338	15.23 341	3.64 351	5.77 372	2.23 373	88.99 351	3.62 372	2.30 368	5.29 368	13.09 366	4.52 374	1.95 368	5.16 367	8.32 367	6.75 365

test123		12.59 337	15.49 340	3.87 350	6.07 371	2.55 372	90.75 336	2.59 373	2.52 367	5.20 369	13.02 367	4.96 373	1.85 369	5.20 366	9.09 366	7.23 364

test_post											10.87 368	76.83 327	99.07 275

test_post1							94.98 225				10.37 369	76.21 331	99.04 278	89.47 285

uanet_test		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

pcd_1.5k_mvsjas		7.98 339	10.65 342	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	95.82 105	0.00 370	0.00 368	0.00 368	0.00 366

sosnet-low-res		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

sosnet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

uncertanet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

Regformer		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

uanet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

eth-test2					0.00 373

eth-test					0.00 373

IU-MVS					99.22 57	95.40 99		98.14 210	85.77 316	98.36 75				95.23 131	99.51 107	99.49 51

save fliter					98.48 147	94.71 126	94.53 243	98.41 175	95.02 167

test_0728_SECOND				98.25 72	99.23 54	95.49 97	96.74 118	98.89 78					99.75 65	95.48 114	99.52 102	99.53 39

GSMVS																98.06 266

test_part2					99.03 91	96.07 72				98.08 111

sam_mvs1												77.80 319				98.06 266

sam_mvs												77.38 323

MTGPA								98.73 126

MTMP							96.55 126	74.60 367

test9_res														91.29 241	98.89 226	99.00 164

agg_prior2														90.34 274	98.90 223	99.10 152

agg_prior					97.80 222	94.96 118		98.36 182		93.49 306			99.53 172

test_prior4						95.38 100	93.61 281

test_prior				97.46 135	97.79 228	94.26 146		98.42 173					99.34 230			98.79 198

旧先验2							93.35 289		77.95 356	95.77 245			98.67 316	90.74 260

新几何2							93.43 284

无先验							93.20 293	97.91 227	80.78 344				99.40 212	87.71 306		97.94 275

原ACMM2							92.82 298

testdata2													99.46 191	87.84 305

segment_acmp												95.34 126

testdata1							92.77 299		93.78 207

test12				97.46 135	97.61 247	94.07 151		97.78 237		93.57 304		93.31 183	99.42 201		98.78 237	98.89 185

plane_prior7					98.70 119	94.67 130

plane_prior6					98.38 155	94.37 140						91.91 222

plane_prior5								98.75 122					99.46 191	92.59 221	99.20 184	99.28 110

plane_prior3						94.51 134			95.29 155	96.16 228

plane_prior2							96.50 128		96.36 101

plane_prior1					98.49 145

plane_prior						94.29 142	95.42 190		94.31 191						98.93 221

n2								0.00 374

nn								0.00 374

door-mid								98.17 206

test11								98.08 217

door								97.81 236

HQP5-MVS						92.47 195

HQP-NCC					97.85 210		94.26 248		93.18 225	92.86 319

ACMP_Plane					97.85 210		94.26 248		93.18 225	92.86 319

BP-MVS														90.51 269

HQP4-MVS										92.87 318			99.23 254			99.06 157

HQP3-MVS								98.43 170							98.74 241

HQP2-MVS												90.33 239

MDTV_nov1_ep13_2view						57.28 369	94.89 228		80.59 345	94.02 288		78.66 316		85.50 328		97.82 282

ACMMP++_ref															99.52 102

ACMMP++															99.55 91

Test By Simon												94.51 155

High-resolution multi-view benchmark