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

Gipuma		99.03 37	99.16 30	98.64 175	99.94 2	98.51 101	99.32 17	99.75 9	99.58 22	98.60 183	99.62 21	98.22 55	99.51 309	97.70 109	99.73 107	97.89 320
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 21	99.31 22	99.53 36	99.91 3	98.98 64	99.63 6	99.58 28	99.44 29	99.78 10	99.76 6	96.39 181	99.92 35	99.44 13	99.92 34	99.68 33

pmmvs6		99.67 3	99.70 3	99.60 13	99.90 4	99.27 21	99.53 7	99.76 8	99.64 12	99.84 8	99.83 2	99.50 5	99.87 87	99.36 14	99.92 34	99.64 41

PS-MVSNAJss		99.46 12	99.49 10	99.35 70	99.90 4	98.15 129	99.20 35	99.65 20	99.48 24	99.92 3	99.71 12	98.07 66	99.96 8	99.53 9	100.00 1	99.93 1

ANet_high		99.57 7	99.67 5	99.28 82	99.89 6	98.09 133	99.14 43	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

anonymousdsp		99.51 10	99.47 12	99.62 6	99.88 7	99.08 62	99.34 15	99.69 15	98.93 81	99.65 22	99.72 11	98.93 19	99.95 15	99.11 27	100.00 1	99.82 9

v7n		99.53 8	99.57 8	99.41 61	99.88 7	98.54 99	99.45 9	99.61 24	99.66 11	99.68 19	99.66 17	98.44 40	99.95 15	99.73 2	99.96 14	99.75 22

mvs_tets		99.63 5	99.67 5	99.49 49	99.88 7	98.61 91	99.34 15	99.71 11	99.27 44	99.90 4	99.74 8	99.68 2	99.97 3	99.55 8	99.99 5	99.88 3

jajsoiax		99.58 6	99.61 7	99.48 51	99.87 10	98.61 91	99.28 29	99.66 19	99.09 66	99.89 6	99.68 14	99.53 4	99.97 3	99.50 10	99.99 5	99.87 4

test_djsdf		99.52 9	99.51 9	99.53 36	99.86 11	98.74 80	99.39 13	99.56 42	99.11 57	99.70 15	99.73 10	99.00 15	99.97 3	99.26 18	99.98 9	99.89 2

MIMVSNet1		99.38 20	99.32 21	99.55 26	99.86 11	99.19 36	99.41 12	99.59 26	99.59 20	99.71 14	99.57 27	97.12 139	99.90 49	99.21 23	99.87 52	99.54 85

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 24	99.85 13	99.11 58	99.90 1	99.78 6	99.63 14	99.78 10	99.67 16	99.48 6	99.81 163	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
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 14	99.34 15	99.69 4	99.58 28	99.90 2	99.86 7	99.78 5	99.58 3	99.95 15	99.00 34	99.95 16	99.78 14

SixPastTwentyTwo		98.75 73	98.62 75	99.16 101	99.83 15	97.96 154	99.28 29	98.20 297	99.37 35	99.70 15	99.65 19	92.65 277	99.93 28	99.04 32	99.84 56	99.60 51

Baseline_NR-MVSNet		98.98 44	98.86 47	99.36 65	99.82 16	98.55 96	97.47 205	99.57 35	99.37 35	99.21 87	99.61 23	96.76 163	99.83 139	98.06 86	99.83 62	99.71 26

pm-mvs1		99.44 13	99.48 11	99.33 75	99.80 17	98.63 88	99.29 25	99.63 21	99.30 42	99.65 22	99.60 25	99.16 14	99.82 150	99.07 29	99.83 62	99.56 73

TransMVSNet (Re)		99.44 13	99.47 12	99.36 65	99.80 17	98.58 94	99.27 31	99.57 35	99.39 33	99.75 12	99.62 21	99.17 12	99.83 139	99.06 30	99.62 154	99.66 36

K. test v3		98.00 165	97.66 184	99.03 127	99.79 19	97.56 185	99.19 39	92.47 361	99.62 17	99.52 35	99.66 17	89.61 295	99.96 8	99.25 20	99.81 69	99.56 73

Anonymous20240521		98.69 83	98.87 45	98.16 228	99.77 20	95.11 268	99.08 47	99.44 84	99.34 38	99.33 63	99.55 29	94.10 255	99.94 23	99.25 20	99.96 14	99.42 142

FC-MVSNet-test		99.27 25	99.25 25	99.34 73	99.77 20	98.37 110	99.30 24	99.57 35	99.61 19	99.40 52	99.50 36	97.12 139	99.85 108	99.02 33	99.94 21	99.80 12

XXY-MVS		99.14 32	99.15 32	99.10 110	99.76 22	97.74 176	98.85 67	99.62 22	98.48 105	99.37 57	99.49 39	98.75 24	99.86 94	98.20 78	99.80 77	99.71 26

TDRefinement		99.42 16	99.38 15	99.55 26	99.76 22	99.33 16	99.68 5	99.71 11	99.38 34	99.53 33	99.61 23	98.64 29	99.80 172	98.24 75	99.84 56	99.52 95

FOURS1					99.73 24	99.67 2	99.43 10	99.54 50	99.43 30	99.26 78

PEN-MVS		99.41 17	99.34 19	99.62 6	99.73 24	99.14 51	99.29 25	99.54 50	99.62 17	99.56 28	99.42 49	98.16 62	99.96 8	98.78 45	99.93 25	99.77 16

lessismore_v0				98.97 134	99.73 24	97.53 187		86.71 371		99.37 57	99.52 35	89.93 293	99.92 35	98.99 35	99.72 114	99.44 135

SteuartSystems-ACMMP		98.79 65	98.54 85	99.54 29	99.73 24	99.16 42	98.23 119	99.31 134	97.92 143	98.90 140	98.90 148	98.00 72	99.88 70	96.15 217	99.72 114	99.58 63
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 154	98.15 146	98.22 224	99.73 24	95.15 265	97.36 212	99.68 16	94.45 293	98.99 122	99.27 67	96.87 153	99.94 23	97.13 137	99.91 40	99.57 68

Vis-MVSNet		99.34 22	99.36 16	99.27 85	99.73 24	98.26 117	99.17 40	99.78 6	99.11 57	99.27 74	99.48 41	98.82 21	99.95 15	98.94 36	99.93 25	99.59 57
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ACMH	96.65 7	99.25 27	99.24 26	99.26 88	99.72 30	98.38 109	99.07 49	99.55 46	98.30 113	99.65 22	99.45 47	99.22 9	99.76 211	98.44 65	99.77 90	99.64 41
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PS-CasMVS		99.40 18	99.33 20	99.62 6	99.71 31	99.10 59	99.29 25	99.53 54	99.53 23	99.46 43	99.41 51	98.23 52	99.95 15	98.89 40	99.95 16	99.81 11

DTE-MVSNet		99.43 15	99.35 17	99.66 4	99.71 31	99.30 17	99.31 20	99.51 58	99.64 12	99.56 28	99.46 43	98.23 52	99.97 3	98.78 45	99.93 25	99.72 25

WR-MVS_H		99.33 23	99.22 27	99.65 5	99.71 31	99.24 24	99.32 17	99.55 46	99.46 27	99.50 39	99.34 60	97.30 128	99.93 28	98.90 38	99.93 25	99.77 16

HPM-MVS_fast		99.01 38	98.82 50	99.57 18	99.71 31	99.35 12	99.00 55	99.50 60	97.33 194	98.94 136	98.86 161	98.75 24	99.82 150	97.53 115	99.71 118	99.56 73

ACMH+	96.62 9	99.08 35	99.00 40	99.33 75	99.71 31	98.83 74	98.60 82	99.58 28	99.11 57	99.53 33	99.18 80	98.81 22	99.67 253	96.71 176	99.77 90	99.50 102

PMVS	91.26 20	97.86 177	97.94 165	97.65 256	99.71 31	97.94 157	98.52 91	98.68 275	98.99 73	97.52 264	99.35 58	97.41 122	98.18 363	91.59 331	99.67 140	96.82 349
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FIs		99.14 32	99.09 34	99.29 80	99.70 37	98.28 116	99.13 44	99.52 57	99.48 24	99.24 83	99.41 51	96.79 160	99.82 150	98.69 53	99.88 49	99.76 20

VPNet		98.87 57	98.83 49	99.01 131	99.70 37	97.62 184	98.43 105	99.35 115	99.47 26	99.28 72	99.05 108	96.72 166	99.82 150	98.09 84	99.36 223	99.59 57

MP-MVS-pluss		98.57 104	98.23 134	99.60 13	99.69 39	99.35 12	97.16 231	99.38 101	94.87 284	98.97 127	98.99 127	98.01 71	99.88 70	97.29 125	99.70 123	99.58 63
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CHOSEN 1792x2688		97.49 205	97.14 220	98.54 196	99.68 40	96.09 240	96.50 267	99.62 22	91.58 332	98.84 153	98.97 133	92.36 279	99.88 70	96.76 169	99.95 16	99.67 35

tfpnnormal		98.90 54	98.90 44	98.91 142	99.67 41	97.82 168	99.00 55	99.44 84	99.45 28	99.51 38	99.24 72	98.20 58	99.86 94	95.92 225	99.69 129	99.04 237

zzz-MVS		98.79 65	98.52 87	99.61 9	99.67 41	99.36 10	97.33 214	99.20 173	98.83 87	98.89 143	98.90 148	96.98 148	99.92 35	97.16 131	99.70 123	99.56 73

MTAPA		98.88 56	98.64 73	99.61 9	99.67 41	99.36 10	98.43 105	99.20 173	98.83 87	98.89 143	98.90 148	96.98 148	99.92 35	97.16 131	99.70 123	99.56 73

CP-MVSNet		99.21 29	99.09 34	99.56 24	99.65 44	98.96 68	99.13 44	99.34 121	99.42 31	99.33 63	99.26 69	97.01 146	99.94 23	98.74 50	99.93 25	99.79 13

HPM-MVS		98.79 65	98.53 86	99.59 17	99.65 44	99.29 18	99.16 41	99.43 90	96.74 231	98.61 181	98.38 240	98.62 30	99.87 87	96.47 196	99.67 140	99.59 57
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 97	98.36 117	99.42 58	99.65 44	99.42 5	98.55 88	99.57 35	97.72 156	98.90 140	99.26 69	96.12 190	99.52 305	95.72 236	99.71 118	99.32 184

TSAR-MVS + MP.		98.63 95	98.49 94	99.06 122	99.64 47	97.90 159	98.51 95	98.94 231	96.96 222	99.24 83	98.89 156	97.83 83	99.81 163	96.88 159	99.49 203	99.48 116
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 61	98.72 60	99.12 106	99.64 47	98.54 99	97.98 152	99.68 16	97.62 162	99.34 62	99.18 80	97.54 108	99.77 204	97.79 101	99.74 104	99.04 237

DIV-MVS_2432*1600		99.25 27	99.18 28	99.44 57	99.63 49	99.06 63	98.69 76	99.54 50	99.31 40	99.62 27	99.53 33	97.36 126	99.86 94	99.24 22	99.71 118	99.39 154

EU-MVSNet		97.66 194	98.50 91	95.13 330	99.63 49	85.84 359	98.35 112	98.21 296	98.23 121	99.54 30	99.46 43	95.02 228	99.68 250	98.24 75	99.87 52	99.87 4

HyFIR lowres test		97.19 230	96.60 251	98.96 135	99.62 51	97.28 199	95.17 320	99.50 60	94.21 298	99.01 118	98.32 249	86.61 311	99.99 2	97.10 139	99.84 56	99.60 51

ACMMP_NAP		98.75 73	98.48 96	99.57 18	99.58 52	99.29 18	97.82 167	99.25 162	96.94 223	98.78 161	99.12 94	98.02 70	99.84 125	97.13 137	99.67 140	99.59 57

nrg030		99.40 18	99.35 17	99.54 29	99.58 52	99.13 54	98.98 58	99.48 70	99.68 9	99.46 43	99.26 69	98.62 30	99.73 226	99.17 26	99.92 34	99.76 20

VDDNet		98.21 149	97.95 163	99.01 131	99.58 52	97.74 176	99.01 53	97.29 323	99.67 10	98.97 127	99.50 36	90.45 290	99.80 172	97.88 97	99.20 248	99.48 116

COLMAP_ROB	96.50 10	98.99 40	98.85 48	99.41 61	99.58 52	99.10 59	98.74 70	99.56 42	99.09 66	99.33 63	99.19 78	98.40 42	99.72 234	95.98 223	99.76 100	99.42 142
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ZNCC-MVS		98.68 87	98.40 110	99.54 29	99.57 56	99.21 27	98.46 102	99.29 151	97.28 200	98.11 224	98.39 238	98.00 72	99.87 87	96.86 162	99.64 148	99.55 81

MSP-MVS		98.40 129	98.00 160	99.61 9	99.57 56	99.25 23	98.57 86	99.35 115	97.55 170	99.31 71	97.71 289	94.61 241	99.88 70	96.14 218	99.19 252	99.70 31
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
testgi		98.32 136	98.39 113	98.13 229	99.57 56	95.54 251	97.78 169	99.49 68	97.37 191	99.19 89	97.65 293	98.96 17	99.49 311	96.50 195	98.99 280	99.34 176

MP-MVS		98.46 121	98.09 151	99.54 29	99.57 56	99.22 26	98.50 96	99.19 178	97.61 164	97.58 258	98.66 200	97.40 123	99.88 70	94.72 263	99.60 163	99.54 85
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 78	98.46 100	99.47 54	99.57 56	98.97 65	98.23 119	99.48 70	96.60 236	99.10 101	99.06 101	98.71 27	99.83 139	95.58 245	99.78 86	99.62 46

LGP-MVS_train				99.47 54	99.57 56	98.97 65		99.48 70	96.60 236	99.10 101	99.06 101	98.71 27	99.83 139	95.58 245	99.78 86	99.62 46

IS-MVSNet		98.19 151	97.90 168	99.08 114	99.57 56	97.97 150	99.31 20	98.32 292	99.01 72	98.98 124	99.03 114	91.59 285	99.79 186	95.49 247	99.80 77	99.48 116

test_0402		98.76 71	98.71 62	98.93 139	99.56 63	98.14 131	98.45 104	99.34 121	99.28 43	98.95 130	98.91 145	98.34 48	99.79 186	95.63 242	99.91 40	98.86 265

EPP-MVSNet		98.30 138	98.04 157	99.07 117	99.56 63	97.83 165	99.29 25	98.07 303	99.03 70	98.59 185	99.13 93	92.16 281	99.90 49	96.87 160	99.68 134	99.49 106

ACMMP		98.75 73	98.50 91	99.52 41	99.56 63	99.16 42	98.87 64	99.37 105	97.16 214	98.82 158	99.01 124	97.71 93	99.87 87	96.29 209	99.69 129	99.54 85
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
FMVSNet1		99.17 30	99.17 29	99.17 98	99.55 66	98.24 119	99.20 35	99.44 84	99.21 46	99.43 47	99.55 29	97.82 86	99.86 94	98.42 67	99.89 48	99.41 145

Vis-MVSNet (Re-imp)		97.46 208	97.16 217	98.34 214	99.55 66	96.10 238	98.94 60	98.44 287	98.32 112	98.16 218	98.62 211	88.76 301	99.73 226	93.88 291	99.79 82	99.18 218

ACMM	96.08 12	98.91 52	98.73 58	99.48 51	99.55 66	99.14 51	98.07 137	99.37 105	97.62 162	99.04 114	98.96 136	98.84 20	99.79 186	97.43 119	99.65 146	99.49 106
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mPP-MVS		98.64 93	98.34 120	99.54 29	99.54 69	99.17 38	98.63 79	99.24 167	97.47 176	98.09 226	98.68 195	97.62 102	99.89 59	96.22 212	99.62 154	99.57 68

XVG-ACMP-BASELINE		98.56 105	98.34 120	99.22 94	99.54 69	98.59 93	97.71 178	99.46 78	97.25 203	98.98 124	98.99 127	97.54 108	99.84 125	95.88 226	99.74 104	99.23 206

region2R		98.69 83	98.40 110	99.54 29	99.53 71	99.17 38	98.52 91	99.31 134	97.46 181	98.44 201	98.51 224	97.83 83	99.88 70	96.46 197	99.58 173	99.58 63

PGM-MVS		98.66 90	98.37 116	99.55 26	99.53 71	99.18 37	98.23 119	99.49 68	97.01 221	98.69 170	98.88 157	98.00 72	99.89 59	95.87 229	99.59 167	99.58 63

Patchmatch-RL test		97.26 223	97.02 224	97.99 240	99.52 73	95.53 252	96.13 285	99.71 11	97.47 176	99.27 74	99.16 86	84.30 332	99.62 273	97.89 94	99.77 90	98.81 271

ACMMPR		98.70 81	98.42 108	99.54 29	99.52 73	99.14 51	98.52 91	99.31 134	97.47 176	98.56 191	98.54 220	97.75 90	99.88 70	96.57 185	99.59 167	99.58 63

GST-MVS		98.61 98	98.30 125	99.52 41	99.51 75	99.20 33	98.26 117	99.25 162	97.44 185	98.67 172	98.39 238	97.68 94	99.85 108	96.00 221	99.51 195	99.52 95

Anonymous20231206		98.21 149	98.21 136	98.20 225	99.51 75	95.43 257	98.13 128	99.32 128	96.16 251	98.93 137	98.82 173	96.00 195	99.83 139	97.32 124	99.73 107	99.36 170

ACMP	95.32 15	98.41 126	98.09 151	99.36 65	99.51 75	98.79 78	97.68 181	99.38 101	95.76 265	98.81 160	98.82 173	98.36 44	99.82 150	94.75 260	99.77 90	99.48 116
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DVP-MVS		98.77 70	98.52 87	99.52 41	99.50 78	99.21 27	98.02 146	98.84 253	97.97 139	99.08 104	99.02 115	97.61 103	99.88 70	96.99 146	99.63 151	99.48 116
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_SECOND				99.60 13	99.50 78	99.23 25	98.02 146	99.32 128					99.88 70	96.99 146	99.63 151	99.68 33

test0726					99.50 78	99.21 27	98.17 127	99.35 115	97.97 139	99.26 78	99.06 101	97.61 103

AllTest		98.44 123	98.20 137	99.16 101	99.50 78	98.55 96	98.25 118	99.58 28	96.80 228	98.88 147	99.06 101	97.65 97	99.57 290	94.45 270	99.61 161	99.37 164

TestCases				99.16 101	99.50 78	98.55 96		99.58 28	96.80 228	98.88 147	99.06 101	97.65 97	99.57 290	94.45 270	99.61 161	99.37 164

XVG-OURS		98.53 114	98.34 120	99.11 108	99.50 78	98.82 76	95.97 289	99.50 60	97.30 198	99.05 112	98.98 131	99.35 7	99.32 334	95.72 236	99.68 134	99.18 218

EG-PatchMatch MVS		98.99 40	99.01 39	98.94 138	99.50 78	97.47 189	98.04 143	99.59 26	98.15 131	99.40 52	99.36 57	98.58 33	99.76 211	98.78 45	99.68 134	99.59 57

SED-MVS		98.91 52	98.72 60	99.49 49	99.49 85	99.17 38	98.10 133	99.31 134	98.03 135	99.66 20	99.02 115	98.36 44	99.88 70	96.91 152	99.62 154	99.41 145

IU-MVS					99.49 85	99.15 47		98.87 244	92.97 315	99.41 49				96.76 169	99.62 154	99.66 36

test_241102_ONE					99.49 85	99.17 38		99.31 134	97.98 137	99.66 20	98.90 148	98.36 44	99.48 314

UA-Net		99.47 11	99.40 14	99.70 2	99.49 85	99.29 18	99.80 3	99.72 10	99.82 3	99.04 114	99.81 3	98.05 69	99.96 8	98.85 42	99.99 5	99.86 6

HFP-MVS		98.71 78	98.44 104	99.51 45	99.49 85	99.16 42	98.52 91	99.31 134	97.47 176	98.58 187	98.50 227	97.97 76	99.85 108	96.57 185	99.59 167	99.53 91

#test#		98.50 117	98.16 144	99.51 45	99.49 85	99.16 42	98.03 144	99.31 134	96.30 248	98.58 187	98.50 227	97.97 76	99.85 108	95.68 239	99.59 167	99.53 91

VPA-MVSNet		99.30 24	99.30 23	99.28 82	99.49 85	98.36 113	99.00 55	99.45 81	99.63 14	99.52 35	99.44 48	98.25 50	99.88 70	99.09 28	99.84 56	99.62 46

XVG-OURS-SEG-HR		98.49 118	98.28 128	99.14 104	99.49 85	98.83 74	96.54 263	99.48 70	97.32 196	99.11 98	98.61 214	99.33 8	99.30 337	96.23 211	98.38 306	99.28 196

114514_t		96.50 266	95.77 271	98.69 172	99.48 93	97.43 192	97.84 165	99.55 46	81.42 365	96.51 313	98.58 217	95.53 214	99.67 253	93.41 304	99.58 173	98.98 246

IterMVS-LS		98.55 109	98.70 65	98.09 230	99.48 93	94.73 274	97.22 224	99.39 99	98.97 76	99.38 55	99.31 64	96.00 195	99.93 28	98.58 56	99.97 11	99.60 51
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v8		99.01 38	99.16 30	98.57 188	99.47 95	96.31 235	98.90 62	99.47 76	99.03 70	99.52 35	99.57 27	96.93 150	99.81 163	99.60 4	99.98 9	99.60 51

XVS		98.72 77	98.45 102	99.53 36	99.46 96	99.21 27	98.65 77	99.34 121	98.62 96	97.54 262	98.63 209	97.50 114	99.83 139	96.79 165	99.53 189	99.56 73

X-MVStestdata		94.32 306	92.59 324	99.53 36	99.46 96	99.21 27	98.65 77	99.34 121	98.62 96	97.54 262	45.85 368	97.50 114	99.83 139	96.79 165	99.53 189	99.56 73

test20.03		98.78 68	98.77 56	98.78 162	99.46 96	97.20 206	97.78 169	99.24 167	99.04 69	99.41 49	98.90 148	97.65 97	99.76 211	97.70 109	99.79 82	99.39 154

abl_6		98.99 40	98.78 54	99.61 9	99.45 99	99.46 4	98.60 82	99.50 60	98.59 98	99.24 83	99.04 111	98.54 35	99.89 59	96.45 198	99.62 154	99.50 102

CSCG		98.68 87	98.50 91	99.20 95	99.45 99	98.63 88	98.56 87	99.57 35	97.87 147	98.85 151	98.04 270	97.66 96	99.84 125	96.72 174	99.81 69	99.13 226

GeoE		99.05 36	98.99 42	99.25 90	99.44 101	98.35 114	98.73 72	99.56 42	98.42 107	98.91 139	98.81 175	98.94 18	99.91 45	98.35 71	99.73 107	99.49 106

v148		98.45 122	98.60 80	98.00 239	99.44 101	94.98 269	97.44 208	99.06 208	98.30 113	99.32 69	98.97 133	96.65 169	99.62 273	98.37 69	99.85 54	99.39 154

v10		98.97 45	99.11 33	98.55 193	99.44 101	96.21 237	98.90 62	99.55 46	98.73 90	99.48 40	99.60 25	96.63 170	99.83 139	99.70 3	99.99 5	99.61 50

V42		98.78 68	98.78 54	98.76 165	99.44 101	97.04 213	98.27 116	99.19 178	97.87 147	99.25 82	99.16 86	96.84 154	99.78 198	99.21 23	99.84 56	99.46 126

MDA-MVSNet-bldmvs		97.94 169	97.91 167	98.06 235	99.44 101	94.96 270	96.63 261	99.15 197	98.35 109	98.83 154	99.11 96	94.31 248	99.85 108	96.60 182	98.72 293	99.37 164

v2v482		98.56 105	98.62 75	98.37 212	99.42 106	95.81 247	97.58 193	99.16 191	97.90 145	99.28 72	99.01 124	95.98 199	99.79 186	99.33 15	99.90 44	99.51 98

OPM-MVS		98.56 105	98.32 124	99.25 90	99.41 107	98.73 83	97.13 233	99.18 182	97.10 217	98.75 166	98.92 144	98.18 59	99.65 266	96.68 178	99.56 182	99.37 164
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 160	98.08 154	98.04 237	99.41 107	94.59 280	94.59 338	99.40 97	97.50 173	98.82 158	98.83 170	96.83 156	99.84 125	97.50 117	99.81 69	99.71 26

test_one_0601					99.39 109	99.20 33		99.31 134	98.49 104	98.66 174	99.02 115	97.64 100

casdiffmvs		98.95 48	99.00 40	98.81 155	99.38 110	97.33 195	97.82 167	99.57 35	99.17 54	99.35 60	99.17 84	98.35 47	99.69 241	98.46 64	99.73 107	99.41 145

baseline		98.96 47	99.02 38	98.76 165	99.38 110	97.26 200	98.49 97	99.50 60	98.86 84	99.19 89	99.06 101	98.23 52	99.69 241	98.71 52	99.76 100	99.33 182

TranMVSNet+NR-MVSNet		99.17 30	99.07 36	99.46 56	99.37 112	98.87 71	98.39 108	99.42 93	99.42 31	99.36 59	99.06 101	98.38 43	99.95 15	98.34 72	99.90 44	99.57 68

tttt0517		95.64 286	94.98 297	97.64 258	99.36 113	93.81 302	98.72 73	90.47 367	98.08 133	98.67 172	98.34 246	73.88 364	99.92 35	97.77 103	99.51 195	99.20 211

test_part2					99.36 113	99.10 59				99.05 112

v1144		98.60 100	98.66 71	98.41 208	99.36 113	95.90 243	97.58 193	99.34 121	97.51 172	99.27 74	99.15 90	96.34 186	99.80 172	99.47 12	99.93 25	99.51 98

CP-MVS		98.70 81	98.42 108	99.52 41	99.36 113	99.12 56	98.72 73	99.36 109	97.54 171	98.30 211	98.40 236	97.86 81	99.89 59	96.53 193	99.72 114	99.56 73

Test_1112_low_res		96.99 247	96.55 255	98.31 217	99.35 117	95.47 255	95.84 300	99.53 54	91.51 334	96.80 303	98.48 232	91.36 286	99.83 139	96.58 183	99.53 189	99.62 46

DeepC-MVS	97.60 4	98.97 45	98.93 43	99.10 110	99.35 117	97.98 149	98.01 149	99.46 78	97.56 169	99.54 30	99.50 36	98.97 16	99.84 125	98.06 86	99.92 34	99.49 106
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 222	96.86 234	98.58 185	99.34 119	96.32 234	96.75 255	99.58 28	93.14 314	96.89 297	97.48 304	92.11 282	99.86 94	96.91 152	99.54 185	99.57 68

SF-MVS		98.53 114	98.27 129	99.32 77	99.31 120	98.75 79	98.19 123	99.41 94	96.77 230	98.83 154	98.90 148	97.80 87	99.82 150	95.68 239	99.52 192	99.38 161

CPTT-MVS		97.84 183	97.36 205	99.27 85	99.31 120	98.46 104	98.29 114	99.27 156	94.90 283	97.83 241	98.37 242	94.90 230	99.84 125	93.85 293	99.54 185	99.51 98

UnsupCasMVSNet_eth		97.89 173	97.60 190	98.75 167	99.31 120	97.17 209	97.62 187	99.35 115	98.72 91	98.76 165	98.68 195	92.57 278	99.74 222	97.76 107	95.60 355	99.34 176

pmmvs-eth3d		98.47 120	98.34 120	98.86 149	99.30 123	97.76 173	97.16 231	99.28 153	95.54 268	99.42 48	99.19 78	97.27 131	99.63 271	97.89 94	99.97 11	99.20 211

Anonymous20231211		99.27 25	99.27 24	99.26 88	99.29 124	98.18 126	99.49 8	99.51 58	99.70 8	99.80 9	99.68 14	96.84 154	99.83 139	99.21 23	99.91 40	99.77 16

UnsupCasMVSNet_bld		97.30 220	96.92 230	98.45 205	99.28 125	96.78 225	96.20 283	99.27 156	95.42 273	98.28 213	98.30 250	93.16 266	99.71 235	94.99 255	97.37 333	98.87 264

DROMVSNet		99.09 34	99.05 37	99.20 95	99.28 125	98.93 69	99.24 33	99.84 3	99.08 68	98.12 222	98.37 242	98.72 26	99.90 49	99.05 31	99.77 90	98.77 279

DPE-MVS		98.59 103	98.26 130	99.57 18	99.27 127	99.15 47	97.01 236	99.39 99	97.67 158	99.44 46	98.99 127	97.53 110	99.89 59	95.40 249	99.68 134	99.66 36
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 182	98.18 140	96.87 296	99.27 127	91.16 342	95.53 310	99.25 162	99.10 63	99.41 49	99.35 58	93.10 268	99.96 8	98.65 54	99.94 21	99.49 106

v1192		98.60 100	98.66 71	98.41 208	99.27 127	95.88 244	97.52 199	99.36 109	97.41 187	99.33 63	99.20 77	96.37 184	99.82 150	99.57 6	99.92 34	99.55 81

N_pmnet		97.63 197	97.17 216	98.99 133	99.27 127	97.86 162	95.98 288	93.41 358	95.25 277	99.47 42	98.90 148	95.63 211	99.85 108	96.91 152	99.73 107	99.27 198

FPMVS		93.44 321	92.23 326	97.08 286	99.25 131	97.86 162	95.61 307	97.16 325	92.90 317	93.76 357	98.65 202	75.94 362	95.66 367	79.30 367	97.49 328	97.73 331

new-patchmatchnet		98.35 134	98.74 57	97.18 282	99.24 132	92.23 327	96.42 272	99.48 70	98.30 113	99.69 17	99.53 33	97.44 121	99.82 150	98.84 43	99.77 90	99.49 106

MCST-MVS		98.00 165	97.63 187	99.10 110	99.24 132	98.17 128	96.89 247	98.73 272	95.66 266	97.92 234	97.70 291	97.17 138	99.66 261	96.18 216	99.23 244	99.47 124

UniMVSNet (Re)		98.87 57	98.71 62	99.35 70	99.24 132	98.73 83	97.73 177	99.38 101	98.93 81	99.12 96	98.73 186	96.77 161	99.86 94	98.63 55	99.80 77	99.46 126

jason		97.45 210	97.35 206	97.76 250	99.24 132	93.93 296	95.86 297	98.42 288	94.24 297	98.50 198	98.13 260	94.82 234	99.91 45	97.22 128	99.73 107	99.43 139
jason: jason.
IterMVS		97.73 189	98.11 150	96.57 303	99.24 132	90.28 343	95.52 312	99.21 171	98.86 84	99.33 63	99.33 62	93.11 267	99.94 23	98.49 62	99.94 21	99.48 116
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 109	98.62 75	98.32 215	99.22 137	95.58 250	97.51 201	99.45 81	97.16 214	99.45 45	99.24 72	96.12 190	99.85 108	99.60 4	99.88 49	99.55 81

ITE_SJBPF				98.87 147	99.22 137	98.48 103		99.35 115	97.50 173	98.28 213	98.60 215	97.64 100	99.35 330	93.86 292	99.27 238	98.79 277

hse-mvs3		97.77 188	97.33 209	99.10 110	99.21 139	97.84 164	98.35 112	98.57 281	99.11 57	98.58 187	99.02 115	88.65 304	99.96 8	98.11 81	96.34 348	99.49 106

v144192		98.54 112	98.57 83	98.45 205	99.21 139	95.98 241	97.63 186	99.36 109	97.15 216	99.32 69	99.18 80	95.84 206	99.84 125	99.50 10	99.91 40	99.54 85

APDe-MVS		98.99 40	98.79 53	99.60 13	99.21 139	99.15 47	98.87 64	99.48 70	97.57 167	99.35 60	99.24 72	97.83 83	99.89 59	97.88 97	99.70 123	99.75 22

DP-MVS		98.93 50	98.81 52	99.28 82	99.21 139	98.45 105	98.46 102	99.33 126	99.63 14	99.48 40	99.15 90	97.23 136	99.75 218	97.17 130	99.66 145	99.63 45

SR-MVS-dyc-post		98.81 63	98.55 84	99.57 18	99.20 143	99.38 6	98.48 100	99.30 144	98.64 92	98.95 130	98.96 136	97.49 117	99.86 94	96.56 188	99.39 218	99.45 130

RE-MVS-def			98.58 82		99.20 143	99.38 6	98.48 100	99.30 144	98.64 92	98.95 130	98.96 136	97.75 90		96.56 188	99.39 218	99.45 130

v1921920		98.54 112	98.60 80	98.38 211	99.20 143	95.76 249	97.56 195	99.36 109	97.23 209	99.38 55	99.17 84	96.02 193	99.84 125	99.57 6	99.90 44	99.54 85

thisisatest0530		95.27 293	94.45 303	97.74 252	99.19 146	94.37 282	97.86 163	90.20 368	97.17 213	98.22 215	97.65 293	73.53 365	99.90 49	96.90 157	99.35 225	98.95 251

Anonymous20240529		98.93 50	98.87 45	99.12 106	99.19 146	98.22 124	99.01 53	98.99 228	99.25 45	99.54 30	99.37 54	97.04 142	99.80 172	97.89 94	99.52 192	99.35 174

APD-MVS_3200maxsize		98.84 60	98.61 78	99.53 36	99.19 146	99.27 21	98.49 97	99.33 126	98.64 92	99.03 117	98.98 131	97.89 79	99.85 108	96.54 192	99.42 214	99.46 126

HQP_MVS		97.99 168	97.67 181	98.93 139	99.19 146	97.65 181	97.77 172	99.27 156	98.20 125	97.79 244	97.98 273	94.90 230	99.70 237	94.42 272	99.51 195	99.45 130

plane_prior7					99.19 146	97.87 161

ab-mvs		98.41 126	98.36 117	98.59 184	99.19 146	97.23 201	99.32 17	98.81 259	97.66 159	98.62 179	99.40 53	96.82 157	99.80 172	95.88 226	99.51 195	98.75 282

F-COLMAP		97.30 220	96.68 245	99.14 104	99.19 146	98.39 107	97.27 220	99.30 144	92.93 316	96.62 308	98.00 271	95.73 209	99.68 250	92.62 319	98.46 305	99.35 174

test1172		98.76 71	98.49 94	99.57 18	99.18 153	99.37 9	98.39 108	99.31 134	98.43 106	98.90 140	98.88 157	97.49 117	99.86 94	96.43 200	99.37 222	99.48 116

SR-MVS		98.71 78	98.43 106	99.57 18	99.18 153	99.35 12	98.36 111	99.29 151	98.29 116	98.88 147	98.85 164	97.53 110	99.87 87	96.14 218	99.31 231	99.48 116

UniMVSNet_NR-MVSNet		98.86 59	98.68 68	99.40 63	99.17 155	98.74 80	97.68 181	99.40 97	99.14 55	99.06 107	98.59 216	96.71 167	99.93 28	98.57 58	99.77 90	99.53 91

LF4IMVS		97.90 171	97.69 180	98.52 197	99.17 155	97.66 180	97.19 228	99.47 76	96.31 247	97.85 240	98.20 257	96.71 167	99.52 305	94.62 264	99.72 114	98.38 303

SMA-MVS		98.40 129	98.03 158	99.51 45	99.16 157	99.21 27	98.05 141	99.22 170	94.16 300	98.98 124	99.10 98	97.52 112	99.79 186	96.45 198	99.64 148	99.53 91
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
DU-MVS		98.82 61	98.63 74	99.39 64	99.16 157	98.74 80	97.54 197	99.25 162	98.84 86	99.06 107	98.76 183	96.76 163	99.93 28	98.57 58	99.77 90	99.50 102

NR-MVSNet		98.95 48	98.82 50	99.36 65	99.16 157	98.72 85	99.22 34	99.20 173	99.10 63	99.72 13	98.76 183	96.38 183	99.86 94	98.00 91	99.82 65	99.50 102

MVS_111021_LR		98.30 138	98.12 149	98.83 152	99.16 157	98.03 143	96.09 286	99.30 144	97.58 166	98.10 225	98.24 253	98.25 50	99.34 331	96.69 177	99.65 146	99.12 227

DSMNet-mixed		97.42 212	97.60 190	96.87 296	99.15 161	91.46 333	98.54 89	99.12 200	92.87 318	97.58 258	99.63 20	96.21 188	99.90 49	95.74 235	99.54 185	99.27 198

D2MVS		97.84 183	97.84 172	97.83 246	99.14 162	94.74 273	96.94 240	98.88 242	95.84 262	98.89 143	98.96 136	94.40 246	99.69 241	97.55 112	99.95 16	99.05 233

pmmvs5		97.64 195	97.49 195	98.08 233	99.14 162	95.12 267	96.70 258	99.05 212	93.77 306	98.62 179	98.83 170	93.23 264	99.75 218	98.33 74	99.76 100	99.36 170

VDD-MVS		98.56 105	98.39 113	99.07 117	99.13 164	98.07 139	98.59 84	97.01 327	99.59 20	99.11 98	99.27 67	94.82 234	99.79 186	98.34 72	99.63 151	99.34 176

xxxxxxxxxxxxxcwj		98.44 123	98.24 132	99.06 122	99.11 165	97.97 150	96.53 264	99.54 50	98.24 119	98.83 154	98.90 148	97.80 87	99.82 150	95.68 239	99.52 192	99.38 161

ETH3D-3000-0.1		98.03 161	97.62 188	99.29 80	99.11 165	98.80 77	97.47 205	99.32 128	95.54 268	98.43 204	98.62 211	96.61 171	99.77 204	93.95 288	99.49 203	99.30 191

save fliter					99.11 165	97.97 150	96.53 264	99.02 221	98.24 119

APD-MVS		98.10 157	97.67 181	99.42 58	99.11 165	98.93 69	97.76 174	99.28 153	94.97 281	98.72 169	98.77 181	97.04 142	99.85 108	93.79 294	99.54 185	99.49 106
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 83	98.71 62	98.62 180	99.10 169	96.37 232	97.23 221	98.87 244	99.20 49	99.19 89	98.99 127	97.30 128	99.85 108	98.77 48	99.79 82	99.65 40

EI-MVSNet		98.40 129	98.51 89	98.04 237	99.10 169	94.73 274	97.20 225	98.87 244	98.97 76	99.06 107	99.02 115	96.00 195	99.80 172	98.58 56	99.82 65	99.60 51

CVMVSNet		96.25 273	97.21 215	93.38 346	99.10 169	80.56 372	97.20 225	98.19 299	96.94 223	99.00 121	99.02 115	89.50 297	99.80 172	96.36 205	99.59 167	99.78 14

EI-MVSNet-Vis-set		98.68 87	98.70 65	98.63 178	99.09 172	96.40 231	97.23 221	98.86 249	99.20 49	99.18 93	98.97 133	97.29 130	99.85 108	98.72 51	99.78 86	99.64 41

HPM-MVS++		98.10 157	97.64 186	99.48 51	99.09 172	99.13 54	97.52 199	98.75 269	97.46 181	96.90 296	97.83 283	96.01 194	99.84 125	95.82 233	99.35 225	99.46 126

DP-MVS Recon		97.33 218	96.92 230	98.57 188	99.09 172	97.99 145	96.79 251	99.35 115	93.18 313	97.71 248	98.07 269	95.00 229	99.31 335	93.97 286	99.13 262	98.42 302

MVS_111021_HR		98.25 146	98.08 154	98.75 167	99.09 172	97.46 190	95.97 289	99.27 156	97.60 165	97.99 233	98.25 252	98.15 64	99.38 328	96.87 160	99.57 177	99.42 142

9.14			97.78 174		99.07 176		97.53 198	99.32 128	95.53 270	98.54 195	98.70 192	97.58 105	99.76 211	94.32 277	99.46 207

PAPM_NR		96.82 254	96.32 262	98.30 218	99.07 176	96.69 227	97.48 203	98.76 266	95.81 264	96.61 309	96.47 332	94.12 254	99.17 347	90.82 343	97.78 325	99.06 232

TAMVS		98.24 147	98.05 156	98.80 157	99.07 176	97.18 208	97.88 160	98.81 259	96.66 235	99.17 94	99.21 75	94.81 236	99.77 204	96.96 150	99.88 49	99.44 135

CLD-MVS		97.49 205	97.16 217	98.48 202	99.07 176	97.03 214	94.71 331	99.21 171	94.46 291	98.06 228	97.16 319	97.57 106	99.48 314	94.46 269	99.78 86	98.95 251
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thres100view900		94.19 309	93.67 313	95.75 319	99.06 180	91.35 336	98.03 144	94.24 353	98.33 111	97.40 273	94.98 355	79.84 350	99.62 273	83.05 360	98.08 319	96.29 353

thres600view7		94.45 304	93.83 310	96.29 308	99.06 180	91.53 332	97.99 150	94.24 353	98.34 110	97.44 271	95.01 353	79.84 350	99.67 253	84.33 358	98.23 309	97.66 334

plane_prior1					99.05 182

YYNet1		97.60 198	97.67 181	97.39 276	99.04 183	93.04 314	95.27 317	98.38 291	97.25 203	98.92 138	98.95 140	95.48 219	99.73 226	96.99 146	98.74 291	99.41 145

MDA-MVSNet_test_wron		97.60 198	97.66 184	97.41 275	99.04 183	93.09 310	95.27 317	98.42 288	97.26 202	98.88 147	98.95 140	95.43 220	99.73 226	97.02 143	98.72 293	99.41 145

MIMVSNet		96.62 262	96.25 266	97.71 253	99.04 183	94.66 277	99.16 41	96.92 331	97.23 209	97.87 238	99.10 98	86.11 317	99.65 266	91.65 329	99.21 247	98.82 268

testtj		97.79 187	97.25 211	99.42 58	99.03 186	98.85 72	97.78 169	99.18 182	95.83 263	98.12 222	98.50 227	95.50 217	99.86 94	92.23 324	99.07 268	99.54 85

PatchMatch-RL		97.24 226	96.78 239	98.61 182	99.03 186	97.83 165	96.36 275	99.06 208	93.49 311	97.36 276	97.78 285	95.75 208	99.49 311	93.44 303	98.77 290	98.52 295

Regformer-3		98.61 98	98.61 78	98.63 178	99.02 188	96.53 229	97.17 229	98.84 253	99.13 56	99.10 101	98.85 164	97.24 135	99.79 186	98.41 68	99.70 123	99.57 68

Regformer-4		98.73 76	98.68 68	98.89 145	99.02 188	97.22 203	97.17 229	99.06 208	99.21 46	99.17 94	98.85 164	97.45 120	99.86 94	98.48 63	99.70 123	99.60 51

ZD-MVS					99.01 190	98.84 73		99.07 207	94.10 301	98.05 230	98.12 263	96.36 185	99.86 94	92.70 318	99.19 252

bset_n11_16_dypcd		96.99 247	96.56 254	98.27 221	99.00 191	95.25 260	92.18 361	94.05 356	98.75 89	99.01 118	98.38 240	88.98 300	99.93 28	98.77 48	99.92 34	99.64 41

CDPH-MVS		97.26 223	96.66 248	99.07 117	99.00 191	98.15 129	96.03 287	99.01 224	91.21 338	97.79 244	97.85 282	96.89 152	99.69 241	92.75 316	99.38 221	99.39 154

diffmvs		98.22 148	98.24 132	98.17 227	99.00 191	95.44 256	96.38 274	99.58 28	97.79 153	98.53 196	98.50 227	96.76 163	99.74 222	97.95 93	99.64 148	99.34 176

WR-MVS		98.40 129	98.19 139	99.03 127	99.00 191	97.65 181	96.85 248	98.94 231	98.57 102	98.89 143	98.50 227	95.60 212	99.85 108	97.54 114	99.85 54	99.59 57

plane_prior6					98.99 195	97.70 179						94.90 230

xiu_mvs_v1_base_debu		97.86 177	98.17 141	96.92 293	98.98 196	93.91 297	96.45 269	99.17 188	97.85 149	98.41 205	97.14 321	98.47 37	99.92 35	98.02 88	99.05 269	96.92 346

xiu_mvs_v1_base		97.86 177	98.17 141	96.92 293	98.98 196	93.91 297	96.45 269	99.17 188	97.85 149	98.41 205	97.14 321	98.47 37	99.92 35	98.02 88	99.05 269	96.92 346

xiu_mvs_v1_base_debi		97.86 177	98.17 141	96.92 293	98.98 196	93.91 297	96.45 269	99.17 188	97.85 149	98.41 205	97.14 321	98.47 37	99.92 35	98.02 88	99.05 269	96.92 346

MVP-Stereo		98.08 159	97.92 166	98.57 188	98.96 199	96.79 222	97.90 159	99.18 182	96.41 243	98.46 199	98.95 140	95.93 202	99.60 280	96.51 194	98.98 282	99.31 188
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 129	98.68 68	97.54 267	98.96 199	97.99 145	97.88 160	99.36 109	98.20 125	99.63 25	99.04 111	98.76 23	95.33 369	96.56 188	99.74 104	99.31 188
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
1121		96.73 256	96.00 267	98.91 142	98.95 201	97.76 173	98.07 137	98.73 272	87.65 356	96.54 310	98.13 260	94.52 243	99.73 226	92.38 322	99.02 276	99.24 205

新几何1				98.91 142	98.94 202	97.76 173		98.76 266	87.58 357	96.75 304	98.10 265	94.80 237	99.78 198	92.73 317	99.00 279	99.20 211

USDC		97.41 213	97.40 201	97.44 273	98.94 202	93.67 306	95.17 320	99.53 54	94.03 303	98.97 127	99.10 98	95.29 222	99.34 331	95.84 232	99.73 107	99.30 191

tfpn200view9		94.03 313	93.44 315	95.78 318	98.93 204	91.44 334	97.60 190	94.29 351	97.94 141	97.10 282	94.31 361	79.67 352	99.62 273	83.05 360	98.08 319	96.29 353

testdata				98.09 230	98.93 204	95.40 258		98.80 261	90.08 346	97.45 270	98.37 242	95.26 223	99.70 237	93.58 299	98.95 284	99.17 222

thres400		94.14 311	93.44 315	96.24 310	98.93 204	91.44 334	97.60 190	94.29 351	97.94 141	97.10 282	94.31 361	79.67 352	99.62 273	83.05 360	98.08 319	97.66 334

TAPA-MVS	96.21 11	96.63 261	95.95 269	98.65 174	98.93 204	98.09 133	96.93 242	99.28 153	83.58 363	98.13 221	97.78 285	96.13 189	99.40 324	93.52 300	99.29 236	98.45 299
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 208	96.93 219	95.54 309	98.78 264	85.72 360	96.86 299	98.11 264	94.43 244			99.10 267	99.23 206

PVSNet_BlendedMVS		97.55 201	97.53 192	97.60 260	98.92 208	93.77 304	96.64 260	99.43 90	94.49 289	97.62 254	99.18 80	96.82 157	99.67 253	94.73 261	99.93 25	99.36 170

PVSNet_Blended		96.88 250	96.68 245	97.47 271	98.92 208	93.77 304	94.71 331	99.43 90	90.98 340	97.62 254	97.36 313	96.82 157	99.67 253	94.73 261	99.56 182	98.98 246

MSDG		97.71 190	97.52 193	98.28 220	98.91 211	96.82 221	94.42 341	99.37 105	97.65 160	98.37 210	98.29 251	97.40 123	99.33 333	94.09 284	99.22 245	98.68 291

Anonymous202405211		97.90 171	97.50 194	99.08 114	98.90 212	98.25 118	98.53 90	96.16 339	98.87 83	99.11 98	98.86 161	90.40 291	99.78 198	97.36 122	99.31 231	99.19 216

原ACMM1				98.35 213	98.90 212	96.25 236		98.83 258	92.48 322	96.07 325	98.10 265	95.39 221	99.71 235	92.61 320	98.99 280	99.08 230

GBi-Net		98.65 91	98.47 98	99.17 98	98.90 212	98.24 119	99.20 35	99.44 84	98.59 98	98.95 130	99.55 29	94.14 251	99.86 94	97.77 103	99.69 129	99.41 145

test1		98.65 91	98.47 98	99.17 98	98.90 212	98.24 119	99.20 35	99.44 84	98.59 98	98.95 130	99.55 29	94.14 251	99.86 94	97.77 103	99.69 129	99.41 145

FMVSNet2		98.49 118	98.40 110	98.75 167	98.90 212	97.14 212	98.61 81	99.13 198	98.59 98	99.19 89	99.28 65	94.14 251	99.82 150	97.97 92	99.80 77	99.29 195

OMC-MVS		97.88 175	97.49 195	99.04 126	98.89 217	98.63 88	96.94 240	99.25 162	95.02 279	98.53 196	98.51 224	97.27 131	99.47 316	93.50 302	99.51 195	99.01 241

ETH3 D test6400		96.46 268	95.59 279	99.08 114	98.88 218	98.21 125	96.53 264	99.18 182	88.87 352	97.08 284	97.79 284	93.64 263	99.77 204	88.92 349	99.40 217	99.28 196

MVSFormer		98.26 144	98.43 106	97.77 249	98.88 218	93.89 300	99.39 13	99.56 42	99.11 57	98.16 218	98.13 260	93.81 258	99.97 3	99.26 18	99.57 177	99.43 139

lupinMVS		97.06 239	96.86 234	97.65 256	98.88 218	93.89 300	95.48 313	97.97 306	93.53 309	98.16 218	97.58 297	93.81 258	99.91 45	96.77 168	99.57 177	99.17 222

DELS-MVS		98.27 142	98.20 137	98.48 202	98.86 221	96.70 226	95.60 308	99.20 173	97.73 155	98.45 200	98.71 189	97.50 114	99.82 150	98.21 77	99.59 167	98.93 256
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
TinyColmap		97.89 173	97.98 161	97.60 260	98.86 221	94.35 283	96.21 282	99.44 84	97.45 183	99.06 107	98.88 157	97.99 75	99.28 340	94.38 276	99.58 173	99.18 218

Regformer-1		98.55 109	98.44 104	98.87 147	98.85 223	97.29 197	96.91 245	98.99 228	98.97 76	98.99 122	98.64 205	97.26 134	99.81 163	97.79 101	99.57 177	99.51 98

Regformer-2		98.60 100	98.46 100	99.02 130	98.85 223	97.71 178	96.91 245	99.09 204	98.98 75	99.01 118	98.64 205	97.37 125	99.84 125	97.75 108	99.57 177	99.52 95

LCM-MVSNet-Re		98.64 93	98.48 96	99.11 108	98.85 223	98.51 101	98.49 97	99.83 4	98.37 108	99.69 17	99.46 43	98.21 57	99.92 35	94.13 283	99.30 234	98.91 260

CS-MVS-test		98.41 126	98.30 125	98.73 171	98.84 226	98.39 107	98.71 75	99.79 5	97.98 137	96.86 299	97.38 310	97.86 81	99.83 139	97.81 100	99.46 207	97.97 318

pmmvs4		97.58 200	97.28 210	98.51 199	98.84 226	96.93 219	95.40 316	98.52 284	93.60 308	98.61 181	98.65 202	95.10 227	99.60 280	96.97 149	99.79 82	98.99 245

NP-MVS					98.84 226	97.39 194					96.84 324

sss		97.21 228	96.93 228	98.06 235	98.83 229	95.22 263	96.75 255	98.48 286	94.49 289	97.27 278	97.90 279	92.77 275	99.80 172	96.57 185	99.32 229	99.16 225

PVSNet	93.40 17	95.67 285	95.70 274	95.57 323	98.83 229	88.57 348	92.50 358	97.72 311	92.69 320	96.49 316	96.44 333	93.72 261	99.43 322	93.61 297	99.28 237	98.71 285

MVE	83.40 22	92.50 328	91.92 331	94.25 337	98.83 229	91.64 331	92.71 357	83.52 373	95.92 260	86.46 370	95.46 349	95.20 224	95.40 368	80.51 365	98.64 299	95.73 361
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ambc				98.24 223	98.82 232	95.97 242	98.62 80	99.00 227		99.27 74	99.21 75	96.99 147	99.50 310	96.55 191	99.50 202	99.26 201

旧先验1					98.82 232	97.45 191		98.76 266			98.34 246	95.50 217			99.01 278	99.23 206

WTY-MVS		96.67 259	96.27 265	97.87 244	98.81 234	94.61 279	96.77 253	97.92 308	94.94 282	97.12 281	97.74 288	91.11 287	99.82 150	93.89 290	98.15 315	99.18 218

3Dnovator+	97.89 3	98.69 83	98.51 89	99.24 92	98.81 234	98.40 106	99.02 52	99.19 178	98.99 73	98.07 227	99.28 65	97.11 141	99.84 125	96.84 163	99.32 229	99.47 124

test_part1		97.91 170	97.46 200	99.27 85	98.80 236	98.18 126	99.07 49	99.36 109	99.75 5	99.63 25	99.49 39	82.20 345	99.89 59	98.87 41	99.95 16	99.74 24

QAPM		97.31 219	96.81 238	98.82 153	98.80 236	97.49 188	99.06 51	99.19 178	90.22 344	97.69 250	99.16 86	96.91 151	99.90 49	90.89 342	99.41 215	99.07 231

VNet		98.42 125	98.30 125	98.79 159	98.79 238	97.29 197	98.23 119	98.66 276	99.31 40	98.85 151	98.80 176	94.80 237	99.78 198	98.13 80	99.13 262	99.31 188

DPM-MVS		96.32 270	95.59 279	98.51 199	98.76 239	97.21 205	94.54 340	98.26 294	91.94 328	96.37 318	97.25 315	93.06 270	99.43 322	91.42 334	98.74 291	98.89 261

3Dnovator	98.27 2	98.81 63	98.73 58	99.05 124	98.76 239	97.81 170	99.25 32	99.30 144	98.57 102	98.55 193	99.33 62	97.95 78	99.90 49	97.16 131	99.67 140	99.44 135

PLC	94.65 16	96.51 264	95.73 273	98.85 150	98.75 241	97.91 158	96.42 272	99.06 208	90.94 341	95.59 331	97.38 310	94.41 245	99.59 284	90.93 340	98.04 322	99.05 233
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 252	96.75 241	97.08 286	98.74 242	93.33 308	96.71 257	98.26 294	96.72 232	98.44 201	97.37 312	95.20 224	99.47 316	91.89 326	97.43 331	98.44 300

hse-mvs2		97.46 208	97.07 221	98.64 175	98.73 243	97.33 195	97.45 207	97.64 316	99.11 57	98.58 187	97.98 273	88.65 304	99.79 186	98.11 81	97.39 332	98.81 271

CDS-MVSNet		97.69 191	97.35 206	98.69 172	98.73 243	97.02 215	96.92 244	98.75 269	95.89 261	98.59 185	98.67 197	92.08 283	99.74 222	96.72 174	99.81 69	99.32 184
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EIA-MVS		98.00 165	97.74 177	98.80 157	98.72 245	98.09 133	98.05 141	99.60 25	97.39 189	96.63 307	95.55 346	97.68 94	99.80 172	96.73 173	99.27 238	98.52 295

LFMVS		97.20 229	96.72 242	98.64 175	98.72 245	96.95 218	98.93 61	94.14 355	99.74 7	98.78 161	99.01 124	84.45 329	99.73 226	97.44 118	99.27 238	99.25 202

new_pmnet		96.99 247	96.76 240	97.67 254	98.72 245	94.89 271	95.95 293	98.20 297	92.62 321	98.55 193	98.54 220	94.88 233	99.52 305	93.96 287	99.44 213	98.59 294

Fast-Effi-MVS+		97.67 193	97.38 203	98.57 188	98.71 248	97.43 192	97.23 221	99.45 81	94.82 285	96.13 321	96.51 329	98.52 36	99.91 45	96.19 214	98.83 288	98.37 305

TEST9					98.71 248	98.08 137	95.96 291	99.03 217	91.40 335	95.85 328	97.53 299	96.52 174	99.76 211

train_agg		97.10 235	96.45 258	99.07 117	98.71 248	98.08 137	95.96 291	99.03 217	91.64 330	95.85 328	97.53 299	96.47 177	99.76 211	93.67 296	99.16 255	99.36 170

TSAR-MVS + GP.		98.18 152	97.98 161	98.77 164	98.71 248	97.88 160	96.32 277	98.66 276	96.33 245	99.23 86	98.51 224	97.48 119	99.40 324	97.16 131	99.46 207	99.02 240

AUN-MVS		96.24 274	95.45 283	98.60 183	98.70 252	97.22 203	97.38 210	97.65 314	95.95 259	95.53 339	97.96 277	82.11 346	99.79 186	96.31 207	97.44 330	98.80 276

our_test_3		97.39 214	97.73 179	96.34 307	98.70 252	89.78 345	94.61 337	98.97 230	96.50 239	99.04 114	98.85 164	95.98 199	99.84 125	97.26 127	99.67 140	99.41 145

ppachtmachnet_test		97.50 203	97.74 177	96.78 301	98.70 252	91.23 341	94.55 339	99.05 212	96.36 244	99.21 87	98.79 178	96.39 181	99.78 198	96.74 171	99.82 65	99.34 176

PCF-MVS	92.86 18	94.36 305	93.00 322	98.42 207	98.70 252	97.56 185	93.16 356	99.11 202	79.59 366	97.55 261	97.43 307	92.19 280	99.73 226	79.85 366	99.45 210	97.97 318
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ETV-MVS		98.03 161	97.86 171	98.56 192	98.69 256	98.07 139	97.51 201	99.50 60	98.10 132	97.50 266	95.51 347	98.41 41	99.88 70	96.27 210	99.24 243	97.71 333

test_prior3		97.48 207	97.00 225	98.95 136	98.69 256	97.95 155	95.74 303	99.03 217	96.48 240	96.11 322	97.63 295	95.92 203	99.59 284	94.16 278	99.20 248	99.30 191

test_prior				98.95 136	98.69 256	97.95 155		99.03 217					99.59 284			99.30 191

agg_prior1		97.06 239	96.40 259	99.03 127	98.68 259	97.99 145	95.76 301	99.01 224	91.73 329	95.59 331	97.50 302	96.49 176	99.77 204	93.71 295	99.14 259	99.34 176

agg_prior					98.68 259	97.99 145		99.01 224		95.59 331			99.77 204

test_8					98.67 261	98.01 144	95.91 296	99.02 221	91.64 330	95.79 330	97.50 302	96.47 177	99.76 211

HQP-NCC					98.67 261		96.29 278		96.05 254	95.55 335

ACMP_Plane					98.67 261		96.29 278		96.05 254	95.55 335

CNVR-MVS		98.17 154	97.87 170	99.07 117	98.67 261	98.24 119	97.01 236	98.93 233	97.25 203	97.62 254	98.34 246	97.27 131	99.57 290	96.42 201	99.33 228	99.39 154

HQP-MVS		97.00 246	96.49 257	98.55 193	98.67 261	96.79 222	96.29 278	99.04 215	96.05 254	95.55 335	96.84 324	93.84 256	99.54 299	92.82 313	99.26 241	99.32 184

thres200		93.72 318	93.14 320	95.46 327	98.66 266	91.29 338	96.61 262	94.63 349	97.39 189	96.83 301	93.71 364	79.88 349	99.56 293	82.40 363	98.13 316	95.54 362

wuyk23d		96.06 276	97.62 188	91.38 349	98.65 267	98.57 95	98.85 67	96.95 329	96.86 227	99.90 4	99.16 86	99.18 11	98.40 362	89.23 348	99.77 90	77.18 367

NCCC		97.86 177	97.47 199	99.05 124	98.61 268	98.07 139	96.98 238	98.90 239	97.63 161	97.04 287	97.93 278	95.99 198	99.66 261	95.31 250	98.82 289	99.43 139

DeepC-MVS_fast	96.85 6	98.30 138	98.15 146	98.75 167	98.61 268	97.23 201	97.76 174	99.09 204	97.31 197	98.75 166	98.66 200	97.56 107	99.64 268	96.10 220	99.55 184	99.39 154
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
thisisatest0515		94.12 312	93.16 319	96.97 291	98.60 270	92.90 315	93.77 352	90.61 366	94.10 301	96.91 293	95.87 342	74.99 363	99.80 172	94.52 267	99.12 265	98.20 308

GA-MVS		95.86 281	95.32 289	97.49 270	98.60 270	94.15 288	93.83 351	97.93 307	95.49 271	96.68 305	97.42 308	83.21 337	99.30 337	96.22 212	98.55 304	99.01 241

OPU-MVS				98.82 153	98.59 272	98.30 115	98.10 133				98.52 223	98.18 59	98.75 360	94.62 264	99.48 205	99.41 145

MSLP-MVS++		98.02 163	98.14 148	97.64 258	98.58 273	95.19 264	97.48 203	99.23 169	97.47 176	97.90 236	98.62 211	97.04 142	98.81 359	97.55 112	99.41 215	98.94 255

test12				98.93 139	98.58 273	97.83 165		98.66 276		96.53 311		95.51 216	99.69 241		99.13 262	99.27 198

CL-MVSNet_2432*1600		97.44 211	97.22 214	98.08 233	98.57 275	95.78 248	94.30 344	98.79 262	96.58 238	98.60 183	98.19 258	94.74 240	99.64 268	96.41 202	98.84 287	98.82 268

CS-MVS		98.16 156	98.22 135	97.97 241	98.56 276	97.01 216	98.10 133	99.70 14	97.45 183	97.29 277	97.19 316	97.72 92	99.80 172	98.37 69	99.62 154	97.11 345

PS-MVSNAJ		97.08 237	97.39 202	96.16 314	98.56 276	92.46 322	95.24 319	98.85 252	97.25 203	97.49 267	95.99 339	98.07 66	99.90 49	96.37 203	98.67 298	96.12 358

CNLPA		97.17 232	96.71 243	98.55 193	98.56 276	98.05 142	96.33 276	98.93 233	96.91 225	97.06 286	97.39 309	94.38 247	99.45 320	91.66 328	99.18 254	98.14 311

xiu_mvs_v2_base		97.16 233	97.49 195	96.17 312	98.54 279	92.46 322	95.45 314	98.84 253	97.25 203	97.48 268	96.49 330	98.31 49	99.90 49	96.34 206	98.68 297	96.15 357

alignmvs		97.35 216	96.88 233	98.78 162	98.54 279	98.09 133	97.71 178	97.69 313	99.20 49	97.59 257	95.90 341	88.12 307	99.55 296	98.18 79	98.96 283	98.70 287

Effi-MVS+		98.02 163	97.82 173	98.62 180	98.53 281	97.19 207	97.33 214	99.68 16	97.30 198	96.68 305	97.46 306	98.56 34	99.80 172	96.63 181	98.20 311	98.86 265

ETH3D cwj APD-0.16		97.55 201	97.00 225	99.19 97	98.51 282	98.64 87	96.85 248	99.13 198	94.19 299	97.65 252	98.40 236	95.78 207	99.81 163	93.37 305	99.16 255	99.12 227

baseline1		95.96 279	95.44 284	97.52 269	98.51 282	93.99 294	98.39 108	96.09 341	98.21 122	98.40 209	97.76 287	86.88 309	99.63 271	95.42 248	89.27 367	98.95 251

MVS_Test		98.18 152	98.36 117	97.67 254	98.48 284	94.73 274	98.18 124	99.02 221	97.69 157	98.04 231	99.11 96	97.22 137	99.56 293	98.57 58	98.90 286	98.71 285

BH-RMVSNet		96.83 252	96.58 252	97.58 262	98.47 285	94.05 289	96.67 259	97.36 319	96.70 234	97.87 238	97.98 273	95.14 226	99.44 321	90.47 344	98.58 303	99.25 202

canonicalmvs		98.34 135	98.26 130	98.58 185	98.46 286	97.82 168	98.96 59	99.46 78	99.19 53	97.46 269	95.46 349	98.59 32	99.46 318	98.08 85	98.71 295	98.46 297

MVS-HIRNet		94.32 306	95.62 277	90.42 350	98.46 286	75.36 373	96.29 278	89.13 370	95.25 277	95.38 341	99.75 7	92.88 273	99.19 346	94.07 285	99.39 218	96.72 351

PHI-MVS		98.29 141	97.95 163	99.34 73	98.44 288	99.16 42	98.12 130	99.38 101	96.01 257	98.06 228	98.43 234	97.80 87	99.67 253	95.69 238	99.58 173	99.20 211

DVP-MVS++.		98.90 54	98.70 65	99.51 45	98.43 289	99.15 47	99.43 10	99.32 128	98.17 128	99.26 78	99.02 115	98.18 59	99.88 70	97.07 140	99.45 210	99.49 106

MSC_two_6792asdad				99.32 77	98.43 289	98.37 110		98.86 249					99.89 59	97.14 135	99.60 163	99.71 26

No_MVS				99.32 77	98.43 289	98.37 110		98.86 249					99.89 59	97.14 135	99.60 163	99.71 26

Fast-Effi-MVS+-dtu		98.27 142	98.09 151	98.81 155	98.43 289	98.11 132	97.61 189	99.50 60	98.64 92	97.39 274	97.52 301	98.12 65	99.95 15	96.90 157	98.71 295	98.38 303

OpenMVS_ROB	95.38 14	95.84 282	95.18 293	97.81 247	98.41 293	97.15 211	97.37 211	98.62 279	83.86 362	98.65 175	98.37 242	94.29 249	99.68 250	88.41 350	98.62 301	96.60 352

DeepPCF-MVS	96.93 5	98.32 136	98.01 159	99.23 93	98.39 294	98.97 65	95.03 324	99.18 182	96.88 226	99.33 63	98.78 179	98.16 62	99.28 340	96.74 171	99.62 154	99.44 135

Patchmatch-test		96.55 263	96.34 261	97.17 283	98.35 295	93.06 311	98.40 107	97.79 309	97.33 194	98.41 205	98.67 197	83.68 336	99.69 241	95.16 252	99.31 231	98.77 279

AdaColmap		97.14 234	96.71 243	98.46 204	98.34 296	97.80 171	96.95 239	98.93 233	95.58 267	96.92 291	97.66 292	95.87 205	99.53 301	90.97 339	99.14 259	98.04 314

OpenMVS	96.65 7	97.09 236	96.68 245	98.32 215	98.32 297	97.16 210	98.86 66	99.37 105	89.48 348	96.29 320	99.15 90	96.56 172	99.90 49	92.90 310	99.20 248	97.89 320

MG-MVS		96.77 255	96.61 250	97.26 280	98.31 298	93.06 311	95.93 294	98.12 302	96.45 242	97.92 234	98.73 186	93.77 260	99.39 326	91.19 338	99.04 272	99.33 182

test_yl		96.69 257	96.29 263	97.90 242	98.28 299	95.24 261	97.29 217	97.36 319	98.21 122	98.17 216	97.86 280	86.27 313	99.55 296	94.87 258	98.32 307	98.89 261

DCV-MVSNet		96.69 257	96.29 263	97.90 242	98.28 299	95.24 261	97.29 217	97.36 319	98.21 122	98.17 216	97.86 280	86.27 313	99.55 296	94.87 258	98.32 307	98.89 261

CHOSEN 280x420		95.51 290	95.47 281	95.65 322	98.25 301	88.27 351	93.25 355	98.88 242	93.53 309	94.65 347	97.15 320	86.17 315	99.93 28	97.41 120	99.93 25	98.73 284

SCA		96.41 269	96.66 248	95.67 320	98.24 302	88.35 350	95.85 299	96.88 332	96.11 252	97.67 251	98.67 197	93.10 268	99.85 108	94.16 278	99.22 245	98.81 271

DeepMVS_CX				93.44 345	98.24 302	94.21 286		94.34 350	64.28 368	91.34 364	94.87 359	89.45 298	92.77 370	77.54 368	93.14 364	93.35 365

MS-PatchMatch		97.68 192	97.75 176	97.45 272	98.23 304	93.78 303	97.29 217	98.84 253	96.10 253	98.64 176	98.65 202	96.04 192	99.36 329	96.84 163	99.14 259	99.20 211

BH-w/o		95.13 296	94.89 300	95.86 316	98.20 305	91.31 337	95.65 306	97.37 318	93.64 307	96.52 312	95.70 344	93.04 271	99.02 352	88.10 351	95.82 354	97.24 343

mvs_anonymous		97.83 185	98.16 144	96.87 296	98.18 306	91.89 329	97.31 216	98.90 239	97.37 191	98.83 154	99.46 43	96.28 187	99.79 186	98.90 38	98.16 314	98.95 251

miper_lstm_enhance		97.18 231	97.16 217	97.25 281	98.16 307	92.85 316	95.15 322	99.31 134	97.25 203	98.74 168	98.78 179	90.07 292	99.78 198	97.19 129	99.80 77	99.11 229

ET-MVSNet_ETH3D		94.30 308	93.21 318	97.58 262	98.14 308	94.47 281	94.78 330	93.24 360	94.72 286	89.56 366	95.87 342	78.57 358	99.81 163	96.91 152	97.11 340	98.46 297

ADS-MVSNet2		95.43 291	94.98 297	96.76 302	98.14 308	91.74 330	97.92 156	97.76 310	90.23 342	96.51 313	98.91 145	85.61 320	99.85 108	92.88 311	96.90 341	98.69 288

ADS-MVSNet		95.24 294	94.93 299	96.18 311	98.14 308	90.10 344	97.92 156	97.32 322	90.23 342	96.51 313	98.91 145	85.61 320	99.74 222	92.88 311	96.90 341	98.69 288

cl_fuxian		97.36 215	97.37 204	97.31 277	98.09 311	93.25 309	95.01 325	99.16 191	97.05 218	98.77 164	98.72 188	92.88 273	99.64 268	96.93 151	99.76 100	99.05 233

FMVSNet3		97.50 203	97.24 213	98.29 219	98.08 312	95.83 246	97.86 163	98.91 238	97.89 146	98.95 130	98.95 140	87.06 308	99.81 163	97.77 103	99.69 129	99.23 206

PAPM		91.88 333	90.34 336	96.51 304	98.06 313	92.56 320	92.44 359	97.17 324	86.35 358	90.38 365	96.01 338	86.61 311	99.21 345	70.65 369	95.43 356	97.75 330

Effi-MVS+-dtu		98.26 144	97.90 168	99.35 70	98.02 314	99.49 3	98.02 146	99.16 191	98.29 116	97.64 253	97.99 272	96.44 179	99.95 15	96.66 179	98.93 285	98.60 292

mvs-test1		97.83 185	97.48 198	98.89 145	98.02 314	99.20 33	97.20 225	99.16 191	98.29 116	96.46 317	97.17 318	96.44 179	99.92 35	96.66 179	97.90 324	97.54 339

eth_miper_zixun_eth		97.23 227	97.25 211	97.17 283	98.00 316	92.77 318	94.71 331	99.18 182	97.27 201	98.56 191	98.74 185	91.89 284	99.69 241	97.06 142	99.81 69	99.05 233

HY-MVS	95.94 13	95.90 280	95.35 288	97.55 266	97.95 317	94.79 272	98.81 69	96.94 330	92.28 325	95.17 343	98.57 218	89.90 294	99.75 218	91.20 337	97.33 337	98.10 312

UGNet		98.53 114	98.45 102	98.79 159	97.94 318	96.96 217	99.08 47	98.54 282	99.10 63	96.82 302	99.47 42	96.55 173	99.84 125	98.56 61	99.94 21	99.55 81
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
MAR-MVS		96.47 267	95.70 274	98.79 159	97.92 319	99.12 56	98.28 115	98.60 280	92.16 327	95.54 338	96.17 337	94.77 239	99.52 305	89.62 347	98.23 309	97.72 332
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
MVSTER		96.86 251	96.55 255	97.79 248	97.91 320	94.21 286	97.56 195	98.87 244	97.49 175	99.06 107	99.05 108	80.72 347	99.80 172	98.44 65	99.82 65	99.37 164

API-MVS		97.04 242	96.91 232	97.42 274	97.88 321	98.23 123	98.18 124	98.50 285	97.57 167	97.39 274	96.75 326	96.77 161	99.15 349	90.16 345	99.02 276	94.88 363

MVS_0304		97.64 195	97.35 206	98.52 197	97.87 322	96.69 227	98.59 84	98.05 305	97.44 185	93.74 358	98.85 164	93.69 262	99.88 70	98.11 81	99.81 69	98.98 246

miper_ehance_all_eth		97.06 239	97.03 223	97.16 285	97.83 323	93.06 311	94.66 334	99.09 204	95.99 258	98.69 170	98.45 233	92.73 276	99.61 279	96.79 165	99.03 273	98.82 268

cl-mvsnet____		97.02 243	96.83 237	97.58 262	97.82 324	94.04 290	94.66 334	99.16 191	97.04 219	98.63 177	98.71 189	88.68 303	99.69 241	97.00 144	99.81 69	99.00 244

cl-mvsnet1		97.02 243	96.84 236	97.58 262	97.82 324	94.03 291	94.66 334	99.16 191	97.04 219	98.63 177	98.71 189	88.69 302	99.69 241	97.00 144	99.81 69	99.01 241

CANet		97.87 176	97.76 175	98.19 226	97.75 326	95.51 253	96.76 254	99.05 212	97.74 154	96.93 290	98.21 256	95.59 213	99.89 59	97.86 99	99.93 25	99.19 216

PVSNet_0	89.98 21	91.15 334	90.30 337	93.70 342	97.72 327	84.34 367	90.24 362	97.42 317	90.20 345	93.79 356	93.09 365	90.90 288	98.89 358	86.57 355	72.76 369	97.87 322

CR-MVSNet		96.28 272	95.95 269	97.28 279	97.71 328	94.22 284	98.11 131	98.92 236	92.31 324	96.91 293	99.37 54	85.44 323	99.81 163	97.39 121	97.36 335	97.81 326

RPMNet		97.02 243	96.93 228	97.30 278	97.71 328	94.22 284	98.11 131	99.30 144	99.37 35	96.91 293	99.34 60	86.72 310	99.87 87	97.53 115	97.36 335	97.81 326

pmmvs3		95.03 298	94.40 304	96.93 292	97.70 330	92.53 321	95.08 323	97.71 312	88.57 353	97.71 248	98.08 268	79.39 354	99.82 150	96.19 214	99.11 266	98.43 301

baseline2		93.73 317	92.83 323	96.42 306	97.70 330	91.28 339	96.84 250	89.77 369	93.96 305	92.44 361	95.93 340	79.14 355	99.77 204	92.94 309	96.76 345	98.21 307

tpm		94.67 302	94.34 306	95.66 321	97.68 332	88.42 349	97.88 160	94.90 347	94.46 291	96.03 327	98.56 219	78.66 356	99.79 186	95.88 226	95.01 358	98.78 278

CANet_DTU		97.26 223	97.06 222	97.84 245	97.57 333	94.65 278	96.19 284	98.79 262	97.23 209	95.14 344	98.24 253	93.22 265	99.84 125	97.34 123	99.84 56	99.04 237

tpm2		93.09 324	92.58 325	94.62 334	97.56 334	86.53 357	97.66 183	95.79 344	86.15 359	94.07 354	98.23 255	75.95 361	99.53 301	90.91 341	96.86 344	97.81 326

TR-MVS		95.55 288	95.12 295	96.86 299	97.54 335	93.94 295	96.49 268	96.53 336	94.36 296	97.03 288	96.61 328	94.26 250	99.16 348	86.91 354	96.31 349	97.47 341

1314		95.74 284	95.60 278	96.17 312	97.53 336	92.75 319	98.07 137	98.31 293	91.22 337	94.25 350	96.68 327	95.53 214	99.03 351	91.64 330	97.18 338	96.74 350

CostFormer		93.97 314	93.78 311	94.51 335	97.53 336	85.83 360	97.98 152	95.96 342	89.29 350	94.99 346	98.63 209	78.63 357	99.62 273	94.54 266	96.50 346	98.09 313

FMVSNet5		96.01 277	95.20 292	98.41 208	97.53 336	96.10 238	98.74 70	99.50 60	97.22 212	98.03 232	99.04 111	69.80 367	99.88 70	97.27 126	99.71 118	99.25 202

PMMVS		96.51 264	95.98 268	98.09 230	97.53 336	95.84 245	94.92 327	98.84 253	91.58 332	96.05 326	95.58 345	95.68 210	99.66 261	95.59 244	98.09 318	98.76 281

PAPR		95.29 292	94.47 302	97.75 251	97.50 340	95.14 266	94.89 328	98.71 274	91.39 336	95.35 342	95.48 348	94.57 242	99.14 350	84.95 357	97.37 333	98.97 250

PatchT		96.65 260	96.35 260	97.54 267	97.40 341	95.32 259	97.98 152	96.64 335	99.33 39	96.89 297	99.42 49	84.32 331	99.81 163	97.69 111	97.49 328	97.48 340

tpm cat1		93.29 322	93.13 321	93.75 341	97.39 342	84.74 363	97.39 209	97.65 314	83.39 364	94.16 351	98.41 235	82.86 340	99.39 326	91.56 332	95.35 357	97.14 344

PatchmatchNet		95.58 287	95.67 276	95.30 329	97.34 343	87.32 354	97.65 185	96.65 334	95.30 276	97.07 285	98.69 193	84.77 326	99.75 218	94.97 256	98.64 299	98.83 267
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
RRT_test8_iter05		95.24 294	95.13 294	95.57 323	97.32 344	87.02 356	97.99 150	99.41 94	98.06 134	99.12 96	99.05 108	66.85 372	99.85 108	98.93 37	99.47 206	99.84 8

Patchmtry		97.35 216	96.97 227	98.50 201	97.31 345	96.47 230	98.18 124	98.92 236	98.95 80	98.78 161	99.37 54	85.44 323	99.85 108	95.96 224	99.83 62	99.17 222

LS3D		98.63 95	98.38 115	99.36 65	97.25 346	99.38 6	99.12 46	99.32 128	99.21 46	98.44 201	98.88 157	97.31 127	99.80 172	96.58 183	99.34 227	98.92 257

IB-MVS	91.63 19	92.24 331	90.90 335	96.27 309	97.22 347	91.24 340	94.36 343	93.33 359	92.37 323	92.24 362	94.58 360	66.20 374	99.89 59	93.16 308	94.63 360	97.66 334
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
tpmrst		95.07 297	95.46 282	93.91 340	97.11 348	84.36 366	97.62 187	96.96 328	94.98 280	96.35 319	98.80 176	85.46 322	99.59 284	95.60 243	96.23 350	97.79 329

MDTV_nov1_ep13			95.22 291		97.06 349	83.20 368	97.74 176	96.16 339	94.37 295	96.99 289	98.83 170	83.95 334	99.53 301	93.90 289	97.95 323

MVS		93.19 323	92.09 327	96.50 305	96.91 350	94.03 291	98.07 137	98.06 304	68.01 367	94.56 349	96.48 331	95.96 201	99.30 337	83.84 359	96.89 343	96.17 355

E-PMN		94.17 310	94.37 305	93.58 343	96.86 351	85.71 361	90.11 363	97.07 326	98.17 128	97.82 243	97.19 316	84.62 328	98.94 355	89.77 346	97.68 327	96.09 359

JIA-IIPM		95.52 289	95.03 296	97.00 288	96.85 352	94.03 291	96.93 242	95.82 343	99.20 49	94.63 348	99.71 12	83.09 338	99.60 280	94.42 272	94.64 359	97.36 342

EMVS		93.83 316	94.02 308	93.23 347	96.83 353	84.96 362	89.77 364	96.32 338	97.92 143	97.43 272	96.36 336	86.17 315	98.93 356	87.68 352	97.73 326	95.81 360

cl-mvsnet2		95.79 283	95.39 287	96.98 290	96.77 354	92.79 317	94.40 342	98.53 283	94.59 288	97.89 237	98.17 259	82.82 341	99.24 342	96.37 203	99.03 273	98.92 257

dp		93.47 320	93.59 314	93.13 348	96.64 355	81.62 371	97.66 183	96.42 337	92.80 319	96.11 322	98.64 205	78.55 359	99.59 284	93.31 306	92.18 366	98.16 310

test-LLR		93.90 315	93.85 309	94.04 338	96.53 356	84.62 364	94.05 348	92.39 362	96.17 249	94.12 352	95.07 351	82.30 342	99.67 253	95.87 229	98.18 312	97.82 324

test-mter		92.33 330	91.76 333	94.04 338	96.53 356	84.62 364	94.05 348	92.39 362	94.00 304	94.12 352	95.07 351	65.63 375	99.67 253	95.87 229	98.18 312	97.82 324

TESTMET0.1,1		92.19 332	91.77 332	93.46 344	96.48 358	82.80 369	94.05 348	91.52 365	94.45 293	94.00 355	94.88 357	66.65 373	99.56 293	95.78 234	98.11 317	98.02 315

DWT-MVSNet_test		92.75 327	92.05 328	94.85 332	96.48 358	87.21 355	97.83 166	94.99 346	92.22 326	92.72 360	94.11 363	70.75 366	99.46 318	95.01 254	94.33 362	97.87 322

miper_enhance_ethall		96.01 277	95.74 272	96.81 300	96.41 360	92.27 326	93.69 353	98.89 241	91.14 339	98.30 211	97.35 314	90.58 289	99.58 289	96.31 207	99.03 273	98.60 292

tpmvs		95.02 299	95.25 290	94.33 336	96.39 361	85.87 358	98.08 136	96.83 333	95.46 272	95.51 340	98.69 193	85.91 318	99.53 301	94.16 278	96.23 350	97.58 337

CMPMVS	75.91 23	96.29 271	95.44 284	98.84 151	96.25 362	98.69 86	97.02 235	99.12 200	88.90 351	97.83 241	98.86 161	89.51 296	98.90 357	91.92 325	99.51 195	98.92 257
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 303	93.69 312	96.99 289	96.05 363	93.61 307	94.97 326	93.49 357	96.17 249	97.57 260	94.88 357	82.30 342	99.01 354	93.60 298	94.17 363	98.37 305

EPMVS		93.72 318	93.27 317	95.09 331	96.04 364	87.76 352	98.13 128	85.01 372	94.69 287	96.92 291	98.64 205	78.47 360	99.31 335	95.04 253	96.46 347	98.20 308

cascas		94.79 301	94.33 307	96.15 315	96.02 365	92.36 325	92.34 360	99.26 161	85.34 361	95.08 345	94.96 356	92.96 272	98.53 361	94.41 275	98.59 302	97.56 338

RRT_MVS		97.07 238	96.57 253	98.58 185	95.89 366	96.33 233	97.36 212	98.77 265	97.85 149	99.08 104	99.12 94	82.30 342	99.96 8	98.82 44	99.90 44	99.45 130

gg-mvs-nofinetune		92.37 329	91.20 334	95.85 317	95.80 367	92.38 324	99.31 20	81.84 374	99.75 5	91.83 363	99.74 8	68.29 368	99.02 352	87.15 353	97.12 339	96.16 356

gm-plane-assit					94.83 368	81.97 370			88.07 355		94.99 354		99.60 280	91.76 327

GG-mvs-BLEND				94.76 333	94.54 369	92.13 328	99.31 20	80.47 375		88.73 368	91.01 367	67.59 371	98.16 364	82.30 364	94.53 361	93.98 364

EPNet_dtu		94.93 300	94.78 301	95.38 328	93.58 370	87.68 353	96.78 252	95.69 345	97.35 193	89.14 367	98.09 267	88.15 306	99.49 311	94.95 257	99.30 234	98.98 246
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
KD-MVS_2432*1600		92.87 325	91.99 329	95.51 325	91.37 371	89.27 346	94.07 346	98.14 300	95.42 273	97.25 279	96.44 333	67.86 369	99.24 342	91.28 335	96.08 352	98.02 315

miper_refine_blended		92.87 325	91.99 329	95.51 325	91.37 371	89.27 346	94.07 346	98.14 300	95.42 273	97.25 279	96.44 333	67.86 369	99.24 342	91.28 335	96.08 352	98.02 315

EPNet		96.14 275	95.44 284	98.25 222	90.76 373	95.50 254	97.92 156	94.65 348	98.97 76	92.98 359	98.85 164	89.12 299	99.87 87	95.99 222	99.68 134	99.39 154
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_method		79.78 335	79.50 338	80.62 351	80.21 374	45.76 376	70.82 365	98.41 290	31.08 370	80.89 371	97.71 289	84.85 325	97.37 365	91.51 333	80.03 368	98.75 282

tmp_tt		78.77 336	78.73 339	78.90 352	58.45 375	74.76 375	94.20 345	78.26 376	39.16 369	86.71 369	92.82 366	80.50 348	75.19 371	86.16 356	92.29 365	86.74 366

testmvs		17.12 338	20.53 341	6.87 354	12.05 376	4.20 378	93.62 354	6.73 377	4.62 372	10.41 372	24.33 369	8.28 377	3.56 373	9.69 371	15.07 370	12.86 369

test123		17.04 339	20.11 342	7.82 353	10.25 377	4.91 377	94.80 329	4.47 378	4.93 371	10.00 373	24.28 370	9.69 376	3.64 372	10.14 370	12.43 371	14.92 368

eth-test2					0.00 378

eth-test					0.00 378

uanet_test		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

cdsmvs_eth3d_5k		24.66 337	32.88 340	0.00 355	0.00 378	0.00 379	0.00 366	99.10 203	0.00 373	0.00 374	97.58 297	99.21 10	0.00 374	0.00 372	0.00 372	0.00 370

pcd_1.5k_mvsjas		8.17 340	10.90 343	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	98.07 66	0.00 374	0.00 372	0.00 372	0.00 370

sosnet-low-res		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

sosnet		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

uncertanet		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

Regformer		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

ab-mvs-re		8.12 341	10.83 344	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	97.48 304	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

uanet		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

PC_three_1452									93.27 312	99.40 52	98.54 220	98.22 55	97.00 366	95.17 251	99.45 210	99.49 106

test_241102_TWO								99.30 144	98.03 135	99.26 78	99.02 115	97.51 113	99.88 70	96.91 152	99.60 163	99.66 36

test_0728_THIRD									98.17 128	99.08 104	99.02 115	97.89 79	99.88 70	97.07 140	99.71 118	99.70 31

GSMVS																98.81 271

sam_mvs1												84.74 327				98.81 271

sam_mvs												84.29 333

MTGPA								99.20 173

test_post1							97.59 192				20.48 372	83.07 339	99.66 261	94.16 278

test_post											21.25 371	83.86 335	99.70 237

patchmatchnet-post											98.77 181	84.37 330	99.85 108

MTMP							97.93 155	91.91 364

test9_res														93.28 307	99.15 258	99.38 161

agg_prior2														92.50 321	99.16 255	99.37 164

test_prior4						97.97 150	95.86 297

test_prior2							95.74 303		96.48 240	96.11 322	97.63 295	95.92 203		94.16 278	99.20 248

旧先验2							95.76 301		88.56 354	97.52 264			99.66 261	94.48 268

新几何2							95.93 294

无先验							95.74 303	98.74 271	89.38 349				99.73 226	92.38 322		99.22 210

原ACMM2							95.53 310

testdata2													99.79 186	92.80 315

segment_acmp												97.02 145

testdata1							95.44 315		96.32 246

plane_prior5								99.27 156					99.70 237	94.42 272	99.51 195	99.45 130

plane_prior4											97.98 273

plane_prior3						97.78 172			97.41 187	97.79 244

plane_prior2							97.77 172		98.20 125

plane_prior						97.65 181	97.07 234		96.72 232						99.36 223

n2								0.00 379

nn								0.00 379

door-mid								99.57 35

test11								98.87 244

door								99.41 94

HQP5-MVS						96.79 222

BP-MVS														92.82 313

HQP4-MVS										95.56 334			99.54 299			99.32 184

HQP3-MVS								99.04 215							99.26 241

HQP2-MVS												93.84 256

MDTV_nov1_ep13_2view						74.92 374	97.69 180		90.06 347	97.75 247		85.78 319		93.52 300		98.69 288

ACMMP++_ref															99.77 90

ACMMP++															99.68 134

Test By Simon												96.52 174

High-resolution multi-view benchmark