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 3	100.00 1	99.85 9

Anonymous20231211		99.71 2	99.70 3	99.74 2	99.97 2	99.52 2	99.74 4	99.82 4	99.73 6	99.91 4	99.89 2	99.27 9	99.94 20	99.02 49	99.94 33	99.75 21

Gipuma		99.03 45	99.16 41	98.64 154	99.94 3	98.51 81	99.32 17	99.75 8	99.58 21	98.60 172	99.62 28	98.22 52	99.51 297	97.70 112	99.73 118	97.89 290
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 24	99.31 28	99.53 32	99.91 4	98.98 49	99.63 6	99.58 36	99.44 30	99.78 10	99.76 6	96.39 172	99.92 34	99.44 26	99.92 49	99.68 30

pmmvs6		99.67 3	99.70 3	99.60 12	99.90 5	99.27 16	99.53 9	99.76 7	99.64 10	99.84 9	99.83 3	99.50 5	99.87 72	99.36 28	99.92 49	99.64 40

PS-MVSNAJss		99.46 14	99.49 12	99.35 61	99.90 5	98.15 100	99.20 35	99.65 20	99.48 25	99.92 3	99.71 14	98.07 61	99.96 8	99.53 21	100.00 1	99.93 1

ANet_high		99.57 9	99.67 5	99.28 70	99.89 7	98.09 104	99.14 44	99.93 1	99.82 2	99.93 2	99.81 4	99.17 14	99.94 20	99.31 30	100.00 1	99.82 10

anonymousdsp		99.51 12	99.47 15	99.62 6	99.88 8	99.08 46	99.34 15	99.69 15	98.93 83	99.65 23	99.72 11	98.93 20	99.95 13	99.11 44	100.00 1	99.82 10

v748		99.44 15	99.48 13	99.33 66	99.88 8	98.43 86	99.42 11	99.53 59	99.63 12	99.69 17	99.60 34	97.99 69	99.91 43	99.60 14	99.96 28	99.66 33

v7n		99.53 10	99.57 10	99.41 52	99.88 8	98.54 79	99.45 10	99.61 30	99.66 9	99.68 20	99.66 22	98.44 42	99.95 13	99.73 8	99.96 28	99.75 21

mvs_tets		99.63 5	99.67 5	99.49 43	99.88 8	98.61 71	99.34 15	99.71 12	99.27 45	99.90 5	99.74 8	99.68 3	99.97 3	99.55 20	99.99 11	99.88 5

pcd1.5k->3k		41.59 328	44.35 329	33.30 341	99.87 12	0.00 359	0.00 350	99.58 36	0.00 354	0.00 355	0.00 356	99.70 2	0.00 357	0.00 354	99.99 11	99.91 2

jajsoiax		99.58 8	99.61 7	99.48 44	99.87 12	98.61 71	99.28 29	99.66 19	99.09 68	99.89 8	99.68 19	99.53 4	99.97 3	99.50 22	99.99 11	99.87 6

v52		99.59 6	99.60 8	99.55 20	99.87 12	99.00 47	99.59 7	99.56 49	99.56 22	99.68 20	99.72 11	98.57 34	99.93 26	99.85 1	99.99 11	99.72 24

V4		99.59 6	99.60 8	99.55 20	99.87 12	99.00 47	99.59 7	99.56 49	99.56 22	99.68 20	99.72 11	98.57 34	99.93 26	99.85 1	99.99 11	99.72 24

test_djsdf		99.52 11	99.51 11	99.53 32	99.86 16	98.74 60	99.39 13	99.56 49	99.11 61	99.70 15	99.73 10	99.00 17	99.97 3	99.26 32	99.98 19	99.89 3

MIMVSNet1		99.38 23	99.32 27	99.55 20	99.86 16	99.19 24	99.41 12	99.59 34	99.59 19	99.71 14	99.57 39	97.12 124	99.90 47	99.21 38	99.87 68	99.54 86

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 18	99.85 18	99.11 41	99.90 1	99.78 5	99.63 12	99.78 10	99.67 21	99.48 6	99.81 142	99.30 31	99.97 23	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
SixPastTwentyTwo		98.75 75	98.62 86	99.16 84	99.83 19	97.96 121	99.28 29	98.20 272	99.37 36	99.70 15	99.65 25	92.65 263	99.93 26	99.04 48	99.84 73	99.60 52

Baseline_NR-MVSNet		98.98 53	98.86 53	99.36 56	99.82 20	98.55 76	97.47 205	99.57 43	99.37 36	99.21 94	99.61 30	96.76 152	99.83 117	98.06 93	99.83 79	99.71 27

wuykxyi23d		99.36 25	99.31 28	99.50 41	99.81 21	98.67 67	98.08 134	99.75 8	98.03 125	99.90 5	99.60 34	99.18 12	99.94 20	99.46 25	99.98 19	99.89 3

pm-mvs1		99.44 15	99.48 13	99.33 66	99.80 22	98.63 68	99.29 25	99.63 25	99.30 42	99.65 23	99.60 34	99.16 16	99.82 129	99.07 46	99.83 79	99.56 75

TransMVSNet (Re)		99.44 15	99.47 15	99.36 56	99.80 22	98.58 74	99.27 31	99.57 43	99.39 33	99.75 12	99.62 28	99.17 14	99.83 117	99.06 47	99.62 155	99.66 33

K. test v3		98.00 164	97.66 178	99.03 105	99.79 24	97.56 152	99.19 39	92.47 343	99.62 16	99.52 39	99.66 22	89.61 278	99.96 8	99.25 34	99.81 88	99.56 75

FC-MVSNet-test		99.27 29	99.25 34	99.34 64	99.77 25	98.37 90	99.30 24	99.57 43	99.61 18	99.40 60	99.50 46	97.12 124	99.85 88	99.02 49	99.94 33	99.80 13

XXY-MVS		99.14 37	99.15 43	99.10 92	99.76 26	97.74 143	98.85 72	99.62 28	98.48 106	99.37 64	99.49 49	98.75 25	99.86 77	98.20 88	99.80 92	99.71 27

TDRefinement		99.42 19	99.38 19	99.55 20	99.76 26	99.33 11	99.68 5	99.71 12	99.38 35	99.53 37	99.61 30	98.64 29	99.80 154	98.24 85	99.84 73	99.52 96

PEN-MVS		99.41 20	99.34 24	99.62 6	99.73 28	99.14 34	99.29 25	99.54 58	99.62 16	99.56 33	99.42 59	98.16 57	99.96 8	98.78 59	99.93 39	99.77 16

lessismore_v0				98.97 113	99.73 28	97.53 154		86.71 352		99.37 64	99.52 45	89.93 276	99.92 34	98.99 51	99.72 123	99.44 134

SteuartSystems-ACMMP		98.79 69	98.54 94	99.54 25	99.73 28	99.16 28	98.23 120	99.31 131	97.92 129	98.90 136	98.90 150	98.00 67	99.88 63	96.15 196	99.72 123	99.58 65
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 155	98.15 144	98.22 210	99.73 28	95.15 242	97.36 209	99.68 16	94.45 278	98.99 122	99.27 77	96.87 143	99.94 20	97.13 138	99.91 54	99.57 70

Vis-MVSNet		99.34 26	99.36 21	99.27 73	99.73 28	98.26 93	99.17 41	99.78 5	99.11 61	99.27 82	99.48 50	98.82 22	99.95 13	98.94 52	99.93 39	99.59 58
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ACMH	96.65 7	99.25 30	99.24 35	99.26 75	99.72 33	98.38 89	99.07 52	99.55 54	98.30 114	99.65 23	99.45 56	99.22 10	99.76 197	98.44 76	99.77 104	99.64 40
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PS-CasMVS		99.40 21	99.33 26	99.62 6	99.71 34	99.10 42	99.29 25	99.53 59	99.53 24	99.46 50	99.41 61	98.23 50	99.95 13	98.89 55	99.95 30	99.81 12

DTE-MVSNet		99.43 18	99.35 22	99.66 4	99.71 34	99.30 12	99.31 20	99.51 64	99.64 10	99.56 33	99.46 52	98.23 50	99.97 3	98.78 59	99.93 39	99.72 24

WR-MVS_H		99.33 27	99.22 36	99.65 5	99.71 34	99.24 19	99.32 17	99.55 54	99.46 28	99.50 44	99.34 70	97.30 109	99.93 26	98.90 53	99.93 39	99.77 16

HPM-MVS_fast		99.01 47	98.82 56	99.57 16	99.71 34	99.35 9	99.00 59	99.50 65	97.33 182	98.94 133	98.86 159	98.75 25	99.82 129	97.53 119	99.71 127	99.56 75

ACMH+	96.62 9	99.08 42	99.00 49	99.33 66	99.71 34	98.83 56	98.60 83	99.58 36	99.11 61	99.53 37	99.18 92	98.81 23	99.67 243	96.71 162	99.77 104	99.50 103

PMVS	91.26 20	97.86 174	97.94 162	97.65 239	99.71 34	97.94 124	98.52 91	98.68 254	98.99 75	97.52 248	99.35 68	97.41 103	98.18 347	91.59 302	99.67 147	96.82 326
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FIs		99.14 37	99.09 45	99.29 69	99.70 40	98.28 92	99.13 46	99.52 63	99.48 25	99.24 90	99.41 61	96.79 149	99.82 129	98.69 65	99.88 64	99.76 19

VPNet		98.87 62	98.83 55	99.01 109	99.70 40	97.62 151	98.43 111	99.35 117	99.47 27	99.28 80	99.05 122	96.72 154	99.82 129	98.09 91	99.36 204	99.59 58

MP-MVS-pluss		98.57 108	98.23 134	99.60 12	99.69 42	99.35 9	97.16 227	99.38 103	94.87 269	98.97 126	98.99 133	98.01 66	99.88 63	97.29 130	99.70 130	99.58 65
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CHOSEN 1792x2688		97.49 197	97.14 208	98.54 176	99.68 43	96.09 215	96.50 261	99.62 28	91.58 314	98.84 146	98.97 138	92.36 265	99.88 63	96.76 157	99.95 30	99.67 31

tfpnnormal		98.90 60	98.90 52	98.91 121	99.67 44	97.82 135	99.00 59	99.44 88	99.45 29	99.51 43	99.24 82	98.20 55	99.86 77	95.92 204	99.69 137	99.04 222

MPTG		98.79 69	98.52 96	99.61 9	99.67 44	99.36 7	97.33 210	99.20 163	98.83 87	98.89 138	98.90 150	96.98 134	99.92 34	97.16 134	99.70 130	99.56 75

MTAPA		98.88 61	98.64 84	99.61 9	99.67 44	99.36 7	98.43 111	99.20 163	98.83 87	98.89 138	98.90 150	96.98 134	99.92 34	97.16 134	99.70 130	99.56 75

CP-MVSNet		99.21 32	99.09 45	99.56 18	99.65 47	98.96 53	99.13 46	99.34 121	99.42 31	99.33 72	99.26 79	97.01 132	99.94 20	98.74 63	99.93 39	99.79 14

HPM-MVS		98.79 69	98.53 95	99.59 15	99.65 47	99.29 13	99.16 42	99.43 93	96.74 213	98.61 170	98.38 223	98.62 30	99.87 72	96.47 180	99.67 147	99.59 58

RPSCF		98.62 103	98.36 123	99.42 50	99.65 47	99.42 5	98.55 89	99.57 43	97.72 148	98.90 136	99.26 79	96.12 180	99.52 292	95.72 215	99.71 127	99.32 174

TSAR-MVS + MP.		98.63 98	98.49 102	99.06 101	99.64 50	97.90 127	98.51 95	98.94 216	96.96 204	99.24 90	98.89 155	97.83 76	99.81 142	96.88 149	99.49 195	99.48 116

PM-MVS		98.82 66	98.72 70	99.12 89	99.64 50	98.54 79	97.98 151	99.68 16	97.62 153	99.34 71	99.18 92	97.54 93	99.77 192	97.79 105	99.74 115	99.04 222

v13		99.24 31	99.39 18	98.77 140	99.63 52	96.79 184	99.24 33	99.65 20	99.39 33	99.62 27	99.70 16	97.50 95	99.84 103	99.78 5	100.00 1	99.67 31

EU-MVSNet		97.66 187	98.50 99	95.13 312	99.63 52	85.84 334	98.35 115	98.21 271	98.23 119	99.54 35	99.46 52	95.02 216	99.68 238	98.24 85	99.87 68	99.87 6

HyFIR lowres test		97.19 219	96.60 235	98.96 114	99.62 54	97.28 164	95.17 317	99.50 65	94.21 284	99.01 119	98.32 230	86.61 289	99.99 2	97.10 141	99.84 73	99.60 52

v12		99.21 32	99.37 20	98.74 148	99.60 55	96.72 189	99.19 39	99.65 20	99.35 39	99.62 27	99.69 17	97.43 102	99.83 117	99.76 6	100.00 1	99.66 33

v11		99.12 40	99.31 28	98.53 177	99.59 56	96.11 212	99.08 49	99.65 20	99.15 56	99.60 30	99.69 17	97.26 115	99.83 117	99.81 3	100.00 1	99.66 33

ACMMP_Plus		98.75 75	98.48 103	99.57 16	99.58 57	99.29 13	97.82 167	99.25 152	96.94 205	98.78 153	99.12 106	98.02 65	99.84 103	97.13 138	99.67 147	99.59 58

nrg030		99.40 21	99.35 22	99.54 25	99.58 57	99.13 37	98.98 62	99.48 74	99.68 7	99.46 50	99.26 79	98.62 30	99.73 217	99.17 43	99.92 49	99.76 19

VDDNet		98.21 150	97.95 160	99.01 109	99.58 57	97.74 143	99.01 55	97.29 292	99.67 8	98.97 126	99.50 46	90.45 275	99.80 154	97.88 102	99.20 227	99.48 116

V9		99.18 34	99.34 24	98.70 149	99.58 57	96.63 192	99.14 44	99.64 24	99.30 42	99.61 29	99.68 19	97.33 107	99.83 117	99.75 7	100.00 1	99.65 37

COLMAP_ROB	96.50 10	98.99 49	98.85 54	99.41 52	99.58 57	99.10 42	98.74 75	99.56 49	99.09 68	99.33 72	99.19 90	98.40 43	99.72 226	95.98 202	99.76 113	99.42 142
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
HSP-MVS		98.34 135	97.94 162	99.54 25	99.57 62	99.25 18	98.57 86	98.84 234	97.55 162	99.31 79	97.71 265	94.61 231	99.88 63	96.14 197	99.19 231	99.48 116

testing_2		98.93 57	98.99 50	98.76 142	99.57 62	97.03 176	97.85 164	99.13 186	98.46 107	99.44 54	99.44 57	98.22 52	99.74 212	98.85 56	99.94 33	99.51 98

testgi		98.32 137	98.39 119	98.13 214	99.57 62	95.54 232	97.78 168	99.49 71	97.37 179	99.19 95	97.65 269	98.96 19	99.49 299	96.50 179	98.99 254	99.34 169

MP-MVS		98.46 125	98.09 150	99.54 25	99.57 62	99.22 20	98.50 96	99.19 169	97.61 155	97.58 242	98.66 188	97.40 104	99.88 63	94.72 236	99.60 161	99.54 86

LPG-MVS_test		98.71 80	98.46 108	99.47 47	99.57 62	98.97 50	98.23 120	99.48 74	96.60 222	99.10 105	99.06 117	98.71 27	99.83 117	95.58 222	99.78 100	99.62 45

LGP-MVS_train				99.47 47	99.57 62	98.97 50		99.48 74	96.60 222	99.10 105	99.06 117	98.71 27	99.83 117	95.58 222	99.78 100	99.62 45

IS-MVSNet		98.19 152	97.90 166	99.08 95	99.57 62	97.97 119	99.31 20	98.32 268	99.01 74	98.98 124	99.03 127	91.59 270	99.79 174	95.49 224	99.80 92	99.48 116

V14		99.14 37	99.30 31	98.66 152	99.56 69	96.53 193	99.08 49	99.63 25	99.24 46	99.60 30	99.66 22	97.23 119	99.82 129	99.73 8	100.00 1	99.65 37

test_0402		98.76 74	98.71 71	98.93 118	99.56 69	98.14 102	98.45 110	99.34 121	99.28 44	98.95 129	98.91 147	98.34 46	99.79 174	95.63 219	99.91 54	98.86 244

EPP-MVSNet		98.30 139	98.04 156	99.07 96	99.56 69	97.83 132	99.29 25	98.07 276	99.03 72	98.59 173	99.13 105	92.16 267	99.90 47	96.87 150	99.68 142	99.49 110

ACMMP		98.75 75	98.50 99	99.52 37	99.56 69	99.16 28	98.87 69	99.37 107	97.16 199	98.82 150	99.01 130	97.71 82	99.87 72	96.29 188	99.69 137	99.54 86
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
no-one		97.98 167	98.10 149	97.61 242	99.55 73	93.82 279	96.70 251	98.94 216	96.18 233	99.52 39	99.41 61	95.90 194	99.81 142	96.72 159	99.99 11	99.20 201

FMVSNet1		99.17 35	99.17 39	99.17 81	99.55 73	98.24 94	99.20 35	99.44 88	99.21 47	99.43 55	99.55 41	97.82 79	99.86 77	98.42 78	99.89 63	99.41 144

Vis-MVSNet (Re-imp)		97.46 201	97.16 206	98.34 201	99.55 73	96.10 213	98.94 64	98.44 264	98.32 113	98.16 195	98.62 199	88.76 283	99.73 217	93.88 260	99.79 96	99.18 207

ACMM	96.08 12	98.91 59	98.73 67	99.48 44	99.55 73	99.14 34	98.07 136	99.37 107	97.62 153	99.04 116	98.96 141	98.84 21	99.79 174	97.43 125	99.65 152	99.49 110
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mPP-MVS		98.64 96	98.34 126	99.54 25	99.54 77	99.17 26	98.63 80	99.24 156	97.47 168	98.09 200	98.68 184	97.62 88	99.89 56	96.22 190	99.62 155	99.57 70

XVG-ACMP-BASELINE		98.56 109	98.34 126	99.22 79	99.54 77	98.59 73	97.71 176	99.46 82	97.25 190	98.98 124	98.99 133	97.54 93	99.84 103	95.88 205	99.74 115	99.23 195

region2R		98.69 87	98.40 117	99.54 25	99.53 79	99.17 26	98.52 91	99.31 131	97.46 173	98.44 184	98.51 213	97.83 76	99.88 63	96.46 181	99.58 168	99.58 65

PGM-MVS		98.66 93	98.37 122	99.55 20	99.53 79	99.18 25	98.23 120	99.49 71	97.01 203	98.69 160	98.88 156	98.00 67	99.89 56	95.87 208	99.59 162	99.58 65

Patchmatch-RL test		97.26 213	97.02 210	97.99 226	99.52 81	95.53 233	96.13 280	99.71 12	97.47 168	99.27 82	99.16 98	84.30 308	99.62 261	97.89 100	99.77 104	98.81 249

v15		99.11 41	99.27 33	98.62 158	99.52 81	96.43 197	99.01 55	99.63 25	99.18 55	99.59 32	99.64 26	97.13 123	99.81 142	99.71 10	100.00 1	99.64 40

ACMMPR		98.70 82	98.42 115	99.54 25	99.52 81	99.14 34	98.52 91	99.31 131	97.47 168	98.56 177	98.54 211	97.75 81	99.88 63	96.57 171	99.59 162	99.58 65

Anonymous20231206		98.21 150	98.21 135	98.20 211	99.51 84	95.43 237	98.13 128	99.32 129	96.16 237	98.93 134	98.82 167	96.00 185	99.83 117	97.32 129	99.73 118	99.36 163

ACMP	95.32 15	98.41 129	98.09 150	99.36 56	99.51 84	98.79 59	97.68 179	99.38 103	95.76 247	98.81 152	98.82 167	98.36 45	99.82 129	94.75 233	99.77 104	99.48 116
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
AllTest		98.44 127	98.20 136	99.16 84	99.50 86	98.55 76	98.25 119	99.58 36	96.80 211	98.88 141	99.06 117	97.65 84	99.57 279	94.45 242	99.61 159	99.37 157

TestCases				99.16 84	99.50 86	98.55 76		99.58 36	96.80 211	98.88 141	99.06 117	97.65 84	99.57 279	94.45 242	99.61 159	99.37 157

v17		99.07 43	99.22 36	98.61 161	99.50 86	96.42 198	99.01 55	99.60 32	99.15 56	99.48 46	99.61 30	97.05 127	99.81 142	99.64 12	99.98 19	99.61 49

v16		99.07 43	99.22 36	98.61 161	99.50 86	96.42 198	99.01 55	99.60 32	99.15 56	99.46 50	99.61 30	97.04 128	99.81 142	99.64 12	99.97 23	99.61 49

XVG-OURS		98.53 118	98.34 126	99.11 90	99.50 86	98.82 58	95.97 284	99.50 65	97.30 186	99.05 113	98.98 136	99.35 7	99.32 321	95.72 215	99.68 142	99.18 207

EG-PatchMatch MVS		98.99 49	99.01 48	98.94 117	99.50 86	97.47 156	98.04 140	99.59 34	98.15 124	99.40 60	99.36 67	98.58 33	99.76 197	98.78 59	99.68 142	99.59 58

UA-Net		99.47 13	99.40 17	99.70 3	99.49 92	99.29 13	99.80 3	99.72 11	99.82 2	99.04 116	99.81 4	98.05 64	99.96 8	98.85 56	99.99 11	99.86 8

HFP-MVS		98.71 80	98.44 112	99.51 39	99.49 92	99.16 28	98.52 91	99.31 131	97.47 168	98.58 175	98.50 216	97.97 71	99.85 88	96.57 171	99.59 162	99.53 91

#test#		98.50 121	98.16 142	99.51 39	99.49 92	99.16 28	98.03 141	99.31 131	96.30 231	98.58 175	98.50 216	97.97 71	99.85 88	95.68 218	99.59 162	99.53 91

VPA-MVSNet		99.30 28	99.30 31	99.28 70	99.49 92	98.36 91	99.00 59	99.45 85	99.63 12	99.52 39	99.44 57	98.25 48	99.88 63	99.09 45	99.84 73	99.62 45

XVG-OURS-SEG-HR		98.49 122	98.28 132	99.14 87	99.49 92	98.83 56	96.54 260	99.48 74	97.32 184	99.11 103	98.61 201	99.33 8	99.30 324	96.23 189	98.38 283	99.28 185

114514_t		96.50 250	95.77 253	98.69 150	99.48 97	97.43 159	97.84 165	99.55 54	81.42 347	96.51 294	98.58 204	95.53 203	99.67 243	93.41 274	99.58 168	98.98 229

IterMVS-LS		98.55 113	98.70 74	98.09 216	99.48 97	94.73 249	97.22 220	99.39 100	98.97 78	99.38 62	99.31 74	96.00 185	99.93 26	98.58 68	99.97 23	99.60 52
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1neww		98.70 82	98.76 63	98.52 178	99.47 99	96.30 206	98.03 141	99.18 173	97.92 129	99.26 87	99.08 111	96.91 137	99.78 183	99.19 40	99.82 82	99.47 124

v7new		98.70 82	98.76 63	98.52 178	99.47 99	96.30 206	98.03 141	99.18 173	97.92 129	99.26 87	99.08 111	96.91 137	99.78 183	99.19 40	99.82 82	99.47 124

v8		99.01 47	99.16 41	98.57 168	99.47 99	96.31 204	98.90 67	99.47 80	99.03 72	99.52 39	99.57 39	96.93 136	99.81 142	99.60 14	99.98 19	99.60 52

v6		98.70 82	98.76 63	98.52 178	99.47 99	96.30 206	98.03 141	99.18 173	97.92 129	99.27 82	99.08 111	96.91 137	99.78 183	99.19 40	99.82 82	99.48 116

XVS		98.72 79	98.45 110	99.53 32	99.46 103	99.21 21	98.65 78	99.34 121	98.62 97	97.54 246	98.63 197	97.50 95	99.83 117	96.79 154	99.53 186	99.56 75

X-MVStestdata		94.32 294	92.59 311	99.53 32	99.46 103	99.21 21	98.65 78	99.34 121	98.62 97	97.54 246	45.85 351	97.50 95	99.83 117	96.79 154	99.53 186	99.56 75

test20.03		98.78 72	98.77 62	98.78 138	99.46 103	97.20 168	97.78 168	99.24 156	99.04 71	99.41 58	98.90 150	97.65 84	99.76 197	97.70 112	99.79 96	99.39 150

v18		99.02 46	99.17 39	98.57 168	99.45 106	96.31 204	98.94 64	99.58 36	99.06 70	99.43 55	99.58 38	96.91 137	99.80 154	99.60 14	99.97 23	99.59 58

abl_6		98.99 49	98.78 60	99.61 9	99.45 106	99.46 4	98.60 83	99.50 65	98.59 99	99.24 90	99.04 124	98.54 37	99.89 56	96.45 182	99.62 155	99.50 103

CSCG		98.68 90	98.50 99	99.20 80	99.45 106	98.63 68	98.56 87	99.57 43	97.87 141	98.85 144	98.04 251	97.66 83	99.84 103	96.72 159	99.81 88	99.13 215

v148		98.45 126	98.60 91	98.00 225	99.44 109	94.98 245	97.44 206	99.06 195	98.30 114	99.32 77	98.97 138	96.65 157	99.62 261	98.37 80	99.85 71	99.39 150

v10		98.97 54	99.11 44	98.55 173	99.44 109	96.21 210	98.90 67	99.55 54	98.73 93	99.48 46	99.60 34	96.63 158	99.83 117	99.70 11	99.99 11	99.61 49

V42		98.78 72	98.78 60	98.76 142	99.44 109	97.04 175	98.27 118	99.19 169	97.87 141	99.25 89	99.16 98	96.84 144	99.78 183	99.21 38	99.84 73	99.46 128

MDA-MVSNet-bldmvs		97.94 168	97.91 165	98.06 221	99.44 109	94.96 246	96.63 256	99.15 185	98.35 109	98.83 147	99.11 107	94.31 237	99.85 88	96.60 168	98.72 265	99.37 157

v7		98.67 92	98.73 67	98.50 183	99.43 113	96.21 210	98.00 149	99.31 131	97.58 157	99.17 99	99.18 92	96.63 158	99.80 154	99.42 27	99.88 64	99.48 116

v2v482		98.56 109	98.62 86	98.37 199	99.42 114	95.81 226	97.58 194	99.16 182	97.90 137	99.28 80	99.01 130	95.98 189	99.79 174	99.33 29	99.90 57	99.51 98

OPM-MVS		98.56 109	98.32 130	99.25 76	99.41 115	98.73 63	97.13 229	99.18 173	97.10 202	98.75 157	98.92 146	98.18 56	99.65 256	96.68 164	99.56 179	99.37 157

PMMVS2		98.07 160	98.08 153	98.04 223	99.41 115	94.59 255	94.59 328	99.40 98	97.50 165	98.82 150	98.83 164	96.83 145	99.84 103	97.50 121	99.81 88	99.71 27

v1141		98.63 98	98.70 74	98.41 192	99.39 117	95.96 219	97.64 184	99.21 159	97.92 129	99.35 68	99.08 111	96.61 161	99.78 183	99.25 34	99.90 57	99.50 103

divwei89l23v2f112		98.63 98	98.70 74	98.41 192	99.39 117	95.96 219	97.64 184	99.21 159	97.92 129	99.35 68	99.08 111	96.61 161	99.78 183	99.25 34	99.90 57	99.50 103

v1		98.63 98	98.70 74	98.41 192	99.39 117	95.96 219	97.64 184	99.20 163	97.92 129	99.36 66	99.07 116	96.63 158	99.78 183	99.25 34	99.90 57	99.50 103

TranMVSNet+NR-MVSNet		99.17 35	99.07 47	99.46 49	99.37 120	98.87 55	98.39 114	99.42 96	99.42 31	99.36 66	99.06 117	98.38 44	99.95 13	98.34 81	99.90 57	99.57 70

test_part2					99.36 121	99.10 42				99.05 113

ESAPD		98.25 147	97.83 170	99.50 41	99.36 121	99.10 42	97.25 215	99.28 141	96.66 219	99.05 113	98.71 179	97.56 90	99.86 77	93.00 279	99.57 172	99.53 91

v1144		98.60 105	98.66 82	98.41 192	99.36 121	95.90 222	97.58 194	99.34 121	97.51 164	99.27 82	99.15 102	96.34 175	99.80 154	99.47 24	99.93 39	99.51 98

CP-MVS		98.70 82	98.42 115	99.52 37	99.36 121	99.12 39	98.72 77	99.36 111	97.54 163	98.30 192	98.40 222	97.86 75	99.89 56	96.53 177	99.72 123	99.56 75

Test_1112_low_res		96.99 231	96.55 238	98.31 204	99.35 125	95.47 236	95.84 298	99.53 59	91.51 316	96.80 285	98.48 219	91.36 271	99.83 117	96.58 169	99.53 186	99.62 45

DeepC-MVS	97.60 4	98.97 54	98.93 51	99.10 92	99.35 125	97.98 118	98.01 148	99.46 82	97.56 161	99.54 35	99.50 46	98.97 18	99.84 103	98.06 93	99.92 49	99.49 110
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 212	96.86 218	98.58 166	99.34 127	96.32 203	96.75 248	99.58 36	93.14 295	96.89 280	97.48 279	92.11 268	99.86 77	96.91 146	99.54 182	99.57 70

1111		93.99 303	93.72 299	94.80 315	99.33 128	85.20 338	95.97 284	99.39 100	97.88 139	98.64 164	98.56 208	57.79 358	99.80 154	96.02 199	99.87 68	99.40 149

.test1245		79.71 326	84.30 327	65.96 340	99.33 128	85.20 338	95.97 284	99.39 100	97.88 139	98.64 164	98.56 208	57.79 358	99.80 154	96.02 199	15.07 352	12.86 353

CPTT-MVS		97.84 179	97.36 197	99.27 73	99.31 130	98.46 84	98.29 116	99.27 146	94.90 268	97.83 220	98.37 224	94.90 218	99.84 103	93.85 262	99.54 182	99.51 98

UnsupCasMVSNet_eth		97.89 170	97.60 183	98.75 144	99.31 130	97.17 171	97.62 188	99.35 117	98.72 94	98.76 156	98.68 184	92.57 264	99.74 212	97.76 110	95.60 336	99.34 169

pmmvs-eth3d		98.47 124	98.34 126	98.86 128	99.30 132	97.76 140	97.16 227	99.28 141	95.54 256	99.42 57	99.19 90	97.27 112	99.63 259	97.89 100	99.97 23	99.20 201

UnsupCasMVSNet_bld		97.30 210	96.92 214	98.45 189	99.28 133	96.78 188	96.20 278	99.27 146	95.42 259	98.28 193	98.30 231	93.16 254	99.71 227	94.99 229	97.37 316	98.87 243

semantic-postprocess				96.87 271	99.27 134	91.16 318		99.25 152	99.10 65	99.41 58	99.35 68	92.91 259	99.96 8	98.65 66	99.94 33	99.49 110

v1192		98.60 105	98.66 82	98.41 192	99.27 134	95.88 223	97.52 200	99.36 111	97.41 176	99.33 72	99.20 89	96.37 174	99.82 129	99.57 18	99.92 49	99.55 83

N_pmnet		97.63 189	97.17 205	98.99 112	99.27 134	97.86 130	95.98 283	93.41 335	95.25 261	99.47 49	98.90 150	95.63 200	99.85 88	96.91 146	99.73 118	99.27 186

FPMVS		93.44 310	92.23 315	97.08 261	99.25 137	97.86 130	95.61 305	97.16 294	92.90 297	93.76 340	98.65 190	75.94 347	95.66 350	79.30 349	97.49 313	97.73 301

new-patchmatchnet		98.35 134	98.74 66	97.18 259	99.24 138	92.23 299	96.42 267	99.48 74	98.30 114	99.69 17	99.53 44	97.44 101	99.82 129	98.84 58	99.77 104	99.49 110

testmv		98.51 120	98.47 105	98.61 161	99.24 138	96.53 193	96.66 254	99.73 10	98.56 105	99.50 44	99.23 86	97.24 117	99.87 72	96.16 195	99.93 39	99.44 134

MCST-MVS		98.00 164	97.63 181	99.10 92	99.24 138	98.17 99	96.89 241	98.73 251	95.66 248	97.92 207	97.70 266	97.17 122	99.66 251	96.18 194	99.23 223	99.47 124

UniMVSNet (Re)		98.87 62	98.71 71	99.35 61	99.24 138	98.73 63	97.73 175	99.38 103	98.93 83	99.12 102	98.73 177	96.77 150	99.86 77	98.63 67	99.80 92	99.46 128

jason		97.45 202	97.35 199	97.76 233	99.24 138	93.93 273	95.86 295	98.42 265	94.24 283	98.50 181	98.13 240	94.82 223	99.91 43	97.22 132	99.73 118	99.43 139
jason: jason.
IterMVS		97.73 182	98.11 148	96.57 281	99.24 138	90.28 319	95.52 309	99.21 159	98.86 85	99.33 72	99.33 72	93.11 255	99.94 20	98.49 74	99.94 33	99.48 116
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
view600		94.87 277	94.41 279	96.26 287	99.22 144	91.37 309	98.49 97	94.45 323	98.75 89	97.85 215	95.98 312	80.38 322	99.75 203	86.06 333	98.49 278	97.66 303

view800		94.87 277	94.41 279	96.26 287	99.22 144	91.37 309	98.49 97	94.45 323	98.75 89	97.85 215	95.98 312	80.38 322	99.75 203	86.06 333	98.49 278	97.66 303

conf0.05thres1000		94.87 277	94.41 279	96.26 287	99.22 144	91.37 309	98.49 97	94.45 323	98.75 89	97.85 215	95.98 312	80.38 322	99.75 203	86.06 333	98.49 278	97.66 303

tfpn		94.87 277	94.41 279	96.26 287	99.22 144	91.37 309	98.49 97	94.45 323	98.75 89	97.85 215	95.98 312	80.38 322	99.75 203	86.06 333	98.49 278	97.66 303

v1240		98.55 113	98.62 86	98.32 202	99.22 144	95.58 231	97.51 202	99.45 85	97.16 199	99.45 53	99.24 82	96.12 180	99.85 88	99.60 14	99.88 64	99.55 83

ITE_SJBPF				98.87 126	99.22 144	98.48 83		99.35 117	97.50 165	98.28 193	98.60 202	97.64 87	99.35 317	93.86 261	99.27 219	98.79 253

conf0.01		94.82 282	94.07 288	97.06 263	99.21 150	94.53 256	98.47 103	92.69 337	95.61 249	97.81 223	95.54 319	77.71 338	99.80 154	91.49 304	98.11 294	96.86 323

conf0.002		94.82 282	94.07 288	97.06 263	99.21 150	94.53 256	98.47 103	92.69 337	95.61 249	97.81 223	95.54 319	77.71 338	99.80 154	91.49 304	98.11 294	96.86 323

thresconf0.02		94.70 286	94.07 288	96.58 277	99.21 150	94.53 256	98.47 103	92.69 337	95.61 249	97.81 223	95.54 319	77.71 338	99.80 154	91.49 304	98.11 294	95.42 341

tfpn_n400		94.70 286	94.07 288	96.58 277	99.21 150	94.53 256	98.47 103	92.69 337	95.61 249	97.81 223	95.54 319	77.71 338	99.80 154	91.49 304	98.11 294	95.42 341

tfpnconf		94.70 286	94.07 288	96.58 277	99.21 150	94.53 256	98.47 103	92.69 337	95.61 249	97.81 223	95.54 319	77.71 338	99.80 154	91.49 304	98.11 294	95.42 341

tfpnview11		94.70 286	94.07 288	96.58 277	99.21 150	94.53 256	98.47 103	92.69 337	95.61 249	97.81 223	95.54 319	77.71 338	99.80 154	91.49 304	98.11 294	95.42 341

v144192		98.54 116	98.57 93	98.45 189	99.21 150	95.98 217	97.63 187	99.36 111	97.15 201	99.32 77	99.18 92	95.84 196	99.84 103	99.50 22	99.91 54	99.54 86

APDe-MVS		98.99 49	98.79 59	99.60 12	99.21 150	99.15 33	98.87 69	99.48 74	97.57 159	99.35 68	99.24 82	97.83 76	99.89 56	97.88 102	99.70 130	99.75 21

DP-MVS		98.93 57	98.81 58	99.28 70	99.21 150	98.45 85	98.46 109	99.33 126	99.63 12	99.48 46	99.15 102	97.23 119	99.75 203	97.17 133	99.66 151	99.63 44

v1921920		98.54 116	98.60 91	98.38 198	99.20 159	95.76 227	97.56 196	99.36 111	97.23 195	99.38 62	99.17 97	96.02 183	99.84 103	99.57 18	99.90 57	99.54 86

APD-MVS_3200maxsize		98.84 65	98.61 89	99.53 32	99.19 160	99.27 16	98.49 97	99.33 126	98.64 95	99.03 118	98.98 136	97.89 74	99.85 88	96.54 176	99.42 199	99.46 128

HQP_MVS		97.99 166	97.67 175	98.93 118	99.19 160	97.65 148	97.77 170	99.27 146	98.20 120	97.79 229	97.98 254	94.90 218	99.70 229	94.42 244	99.51 189	99.45 132

plane_prior7					99.19 160	97.87 129

ab-mvs		98.41 129	98.36 123	98.59 165	99.19 160	97.23 165	99.32 17	98.81 240	97.66 150	98.62 168	99.40 64	96.82 146	99.80 154	95.88 205	99.51 189	98.75 258

F-COLMAP		97.30 210	96.68 229	99.14 87	99.19 160	98.39 88	97.27 214	99.30 138	92.93 296	96.62 289	98.00 252	95.73 198	99.68 238	92.62 289	98.46 282	99.35 168

UniMVSNet_NR-MVSNet		98.86 64	98.68 79	99.40 54	99.17 165	98.74 60	97.68 179	99.40 98	99.14 59	99.06 108	98.59 203	96.71 155	99.93 26	98.57 70	99.77 104	99.53 91

LF4IMVS		97.90 169	97.69 174	98.52 178	99.17 165	97.66 147	97.19 224	99.47 80	96.31 230	97.85 215	98.20 239	96.71 155	99.52 292	94.62 237	99.72 123	98.38 278

DU-MVS		98.82 66	98.63 85	99.39 55	99.16 167	98.74 60	97.54 199	99.25 152	98.84 86	99.06 108	98.76 175	96.76 152	99.93 26	98.57 70	99.77 104	99.50 103

NR-MVSNet		98.95 56	98.82 56	99.36 56	99.16 167	98.72 65	99.22 34	99.20 163	99.10 65	99.72 13	98.76 175	96.38 173	99.86 77	98.00 98	99.82 82	99.50 103

MVS_111021_LR		98.30 139	98.12 147	98.83 131	99.16 167	98.03 112	96.09 281	99.30 138	97.58 157	98.10 199	98.24 235	98.25 48	99.34 318	96.69 163	99.65 152	99.12 216

DSMNet-mixed		97.42 204	97.60 183	96.87 271	99.15 170	91.46 306	98.54 90	99.12 188	92.87 298	97.58 242	99.63 27	96.21 177	99.90 47	95.74 214	99.54 182	99.27 186

pmmvs5		97.64 188	97.49 187	98.08 219	99.14 171	95.12 244	96.70 251	99.05 199	93.77 288	98.62 168	98.83 164	93.23 252	99.75 203	98.33 83	99.76 113	99.36 163

VDD-MVS		98.56 109	98.39 119	99.07 96	99.13 172	98.07 109	98.59 85	97.01 297	99.59 19	99.11 103	99.27 77	94.82 223	99.79 174	98.34 81	99.63 154	99.34 169

APD-MVS		98.10 157	97.67 175	99.42 50	99.11 173	98.93 54	97.76 172	99.28 141	94.97 266	98.72 159	98.77 173	97.04 128	99.85 88	93.79 263	99.54 182	99.49 110
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 87	98.71 71	98.62 158	99.10 174	96.37 202	97.23 217	98.87 228	99.20 50	99.19 95	98.99 133	97.30 109	99.85 88	98.77 62	99.79 96	99.65 37

EI-MVSNet		98.40 131	98.51 97	98.04 223	99.10 174	94.73 249	97.20 221	98.87 228	98.97 78	99.06 108	99.02 128	96.00 185	99.80 154	98.58 68	99.82 82	99.60 52

CVMVSNet		96.25 255	97.21 203	93.38 332	99.10 174	80.56 352	97.20 221	98.19 274	96.94 205	99.00 121	99.02 128	89.50 280	99.80 154	96.36 186	99.59 162	99.78 15

EI-MVSNet-Vis-set		98.68 90	98.70 74	98.63 156	99.09 177	96.40 200	97.23 217	98.86 232	99.20 50	99.18 98	98.97 138	97.29 111	99.85 88	98.72 64	99.78 100	99.64 40

HPM-MVS++		98.10 157	97.64 180	99.48 44	99.09 177	99.13 37	97.52 200	98.75 248	97.46 173	96.90 279	97.83 260	96.01 184	99.84 103	95.82 212	99.35 206	99.46 128

DP-MVS Recon		97.33 208	96.92 214	98.57 168	99.09 177	97.99 114	96.79 244	99.35 117	93.18 294	97.71 233	98.07 250	95.00 217	99.31 322	93.97 256	99.13 241	98.42 276

MVS_111021_HR		98.25 147	98.08 153	98.75 144	99.09 177	97.46 157	95.97 284	99.27 146	97.60 156	97.99 206	98.25 234	98.15 59	99.38 315	96.87 150	99.57 172	99.42 142

PAPM_NR		96.82 238	96.32 245	98.30 205	99.07 181	96.69 191	97.48 203	98.76 245	95.81 246	96.61 290	96.47 305	94.12 243	99.17 331	90.82 318	97.78 310	99.06 220

TAMVS		98.24 149	98.05 155	98.80 134	99.07 181	97.18 170	97.88 160	98.81 240	96.66 219	99.17 99	99.21 87	94.81 225	99.77 192	96.96 145	99.88 64	99.44 134

CLD-MVS		97.49 197	97.16 206	98.48 185	99.07 181	97.03 176	94.71 326	99.21 159	94.46 276	98.06 202	97.16 292	97.57 89	99.48 302	94.46 241	99.78 100	98.95 233
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
conf200view11		94.24 296	93.67 301	95.94 299	99.06 184	91.35 313	98.03 141	94.24 330	98.33 111	97.40 257	94.98 334	79.84 327	99.62 261	83.05 341	98.08 302	96.86 323

thres100view900		94.19 297	93.67 301	95.75 304	99.06 184	91.35 313	98.03 141	94.24 330	98.33 111	97.40 257	94.98 334	79.84 327	99.62 261	83.05 341	98.08 302	96.29 330

thres600view7		94.45 292	93.83 297	96.29 285	99.06 184	91.53 305	97.99 150	94.24 330	98.34 110	97.44 254	95.01 332	79.84 327	99.67 243	84.33 339	98.23 286	97.66 303

DI_MVS_plusplus_test		97.57 194	97.40 193	98.07 220	99.06 184	95.71 229	96.58 259	96.96 298	96.71 216	98.69 160	98.13 240	93.81 247	99.68 238	97.45 123	99.19 231	98.80 252

plane_prior1					99.05 188

Test4		97.43 203	97.18 204	98.18 213	99.05 188	96.02 216	96.62 257	99.09 192	96.25 232	98.63 167	97.70 266	90.49 274	99.68 238	97.50 121	99.30 214	98.83 246

YYNet1		97.60 190	97.67 175	97.39 255	99.04 190	93.04 291	95.27 314	98.38 267	97.25 190	98.92 135	98.95 142	95.48 207	99.73 217	96.99 143	98.74 264	99.41 144

MDA-MVSNet_test_wron		97.60 190	97.66 178	97.41 254	99.04 190	93.09 288	95.27 314	98.42 265	97.26 189	98.88 141	98.95 142	95.43 208	99.73 217	97.02 142	98.72 265	99.41 144

MIMVSNet		96.62 245	96.25 248	97.71 236	99.04 190	94.66 252	99.16 42	96.92 302	97.23 195	97.87 212	99.10 109	86.11 293	99.65 256	91.65 299	99.21 226	98.82 248

test_normal		97.58 192	97.41 192	98.10 215	99.03 193	95.72 228	96.21 276	97.05 296	96.71 216	98.65 162	98.12 244	93.87 244	99.69 233	97.68 116	99.35 206	98.88 242

PatchMatch-RL		97.24 216	96.78 222	98.61 161	99.03 193	97.83 132	96.36 269	99.06 195	93.49 293	97.36 262	97.78 262	95.75 197	99.49 299	93.44 273	98.77 263	98.52 270

Regformer-3		98.61 104	98.61 89	98.63 156	99.02 195	96.53 193	97.17 225	98.84 234	99.13 60	99.10 105	98.85 161	97.24 117	99.79 174	98.41 79	99.70 130	99.57 70

Regformer-4		98.73 78	98.68 79	98.89 124	99.02 195	97.22 167	97.17 225	99.06 195	99.21 47	99.17 99	98.85 161	97.45 100	99.86 77	98.48 75	99.70 130	99.60 52

tfpn1000		94.81 284	94.25 287	96.47 284	99.01 197	93.47 286	98.56 87	92.30 346	96.17 234	97.90 210	96.29 308	76.70 344	99.77 192	93.02 278	98.29 284	96.16 333

CDPH-MVS		97.26 213	96.66 232	99.07 96	99.00 198	98.15 100	96.03 282	99.01 210	91.21 320	97.79 229	97.85 259	96.89 142	99.69 233	92.75 287	99.38 203	99.39 150

WR-MVS		98.40 131	98.19 138	99.03 105	99.00 198	97.65 148	96.85 243	98.94 216	98.57 103	98.89 138	98.50 216	95.60 201	99.85 88	97.54 118	99.85 71	99.59 58

plane_prior6					98.99 200	97.70 146						94.90 218

xiu_mvs_v1_base_debu		97.86 174	98.17 139	96.92 268	98.98 201	93.91 274	96.45 264	99.17 179	97.85 143	98.41 187	97.14 294	98.47 39	99.92 34	98.02 95	99.05 246	96.92 320

xiu_mvs_v1_base		97.86 174	98.17 139	96.92 268	98.98 201	93.91 274	96.45 264	99.17 179	97.85 143	98.41 187	97.14 294	98.47 39	99.92 34	98.02 95	99.05 246	96.92 320

xiu_mvs_v1_base_debi		97.86 174	98.17 139	96.92 268	98.98 201	93.91 274	96.45 264	99.17 179	97.85 143	98.41 187	97.14 294	98.47 39	99.92 34	98.02 95	99.05 246	96.92 320

MVP-Stereo		98.08 159	97.92 164	98.57 168	98.96 204	96.79 184	97.90 159	99.18 173	96.41 227	98.46 182	98.95 142	95.93 191	99.60 268	96.51 178	98.98 256	99.31 178
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 131	98.68 79	97.54 247	98.96 204	97.99 114	97.88 160	99.36 111	98.20 120	99.63 26	99.04 124	98.76 24	95.33 352	96.56 174	99.74 115	99.31 178

1121		96.73 241	96.00 249	98.91 121	98.95 206	97.76 140	98.07 136	98.73 251	87.65 337	96.54 291	98.13 240	94.52 233	99.73 217	92.38 293	99.02 250	99.24 194

新几何1				98.91 121	98.94 207	97.76 140		98.76 245	87.58 338	96.75 286	98.10 246	94.80 226	99.78 183	92.73 288	99.00 253	99.20 201

USDC		97.41 205	97.40 193	97.44 252	98.94 207	93.67 283	95.17 317	99.53 59	94.03 286	98.97 126	99.10 109	95.29 210	99.34 318	95.84 211	99.73 118	99.30 181

tfpn200view9		94.03 302	93.44 305	95.78 303	98.93 209	91.44 307	97.60 191	94.29 328	97.94 127	97.10 267	94.31 342	79.67 330	99.62 261	83.05 341	98.08 302	96.29 330

testdata				98.09 216	98.93 209	95.40 238		98.80 242	90.08 328	97.45 253	98.37 224	95.26 211	99.70 229	93.58 269	98.95 258	99.17 211

thres400		94.14 299	93.44 305	96.24 291	98.93 209	91.44 307	97.60 191	94.29 328	97.94 127	97.10 267	94.31 342	79.67 330	99.62 261	83.05 341	98.08 302	97.66 303

TAPA-MVS	96.21 11	96.63 244	95.95 251	98.65 153	98.93 209	98.09 104	96.93 236	99.28 141	83.58 345	98.13 198	97.78 262	96.13 179	99.40 311	93.52 270	99.29 217	98.45 273
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 213	96.93 181	95.54 307	98.78 244	85.72 342	96.86 282	98.11 245	94.43 234			99.10 245	99.23 195

PVSNet_BlendedMVS		97.55 195	97.53 185	97.60 243	98.92 213	93.77 281	96.64 255	99.43 93	94.49 274	97.62 238	99.18 92	96.82 146	99.67 243	94.73 234	99.93 39	99.36 163

PVSNet_Blended		96.88 234	96.68 229	97.47 250	98.92 213	93.77 281	94.71 326	99.43 93	90.98 321	97.62 238	97.36 288	96.82 146	99.67 243	94.73 234	99.56 179	98.98 229

MSDG		97.71 183	97.52 186	98.28 207	98.91 216	96.82 183	94.42 329	99.37 107	97.65 151	98.37 191	98.29 232	97.40 104	99.33 320	94.09 254	99.22 224	98.68 266

原ACMM1				98.35 200	98.90 217	96.25 209		98.83 239	92.48 302	96.07 306	98.10 246	95.39 209	99.71 227	92.61 290	98.99 254	99.08 217

GBi-Net		98.65 94	98.47 105	99.17 81	98.90 217	98.24 94	99.20 35	99.44 88	98.59 99	98.95 129	99.55 41	94.14 240	99.86 77	97.77 107	99.69 137	99.41 144

test1		98.65 94	98.47 105	99.17 81	98.90 217	98.24 94	99.20 35	99.44 88	98.59 99	98.95 129	99.55 41	94.14 240	99.86 77	97.77 107	99.69 137	99.41 144

FMVSNet2		98.49 122	98.40 117	98.75 144	98.90 217	97.14 174	98.61 82	99.13 186	98.59 99	99.19 95	99.28 75	94.14 240	99.82 129	97.97 99	99.80 92	99.29 184

OMC-MVS		97.88 172	97.49 187	99.04 104	98.89 221	98.63 68	96.94 235	99.25 152	95.02 264	98.53 180	98.51 213	97.27 112	99.47 303	93.50 272	99.51 189	99.01 226

MVSFormer		98.26 145	98.43 114	97.77 232	98.88 222	93.89 277	99.39 13	99.56 49	99.11 61	98.16 195	98.13 240	93.81 247	99.97 3	99.26 32	99.57 172	99.43 139

lupinMVS		97.06 226	96.86 218	97.65 239	98.88 222	93.89 277	95.48 310	97.97 278	93.53 291	98.16 195	97.58 272	93.81 247	99.91 43	96.77 156	99.57 172	99.17 211

tfpn_ndepth		94.12 300	93.51 304	95.94 299	98.86 224	93.60 285	98.16 127	91.90 348	94.66 273	97.41 256	95.24 329	76.24 345	99.73 217	91.21 310	97.88 309	94.50 346

DELS-MVS		98.27 143	98.20 136	98.48 185	98.86 224	96.70 190	95.60 306	99.20 163	97.73 147	98.45 183	98.71 179	97.50 95	99.82 129	98.21 87	99.59 162	98.93 236
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		97.89 170	97.98 158	97.60 243	98.86 224	94.35 263	96.21 276	99.44 88	97.45 175	99.06 108	98.88 156	97.99 69	99.28 327	94.38 248	99.58 168	99.18 207

Regformer-1		98.55 113	98.44 112	98.87 126	98.85 227	97.29 162	96.91 239	98.99 215	98.97 78	98.99 122	98.64 193	97.26 115	99.81 142	97.79 105	99.57 172	99.51 98

Regformer-2		98.60 105	98.46 108	99.02 108	98.85 227	97.71 145	96.91 239	99.09 192	98.98 77	99.01 119	98.64 193	97.37 106	99.84 103	97.75 111	99.57 172	99.52 96

LCM-MVSNet-Re		98.64 96	98.48 103	99.11 90	98.85 227	98.51 81	98.49 97	99.83 3	98.37 108	99.69 17	99.46 52	98.21 54	99.92 34	94.13 253	99.30 214	98.91 239

pmmvs4		97.58 192	97.28 201	98.51 182	98.84 230	96.93 181	95.40 313	98.52 261	93.60 290	98.61 170	98.65 190	95.10 215	99.60 268	96.97 144	99.79 96	98.99 228

NP-MVS					98.84 230	97.39 161					96.84 297

sss		97.21 217	96.93 213	98.06 221	98.83 232	95.22 240	96.75 248	98.48 263	94.49 274	97.27 264	97.90 258	92.77 261	99.80 154	96.57 171	99.32 211	99.16 214

PVSNet	93.40 17	95.67 263	95.70 255	95.57 308	98.83 232	88.57 323	92.50 342	97.72 284	92.69 300	96.49 297	96.44 306	93.72 251	99.43 309	93.61 267	99.28 218	98.71 260

MVE	83.40 22	92.50 316	91.92 318	94.25 322	98.83 232	91.64 304	92.71 341	83.52 354	95.92 244	86.46 352	95.46 326	95.20 212	95.40 351	80.51 347	98.64 272	95.73 339
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ambc				98.24 209	98.82 235	95.97 218	98.62 81	99.00 214		99.27 82	99.21 87	96.99 133	99.50 298	96.55 175	99.50 194	99.26 189

旧先验1					98.82 235	97.45 158		98.76 245			98.34 227	95.50 206			99.01 252	99.23 195

WTY-MVS		96.67 242	96.27 246	97.87 228	98.81 237	94.61 254	96.77 246	97.92 280	94.94 267	97.12 266	97.74 264	91.11 272	99.82 129	93.89 259	98.15 292	99.18 207

3Dnovator+	97.89 3	98.69 87	98.51 97	99.24 77	98.81 237	98.40 87	99.02 54	99.19 169	98.99 75	98.07 201	99.28 75	97.11 126	99.84 103	96.84 152	99.32 211	99.47 124

QAPM		97.31 209	96.81 221	98.82 132	98.80 239	97.49 155	99.06 53	99.19 169	90.22 326	97.69 235	99.16 98	96.91 137	99.90 47	90.89 316	99.41 200	99.07 219

VNet		98.42 128	98.30 131	98.79 135	98.79 240	97.29 162	98.23 120	98.66 255	99.31 41	98.85 144	98.80 169	94.80 226	99.78 183	98.13 90	99.13 241	99.31 178

3Dnovator	98.27 2	98.81 68	98.73 67	99.05 102	98.76 241	97.81 137	99.25 32	99.30 138	98.57 103	98.55 178	99.33 72	97.95 73	99.90 47	97.16 134	99.67 147	99.44 134

PLC	94.65 16	96.51 248	95.73 254	98.85 129	98.75 242	97.91 125	96.42 267	99.06 195	90.94 322	95.59 313	97.38 286	94.41 235	99.59 272	90.93 314	98.04 306	99.05 221
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 236	96.75 224	97.08 261	98.74 243	93.33 287	96.71 250	98.26 270	96.72 214	98.44 184	97.37 287	95.20 212	99.47 303	91.89 296	97.43 315	98.44 274

CDS-MVSNet		97.69 184	97.35 199	98.69 150	98.73 244	97.02 178	96.92 238	98.75 248	95.89 245	98.59 173	98.67 186	92.08 269	99.74 212	96.72 159	99.81 88	99.32 174
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
LFMVS		97.20 218	96.72 225	98.64 154	98.72 245	96.95 180	98.93 66	94.14 333	99.74 5	98.78 153	99.01 130	84.45 305	99.73 217	97.44 124	99.27 219	99.25 191

new_pmnet		96.99 231	96.76 223	97.67 237	98.72 245	94.89 247	95.95 291	98.20 272	92.62 301	98.55 178	98.54 211	94.88 221	99.52 292	93.96 257	99.44 198	98.59 268

Fast-Effi-MVS+		97.67 186	97.38 196	98.57 168	98.71 247	97.43 159	97.23 217	99.45 85	94.82 271	96.13 302	96.51 302	98.52 38	99.91 43	96.19 192	98.83 261	98.37 280

TEST9					98.71 247	98.08 107	95.96 288	99.03 203	91.40 317	95.85 309	97.53 274	96.52 165	99.76 197

train_agg		97.10 223	96.45 241	99.07 96	98.71 247	98.08 107	95.96 288	99.03 203	91.64 311	95.85 309	97.53 274	96.47 168	99.76 197	93.67 265	99.16 234	99.36 163

TSAR-MVS + GP.		98.18 153	97.98 158	98.77 140	98.71 247	97.88 128	96.32 271	98.66 255	96.33 228	99.23 93	98.51 213	97.48 99	99.40 311	97.16 134	99.46 196	99.02 225

PCF-MVS	92.86 18	94.36 293	93.00 310	98.42 191	98.70 251	97.56 152	93.16 340	99.11 190	79.59 348	97.55 245	97.43 283	92.19 266	99.73 217	79.85 348	99.45 197	97.97 289
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_prior3		97.48 200	97.00 211	98.95 115	98.69 252	97.95 122	95.74 301	99.03 203	96.48 224	96.11 303	97.63 270	95.92 192	99.59 272	94.16 249	99.20 227	99.30 181

test_prior				98.95 115	98.69 252	97.95 122		99.03 203					99.59 272			99.30 181

agg_prior3		96.95 233	96.27 246	99.00 111	98.68 254	97.91 125	95.96 288	99.01 210	90.74 323	95.60 312	97.45 282	96.14 178	99.74 212	93.67 265	99.16 234	99.36 163

agg_prior1		97.06 226	96.40 242	99.03 105	98.68 254	97.99 114	95.76 299	99.01 210	91.73 310	95.59 313	97.50 277	96.49 167	99.77 192	93.71 264	99.14 238	99.34 169

agg_prior					98.68 254	97.99 114		99.01 210		95.59 313			99.77 192

test_8					98.67 257	98.01 113	95.91 294	99.02 207	91.64 311	95.79 311	97.50 277	96.47 168	99.76 197

HQP-NCC					98.67 257		96.29 272		96.05 240	95.55 317

ACMP_Plane					98.67 257		96.29 272		96.05 240	95.55 317

CNVR-MVS		98.17 155	97.87 169	99.07 96	98.67 257	98.24 94	97.01 232	98.93 219	97.25 190	97.62 238	98.34 227	97.27 112	99.57 279	96.42 184	99.33 209	99.39 150

HQP-MVS		97.00 230	96.49 240	98.55 173	98.67 257	96.79 184	96.29 272	99.04 201	96.05 240	95.55 317	96.84 297	93.84 245	99.54 286	92.82 284	99.26 221	99.32 174

thres200		93.72 307	93.14 308	95.46 309	98.66 262	91.29 316	96.61 258	94.63 322	97.39 178	96.83 283	93.71 345	79.88 326	99.56 282	82.40 345	98.13 293	95.54 340

PNet_i23d		91.80 322	92.35 314	90.14 337	98.65 263	73.10 356	89.22 349	99.02 207	95.23 263	97.87 212	97.82 261	78.45 337	98.89 342	88.73 324	86.14 350	98.42 276

wuyk23d		96.06 257	97.62 182	91.38 335	98.65 263	98.57 75	98.85 72	96.95 300	96.86 209	99.90 5	99.16 98	99.18 12	98.40 346	89.23 323	99.77 104	77.18 351

NCCC		97.86 174	97.47 191	99.05 102	98.61 265	98.07 109	96.98 233	98.90 225	97.63 152	97.04 271	97.93 257	95.99 188	99.66 251	95.31 225	98.82 262	99.43 139

DeepC-MVS_fast	96.85 6	98.30 139	98.15 144	98.75 144	98.61 265	97.23 165	97.76 172	99.09 192	97.31 185	98.75 157	98.66 188	97.56 90	99.64 258	96.10 198	99.55 181	99.39 150
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
GA-MVS		95.86 260	95.32 265	97.49 249	98.60 267	94.15 268	93.83 336	97.93 279	95.49 257	96.68 287	97.42 284	83.21 313	99.30 324	96.22 190	98.55 277	99.01 226

MSLP-MVS++		98.02 161	98.14 146	97.64 241	98.58 268	95.19 241	97.48 203	99.23 158	97.47 168	97.90 210	98.62 199	97.04 128	98.81 344	97.55 117	99.41 200	98.94 235

test12				98.93 118	98.58 268	97.83 132		98.66 255		96.53 292		95.51 205	99.69 233		99.13 241	99.27 186

PS-MVSNAJ		97.08 225	97.39 195	96.16 295	98.56 270	92.46 295	95.24 316	98.85 233	97.25 190	97.49 250	95.99 311	98.07 61	99.90 47	96.37 185	98.67 271	96.12 336

CNLPA		97.17 220	96.71 227	98.55 173	98.56 270	98.05 111	96.33 270	98.93 219	96.91 207	97.06 270	97.39 285	94.38 236	99.45 307	91.66 298	99.18 233	98.14 284

test1235678		97.06 226	96.84 220	97.73 235	98.55 272	94.46 262	94.80 324	99.36 111	96.85 210	98.83 147	98.26 233	92.72 262	99.82 129	92.49 292	99.70 130	98.91 239

xiu_mvs_v2_base		97.16 221	97.49 187	96.17 293	98.54 273	92.46 295	95.45 311	98.84 234	97.25 190	97.48 251	96.49 303	98.31 47	99.90 47	96.34 187	98.68 270	96.15 335

alignmvs		97.35 206	96.88 217	98.78 138	98.54 273	98.09 104	97.71 176	97.69 286	99.20 50	97.59 241	95.90 316	88.12 286	99.55 285	98.18 89	98.96 257	98.70 262

Effi-MVS+		98.02 161	97.82 171	98.62 158	98.53 275	97.19 169	97.33 210	99.68 16	97.30 186	96.68 287	97.46 281	98.56 36	99.80 154	96.63 167	98.20 288	98.86 244

MVS_Test		98.18 153	98.36 123	97.67 237	98.48 276	94.73 249	98.18 124	99.02 207	97.69 149	98.04 204	99.11 107	97.22 121	99.56 282	98.57 70	98.90 260	98.71 260

BH-RMVSNet		96.83 236	96.58 236	97.58 245	98.47 277	94.05 269	96.67 253	97.36 290	96.70 218	97.87 212	97.98 254	95.14 214	99.44 308	90.47 319	98.58 276	99.25 191

canonicalmvs		98.34 135	98.26 133	98.58 166	98.46 278	97.82 135	98.96 63	99.46 82	99.19 54	97.46 252	95.46 326	98.59 32	99.46 305	98.08 92	98.71 268	98.46 272

MVS-HIRNet		94.32 294	95.62 258	90.42 336	98.46 278	75.36 353	96.29 272	89.13 351	95.25 261	95.38 323	99.75 7	92.88 260	99.19 330	94.07 255	99.39 202	96.72 328

PHI-MVS		98.29 142	97.95 160	99.34 64	98.44 280	99.16 28	98.12 130	99.38 103	96.01 243	98.06 202	98.43 220	97.80 80	99.67 243	95.69 217	99.58 168	99.20 201

Fast-Effi-MVS+-dtu		98.27 143	98.09 150	98.81 133	98.43 281	98.11 103	97.61 190	99.50 65	98.64 95	97.39 259	97.52 276	98.12 60	99.95 13	96.90 148	98.71 268	98.38 278

OpenMVS_ROB	95.38 14	95.84 261	95.18 270	97.81 230	98.41 282	97.15 173	97.37 208	98.62 258	83.86 344	98.65 162	98.37 224	94.29 238	99.68 238	88.41 325	98.62 274	96.60 329

DeepPCF-MVS	96.93 5	98.32 137	98.01 157	99.23 78	98.39 283	98.97 50	95.03 320	99.18 173	96.88 208	99.33 72	98.78 171	98.16 57	99.28 327	96.74 158	99.62 155	99.44 134

diffmvs		97.49 197	97.36 197	97.91 227	98.38 284	95.70 230	97.95 154	99.31 131	94.87 269	96.14 301	98.78 171	94.84 222	99.43 309	97.69 114	98.26 285	98.59 268

Patchmatch-test		96.55 247	96.34 244	97.17 260	98.35 285	93.06 289	98.40 113	97.79 281	97.33 182	98.41 187	98.67 186	83.68 312	99.69 233	95.16 226	99.31 213	98.77 255

AdaColmap		97.14 222	96.71 227	98.46 187	98.34 286	97.80 138	96.95 234	98.93 219	95.58 255	96.92 275	97.66 268	95.87 195	99.53 288	90.97 313	99.14 238	98.04 287

OpenMVS	96.65 7	97.09 224	96.68 229	98.32 202	98.32 287	97.16 172	98.86 71	99.37 107	89.48 330	96.29 300	99.15 102	96.56 163	99.90 47	92.90 281	99.20 227	97.89 290

MG-MVS		96.77 240	96.61 234	97.26 258	98.31 288	93.06 289	95.93 292	98.12 275	96.45 226	97.92 207	98.73 177	93.77 250	99.39 313	91.19 312	99.04 249	99.33 173

CHOSEN 280x420		95.51 268	95.47 260	95.65 306	98.25 289	88.27 326	93.25 339	98.88 227	93.53 291	94.65 329	97.15 293	86.17 291	99.93 26	97.41 126	99.93 39	98.73 259

test12356		94.85 281	95.12 271	94.03 325	98.25 289	83.12 347	93.85 335	99.33 126	94.17 285	97.28 263	97.20 289	85.83 295	99.75 203	90.85 317	99.33 209	99.22 199

Patchmatch-test1		96.44 252	96.72 225	95.60 307	98.24 291	88.35 325	95.85 297	96.88 304	96.11 238	97.67 236	98.57 205	93.10 256	99.69 233	94.79 232	99.22 224	98.77 255

DeepMVS_CX				93.44 331	98.24 291	94.21 266		94.34 327	64.28 350	91.34 345	94.87 339	89.45 281	92.77 353	77.54 350	93.14 346	93.35 348

MS-PatchMatch		97.68 185	97.75 173	97.45 251	98.23 293	93.78 280	97.29 213	98.84 234	96.10 239	98.64 164	98.65 190	96.04 182	99.36 316	96.84 152	99.14 238	99.20 201

MVS_0304		98.02 161	97.88 168	98.46 187	98.22 294	96.39 201	96.50 261	99.49 71	98.03 125	97.24 265	98.33 229	94.80 226	99.90 47	98.31 84	99.95 30	99.08 217

BH-w/o		95.13 272	94.89 276	95.86 301	98.20 295	91.31 315	95.65 304	97.37 289	93.64 289	96.52 293	95.70 317	93.04 257	99.02 336	88.10 326	95.82 334	97.24 318

mvs_anonymous		97.83 180	98.16 142	96.87 271	98.18 296	91.89 301	97.31 212	98.90 225	97.37 179	98.83 147	99.46 52	96.28 176	99.79 174	98.90 53	98.16 291	98.95 233

ADS-MVSNet2		95.43 269	94.98 274	96.76 275	98.14 297	91.74 302	97.92 156	97.76 282	90.23 324	96.51 294	98.91 147	85.61 297	99.85 88	92.88 282	96.90 324	98.69 263

ADS-MVSNet		95.24 271	94.93 275	96.18 292	98.14 297	90.10 320	97.92 156	97.32 291	90.23 324	96.51 294	98.91 147	85.61 297	99.74 212	92.88 282	96.90 324	98.69 263

FMVSNet3		97.50 196	97.24 202	98.29 206	98.08 299	95.83 225	97.86 163	98.91 224	97.89 138	98.95 129	98.95 142	87.06 287	99.81 142	97.77 107	99.69 137	99.23 195

PAPM		91.88 321	90.34 323	96.51 282	98.06 300	92.56 293	92.44 343	97.17 293	86.35 340	90.38 348	96.01 310	86.61 289	99.21 329	70.65 351	95.43 337	97.75 300

Effi-MVS+-dtu		98.26 145	97.90 166	99.35 61	98.02 301	99.49 3	98.02 147	99.16 182	98.29 117	97.64 237	97.99 253	96.44 170	99.95 13	96.66 165	98.93 259	98.60 267

mvs-test1		97.83 180	97.48 190	98.89 124	98.02 301	99.20 23	97.20 221	99.16 182	98.29 117	96.46 298	97.17 291	96.44 170	99.92 34	96.66 165	97.90 308	97.54 313

HY-MVS	95.94 13	95.90 259	95.35 264	97.55 246	97.95 303	94.79 248	98.81 74	96.94 301	92.28 306	95.17 325	98.57 205	89.90 277	99.75 203	91.20 311	97.33 320	98.10 285

UGNet		98.53 118	98.45 110	98.79 135	97.94 304	96.96 179	99.08 49	98.54 260	99.10 65	96.82 284	99.47 51	96.55 164	99.84 103	98.56 73	99.94 33	99.55 83
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		96.47 251	95.70 255	98.79 135	97.92 305	99.12 39	98.28 117	98.60 259	92.16 308	95.54 320	96.17 309	94.77 229	99.52 292	89.62 322	98.23 286	97.72 302
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
testus		95.52 266	95.32 265	96.13 297	97.91 306	89.49 322	93.62 337	99.61 30	92.41 303	97.38 261	95.42 328	94.72 230	99.63 259	88.06 327	98.72 265	99.26 189

MVSTER		96.86 235	96.55 238	97.79 231	97.91 306	94.21 266	97.56 196	98.87 228	97.49 167	99.06 108	99.05 122	80.72 320	99.80 154	98.44 76	99.82 82	99.37 157

API-MVS		97.04 229	96.91 216	97.42 253	97.88 308	98.23 98	98.18 124	98.50 262	97.57 159	97.39 259	96.75 299	96.77 150	99.15 333	90.16 320	99.02 250	94.88 345

CANet		97.87 173	97.76 172	98.19 212	97.75 309	95.51 234	96.76 247	99.05 199	97.74 146	96.93 274	98.21 238	95.59 202	99.89 56	97.86 104	99.93 39	99.19 206

PVSNet_0	89.98 21	91.15 324	90.30 324	93.70 328	97.72 310	84.34 345	90.24 346	97.42 288	90.20 327	93.79 339	93.09 348	90.90 273	98.89 342	86.57 331	72.76 351	97.87 292

CR-MVSNet		96.28 254	95.95 251	97.28 256	97.71 311	94.22 264	98.11 131	98.92 222	92.31 305	96.91 277	99.37 65	85.44 300	99.81 142	97.39 127	97.36 318	97.81 296

RPMNet		96.82 238	96.66 232	97.28 256	97.71 311	94.22 264	98.11 131	96.90 303	99.37 36	96.91 277	99.34 70	86.72 288	99.81 142	97.53 119	97.36 318	97.81 296

pmmvs3		95.03 274	94.40 283	96.93 267	97.70 313	92.53 294	95.08 319	97.71 285	88.57 334	97.71 233	98.08 249	79.39 332	99.82 129	96.19 192	99.11 244	98.43 275

tpm		94.67 290	94.34 285	95.66 305	97.68 314	88.42 324	97.88 160	94.90 320	94.46 276	96.03 308	98.56 208	78.66 333	99.79 174	95.88 205	95.01 339	98.78 254

LP		96.60 246	96.57 237	96.68 276	97.64 315	91.70 303	98.11 131	97.74 283	97.29 188	97.91 209	99.24 82	88.35 284	99.85 88	97.11 140	95.76 335	98.49 271

CANet_DTU		97.26 213	97.06 209	97.84 229	97.57 316	94.65 253	96.19 279	98.79 243	97.23 195	95.14 326	98.24 235	93.22 253	99.84 103	97.34 128	99.84 73	99.04 222

tpm2		93.09 313	92.58 312	94.62 317	97.56 317	86.53 332	97.66 181	95.79 317	86.15 341	94.07 337	98.23 237	75.95 346	99.53 288	90.91 315	96.86 327	97.81 296

TR-MVS		95.55 265	95.12 271	96.86 274	97.54 318	93.94 272	96.49 263	96.53 311	94.36 281	97.03 272	96.61 301	94.26 239	99.16 332	86.91 330	96.31 331	97.47 315

1314		95.74 262	95.60 259	96.17 293	97.53 319	92.75 292	98.07 136	98.31 269	91.22 319	94.25 333	96.68 300	95.53 203	99.03 335	91.64 300	97.18 321	96.74 327

CostFormer		93.97 304	93.78 298	94.51 319	97.53 319	85.83 335	97.98 151	95.96 315	89.29 332	94.99 328	98.63 197	78.63 334	99.62 261	94.54 239	96.50 329	98.09 286

FMVSNet5		96.01 258	95.20 269	98.41 192	97.53 319	96.10 213	98.74 75	99.50 65	97.22 198	98.03 205	99.04 124	69.80 350	99.88 63	97.27 131	99.71 127	99.25 191

PMMVS		96.51 248	95.98 250	98.09 216	97.53 319	95.84 224	94.92 322	98.84 234	91.58 314	96.05 307	95.58 318	95.68 199	99.66 251	95.59 221	98.09 301	98.76 257

PAPR		95.29 270	94.47 278	97.75 234	97.50 323	95.14 243	94.89 323	98.71 253	91.39 318	95.35 324	95.48 325	94.57 232	99.14 334	84.95 337	97.37 316	98.97 232

tpmp4_e23		92.91 314	92.45 313	94.29 321	97.41 324	85.62 337	97.95 154	96.77 306	87.55 339	91.33 346	98.57 205	74.21 348	99.59 272	91.62 301	96.64 328	97.65 310

PatchT		96.65 243	96.35 243	97.54 247	97.40 325	95.32 239	97.98 151	96.64 309	99.33 40	96.89 280	99.42 59	84.32 307	99.81 142	97.69 114	97.49 313	97.48 314

tpm cat1		93.29 311	93.13 309	93.75 327	97.39 326	84.74 341	97.39 207	97.65 287	83.39 346	94.16 334	98.41 221	82.86 316	99.39 313	91.56 303	95.35 338	97.14 319

PatchmatchNet		95.58 264	95.67 257	95.30 311	97.34 327	87.32 329	97.65 183	96.65 308	95.30 260	97.07 269	98.69 182	84.77 302	99.75 203	94.97 230	98.64 272	98.83 246
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 206	96.97 212	98.50 183	97.31 328	96.47 196	98.18 124	98.92 222	98.95 82	98.78 153	99.37 65	85.44 300	99.85 88	95.96 203	99.83 79	99.17 211

LS3D		98.63 98	98.38 121	99.36 56	97.25 329	99.38 6	99.12 48	99.32 129	99.21 47	98.44 184	98.88 156	97.31 108	99.80 154	96.58 169	99.34 208	98.92 237

IB-MVS	91.63 19	92.24 319	90.90 322	96.27 286	97.22 330	91.24 317	94.36 330	93.33 336	92.37 304	92.24 343	94.58 341	66.20 355	99.89 56	93.16 277	94.63 341	97.66 303
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
tpmrst		95.07 273	95.46 261	93.91 326	97.11 331	84.36 344	97.62 188	96.96 298	94.98 265	96.35 299	98.80 169	85.46 299	99.59 272	95.60 220	96.23 332	97.79 299

MDTV_nov1_ep13			95.22 268		97.06 332	83.20 346	97.74 174	96.16 314	94.37 280	96.99 273	98.83 164	83.95 310	99.53 288	93.90 258	97.95 307

PatchFormer-LS_test		94.08 301	93.91 295	94.59 318	96.93 333	86.86 331	97.55 198	96.57 310	94.27 282	94.38 332	93.64 347	80.96 319	99.59 272	96.44 183	94.48 343	97.31 317

MVS		93.19 312	92.09 316	96.50 283	96.91 334	94.03 270	98.07 136	98.06 277	68.01 349	94.56 331	96.48 304	95.96 190	99.30 324	83.84 340	96.89 326	96.17 332

E-PMN		94.17 298	94.37 284	93.58 329	96.86 335	85.71 336	90.11 347	97.07 295	98.17 123	97.82 222	97.19 290	84.62 304	98.94 339	89.77 321	97.68 312	96.09 337

JIA-IIPM		95.52 266	95.03 273	97.00 265	96.85 336	94.03 270	96.93 236	95.82 316	99.20 50	94.63 330	99.71 14	83.09 314	99.60 268	94.42 244	94.64 340	97.36 316

EMVS		93.83 306	94.02 294	93.23 333	96.83 337	84.96 340	89.77 348	96.32 313	97.92 129	97.43 255	96.36 307	86.17 291	98.93 340	87.68 328	97.73 311	95.81 338

dp		93.47 309	93.59 303	93.13 334	96.64 338	81.62 351	97.66 181	96.42 312	92.80 299	96.11 303	98.64 193	78.55 335	99.59 272	93.31 275	92.18 349	98.16 283

test-LLR		93.90 305	93.85 296	94.04 323	96.53 339	84.62 342	94.05 332	92.39 344	96.17 234	94.12 335	95.07 330	82.30 317	99.67 243	95.87 208	98.18 289	97.82 294

test-mter		92.33 318	91.76 320	94.04 323	96.53 339	84.62 342	94.05 332	92.39 344	94.00 287	94.12 335	95.07 330	65.63 357	99.67 243	95.87 208	98.18 289	97.82 294

TESTMET0.1,1		92.19 320	91.77 319	93.46 330	96.48 341	82.80 349	94.05 332	91.52 349	94.45 278	94.00 338	94.88 337	66.65 354	99.56 282	95.78 213	98.11 294	98.02 288

DWT-MVSNet_test		92.75 315	92.05 317	94.85 314	96.48 341	87.21 330	97.83 166	94.99 319	92.22 307	92.72 342	94.11 344	70.75 349	99.46 305	95.01 228	94.33 344	97.87 292

tpmvs		95.02 275	95.25 267	94.33 320	96.39 343	85.87 333	98.08 134	96.83 305	95.46 258	95.51 321	98.69 182	85.91 294	99.53 288	94.16 249	96.23 332	97.58 311

CMPMVS	75.91 23	96.29 253	95.44 262	98.84 130	96.25 344	98.69 66	97.02 231	99.12 188	88.90 333	97.83 220	98.86 159	89.51 279	98.90 341	91.92 295	99.51 189	98.92 237
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 291	93.69 300	96.99 266	96.05 345	93.61 284	94.97 321	93.49 334	96.17 234	97.57 244	94.88 337	82.30 317	99.01 338	93.60 268	94.17 345	98.37 280

EPMVS		93.72 307	93.27 307	95.09 313	96.04 346	87.76 327	98.13 128	85.01 353	94.69 272	96.92 275	98.64 193	78.47 336	99.31 322	95.04 227	96.46 330	98.20 282

cascas		94.79 285	94.33 286	96.15 296	96.02 347	92.36 298	92.34 344	99.26 151	85.34 343	95.08 327	94.96 336	92.96 258	98.53 345	94.41 247	98.59 275	97.56 312

gg-mvs-nofinetune		92.37 317	91.20 321	95.85 302	95.80 348	92.38 297	99.31 20	81.84 355	99.75 4	91.83 344	99.74 8	68.29 351	99.02 336	87.15 329	97.12 322	96.16 333

gm-plane-assit					94.83 349	81.97 350			88.07 336		94.99 333		99.60 268	91.76 297

GG-mvs-BLEND				94.76 316	94.54 350	92.13 300	99.31 20	80.47 356		88.73 350	91.01 350	67.59 352	98.16 348	82.30 346	94.53 342	93.98 347

test2356		91.64 323	90.19 326	96.00 298	94.30 351	89.58 321	90.84 345	96.68 307	91.76 309	95.48 322	93.69 346	67.05 353	99.52 292	84.83 338	97.08 323	98.91 239

testpf		89.08 325	90.27 325	85.50 338	94.03 352	82.85 348	96.87 242	91.09 350	91.61 313	90.96 347	94.86 340	66.15 356	95.83 349	94.58 238	92.27 348	77.82 350

EPNet_dtu		94.93 276	94.78 277	95.38 310	93.58 353	87.68 328	96.78 245	95.69 318	97.35 181	89.14 349	98.09 248	88.15 285	99.49 299	94.95 231	99.30 214	98.98 229
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPNet		96.14 256	95.44 262	98.25 208	90.76 354	95.50 235	97.92 156	94.65 321	98.97 78	92.98 341	98.85 161	89.12 282	99.87 72	95.99 201	99.68 142	99.39 150
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tmp_tt		78.77 327	78.73 328	78.90 339	58.45 355	74.76 355	94.20 331	78.26 357	39.16 351	86.71 351	92.82 349	80.50 321	75.19 354	86.16 332	92.29 347	86.74 349

testmvs		17.12 330	20.53 331	6.87 343	12.05 356	4.20 358	93.62 337	6.73 358	4.62 353	10.41 353	24.33 352	8.28 361	3.56 356	9.69 353	15.07 352	12.86 353

test123		17.04 331	20.11 332	7.82 342	10.25 357	4.91 357	94.80 324	4.47 359	4.93 352	10.00 354	24.28 353	9.69 360	3.64 355	10.14 352	12.43 354	14.92 352

cdsmvs_eth3d_5k		24.66 329	32.88 330	0.00 344	0.00 358	0.00 359	0.00 350	99.10 191	0.00 354	0.00 355	97.58 272	99.21 11	0.00 357	0.00 354	0.00 355	0.00 355

pcd_1.5k_mvsjas		8.17 332	10.90 333	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	0.00 356	98.07 61	0.00 357	0.00 354	0.00 355	0.00 355

sosnet-low-res		0.00 334	0.00 335	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	0.00 356	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

sosnet		0.00 334	0.00 335	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	0.00 356	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

uncertanet		0.00 334	0.00 335	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	0.00 356	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

Regformer		0.00 334	0.00 335	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	0.00 356	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

ab-mvs-re		8.12 333	10.83 334	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	97.48 279	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

uanet		0.00 334	0.00 335	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	0.00 356	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

GSMVS																98.81 249

test_part3							97.25 215		96.66 219		98.71 179		99.86 77	93.00 279

test_part1								99.28 141				97.56 90			99.57 172	99.53 91

sam_mvs1												84.74 303				98.81 249

sam_mvs												84.29 309

MTGPA								99.20 163

test_post1							97.59 193				20.48 355	83.07 315	99.66 251	94.16 249

test_post											21.25 354	83.86 311	99.70 229

patchmatchnet-post											98.77 173	84.37 306	99.85 88

MTMP								91.91 347

test9_res														93.28 276	99.15 237	99.38 156

agg_prior2														92.50 291	99.16 234	99.37 157

test_prior4						97.97 119	95.86 295

test_prior2							95.74 301		96.48 224	96.11 303	97.63 270	95.92 192		94.16 249	99.20 227

旧先验2							95.76 299		88.56 335	97.52 248			99.66 251	94.48 240

新几何2							95.93 292

无先验							95.74 301	98.74 250	89.38 331				99.73 217	92.38 293		99.22 199

原ACMM2							95.53 308

testdata2													99.79 174	92.80 286

segment_acmp												97.02 131

testdata1							95.44 312		96.32 229

plane_prior5								99.27 146					99.70 229	94.42 244	99.51 189	99.45 132

plane_prior4											97.98 254

plane_prior3						97.78 139			97.41 176	97.79 229

plane_prior2							97.77 170		98.20 120

plane_prior						97.65 148	97.07 230		96.72 214						99.36 204

n2								0.00 360

nn								0.00 360

door-mid								99.57 43

test11								98.87 228

door								99.41 97

HQP5-MVS						96.79 184

BP-MVS														92.82 284

HQP4-MVS										95.56 316			99.54 286			99.32 174

HQP3-MVS								99.04 201							99.26 221

HQP2-MVS												93.84 245

MDTV_nov1_ep13_2view						74.92 354	97.69 178		90.06 329	97.75 232		85.78 296		93.52 270		98.69 263

ACMMP++_ref															99.77 104

ACMMP++															99.68 142

Test By Simon												96.52 165

High-resolution multi-view benchmark