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		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 3	99.99 1	100.00 1	99.98 8	99.78 8	100.00 1	99.92 3	100.00 1	99.87 10

ANet_high		99.88 4	99.87 4	99.91 2	99.99 1	99.91 2	99.65 55	100.00 1	99.90 6	100.00 1	99.97 9	99.61 17	99.97 16	99.75 31	100.00 1	99.84 15

Gipuma		99.57 48	99.59 43	99.49 163	99.98 3	99.71 53	99.72 26	99.84 36	99.81 28	99.94 20	99.78 80	98.91 82	99.71 302	98.41 156	99.95 67	99.05 282
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
anonymousdsp		99.80 12	99.77 13	99.90 4	99.96 4	99.88 7	99.73 22	99.85 28	99.70 51	99.92 30	99.93 13	99.45 22	99.97 16	99.36 65	100.00 1	99.85 14

v7n		99.82 11	99.80 11	99.88 11	99.96 4	99.84 18	99.82 9	99.82 47	99.84 22	99.94 20	99.91 19	99.13 56	99.96 33	99.83 20	99.99 20	99.83 18

PS-MVSNAJss		99.84 9	99.82 9	99.89 6	99.96 4	99.77 37	99.68 42	99.85 28	99.95 3	99.98 3	99.92 16	99.28 38	99.98 7	99.75 31	100.00 1	99.94 2

jajsoiax		99.89 3	99.89 3	99.89 6	99.96 4	99.78 35	99.70 30	99.86 21	99.89 10	99.98 3	99.90 22	99.94 2	99.98 7	99.75 31	100.00 1	99.90 5

mvs_tets		99.90 2	99.90 2	99.90 4	99.96 4	99.79 33	99.72 26	99.88 17	99.92 5	99.98 3	99.93 13	99.94 2	99.98 7	99.77 30	100.00 1	99.92 3

v52		99.85 7	99.84 7	99.89 6	99.96 4	99.89 5	99.87 4	99.81 55	99.85 18	99.96 8	99.90 22	99.27 41	99.95 41	99.93 1	99.99 20	99.82 23

V4		99.85 7	99.84 7	99.88 11	99.96 4	99.89 5	99.87 4	99.81 55	99.85 18	99.96 8	99.90 22	99.27 41	99.95 41	99.93 1	100.00 1	99.82 23

OurMVSNet-221017-0		99.75 18	99.71 24	99.84 20	99.96 4	99.83 22	99.83 7	99.85 28	99.80 31	99.93 25	99.93 13	98.54 140	99.93 65	99.59 39	99.98 36	99.76 38

pcd1.5k->3k		49.97 338	55.52 339	33.31 351	99.95 12	0.00 369	0.00 360	99.81 55	0.00 364	0.00 366	100.00 1	99.96 1	0.00 366	0.00 363	100.00 1	99.92 3

v748		99.76 16	99.74 20	99.84 20	99.95 12	99.83 22	99.82 9	99.80 59	99.82 26	99.95 16	99.87 37	98.72 111	99.93 65	99.72 34	99.98 36	99.75 42

pmmvs6		99.86 6	99.86 6	99.83 24	99.94 14	99.90 3	99.83 7	99.91 10	99.85 18	99.94 20	99.95 11	99.73 10	99.90 111	99.65 35	99.97 46	99.69 58

test_djsdf		99.84 9	99.81 10	99.91 2	99.94 14	99.84 18	99.77 14	99.80 59	99.73 43	99.97 6	99.92 16	99.77 9	99.98 7	99.43 55	100.00 1	99.90 5

MIMVSNet1		99.66 36	99.62 37	99.80 30	99.94 14	99.87 8	99.69 39	99.77 72	99.78 34	99.93 25	99.89 31	97.94 195	99.92 83	99.65 35	99.98 36	99.62 113

K. test v3		98.87 207	98.60 215	99.69 80	99.93 17	99.46 113	99.74 20	94.97 362	99.78 34	99.88 47	99.88 34	93.66 290	99.97 16	99.61 38	99.95 67	99.64 95

SixPastTwentyTwo		99.42 85	99.30 104	99.76 43	99.92 18	99.67 69	99.70 30	99.14 287	99.65 68	99.89 39	99.90 22	96.20 267	99.94 54	99.42 59	99.92 91	99.67 71

wuykxyi23d		99.65 41	99.64 35	99.69 80	99.92 18	99.20 190	98.89 220	99.99 2	98.73 204	99.95 16	99.80 64	99.84 4	99.99 4	99.64 37	99.98 36	99.89 9

Anonymous20240521		99.67 35	99.62 37	99.84 20	99.91 20	99.85 12	99.81 11	99.76 78	99.72 46	99.92 30	99.83 51	98.10 181	99.90 111	99.58 42	99.97 46	99.77 34

pm-mvs1		99.79 13	99.79 12	99.78 38	99.91 20	99.83 22	99.76 17	99.87 19	99.73 43	99.89 39	99.87 37	99.63 15	99.87 160	99.54 46	99.92 91	99.63 99

TransMVSNet (Re)		99.78 14	99.77 13	99.81 28	99.91 20	99.85 12	99.75 18	99.86 21	99.70 51	99.91 33	99.89 31	99.60 19	99.87 160	99.59 39	99.74 194	99.71 51

Baseline_NR-MVSNet		99.49 69	99.37 89	99.82 25	99.91 20	99.84 18	98.83 231	99.86 21	99.68 58	99.65 129	99.88 34	97.67 216	99.87 160	99.03 109	99.86 129	99.76 38

LTVRE_ROB	99.19 1	99.88 4	99.87 4	99.88 11	99.91 20	99.90 3	99.96 1	99.92 6	99.90 6	99.97 6	99.87 37	99.81 7	99.95 41	99.54 46	99.99 20	99.80 25
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
PVSNet_Blended_VisFu		99.40 92	99.38 85	99.44 178	99.90 25	98.66 240	98.94 218	99.91 10	97.97 261	99.79 80	99.73 101	99.05 68	99.97 16	99.15 95	99.99 20	99.68 64

TDRefinement		99.72 24	99.70 27	99.77 40	99.90 25	99.85 12	99.86 6	99.92 6	99.69 55	99.78 83	99.92 16	99.37 29	99.88 140	98.93 125	99.95 67	99.60 124

XXY-MVS		99.71 26	99.67 31	99.81 28	99.89 27	99.72 52	99.59 67	99.82 47	99.39 116	99.82 66	99.84 50	99.38 27	99.91 93	99.38 62	99.93 88	99.80 25

FC-MVSNet-test		99.70 27	99.65 33	99.86 17	99.88 28	99.86 11	99.72 26	99.78 69	99.90 6	99.82 66	99.83 51	98.45 154	99.87 160	99.51 49	99.97 46	99.86 12

EU-MVSNet		99.39 96	99.62 37	98.72 280	99.88 28	96.44 312	99.56 72	99.85 28	99.90 6	99.90 35	99.85 45	98.09 183	99.83 231	99.58 42	99.95 67	99.90 5

CHOSEN 1792x2688		99.39 96	99.30 104	99.65 98	99.88 28	99.25 177	98.78 240	99.88 17	98.66 208	99.96 8	99.79 71	97.45 227	99.93 65	99.34 67	99.99 20	99.78 32

Vis-MVSNet		99.75 18	99.74 20	99.79 35	99.88 28	99.66 71	99.69 39	99.92 6	99.67 60	99.77 88	99.75 95	99.61 17	99.98 7	99.35 66	99.98 36	99.72 48
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tfpnnormal		99.43 82	99.38 85	99.60 128	99.87 32	99.75 44	99.59 67	99.78 69	99.71 49	99.90 35	99.69 127	98.85 88	99.90 111	97.25 236	99.78 177	99.15 257

SteuartSystems-ACMMP		99.30 117	99.14 129	99.76 43	99.87 32	99.66 71	99.18 157	99.60 164	98.55 217	99.57 153	99.67 147	99.03 70	99.94 54	97.01 248	99.80 168	99.69 58
Skip Steuart: Steuart Systems R&D Blog.
no-one		99.28 120	99.23 120	99.45 176	99.87 32	99.08 205	98.95 215	99.52 205	98.88 182	99.77 88	99.83 51	97.78 208	99.90 111	98.46 154	99.99 20	99.38 216

v13		99.76 16	99.77 13	99.73 63	99.86 35	99.55 99	99.77 14	99.86 21	99.79 33	99.96 8	99.91 19	98.90 83	99.87 160	99.91 5	100.00 1	99.78 32

lessismore_v0				99.64 106	99.86 35	99.38 144		90.66 365		99.89 39	99.83 51	94.56 284	99.97 16	99.56 45	99.92 91	99.57 143

ACMH+	98.40 8	99.50 67	99.43 79	99.71 73	99.86 35	99.76 42	99.32 116	99.77 72	99.53 90	99.77 88	99.76 91	99.26 44	99.78 274	97.77 201	99.88 115	99.60 124

ACMH	98.42 6	99.59 46	99.54 54	99.72 69	99.86 35	99.62 84	99.56 72	99.79 67	98.77 196	99.80 75	99.85 45	99.64 14	99.85 198	98.70 140	99.89 109	99.70 55
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v12		99.75 18	99.77 13	99.72 69	99.85 39	99.53 102	99.75 18	99.86 21	99.78 34	99.96 8	99.90 22	98.88 86	99.86 180	99.91 5	100.00 1	99.77 34

v11		99.75 18	99.76 17	99.71 73	99.85 39	99.49 105	99.73 22	99.84 36	99.75 39	99.95 16	99.90 22	98.93 78	99.86 180	99.92 3	100.00 1	99.77 34

HyFIR lowres test		98.91 200	98.64 213	99.73 63	99.85 39	99.47 109	98.07 305	99.83 39	98.64 210	99.89 39	99.60 185	92.57 300	100.00 1	99.33 69	99.97 46	99.72 48

FIs		99.65 41	99.58 45	99.84 20	99.84 42	99.85 12	99.66 50	99.75 84	99.86 15	99.74 102	99.79 71	98.27 167	99.85 198	99.37 64	99.93 88	99.83 18

V9		99.74 22	99.75 19	99.71 73	99.84 42	99.50 103	99.74 20	99.86 21	99.76 38	99.96 8	99.90 22	98.83 89	99.85 198	99.91 5	100.00 1	99.77 34

XVG-OURS-SEG-HR		99.16 157	98.99 175	99.66 94	99.84 42	99.64 78	98.25 286	99.73 92	98.39 231	99.63 135	99.43 233	99.70 12	99.90 111	97.34 228	98.64 319	99.44 199

PMVS	92.94 21	98.82 212	98.81 201	98.85 265	99.84 42	97.99 282	99.20 155	99.47 220	99.71 49	99.42 189	99.82 59	98.09 183	99.47 351	93.88 337	99.85 132	99.07 280
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MP-MVS-pluss		99.14 160	98.92 185	99.80 30	99.83 46	99.83 22	98.61 248	99.63 143	96.84 305	99.44 183	99.58 193	98.81 90	99.91 93	97.70 205	99.82 155	99.67 71
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
V14		99.73 23	99.74 20	99.69 80	99.83 46	99.48 108	99.72 26	99.85 28	99.74 40	99.96 8	99.89 31	98.79 97	99.85 198	99.91 5	100.00 1	99.76 38

PM-MVS		99.36 103	99.29 109	99.58 134	99.83 46	99.66 71	98.95 215	99.86 21	98.85 185	99.81 72	99.73 101	98.40 159	99.92 83	98.36 160	99.83 146	99.17 255

PEN-MVS		99.66 36	99.59 43	99.89 6	99.83 46	99.87 8	99.66 50	99.73 92	99.70 51	99.84 61	99.73 101	98.56 134	99.96 33	99.29 78	99.94 80	99.83 18

HPM-MVS_fast		99.43 82	99.30 104	99.80 30	99.83 46	99.81 28	99.52 75	99.70 108	98.35 239	99.51 175	99.50 221	99.31 34	99.88 140	98.18 177	99.84 136	99.69 58

RPSCF		99.18 151	99.02 166	99.64 106	99.83 46	99.85 12	99.44 86	99.82 47	98.33 244	99.50 177	99.78 80	97.90 197	99.65 335	96.78 259	99.83 146	99.44 199

COLMAP_ROB	98.06 12	99.45 80	99.37 89	99.70 79	99.83 46	99.70 60	99.38 97	99.78 69	99.53 90	99.67 119	99.78 80	99.19 48	99.86 180	97.32 229	99.87 122	99.55 147
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TSAR-MVS + MP.		99.34 110	99.24 118	99.63 110	99.82 53	99.37 147	99.26 139	99.35 253	98.77 196	99.57 153	99.70 121	99.27 41	99.88 140	97.71 204	99.75 186	99.65 89

new-patchmatchnet		99.35 105	99.57 48	98.71 281	99.82 53	96.62 310	98.55 257	99.75 84	99.50 93	99.88 47	99.87 37	99.31 34	99.88 140	99.43 55	100.00 1	99.62 113

v15		99.72 24	99.73 23	99.68 83	99.82 53	99.44 120	99.70 30	99.85 28	99.72 46	99.95 16	99.88 34	98.76 104	99.84 214	99.90 9	100.00 1	99.75 42

VPNet		99.46 78	99.37 89	99.71 73	99.82 53	99.59 91	99.48 81	99.70 108	99.81 28	99.69 114	99.58 193	97.66 220	99.86 180	99.17 91	99.44 255	99.67 71

XVG-OURS		99.21 143	99.06 155	99.65 98	99.82 53	99.62 84	97.87 325	99.74 89	98.36 234	99.66 123	99.68 140	99.71 11	99.90 111	96.84 256	99.88 115	99.43 205

XVG-ACMP-BASELINE		99.23 132	99.10 145	99.63 110	99.82 53	99.58 93	98.83 231	99.72 102	98.36 234	99.60 149	99.71 114	98.92 80	99.91 93	97.08 245	99.84 136	99.40 210

LPG-MVS_test		99.22 140	99.05 159	99.74 57	99.82 53	99.63 82	99.16 170	99.73 92	97.56 282	99.64 131	99.69 127	99.37 29	99.89 125	96.66 266	99.87 122	99.69 58

LGP-MVS_train				99.74 57	99.82 53	99.63 82		99.73 92	97.56 282	99.64 131	99.69 127	99.37 29	99.89 125	96.66 266	99.87 122	99.69 58

zzz-MVS		99.30 117	99.14 129	99.80 30	99.81 61	99.81 28	98.73 244	99.53 195	99.27 129	99.42 189	99.63 166	98.21 173	99.95 41	97.83 198	99.79 171	99.65 89

MTAPA		99.35 105	99.20 124	99.80 30	99.81 61	99.81 28	99.33 113	99.53 195	99.27 129	99.42 189	99.63 166	98.21 173	99.95 41	97.83 198	99.79 171	99.65 89

testing_2		99.58 47	99.56 52	99.62 119	99.81 61	99.44 120	99.14 177	99.43 231	99.69 55	99.82 66	99.79 71	99.14 53	99.79 266	99.31 74	99.95 67	99.63 99

v17		99.70 27	99.71 24	99.67 86	99.81 61	99.44 120	99.70 30	99.83 39	99.69 55	99.94 20	99.87 37	98.70 112	99.84 214	99.88 14	99.99 20	99.73 45

v16		99.70 27	99.71 24	99.67 86	99.81 61	99.43 126	99.70 30	99.83 39	99.70 51	99.94 20	99.87 37	98.69 114	99.84 214	99.88 14	99.99 20	99.73 45

v10		99.69 31	99.69 28	99.66 94	99.81 61	99.39 138	99.66 50	99.75 84	99.60 83	99.92 30	99.87 37	98.75 107	99.86 180	99.90 9	99.99 20	99.73 45

HPM-MVS		99.25 127	99.07 153	99.78 38	99.81 61	99.75 44	99.61 62	99.67 122	97.72 274	99.35 211	99.25 271	99.23 45	99.92 83	97.21 240	99.82 155	99.67 71
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
IterMVS-LS		99.41 89	99.47 70	99.25 227	99.81 61	98.09 278	98.85 228	99.76 78	99.62 74	99.83 65	99.64 158	98.54 140	99.97 16	99.15 95	99.99 20	99.68 64
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1neww		99.55 55	99.54 54	99.61 122	99.80 69	99.39 138	99.32 116	99.61 150	99.18 146	99.87 52	99.69 127	98.64 126	99.82 239	99.79 26	99.94 80	99.60 124

v7new		99.55 55	99.54 54	99.61 122	99.80 69	99.39 138	99.32 116	99.61 150	99.18 146	99.87 52	99.69 127	98.64 126	99.82 239	99.79 26	99.94 80	99.60 124

v1240		99.56 51	99.58 45	99.51 159	99.80 69	99.00 210	99.00 204	99.65 135	99.15 153	99.90 35	99.75 95	99.09 60	99.88 140	99.90 9	99.96 59	99.67 71

v8		99.68 32	99.69 28	99.65 98	99.80 69	99.40 135	99.66 50	99.76 78	99.64 70	99.93 25	99.85 45	98.66 121	99.84 214	99.88 14	99.99 20	99.71 51

v7		99.56 51	99.54 54	99.61 122	99.80 69	99.39 138	99.30 126	99.59 169	99.14 155	99.82 66	99.72 107	98.75 107	99.84 214	99.83 20	99.94 80	99.61 118

v6		99.55 55	99.54 54	99.61 122	99.80 69	99.39 138	99.32 116	99.60 164	99.18 146	99.87 52	99.68 140	98.65 123	99.82 239	99.79 26	99.95 67	99.61 118

MDA-MVSNet-bldmvs		99.06 172	99.05 159	99.07 247	99.80 69	97.83 288	98.89 220	99.72 102	99.29 125	99.63 135	99.70 121	96.47 260	99.89 125	98.17 179	99.82 155	99.50 175

PS-CasMVS		99.66 36	99.58 45	99.89 6	99.80 69	99.85 12	99.66 50	99.73 92	99.62 74	99.84 61	99.71 114	98.62 128	99.96 33	99.30 75	99.96 59	99.86 12

DTE-MVSNet		99.68 32	99.61 41	99.88 11	99.80 69	99.87 8	99.67 47	99.71 105	99.72 46	99.84 61	99.78 80	98.67 119	99.97 16	99.30 75	99.95 67	99.80 25

WR-MVS_H		99.61 45	99.53 62	99.87 15	99.80 69	99.83 22	99.67 47	99.75 84	99.58 86	99.85 58	99.69 127	98.18 178	99.94 54	99.28 80	99.95 67	99.83 18

IS-MVSNet		99.03 178	98.85 194	99.55 149	99.80 69	99.25 177	99.73 22	99.15 286	99.37 118	99.61 147	99.71 114	94.73 282	99.81 258	97.70 205	99.88 115	99.58 139

EPP-MVSNet		99.17 154	99.00 171	99.66 94	99.80 69	99.43 126	99.70 30	99.24 278	99.48 95	99.56 161	99.77 87	94.89 280	99.93 65	98.72 139	99.89 109	99.63 99

ACMM	98.09 11	99.46 78	99.38 85	99.72 69	99.80 69	99.69 64	99.13 182	99.65 135	98.99 170	99.64 131	99.72 107	99.39 23	99.86 180	98.23 170	99.81 163	99.60 124
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v1144		99.54 60	99.53 62	99.59 130	99.79 82	99.28 167	99.10 186	99.61 150	99.20 144	99.84 61	99.73 101	98.67 119	99.84 214	99.86 19	99.98 36	99.64 95

v18		99.68 32	99.69 28	99.65 98	99.79 82	99.40 135	99.68 42	99.83 39	99.66 65	99.93 25	99.85 45	98.65 123	99.84 214	99.87 18	99.99 20	99.71 51

V42		99.56 51	99.54 54	99.63 110	99.79 82	99.46 113	99.39 91	99.59 169	99.24 138	99.86 57	99.70 121	98.55 138	99.82 239	99.79 26	99.95 67	99.60 124

test20.03		99.55 55	99.54 54	99.58 134	99.79 82	99.37 147	99.02 200	99.89 14	99.60 83	99.82 66	99.62 173	98.81 90	99.89 125	99.43 55	99.86 129	99.47 188

test_0402		99.22 140	99.14 129	99.45 176	99.79 82	99.43 126	99.28 135	99.68 117	99.54 88	99.40 199	99.56 203	99.07 65	99.82 239	96.01 292	99.96 59	99.11 266

ACMMP		99.25 127	99.08 149	99.74 57	99.79 82	99.68 67	99.50 77	99.65 135	98.07 255	99.52 173	99.69 127	98.57 133	99.92 83	97.18 242	99.79 171	99.63 99
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
HSP-MVS		99.01 184	98.76 205	99.76 43	99.78 88	99.73 50	99.35 104	99.31 262	98.54 219	99.54 168	98.99 307	96.81 252	99.93 65	96.97 250	99.53 244	99.61 118

v144192		99.55 55	99.54 54	99.58 134	99.78 88	99.20 190	99.11 185	99.62 146	99.18 146	99.89 39	99.72 107	98.66 121	99.87 160	99.88 14	99.97 46	99.66 81

AllTest		99.21 143	99.07 153	99.63 110	99.78 88	99.64 78	99.12 184	99.83 39	98.63 211	99.63 135	99.72 107	98.68 116	99.75 288	96.38 278	99.83 146	99.51 169

TestCases				99.63 110	99.78 88	99.64 78		99.83 39	98.63 211	99.63 135	99.72 107	98.68 116	99.75 288	96.38 278	99.83 146	99.51 169

v1141		99.54 60	99.52 64	99.57 140	99.78 88	99.27 171	99.15 172	99.61 150	99.26 133	99.89 39	99.69 127	98.56 134	99.82 239	99.82 23	99.97 46	99.63 99

divwei89l23v2f112		99.54 60	99.52 64	99.57 140	99.78 88	99.27 171	99.15 172	99.61 150	99.26 133	99.89 39	99.69 127	98.56 134	99.82 239	99.82 23	99.96 59	99.63 99

v2v482		99.50 67	99.47 70	99.58 134	99.78 88	99.25 177	99.14 177	99.58 177	99.25 136	99.81 72	99.62 173	98.24 169	99.84 214	99.83 20	99.97 46	99.64 95

FMVSNet1		99.66 36	99.63 36	99.73 63	99.78 88	99.77 37	99.68 42	99.70 108	99.67 60	99.82 66	99.83 51	98.98 72	99.90 111	99.24 82	99.97 46	99.53 158

Vis-MVSNet (Re-imp)		98.77 218	98.58 218	99.34 205	99.78 88	98.88 226	99.61 62	99.56 183	99.11 158	99.24 232	99.56 203	93.00 298	99.78 274	97.43 224	99.89 109	99.35 225

ACMP	97.51 14	99.05 175	98.84 196	99.67 86	99.78 88	99.55 99	98.88 222	99.66 126	97.11 301	99.47 180	99.60 185	99.07 65	99.89 125	96.18 284	99.85 132	99.58 139
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
pmmvs-eth3d		99.48 71	99.47 70	99.51 159	99.77 98	99.41 134	98.81 235	99.66 126	99.42 113	99.75 94	99.66 152	99.20 47	99.76 282	98.98 114	99.99 20	99.36 223

Patchmatch-RL test		98.60 229	98.36 238	99.33 207	99.77 98	99.07 207	98.27 284	99.87 19	98.91 180	99.74 102	99.72 107	90.57 321	99.79 266	98.55 150	99.85 132	99.11 266

v1192		99.57 48	99.57 48	99.57 140	99.77 98	99.22 184	99.04 197	99.60 164	99.18 146	99.87 52	99.72 107	99.08 63	99.85 198	99.89 13	99.98 36	99.66 81

v1		99.54 60	99.52 64	99.58 134	99.77 98	99.28 167	99.15 172	99.61 150	99.26 133	99.88 47	99.68 140	98.56 134	99.82 239	99.82 23	99.97 46	99.63 99

EG-PatchMatch MVS		99.57 48	99.56 52	99.62 119	99.77 98	99.33 157	99.26 139	99.76 78	99.32 124	99.80 75	99.78 80	99.29 36	99.87 160	99.15 95	99.91 101	99.66 81

pmmvs5		99.19 148	99.11 138	99.42 183	99.76 103	98.88 226	98.55 257	99.73 92	98.82 189	99.72 106	99.62 173	96.56 256	99.82 239	99.32 72	99.95 67	99.56 144

nrg030		99.70 27	99.66 32	99.82 25	99.76 103	99.84 18	99.61 62	99.70 108	99.93 4	99.78 83	99.68 140	99.10 58	99.78 274	99.45 53	99.96 59	99.83 18

v148		99.40 92	99.41 81	99.39 194	99.76 103	98.94 217	99.09 190	99.59 169	99.17 151	99.81 72	99.61 182	98.41 157	99.69 309	99.32 72	99.94 80	99.53 158

region2R		99.23 132	99.05 159	99.77 40	99.76 103	99.70 60	99.31 123	99.59 169	98.41 229	99.32 219	99.36 248	98.73 110	99.93 65	97.29 231	99.74 194	99.67 71

MP-MVS		99.06 172	98.83 199	99.76 43	99.76 103	99.71 53	99.32 116	99.50 211	98.35 239	98.97 262	99.48 224	98.37 160	99.92 83	95.95 298	99.75 186	99.63 99
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PMMVS2		99.48 71	99.45 74	99.57 140	99.76 103	98.99 211	98.09 301	99.90 13	98.95 174	99.78 83	99.58 193	99.57 20	99.93 65	99.48 51	99.95 67	99.79 31

CP-MVSNet		99.54 60	99.43 79	99.87 15	99.76 103	99.82 27	99.57 70	99.61 150	99.54 88	99.80 75	99.64 158	97.79 207	99.95 41	99.21 83	99.94 80	99.84 15

mPP-MVS		99.19 148	99.00 171	99.76 43	99.76 103	99.68 67	99.38 97	99.54 190	98.34 243	99.01 259	99.50 221	98.53 144	99.93 65	97.18 242	99.78 177	99.66 81

semantic-postprocess				98.51 285	99.75 111	95.90 323		99.84 36	99.84 22	99.89 39	99.73 101	95.96 272	99.99 4	99.33 69	100.00 1	99.63 99

ACMMP_Plus		99.28 120	99.11 138	99.79 35	99.75 111	99.81 28	98.95 215	99.53 195	98.27 248	99.53 171	99.73 101	98.75 107	99.87 160	97.70 205	99.83 146	99.68 64

v1921920		99.56 51	99.57 48	99.55 149	99.75 111	99.11 199	99.05 195	99.61 150	99.15 153	99.88 47	99.71 114	99.08 63	99.87 160	99.90 9	99.97 46	99.66 81

testgi		99.29 119	99.26 115	99.37 200	99.75 111	98.81 233	98.84 229	99.89 14	98.38 232	99.75 94	99.04 305	99.36 32	99.86 180	99.08 106	99.25 283	99.45 194

PGM-MVS		99.20 145	99.01 169	99.77 40	99.75 111	99.71 53	99.16 170	99.72 102	97.99 259	99.42 189	99.60 185	98.81 90	99.93 65	96.91 252	99.74 194	99.66 81

jason		99.16 157	99.11 138	99.32 211	99.75 111	98.44 249	98.26 285	99.39 243	98.70 206	99.74 102	99.30 261	98.54 140	99.97 16	98.48 153	99.82 155	99.55 147
jason: jason.
Anonymous20231206		99.35 105	99.31 99	99.47 168	99.74 117	99.06 209	99.28 135	99.74 89	99.23 140	99.72 106	99.53 212	97.63 222	99.88 140	99.11 103	99.84 136	99.48 183

ACMMPR		99.23 132	99.06 155	99.76 43	99.74 117	99.69 64	99.31 123	99.59 169	98.36 234	99.35 211	99.38 242	98.61 130	99.93 65	97.43 224	99.75 186	99.67 71

IterMVS		98.97 190	99.16 126	98.42 290	99.74 117	95.64 330	98.06 306	99.83 39	99.83 25	99.85 58	99.74 97	96.10 270	99.99 4	99.27 81	100.00 1	99.63 99
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
conf0.01		97.19 295	96.74 301	98.51 285	99.73 120	98.35 258	99.35 104	95.78 353	96.54 309	99.39 200	99.08 293	86.57 346	99.88 140	95.69 306	98.57 322	97.30 349

conf0.002		97.19 295	96.74 301	98.51 285	99.73 120	98.35 258	99.35 104	95.78 353	96.54 309	99.39 200	99.08 293	86.57 346	99.88 140	95.69 306	98.57 322	97.30 349

thresconf0.02		97.25 290	96.74 301	98.75 275	99.73 120	98.35 258	99.35 104	95.78 353	96.54 309	99.39 200	99.08 293	86.57 346	99.88 140	95.69 306	98.57 322	98.02 332

tfpn_n400		97.25 290	96.74 301	98.75 275	99.73 120	98.35 258	99.35 104	95.78 353	96.54 309	99.39 200	99.08 293	86.57 346	99.88 140	95.69 306	98.57 322	98.02 332

tfpnconf		97.25 290	96.74 301	98.75 275	99.73 120	98.35 258	99.35 104	95.78 353	96.54 309	99.39 200	99.08 293	86.57 346	99.88 140	95.69 306	98.57 322	98.02 332

tfpnview11		97.25 290	96.74 301	98.75 275	99.73 120	98.35 258	99.35 104	95.78 353	96.54 309	99.39 200	99.08 293	86.57 346	99.88 140	95.69 306	98.57 322	98.02 332

HFP-MVS		99.25 127	99.08 149	99.76 43	99.73 120	99.70 60	99.31 123	99.59 169	98.36 234	99.36 209	99.37 243	98.80 94	99.91 93	97.43 224	99.75 186	99.68 64

#test#		99.12 164	98.90 189	99.76 43	99.73 120	99.70 60	99.10 186	99.59 169	97.60 280	99.36 209	99.37 243	98.80 94	99.91 93	96.84 256	99.75 186	99.68 64

testmv		99.53 66	99.51 67	99.59 130	99.73 120	99.31 160	98.48 266	99.92 6	99.57 87	99.87 52	99.79 71	99.12 57	99.91 93	99.16 94	99.99 20	99.55 147

114514_t		98.49 240	98.11 255	99.64 106	99.73 120	99.58 93	99.24 144	99.76 78	89.94 355	99.42 189	99.56 203	97.76 209	99.86 180	97.74 203	99.82 155	99.47 188

UA-Net		99.78 14	99.76 17	99.86 17	99.72 130	99.71 53	99.91 3	99.95 5	99.96 2	99.71 110	99.91 19	99.15 52	99.97 16	99.50 50	100.00 1	99.90 5

N_pmnet		98.73 223	98.53 223	99.35 204	99.72 130	98.67 239	98.34 280	94.65 363	98.35 239	99.79 80	99.68 140	98.03 187	99.93 65	98.28 168	99.92 91	99.44 199

DeepC-MVS	98.90 4	99.62 43	99.61 41	99.67 86	99.72 130	99.44 120	99.24 144	99.71 105	99.27 129	99.93 25	99.90 22	99.70 12	99.93 65	98.99 112	99.99 20	99.64 95
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
XVS		99.27 125	99.11 138	99.75 53	99.71 133	99.71 53	99.37 101	99.61 150	99.29 125	98.76 287	99.47 227	98.47 151	99.88 140	97.62 212	99.73 200	99.67 71

X-MVStestdata		96.09 326	94.87 334	99.75 53	99.71 133	99.71 53	99.37 101	99.61 150	99.29 125	98.76 287	61.30 368	98.47 151	99.88 140	97.62 212	99.73 200	99.67 71

VDDNet		98.97 190	98.82 200	99.42 183	99.71 133	98.81 233	99.62 58	98.68 308	99.81 28	99.38 207	99.80 64	94.25 286	99.85 198	98.79 133	99.32 274	99.59 135

abl_6		99.36 103	99.23 120	99.75 53	99.71 133	99.74 49	99.33 113	99.76 78	99.07 165	99.65 129	99.63 166	99.09 60	99.92 83	97.13 244	99.76 183	99.58 139

DSMNet-mixed		99.48 71	99.65 33	98.95 255	99.71 133	97.27 301	99.50 77	99.82 47	99.59 85	99.41 195	99.85 45	99.62 16	100.00 1	99.53 48	99.89 109	99.59 135

CSCG		99.37 100	99.29 109	99.60 128	99.71 133	99.46 113	99.43 87	99.85 28	98.79 193	99.41 195	99.60 185	98.92 80	99.92 83	98.02 186	99.92 91	99.43 205

LF4IMVS		99.01 184	98.92 185	99.27 218	99.71 133	99.28 167	98.59 251	99.77 72	98.32 245	99.39 200	99.41 237	98.62 128	99.84 214	96.62 269	99.84 136	98.69 303

OPM-MVS		99.26 126	99.13 132	99.63 110	99.70 140	99.61 88	98.58 252	99.48 216	98.50 222	99.52 173	99.63 166	99.14 53	99.76 282	97.89 194	99.77 181	99.51 169

new_pmnet		98.88 206	98.89 190	98.84 267	99.70 140	97.62 295	98.15 293	99.50 211	97.98 260	99.62 142	99.54 210	98.15 179	99.94 54	97.55 217	99.84 136	98.95 289

view600		96.86 305	96.52 308	97.88 310	99.69 142	95.87 325	99.39 91	97.68 334	99.11 158	98.96 264	97.82 350	87.40 332	99.79 266	89.78 345	98.83 303	97.98 336

view800		96.86 305	96.52 308	97.88 310	99.69 142	95.87 325	99.39 91	97.68 334	99.11 158	98.96 264	97.82 350	87.40 332	99.79 266	89.78 345	98.83 303	97.98 336

conf0.05thres1000		96.86 305	96.52 308	97.88 310	99.69 142	95.87 325	99.39 91	97.68 334	99.11 158	98.96 264	97.82 350	87.40 332	99.79 266	89.78 345	98.83 303	97.98 336

tfpn		96.86 305	96.52 308	97.88 310	99.69 142	95.87 325	99.39 91	97.68 334	99.11 158	98.96 264	97.82 350	87.40 332	99.79 266	89.78 345	98.83 303	97.98 336

PNet_i23d		97.02 300	97.87 273	94.49 347	99.69 142	84.81 366	95.18 359	99.85 28	97.83 271	99.32 219	99.57 199	95.53 277	99.47 351	96.09 286	97.74 350	99.18 253

wuyk23d		97.58 282	99.13 132	92.93 348	99.69 142	99.49 105	99.52 75	99.77 72	97.97 261	99.96 8	99.79 71	99.84 4	99.94 54	95.85 300	99.82 155	79.36 360

DeepMVS_CX				97.98 306	99.69 142	96.95 306		99.26 272	75.51 360	95.74 360	98.28 343	96.47 260	99.62 339	91.23 343	97.89 348	97.38 347

VPA-MVSNet		99.66 36	99.62 37	99.79 35	99.68 149	99.75 44	99.62 58	99.69 114	99.85 18	99.80 75	99.81 62	98.81 90	99.91 93	99.47 52	99.88 115	99.70 55

UnsupCasMVSNet_eth		98.83 210	98.57 219	99.59 130	99.68 149	99.45 118	98.99 208	99.67 122	99.48 95	99.55 165	99.36 248	94.92 279	99.86 180	98.95 123	96.57 355	99.45 194

Test_1112_low_res		98.95 196	98.73 206	99.63 110	99.68 149	99.15 196	98.09 301	99.80 59	97.14 298	99.46 182	99.40 238	96.11 269	99.89 125	99.01 111	99.84 136	99.84 15

MVE	92.54 22	96.66 313	96.11 317	98.31 297	99.68 149	97.55 297	97.94 320	95.60 359	99.37 118	90.68 363	98.70 332	96.56 256	98.61 361	86.94 359	99.55 239	98.77 301
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tfpn1000		97.28 289	96.83 298	98.64 282	99.67 153	97.68 294	99.41 88	95.47 360	97.14 298	99.43 187	99.07 300	85.87 353	99.88 140	96.78 259	98.67 318	98.34 318

our_test_3		98.85 209	99.09 147	98.13 303	99.66 154	94.90 339	97.72 329	99.58 177	99.07 165	99.64 131	99.62 173	98.19 176	99.93 65	98.41 156	99.95 67	99.55 147

ppachtmachnet_test		98.89 205	99.12 135	98.20 300	99.66 154	95.24 336	97.63 331	99.68 117	99.08 163	99.78 83	99.62 173	98.65 123	99.88 140	98.02 186	99.96 59	99.48 183

CP-MVS		99.23 132	99.05 159	99.75 53	99.66 154	99.66 71	99.38 97	99.62 146	98.38 232	99.06 257	99.27 267	98.79 97	99.94 54	97.51 220	99.82 155	99.66 81

1112_ss		99.05 175	98.84 196	99.67 86	99.66 154	99.29 165	98.52 262	99.82 47	97.65 278	99.43 187	99.16 284	96.42 262	99.91 93	99.07 107	99.84 136	99.80 25

1111		97.29 288	96.71 307	99.04 250	99.65 158	97.72 290	98.35 278	99.80 59	99.40 114	99.66 123	99.43 233	75.10 367	99.87 160	98.98 114	99.98 36	99.52 166

.test1245		85.84 337	89.27 338	75.54 350	99.65 158	97.72 290	98.35 278	99.80 59	99.40 114	99.66 123	99.43 233	75.10 367	99.87 160	98.98 114	33.07 361	29.03 362

YYNet1		98.95 196	98.99 175	98.84 267	99.64 160	97.14 304	98.22 288	99.32 258	98.92 179	99.59 150	99.66 152	97.40 229	99.83 231	98.27 169	99.90 103	99.55 147

MDA-MVSNet_test_wron		98.95 196	98.99 175	98.85 265	99.64 160	97.16 303	98.23 287	99.33 256	98.93 177	99.56 161	99.66 152	97.39 231	99.83 231	98.29 167	99.88 115	99.55 147

tfpn111		96.50 316	96.12 316	97.65 321	99.63 162	95.93 320	99.18 157	97.57 339	98.75 201	98.70 292	97.31 360	87.04 337	99.72 296	88.27 352	98.61 321	97.30 349

conf200view11		96.43 317	96.03 319	97.63 322	99.63 162	95.93 320	99.18 157	97.57 339	98.75 201	98.70 292	97.31 360	87.04 337	99.67 323	87.62 354	98.51 331	97.30 349

thres100view900		96.39 319	96.03 319	97.47 325	99.63 162	95.93 320	99.18 157	97.57 339	98.75 201	98.70 292	97.31 360	87.04 337	99.67 323	87.62 354	98.51 331	96.81 354

thres600view7		96.60 314	96.16 315	97.93 308	99.63 162	96.09 318	99.18 157	97.57 339	98.77 196	98.72 290	97.32 359	87.04 337	99.72 296	88.57 350	98.62 320	97.98 336

ITE_SJBPF				99.38 196	99.63 162	99.44 120		99.73 92	98.56 216	99.33 217	99.53 212	98.88 86	99.68 318	96.01 292	99.65 221	99.02 285

test_part2					99.62 167	99.67 69				99.55 165

v1.0		41.33 339	55.11 340	0.00 354	99.62 167	0.00 369	0.00 360	99.53 195	97.71 275	99.55 165	99.57 199	0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

Anonymous20231211		99.62 43	99.57 48	99.76 43	99.61 169	99.60 89	99.81 11	99.73 92	99.82 26	99.90 35	99.90 22	97.97 194	99.86 180	99.42 59	99.96 59	99.80 25

CPTT-MVS		98.74 221	98.44 227	99.64 106	99.61 169	99.38 144	99.18 157	99.55 186	96.49 315	99.27 226	99.37 243	97.11 245	99.92 83	95.74 305	99.67 216	99.62 113

tfpn_ndepth		96.93 304	96.43 312	98.42 290	99.60 171	97.72 290	99.22 151	95.16 361	95.91 322	99.26 228	98.79 327	85.56 354	99.87 160	96.03 291	98.35 335	97.68 344

MSDG		99.08 170	98.98 178	99.37 200	99.60 171	99.13 197	97.54 335	99.74 89	98.84 188	99.53 171	99.55 208	99.10 58	99.79 266	97.07 246	99.86 129	99.18 253

FPMVS		96.32 321	95.50 328	98.79 272	99.60 171	98.17 272	98.46 271	98.80 302	97.16 297	96.28 355	99.63 166	82.19 358	99.09 357	88.45 351	98.89 302	99.10 270

xiu_mvs_v1_base_debu		99.23 132	99.34 94	98.91 259	99.59 174	98.23 267	98.47 267	99.66 126	99.61 78	99.68 116	98.94 318	99.39 23	99.97 16	99.18 88	99.55 239	98.51 311

xiu_mvs_v1_base		99.23 132	99.34 94	98.91 259	99.59 174	98.23 267	98.47 267	99.66 126	99.61 78	99.68 116	98.94 318	99.39 23	99.97 16	99.18 88	99.55 239	98.51 311

xiu_mvs_v1_base_debi		99.23 132	99.34 94	98.91 259	99.59 174	98.23 267	98.47 267	99.66 126	99.61 78	99.68 116	98.94 318	99.39 23	99.97 16	99.18 88	99.55 239	98.51 311

tfpn200view9		96.30 322	95.89 321	97.53 323	99.58 177	96.11 316	99.00 204	97.54 344	98.43 226	98.52 306	96.98 365	86.85 341	99.67 323	87.62 354	98.51 331	96.81 354

EI-MVSNet		99.38 98	99.44 76	99.21 232	99.58 177	98.09 278	99.26 139	99.46 223	99.62 74	99.75 94	99.67 147	98.54 140	99.85 198	99.15 95	99.92 91	99.68 64

CVMVSNet		98.61 228	98.88 191	97.80 316	99.58 177	93.60 344	99.26 139	99.64 140	99.66 65	99.72 106	99.67 147	93.26 293	99.93 65	99.30 75	99.81 163	99.87 10

thres400		96.40 318	95.89 321	97.92 309	99.58 177	96.11 316	99.00 204	97.54 344	98.43 226	98.52 306	96.98 365	86.85 341	99.67 323	87.62 354	98.51 331	97.98 336

MCST-MVS		99.02 180	98.81 201	99.65 98	99.58 177	99.49 105	98.58 252	99.07 290	98.40 230	99.04 258	99.25 271	98.51 148	99.80 263	97.31 230	99.51 246	99.65 89

HQP_MVS		98.90 202	98.68 210	99.55 149	99.58 177	99.24 180	98.80 236	99.54 190	98.94 175	99.14 247	99.25 271	97.24 237	99.82 239	95.84 301	99.78 177	99.60 124

plane_prior7					99.58 177	99.38 144

TranMVSNet+NR-MVSNet		99.54 60	99.47 70	99.76 43	99.58 177	99.64 78	99.30 126	99.63 143	99.61 78	99.71 110	99.56 203	98.76 104	99.96 33	99.14 101	99.92 91	99.68 64

MVS_111021_LR		99.13 162	99.03 165	99.42 183	99.58 177	99.32 159	97.91 324	99.73 92	98.68 207	99.31 221	99.48 224	99.09 60	99.66 328	97.70 205	99.77 181	99.29 238

ESAPD		99.14 160	98.92 185	99.82 25	99.57 186	99.77 37	98.74 242	99.60 164	98.55 217	99.76 91	99.69 127	98.23 172	99.92 83	96.39 277	99.75 186	99.76 38

EI-MVSNet-UG-set		99.48 71	99.50 68	99.42 183	99.57 186	98.65 242	99.24 144	99.46 223	99.68 58	99.80 75	99.66 152	98.99 71	99.89 125	99.19 86	99.90 103	99.72 48

EI-MVSNet-Vis-set		99.47 77	99.49 69	99.42 183	99.57 186	98.66 240	99.24 144	99.46 223	99.67 60	99.79 80	99.65 157	98.97 74	99.89 125	99.15 95	99.89 109	99.71 51

pmmvs4		99.13 162	99.06 155	99.36 203	99.57 186	99.10 202	98.01 309	99.25 275	98.78 195	99.58 151	99.44 232	98.24 169	99.76 282	98.74 138	99.93 88	99.22 243

DI_MVS_plusplus_test		98.80 215	98.65 212	99.27 218	99.57 186	98.90 224	98.44 273	97.95 330	99.02 169	99.51 175	99.23 279	96.18 268	99.76 282	98.52 152	99.42 262	99.14 261

MVSFormer		99.41 89	99.44 76	99.31 213	99.57 186	98.40 253	99.77 14	99.80 59	99.73 43	99.63 135	99.30 261	98.02 189	99.98 7	99.43 55	99.69 209	99.55 147

lupinMVS		98.96 193	98.87 192	99.24 229	99.57 186	98.40 253	98.12 297	99.18 283	98.28 247	99.63 135	99.13 286	98.02 189	99.97 16	98.22 171	99.69 209	99.35 225

Test4		98.65 226	98.44 227	99.27 218	99.57 186	98.86 229	98.43 274	99.41 234	98.85 185	99.57 153	98.95 317	93.05 296	99.75 288	98.57 148	99.56 233	99.19 250

ab-mvs		99.33 113	99.28 111	99.47 168	99.57 186	99.39 138	99.78 13	99.43 231	98.87 183	99.57 153	99.82 59	98.06 186	99.87 160	98.69 142	99.73 200	99.15 257

DP-MVS		99.48 71	99.39 83	99.74 57	99.57 186	99.62 84	99.29 134	99.61 150	99.87 13	99.74 102	99.76 91	98.69 114	99.87 160	98.20 173	99.80 168	99.75 42

F-COLMAP		98.74 221	98.45 226	99.62 119	99.57 186	99.47 109	98.84 229	99.65 135	96.31 317	98.93 270	99.19 283	97.68 215	99.87 160	96.52 272	99.37 269	99.53 158

CLD-MVS		98.76 219	98.57 219	99.33 207	99.57 186	98.97 214	97.53 337	99.55 186	96.41 316	99.27 226	99.13 286	99.07 65	99.78 274	96.73 263	99.89 109	99.23 242
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_normal		98.82 212	98.67 211	99.27 218	99.56 198	98.83 232	98.22 288	98.01 327	99.03 168	99.49 179	99.24 276	96.21 266	99.76 282	98.69 142	99.56 233	99.22 243

UnsupCasMVSNet_bld		98.55 235	98.27 244	99.40 191	99.56 198	99.37 147	97.97 317	99.68 117	97.49 286	99.08 252	99.35 253	95.41 278	99.82 239	97.70 205	98.19 341	99.01 286

APDe-MVS		99.48 71	99.36 92	99.85 19	99.55 200	99.81 28	99.50 77	99.69 114	98.99 170	99.75 94	99.71 114	98.79 97	99.93 65	98.46 154	99.85 132	99.80 25

PVSNet_BlendedMVS		99.03 178	99.01 169	99.09 243	99.54 201	97.99 282	98.58 252	99.82 47	97.62 279	99.34 215	99.71 114	98.52 146	99.77 280	97.98 190	99.97 46	99.52 166

PVSNet_Blended		98.70 224	98.59 216	99.02 252	99.54 201	97.99 282	97.58 334	99.82 47	95.70 328	99.34 215	98.98 310	98.52 146	99.77 280	97.98 190	99.83 146	99.30 235

USDC		98.96 193	98.93 182	99.05 249	99.54 201	97.99 282	97.07 347	99.80 59	98.21 250	99.75 94	99.77 87	98.43 155	99.64 337	97.90 193	99.88 115	99.51 169

Anonymous20240529		99.42 85	99.34 94	99.65 98	99.53 204	99.60 89	99.63 57	99.39 243	99.47 99	99.76 91	99.78 80	98.13 180	99.86 180	98.70 140	99.68 211	99.49 181

APD-MVS_3200maxsize		99.31 116	99.16 126	99.74 57	99.53 204	99.75 44	99.27 138	99.61 150	99.19 145	99.57 153	99.64 158	98.76 104	99.90 111	97.29 231	99.62 224	99.56 144

MIMVSNet		98.43 245	98.20 249	99.11 240	99.53 204	98.38 256	99.58 69	98.61 311	98.96 173	99.33 217	99.76 91	90.92 314	99.81 258	97.38 227	99.76 183	99.15 257

Regformer-3		99.41 89	99.41 81	99.40 191	99.52 207	98.70 237	99.17 164	99.44 228	99.62 74	99.75 94	99.60 185	98.90 83	99.85 198	98.89 127	99.84 136	99.65 89

Regformer-4		99.45 80	99.44 76	99.50 161	99.52 207	98.94 217	99.17 164	99.53 195	99.64 70	99.76 91	99.60 185	98.96 77	99.90 111	98.91 126	99.84 136	99.67 71

HPM-MVS++		98.96 193	98.70 208	99.74 57	99.52 207	99.71 53	98.86 225	99.19 282	98.47 225	98.59 302	99.06 301	98.08 185	99.91 93	96.94 251	99.60 229	99.60 124

GA-MVS		97.99 274	97.68 281	98.93 258	99.52 207	98.04 281	97.19 346	99.05 293	98.32 245	98.81 281	98.97 313	89.89 328	99.41 355	98.33 163	99.05 293	99.34 227

test222					99.51 211	99.08 205	97.83 327	99.29 266	95.21 335	98.68 296	99.31 258	97.28 236			99.38 267	99.43 205

testdata				99.42 183	99.51 211	98.93 221		99.30 265	96.20 318	98.87 277	99.40 238	98.33 164	99.89 125	96.29 281	99.28 278	99.44 199

casdiffmvs1		99.40 92	99.38 85	99.46 171	99.51 211	99.31 160	99.53 74	99.64 140	99.74 40	99.08 252	99.77 87	98.10 181	99.73 294	99.59 39	99.47 251	99.33 228

plane_prior1					99.51 211

UniMVSNet (Re)		99.37 100	99.26 115	99.68 83	99.51 211	99.58 93	98.98 212	99.60 164	99.43 111	99.70 112	99.36 248	97.70 211	99.88 140	99.20 85	99.87 122	99.59 135

DELS-MVS		99.34 110	99.30 104	99.48 166	99.51 211	99.36 150	98.12 297	99.53 195	99.36 120	99.41 195	99.61 182	99.22 46	99.87 160	99.21 83	99.68 211	99.20 247
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
新几何1				99.52 156	99.50 217	99.22 184		99.26 272	95.66 330	98.60 301	99.28 265	97.67 216	99.89 125	95.95 298	99.32 274	99.45 194

SD-MVS		99.01 184	99.30 104	98.15 302	99.50 217	99.40 135	98.94 218	99.61 150	99.22 143	99.75 94	99.82 59	99.54 21	95.51 363	97.48 221	99.87 122	99.54 155

CDPH-MVS		98.56 233	98.20 249	99.61 122	99.50 217	99.46 113	98.32 282	99.41 234	95.22 334	99.21 238	99.10 292	98.34 162	99.82 239	95.09 325	99.66 219	99.56 144

APD-MVS		98.87 207	98.59 216	99.71 73	99.50 217	99.62 84	99.01 202	99.57 180	96.80 307	99.54 168	99.63 166	98.29 165	99.91 93	95.24 322	99.71 206	99.61 118
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_HR		99.12 164	99.02 166	99.40 191	99.50 217	99.11 199	97.92 322	99.71 105	98.76 199	99.08 252	99.47 227	99.17 50	99.54 347	97.85 197	99.76 183	99.54 155

旧先验1					99.49 222	99.29 165		99.26 272			99.39 241	97.67 216			99.36 270	99.46 192

1121		98.56 233	98.24 245	99.52 156	99.49 222	99.24 180	99.30 126	99.22 280	95.77 326	98.52 306	99.29 264	97.39 231	99.85 198	95.79 303	99.34 271	99.46 192

GBi-Net		99.42 85	99.31 99	99.73 63	99.49 222	99.77 37	99.68 42	99.70 108	99.44 106	99.62 142	99.83 51	97.21 239	99.90 111	98.96 119	99.90 103	99.53 158

test1		99.42 85	99.31 99	99.73 63	99.49 222	99.77 37	99.68 42	99.70 108	99.44 106	99.62 142	99.83 51	97.21 239	99.90 111	98.96 119	99.90 103	99.53 158

FMVSNet2		99.35 105	99.28 111	99.55 149	99.49 222	99.35 154	99.45 84	99.57 180	99.44 106	99.70 112	99.74 97	97.21 239	99.87 160	99.03 109	99.94 80	99.44 199

DP-MVS Recon		98.50 238	98.23 246	99.31 213	99.49 222	99.46 113	98.56 256	99.63 143	94.86 340	98.85 279	99.37 243	97.81 205	99.59 344	96.08 287	99.44 255	98.88 294

MVP-Stereo		99.16 157	99.08 149	99.43 181	99.48 228	99.07 207	99.08 192	99.55 186	98.63 211	99.31 221	99.68 140	98.19 176	99.78 274	98.18 177	99.58 231	99.45 194
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
thres200		96.09 326	95.68 327	97.33 329	99.48 228	96.22 315	98.53 261	97.57 339	98.06 256	98.37 314	96.73 367	86.84 343	99.61 343	86.99 358	98.57 322	96.16 357

sss		98.90 202	98.77 204	99.27 218	99.48 228	98.44 249	98.72 245	99.32 258	97.94 263	99.37 208	99.35 253	96.31 264	99.91 93	98.85 129	99.63 223	99.47 188

PAPM_NR		98.36 252	98.04 259	99.33 207	99.48 228	98.93 221	98.79 239	99.28 269	97.54 284	98.56 305	98.57 336	97.12 244	99.69 309	94.09 335	98.90 301	99.38 216

TAMVS		99.49 69	99.45 74	99.63 110	99.48 228	99.42 130	99.45 84	99.57 180	99.66 65	99.78 83	99.83 51	97.85 202	99.86 180	99.44 54	99.96 59	99.61 118

原ACMM1				99.37 200	99.47 233	98.87 228		99.27 270	96.74 308	98.26 318	99.32 256	97.93 196	99.82 239	95.96 297	99.38 267	99.43 205

plane_prior6					99.47 233	99.26 173						97.24 237

UniMVSNet_NR-MVSNet		99.37 100	99.25 117	99.72 69	99.47 233	99.56 96	98.97 213	99.61 150	99.43 111	99.67 119	99.28 265	97.85 202	99.95 41	99.17 91	99.81 163	99.65 89

TAPA-MVS	97.92 13	98.03 272	97.55 284	99.46 171	99.47 233	99.44 120	98.50 264	99.62 146	86.79 356	99.07 256	99.26 269	98.26 168	99.62 339	97.28 233	99.73 200	99.31 234
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SMA-MVS		99.19 148	99.00 171	99.73 63	99.46 237	99.73 50	99.13 182	99.52 205	97.40 290	99.57 153	99.64 158	98.93 78	99.83 231	97.61 214	99.79 171	99.63 99

test12356		98.43 245	98.39 234	98.55 284	99.46 237	96.36 313	97.32 344	99.81 55	97.60 280	99.62 142	99.37 243	94.57 283	99.89 125	97.80 200	99.92 91	99.40 210

test1235678		98.93 199	98.84 196	99.19 235	99.46 237	98.55 244	97.53 337	99.77 72	98.76 199	99.69 114	99.48 224	96.69 253	99.90 111	98.30 166	99.91 101	99.11 266

PVSNet	97.47 15	98.42 247	98.44 227	98.35 294	99.46 237	96.26 314	96.70 352	99.34 255	97.68 277	99.00 260	99.13 286	97.40 229	99.72 296	97.59 216	99.68 211	99.08 276

TinyColmap		98.97 190	98.93 182	99.07 247	99.46 237	98.19 270	97.75 328	99.75 84	98.79 193	99.54 168	99.70 121	98.97 74	99.62 339	96.63 268	99.83 146	99.41 209

PatchMatch-RL		98.68 225	98.47 224	99.30 215	99.44 242	99.28 167	98.14 295	99.54 190	97.12 300	99.11 250	99.25 271	97.80 206	99.70 303	96.51 273	99.30 276	98.93 291

PCF-MVS	96.03 18	96.73 311	95.86 323	99.33 207	99.44 242	99.16 194	96.87 349	99.44 228	86.58 357	98.95 268	99.40 238	94.38 285	99.88 140	87.93 353	99.80 168	98.95 289
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VDD-MVS		99.20 145	99.11 138	99.44 178	99.43 244	98.98 212	99.50 77	98.32 323	99.80 31	99.56 161	99.69 127	96.99 249	99.85 198	98.99 112	99.73 200	99.50 175

DU-MVS		99.33 113	99.21 123	99.71 73	99.43 244	99.56 96	98.83 231	99.53 195	99.38 117	99.67 119	99.36 248	97.67 216	99.95 41	99.17 91	99.81 163	99.63 99

NR-MVSNet		99.40 92	99.31 99	99.68 83	99.43 244	99.55 99	99.73 22	99.50 211	99.46 103	99.88 47	99.36 248	97.54 223	99.87 160	98.97 118	99.87 122	99.63 99

WTY-MVS		98.59 231	98.37 237	99.26 223	99.43 244	98.40 253	98.74 242	99.13 289	98.10 254	99.21 238	99.24 276	94.82 281	99.90 111	97.86 196	98.77 310	99.49 181

casdiffmvs		99.24 130	99.23 120	99.26 223	99.42 248	98.85 231	99.48 81	99.58 177	99.67 60	98.70 292	99.67 147	97.85 202	99.72 296	99.41 61	99.28 278	99.20 247

Regformer-1		99.32 115	99.27 113	99.47 168	99.41 249	98.95 216	98.99 208	99.48 216	99.48 95	99.66 123	99.52 214	98.78 100	99.87 160	98.36 160	99.74 194	99.60 124

Regformer-2		99.34 110	99.27 113	99.53 154	99.41 249	99.10 202	98.99 208	99.53 195	99.47 99	99.66 123	99.52 214	98.80 94	99.89 125	98.31 165	99.74 194	99.60 124

pmmvs3		98.08 270	97.80 275	98.91 259	99.41 249	97.69 293	97.87 325	99.66 126	95.87 323	99.50 177	99.51 218	90.35 323	99.97 16	98.55 150	99.47 251	99.08 276

NP-MVS					99.40 252	99.13 197					98.83 324

QAPM		98.40 250	97.99 261	99.65 98	99.39 253	99.47 109	99.67 47	99.52 205	91.70 352	98.78 286	99.80 64	98.55 138	99.95 41	94.71 329	99.75 186	99.53 158

OMC-MVS		98.90 202	98.72 207	99.44 178	99.39 253	99.42 130	98.58 252	99.64 140	97.31 294	99.44 183	99.62 173	98.59 132	99.69 309	96.17 285	99.79 171	99.22 243

3Dnovator	99.15 2	99.43 82	99.36 92	99.65 98	99.39 253	99.42 130	99.70 30	99.56 183	99.23 140	99.35 211	99.80 64	99.17 50	99.95 41	98.21 172	99.84 136	99.59 135

Fast-Effi-MVS+		99.02 180	98.87 192	99.46 171	99.38 256	99.50 103	99.04 197	99.79 67	97.17 296	98.62 299	98.74 331	99.34 33	99.95 41	98.32 164	99.41 264	98.92 292

BH-untuned		98.22 264	98.09 256	98.58 283	99.38 256	97.24 302	98.55 257	98.98 296	97.81 272	99.20 243	98.76 329	97.01 248	99.65 335	94.83 326	98.33 336	98.86 296

xiu_mvs_v2_base		99.02 180	99.11 138	98.77 273	99.37 258	98.09 278	98.13 296	99.51 208	99.47 99	99.42 189	98.54 338	99.38 27	99.97 16	98.83 130	99.33 273	98.24 323

PS-MVSNAJ		99.00 187	99.08 149	98.76 274	99.37 258	98.10 277	98.00 311	99.51 208	99.47 99	99.41 195	98.50 340	99.28 38	99.97 16	98.83 130	99.34 271	98.20 327

diffmvs		99.17 154	99.19 125	99.10 242	99.36 260	98.41 252	99.24 144	99.68 117	99.46 103	98.30 315	99.68 140	98.49 150	99.91 93	99.10 104	99.43 261	98.98 287

ambc				99.20 234	99.35 261	98.53 245	99.17 164	99.46 223		99.67 119	99.80 64	98.46 153	99.70 303	97.92 192	99.70 208	99.38 216

TEST9					99.35 261	99.35 154	98.11 299	99.41 234	94.83 342	97.92 334	98.99 307	98.02 189	99.85 198

train_agg		98.35 255	97.95 265	99.57 140	99.35 261	99.35 154	98.11 299	99.41 234	94.90 338	97.92 334	98.99 307	98.02 189	99.85 198	95.38 320	99.44 255	99.50 175

agg_prior1		98.33 258	97.92 268	99.57 140	99.35 261	99.36 150	97.99 313	99.39 243	94.85 341	97.76 344	98.98 310	98.03 187	99.85 198	95.49 315	99.44 255	99.51 169

agg_prior					99.35 261	99.36 150		99.39 243		97.76 344			99.85 198

test_prior3		98.62 227	98.34 240	99.46 171	99.35 261	99.22 184	97.95 318	99.39 243	97.87 266	98.05 329	99.05 302	97.90 197	99.69 309	95.99 294	99.49 249	99.48 183

test_prior				99.46 171	99.35 261	99.22 184		99.39 243					99.69 309			99.48 183

MVS_Test		99.28 120	99.31 99	99.19 235	99.35 261	98.79 235	99.36 103	99.49 215	99.17 151	99.21 238	99.67 147	98.78 100	99.66 328	99.09 105	99.66 219	99.10 270

CDS-MVSNet		99.22 140	99.13 132	99.50 161	99.35 261	99.11 199	98.96 214	99.54 190	99.46 103	99.61 147	99.70 121	96.31 264	99.83 231	99.34 67	99.88 115	99.55 147
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
3Dnovator+	98.92 3	99.35 105	99.24 118	99.67 86	99.35 261	99.47 109	99.62 58	99.50 211	99.44 106	99.12 249	99.78 80	98.77 103	99.94 54	97.87 195	99.72 205	99.62 113

Anonymous202405211		98.75 220	98.46 225	99.63 110	99.34 271	99.66 71	99.47 83	97.65 338	99.28 128	99.56 161	99.50 221	93.15 294	99.84 214	98.62 146	99.58 231	99.40 210

CHOSEN 280x420		98.41 248	98.41 232	98.40 292	99.34 271	95.89 324	96.94 348	99.44 228	98.80 192	99.25 229	99.52 214	93.51 291	99.98 7	98.94 124	99.98 36	99.32 233

test_8					99.34 271	99.31 160	98.08 304	99.40 240	94.90 338	97.87 338	98.97 313	98.02 189	99.84 214

agg_prior3		98.24 261	97.81 274	99.53 154	99.34 271	99.26 173	98.09 301	99.39 243	94.21 346	97.77 343	98.96 315	97.74 210	99.84 214	95.38 320	99.44 255	99.50 175

TSAR-MVS + GP.		99.12 164	99.04 164	99.38 196	99.34 271	99.16 194	98.15 293	99.29 266	98.18 252	99.63 135	99.62 173	99.18 49	99.68 318	98.20 173	99.74 194	99.30 235

LCM-MVSNet-Re		99.28 120	99.15 128	99.67 86	99.33 276	99.76 42	99.34 111	99.97 3	98.93 177	99.91 33	99.79 71	98.68 116	99.93 65	96.80 258	99.56 233	99.30 235

PLC	97.35 16	98.36 252	97.99 261	99.48 166	99.32 277	99.24 180	98.50 264	99.51 208	95.19 336	98.58 303	98.96 315	96.95 250	99.83 231	95.63 312	99.25 283	99.37 220
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
Effi-MVS+		99.06 172	98.97 179	99.34 205	99.31 278	98.98 212	98.31 283	99.91 10	98.81 190	98.79 284	98.94 318	99.14 53	99.84 214	98.79 133	98.74 314	99.20 247

HQP-NCC					99.31 278		97.98 314		97.45 287	98.15 323

ACMP_Plane					99.31 278		97.98 314		97.45 287	98.15 323

HQP-MVS		98.36 252	98.02 260	99.39 194	99.31 278	98.94 217	97.98 314	99.37 250	97.45 287	98.15 323	98.83 324	96.67 254	99.70 303	94.73 327	99.67 216	99.53 158

WR-MVS		99.11 167	98.93 182	99.66 94	99.30 282	99.42 130	98.42 275	99.37 250	99.04 167	99.57 153	99.20 282	96.89 251	99.86 180	98.66 145	99.87 122	99.70 55

test12				99.54 153	99.29 283	99.33 157		99.16 285		98.43 312		97.54 223	99.82 239		99.47 251	99.48 183

OpenMVS_ROB	97.31 17	97.36 287	96.84 297	98.89 264	99.29 283	99.45 118	98.87 224	99.48 216	86.54 358	99.44 183	99.74 97	97.34 234	99.86 180	91.61 341	99.28 278	97.37 348

MVS-HIRNet		97.86 275	98.22 247	96.76 334	99.28 285	91.53 356	98.38 277	92.60 364	99.13 156	99.31 221	99.96 10	97.18 243	99.68 318	98.34 162	99.83 146	99.07 280

DeepC-MVS_fast	98.47 5	99.23 132	99.12 135	99.56 146	99.28 285	99.22 184	98.99 208	99.40 240	99.08 163	99.58 151	99.64 158	98.90 83	99.83 231	97.44 223	99.75 186	99.63 99
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
Patchmatch-test		98.10 269	97.98 263	98.48 289	99.27 287	96.48 311	99.40 90	99.07 290	98.81 190	99.23 233	99.57 199	90.11 325	99.87 160	96.69 264	99.64 222	99.09 273

Fast-Effi-MVS+-dtu		99.20 145	99.12 135	99.43 181	99.25 288	99.69 64	99.05 195	99.82 47	99.50 93	98.97 262	99.05 302	98.98 72	99.98 7	98.20 173	99.24 285	98.62 304

CNVR-MVS		98.99 189	98.80 203	99.56 146	99.25 288	99.43 126	98.54 260	99.27 270	98.58 215	98.80 283	99.43 233	98.53 144	99.70 303	97.22 238	99.59 230	99.54 155

LFMVS		98.46 243	98.19 252	99.26 223	99.24 290	98.52 246	99.62 58	96.94 347	99.87 13	99.31 221	99.58 193	91.04 312	99.81 258	98.68 144	99.42 262	99.45 194

VNet		99.18 151	99.06 155	99.56 146	99.24 290	99.36 150	99.33 113	99.31 262	99.67 60	99.47 180	99.57 199	96.48 259	99.84 214	99.15 95	99.30 276	99.47 188

DeepPCF-MVS	98.42 6	99.18 151	99.02 166	99.67 86	99.22 292	99.75 44	97.25 345	99.47 220	98.72 205	99.66 123	99.70 121	99.29 36	99.63 338	98.07 185	99.81 163	99.62 113

MSLP-MVS++		99.05 175	99.09 147	98.91 259	99.21 293	98.36 257	98.82 234	99.47 220	98.85 185	98.90 275	99.56 203	98.78 100	99.09 357	98.57 148	99.68 211	99.26 239

NCCC		98.82 212	98.57 219	99.58 134	99.21 293	99.31 160	98.61 248	99.25 275	98.65 209	98.43 312	99.26 269	97.86 201	99.81 258	96.55 271	99.27 282	99.61 118

BH-RMVSNet		98.41 248	98.14 254	99.21 232	99.21 293	98.47 247	98.60 250	98.26 324	98.35 239	98.93 270	99.31 258	97.20 242	99.66 328	94.32 331	99.10 291	99.51 169

Patchmatch-test1		98.13 267	98.40 233	97.31 330	99.20 296	92.99 346	98.17 292	98.49 317	98.24 249	99.10 251	99.52 214	96.01 271	99.83 231	97.22 238	99.62 224	99.12 265

mvs_anonymous		99.28 120	99.39 83	98.94 256	99.19 297	97.81 289	99.02 200	99.55 186	99.78 34	99.85 58	99.80 64	98.24 169	99.86 180	99.57 44	99.50 247	99.15 257

OpenMVS	98.12 10	98.23 263	97.89 272	99.26 223	99.19 297	99.26 173	99.65 55	99.69 114	91.33 353	98.14 327	99.77 87	98.28 166	99.96 33	95.41 319	99.55 239	98.58 308

CNLPA		98.57 232	98.34 240	99.28 216	99.18 299	99.10 202	98.34 280	99.41 234	98.48 224	98.52 306	98.98 310	97.05 247	99.78 274	95.59 313	99.50 247	98.96 288

0601test		98.25 260	97.95 265	99.13 239	99.17 300	98.47 247	99.00 204	98.67 310	98.97 172	99.22 237	99.02 306	91.31 310	99.69 309	97.26 234	98.93 298	99.24 241

MG-MVS		98.52 237	98.39 234	98.94 256	99.15 301	97.39 300	98.18 290	99.21 281	98.89 181	99.23 233	99.63 166	97.37 233	99.74 292	94.22 333	99.61 228	99.69 58

ADS-MVSNet2		97.78 277	97.66 283	98.12 304	99.14 302	95.36 333	99.22 151	98.75 304	96.97 302	98.25 319	99.64 158	90.90 315	99.94 54	96.51 273	99.56 233	99.08 276

ADS-MVSNet		97.72 279	97.67 282	97.86 314	99.14 302	94.65 340	99.22 151	98.86 298	96.97 302	98.25 319	99.64 158	90.90 315	99.84 214	96.51 273	99.56 233	99.08 276

FMVSNet3		98.80 215	98.63 214	99.32 211	99.13 304	98.72 236	99.10 186	99.48 216	99.23 140	99.62 142	99.64 158	92.57 300	99.86 180	98.96 119	99.90 103	99.39 213

PHI-MVS		99.11 167	98.95 181	99.59 130	99.13 304	99.59 91	99.17 164	99.65 135	97.88 265	99.25 229	99.46 230	98.97 74	99.80 263	97.26 234	99.82 155	99.37 220

alignmvs		98.28 259	97.96 264	99.25 227	99.12 306	98.93 221	99.03 199	98.42 320	99.64 70	98.72 290	97.85 348	90.86 317	99.62 339	98.88 128	99.13 289	99.19 250

PAPM		95.61 334	94.71 335	98.31 297	99.12 306	96.63 309	96.66 353	98.46 318	90.77 354	96.25 356	98.68 333	93.01 297	99.69 309	81.60 360	97.86 349	98.62 304

AdaColmap		98.60 229	98.35 239	99.38 196	99.12 306	99.22 184	98.67 247	99.42 233	97.84 270	98.81 281	99.27 267	97.32 235	99.81 258	95.14 323	99.53 244	99.10 270

MS-PatchMatch		99.00 187	98.97 179	99.09 243	99.11 309	98.19 270	98.76 241	99.33 256	98.49 223	99.44 183	99.58 193	98.21 173	99.69 309	98.20 173	99.62 224	99.39 213

testus		98.15 266	98.06 258	98.40 292	99.11 309	95.95 319	96.77 350	99.89 14	95.83 324	99.23 233	98.47 341	97.50 225	99.84 214	96.58 270	99.20 288	99.39 213

canonicalmvs		99.02 180	99.00 171	99.09 243	99.10 311	98.70 237	99.61 62	99.66 126	99.63 73	98.64 298	97.65 355	99.04 69	99.54 347	98.79 133	98.92 299	99.04 283

MVS_0304		99.17 154	99.10 145	99.38 196	99.08 312	98.86 229	98.46 271	99.73 92	99.53 90	99.35 211	99.30 261	97.11 245	99.96 33	99.33 69	99.99 20	99.33 228

BH-w/o		97.20 294	97.01 292	97.76 317	99.08 312	95.69 329	98.03 308	98.52 314	95.76 327	97.96 333	98.02 346	95.62 275	99.47 351	92.82 339	97.25 353	98.12 329

MVSTER		98.47 242	98.22 247	99.24 229	99.06 314	98.35 258	99.08 192	99.46 223	99.27 129	99.75 94	99.66 152	88.61 331	99.85 198	99.14 101	99.92 91	99.52 166

CR-MVSNet		98.35 255	98.20 249	98.83 269	99.05 315	98.12 274	99.30 126	99.67 122	97.39 291	99.16 244	99.79 71	91.87 306	99.91 93	98.78 136	98.77 310	98.44 314

RPMNet		98.53 236	98.44 227	98.83 269	99.05 315	98.12 274	99.30 126	98.78 303	99.86 15	99.16 244	99.74 97	92.53 302	99.91 93	98.75 137	98.77 310	98.44 314

HY-MVS	98.23 9	98.21 265	97.95 265	98.99 253	99.03 317	98.24 266	99.61 62	98.72 306	96.81 306	98.73 289	99.51 218	94.06 287	99.86 180	96.91 252	98.20 339	98.86 296

PMMVS		98.49 240	98.29 243	99.11 240	98.96 318	98.42 251	97.54 335	99.32 258	97.53 285	98.47 311	98.15 345	97.88 200	99.82 239	97.46 222	99.24 285	99.09 273

PatchT		98.45 244	98.32 242	98.83 269	98.94 319	98.29 265	99.24 144	98.82 301	99.84 22	99.08 252	99.76 91	91.37 309	99.94 54	98.82 132	99.00 297	98.26 321

tpm		97.15 297	96.95 294	97.75 318	98.91 320	94.24 342	99.32 116	97.96 328	97.71 275	98.29 316	99.32 256	86.72 344	99.92 83	98.10 184	96.24 357	99.09 273

1314		98.00 273	97.90 271	98.27 299	98.90 321	97.45 299	99.30 126	99.06 292	94.98 337	97.21 351	99.12 290	98.43 155	99.67 323	95.58 314	98.56 329	97.71 343

tpmp4_e23		96.11 325	96.06 318	96.27 342	98.90 321	90.70 361	99.34 111	99.03 294	93.72 347	96.56 354	99.31 258	83.63 356	99.75 288	96.06 289	98.02 346	98.35 317

CostFormer		96.71 312	96.79 300	96.46 341	98.90 321	90.71 360	99.41 88	98.68 308	94.69 343	98.14 327	99.34 255	86.32 352	99.80 263	97.60 215	98.07 344	98.88 294

UGNet		99.38 98	99.34 94	99.49 163	98.90 321	98.90 224	99.70 30	99.35 253	99.86 15	98.57 304	99.81 62	98.50 149	99.93 65	99.38 62	99.98 36	99.66 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
Effi-MVS+-dtu		99.07 171	98.92 185	99.52 156	98.89 325	99.78 35	99.15 172	99.66 126	99.34 121	98.92 272	99.24 276	97.69 213	99.98 7	98.11 182	99.28 278	98.81 299

mvs-test1		98.83 210	98.70 208	99.22 231	98.89 325	99.65 76	98.88 222	99.66 126	99.34 121	98.29 316	98.94 318	97.69 213	99.96 33	98.11 182	98.54 330	98.04 331

Patchmtry		98.78 217	98.54 222	99.49 163	98.89 325	99.19 192	99.32 116	99.67 122	99.65 68	99.72 106	99.79 71	91.87 306	99.95 41	98.00 189	99.97 46	99.33 228

LP		98.34 257	98.44 227	98.05 305	98.88 328	95.31 335	99.28 135	98.74 305	99.12 157	98.98 261	99.79 71	93.40 292	99.93 65	98.38 158	99.41 264	98.90 293

tpm2		96.35 320	96.22 314	96.73 336	98.88 328	91.75 354	99.21 154	98.51 315	93.27 349	97.89 336	99.21 281	84.83 355	99.70 303	96.04 290	98.18 342	98.75 302

tpm cat1		96.78 310	96.98 293	96.16 345	98.85 330	90.59 362	99.08 192	99.32 258	92.37 350	97.73 346	99.46 230	91.15 311	99.69 309	96.07 288	98.80 307	98.21 325

CANet		99.11 167	99.05 159	99.28 216	98.83 331	98.56 243	98.71 246	99.41 234	99.25 136	99.23 233	99.22 280	97.66 220	99.94 54	99.19 86	99.97 46	99.33 228

FMVSNet5		97.80 276	97.25 287	99.42 183	98.83 331	98.97 214	99.38 97	99.80 59	98.87 183	99.25 229	99.69 127	80.60 363	99.91 93	98.96 119	99.90 103	99.38 216

API-MVS		98.38 251	98.39 234	98.35 294	98.83 331	99.26 173	99.14 177	99.18 283	98.59 214	98.66 297	98.78 328	98.61 130	99.57 346	94.14 334	99.56 233	96.21 356

PatchmatchNet		97.65 280	97.80 275	97.18 331	98.82 334	92.49 348	99.17 164	98.39 321	98.12 253	98.79 284	99.58 193	90.71 319	99.89 125	97.23 237	99.41 264	99.16 256
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PAPR		97.56 283	97.07 289	99.04 250	98.80 335	98.11 276	97.63 331	99.25 275	94.56 344	98.02 332	98.25 344	97.43 228	99.68 318	90.90 344	98.74 314	99.33 228

CANet_DTU		98.91 200	98.85 194	99.09 243	98.79 336	98.13 273	98.18 290	99.31 262	99.48 95	98.86 278	99.51 218	96.56 256	99.95 41	99.05 108	99.95 67	99.19 250

E-PMN		97.14 299	97.43 285	96.27 342	98.79 336	91.62 355	95.54 356	99.01 295	99.44 106	98.88 276	99.12 290	92.78 299	99.68 318	94.30 332	99.03 295	97.50 345

PVSNet_0	95.53 19	95.85 331	95.31 330	97.47 325	98.78 338	93.48 345	95.72 355	99.40 240	96.18 319	97.37 348	97.73 354	95.73 273	99.58 345	95.49 315	81.40 360	99.36 223

MAR-MVS		98.24 261	97.92 268	99.19 235	98.78 338	99.65 76	99.17 164	99.14 287	95.36 332	98.04 331	98.81 326	97.47 226	99.72 296	95.47 317	99.06 292	98.21 325
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
EMVS		96.96 302	97.28 286	95.99 346	98.76 340	91.03 358	95.26 358	98.61 311	99.34 121	98.92 272	98.88 323	93.79 288	99.66 328	92.87 338	99.05 293	97.30 349

PatchFormer-LS_test		96.95 303	97.07 289	96.62 339	98.76 340	91.85 352	99.18 157	98.45 319	97.29 295	97.73 346	97.22 364	88.77 330	99.76 282	98.13 181	98.04 345	98.25 322

IB-MVS	95.41 20	95.30 335	94.46 337	97.84 315	98.76 340	95.33 334	97.33 343	96.07 351	96.02 320	95.37 361	97.41 358	76.17 366	99.96 33	97.54 218	95.44 359	98.22 324
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
tpmrst		97.73 278	98.07 257	96.73 336	98.71 343	92.00 350	99.10 186	98.86 298	98.52 220	98.92 272	99.54 210	91.90 304	99.82 239	98.02 186	99.03 295	98.37 316

MDTV_nov1_ep13			97.73 279		98.70 344	90.83 359	99.15 172	98.02 326	98.51 221	98.82 280	99.61 182	90.98 313	99.66 328	96.89 254	98.92 299

dp		96.86 305	97.07 289	96.24 344	98.68 345	90.30 363	99.19 156	98.38 322	97.35 293	98.23 321	99.59 191	87.23 336	99.82 239	96.27 282	98.73 316	98.59 306

JIA-IIPM		98.06 271	97.92 268	98.50 288	98.59 346	97.02 305	98.80 236	98.51 315	99.88 12	97.89 336	99.87 37	91.89 305	99.90 111	98.16 180	97.68 351	98.59 306

MVS		95.72 333	94.63 336	98.99 253	98.56 347	97.98 287	99.30 126	98.86 298	72.71 361	97.30 349	99.08 293	98.34 162	99.74 292	89.21 349	98.33 336	99.26 239

TR-MVS		97.44 284	97.15 288	98.32 296	98.53 348	97.46 298	98.47 267	97.91 331	96.85 304	98.21 322	98.51 339	96.42 262	99.51 349	92.16 340	97.29 352	97.98 336

DWT-MVSNet_test		96.03 328	95.80 325	96.71 338	98.50 349	91.93 351	99.25 143	97.87 332	95.99 321	96.81 353	97.61 356	81.02 360	99.66 328	97.20 241	97.98 347	98.54 309

tpmvs		97.39 285	97.69 280	96.52 340	98.41 350	91.76 353	99.30 126	98.94 297	97.74 273	97.85 339	99.55 208	92.40 303	99.73 294	96.25 283	98.73 316	98.06 330

LS3D		99.24 130	99.11 138	99.61 122	98.38 351	99.79 33	99.57 70	99.68 117	99.61 78	99.15 246	99.71 114	98.70 112	99.91 93	97.54 218	99.68 211	99.13 264

CMPMVS	77.52 23	98.50 238	98.19 252	99.41 190	98.33 352	99.56 96	99.01 202	99.59 169	95.44 331	99.57 153	99.80 64	95.64 274	99.46 354	96.47 276	99.92 91	99.21 246
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
TESTMET0.1,1		96.24 323	95.84 324	97.41 327	98.24 353	93.84 343	97.38 340	95.84 352	98.43 226	97.81 340	98.56 337	79.77 364	99.89 125	97.77 201	98.77 310	98.52 310

gg-mvs-nofinetune		95.87 330	95.17 333	97.97 307	98.19 354	96.95 306	99.69 39	89.23 367	99.89 10	96.24 357	99.94 12	81.19 359	99.51 349	93.99 336	98.20 339	97.44 346

test-LLR		97.15 297	96.95 294	97.74 319	98.18 355	95.02 337	97.38 340	96.10 349	98.00 257	97.81 340	98.58 334	90.04 326	99.91 93	97.69 210	98.78 308	98.31 319

test-mter		96.23 324	95.73 326	97.74 319	98.18 355	95.02 337	97.38 340	96.10 349	97.90 264	97.81 340	98.58 334	79.12 365	99.91 93	97.69 210	98.78 308	98.31 319

EPMVS		96.53 315	96.32 313	97.17 332	98.18 355	92.97 347	99.39 91	89.95 366	98.21 250	98.61 300	99.59 191	86.69 345	99.72 296	96.99 249	99.23 287	98.81 299

test0.0.03 1		97.37 286	96.91 296	98.74 279	97.72 358	97.57 296	97.60 333	97.36 346	98.00 257	99.21 238	98.02 346	90.04 326	99.79 266	98.37 159	95.89 358	98.86 296

GG-mvs-BLEND				97.36 328	97.59 359	96.87 308	99.70 30	88.49 368		94.64 362	97.26 363	80.66 362	99.12 356	91.50 342	96.50 356	96.08 358

gm-plane-assit					97.59 359	89.02 365			93.47 348		98.30 342		99.84 214	96.38 278

cascas		96.99 301	96.82 299	97.48 324	97.57 361	95.64 330	96.43 354	99.56 183	91.75 351	97.13 352	97.61 356	95.58 276	98.63 360	96.68 265	99.11 290	98.18 328

testpf		94.48 336	95.31 330	91.99 349	97.22 362	89.64 364	98.86 225	96.52 348	94.36 345	96.09 358	98.76 329	82.21 357	98.73 359	97.05 247	96.74 354	87.60 359

test2356		95.99 329	95.26 332	98.18 301	96.93 363	95.53 332	95.31 357	98.71 307	95.67 329	98.48 310	97.83 349	80.72 361	99.88 140	95.47 317	98.21 338	99.11 266

EPNet_dtu		97.62 281	97.79 277	97.11 333	96.67 364	92.31 349	98.51 263	98.04 325	99.24 138	95.77 359	99.47 227	93.78 289	99.66 328	98.98 114	99.62 224	99.37 220
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPNet		98.13 267	97.77 278	99.18 238	94.57 365	97.99 282	99.24 144	97.96 328	99.74 40	97.29 350	99.62 173	93.13 295	99.97 16	98.59 147	99.83 146	99.58 139
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tmp_tt		95.75 332	95.42 329	96.76 334	89.90 366	94.42 341	98.86 225	97.87 332	78.01 359	99.30 225	99.69 127	97.70 211	95.89 362	99.29 78	98.14 343	99.95 1

testmvs		28.94 341	33.33 341	15.79 353	26.03 367	9.81 368	96.77 350	15.67 369	11.55 363	23.87 365	50.74 371	19.03 370	8.53 365	23.21 362	33.07 361	29.03 362

test123		29.31 340	33.05 343	18.08 352	25.93 368	12.24 367	97.53 337	10.93 370	11.78 362	24.21 364	50.08 372	21.04 369	8.60 364	23.51 361	32.43 363	33.39 361

cdsmvs_eth3d_5k		24.88 342	33.17 342	0.00 354	0.00 369	0.00 369	0.00 360	99.62 146	0.00 364	0.00 366	99.13 286	99.82 6	0.00 366	0.00 363	0.00 364	0.00 364

pcd_1.5k_mvsjas		16.61 343	22.14 344	0.00 354	0.00 369	0.00 369	0.00 360	0.00 371	0.00 364	0.00 366	100.00 1	99.28 38	0.00 366	0.00 363	0.00 364	0.00 364

sosnet-low-res		8.33 344	11.11 345	0.00 354	0.00 369	0.00 369	0.00 360	0.00 371	0.00 364	0.00 366	100.00 1	0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

sosnet		8.33 344	11.11 345	0.00 354	0.00 369	0.00 369	0.00 360	0.00 371	0.00 364	0.00 366	100.00 1	0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

uncertanet		8.33 344	11.11 345	0.00 354	0.00 369	0.00 369	0.00 360	0.00 371	0.00 364	0.00 366	100.00 1	0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

Regformer		8.33 344	11.11 345	0.00 354	0.00 369	0.00 369	0.00 360	0.00 371	0.00 364	0.00 366	100.00 1	0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

ab-mvs-re		8.26 349	11.02 350	0.00 354	0.00 369	0.00 369	0.00 360	0.00 371	0.00 364	0.00 366	99.16 284	0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

uanet		8.33 344	11.11 345	0.00 354	0.00 369	0.00 369	0.00 360	0.00 371	0.00 364	0.00 366	100.00 1	0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

GSMVS																99.14 261

test_part1				0.00 354		0.00 369	0.00 360	99.53 195				0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

sam_mvs1												90.81 318				99.14 261

sam_mvs												90.52 322

MTGPA								99.53 195

test_post1							99.14 177				51.63 370	89.54 329	99.82 239	96.86 255

test_post											52.41 369	90.25 324	99.86 180

patchmatchnet-post											99.62 173	90.58 320	99.94 54

MTMP							99.09 190	98.59 313

test9_res														95.10 324	99.44 255	99.50 175

agg_prior2														94.58 330	99.46 254	99.50 175

test_prior4						99.19 192	98.00 311

test_prior2							97.95 318		97.87 266	98.05 329	99.05 302	97.90 197		95.99 294	99.49 249

旧先验2							97.94 320		95.33 333	98.94 269			99.88 140	96.75 261

新几何2							98.04 307

无先验							98.01 309	99.23 279	95.83 324				99.85 198	95.79 303		99.44 199

原ACMM2							97.92 322

testdata2													99.89 125	95.99 294

segment_acmp												98.37 160

testdata1							97.72 329		97.86 269

plane_prior5								99.54 190					99.82 239	95.84 301	99.78 177	99.60 124

plane_prior4											99.25 271

plane_prior3						99.31 160			98.36 234	99.14 247

plane_prior2							98.80 236		98.94 175

plane_prior						99.24 180	98.42 275		97.87 266						99.71 206

n2								0.00 371

nn								0.00 371

door-mid								99.83 39

test11								99.29 266

door								99.77 72

HQP5-MVS						98.94 217

BP-MVS														94.73 327

HQP4-MVS										98.15 323			99.70 303			99.53 158

HQP3-MVS								99.37 250							99.67 216

HQP2-MVS												96.67 254

MDTV_nov1_ep13_2view						91.44 357	99.14 177		97.37 292	99.21 238		91.78 308		96.75 261		99.03 284

ACMMP++_ref															99.94 80

ACMMP++															99.79 171

Test By Simon												98.41 157

High-resolution multi-view benchmark