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.

APDe-MVS		99.66 1	99.57 1	99.92 1	99.77 29	99.89 1	99.75 33	99.56 43	99.02 9	99.88 3	99.85 24	99.18 4	99.96 11	99.22 22	99.92 8	99.90 1

Regformer-4		99.59 2	99.54 4	99.73 37	99.76 32	99.41 62	99.58 76	99.49 92	99.02 9	99.88 3	99.80 58	99.00 16	99.94 27	99.45 7	99.92 8	99.84 10

EI-MVSNet-UG-set		99.58 3	99.57 1	99.64 52	99.78 25	99.14 84	99.60 71	99.45 127	99.01 12	99.90 1	99.83 34	98.98 17	99.93 40	99.59 1	99.95 4	99.86 4

EI-MVSNet-Vis-set		99.58 3	99.56 3	99.64 52	99.78 25	99.15 83	99.61 70	99.45 127	99.01 12	99.89 2	99.82 42	99.01 10	99.92 47	99.56 3	99.95 4	99.85 6

Regformer-3		99.57 5	99.53 5	99.68 42	99.76 32	99.29 71	99.58 76	99.44 133	99.01 12	99.87 6	99.80 58	98.97 18	99.91 56	99.44 8	99.92 8	99.83 20

Regformer-2		99.54 6	99.47 7	99.75 30	99.71 54	99.52 50	99.49 112	99.49 92	98.94 24	99.83 8	99.76 75	99.01 10	99.94 27	99.15 29	99.87 28	99.80 31

SteuartSystems-ACMMP		99.54 6	99.42 10	99.87 2	99.82 20	99.81 7	99.59 73	99.51 79	98.62 36	99.79 14	99.83 34	99.28 2	99.97 6	98.48 90	99.90 18	99.84 10
Skip Steuart: Steuart Systems R&D Blog.
Regformer-1		99.53 8	99.47 7	99.72 39	99.71 54	99.44 59	99.49 112	99.46 116	98.95 23	99.83 8	99.76 75	99.01 10	99.93 40	99.17 27	99.87 28	99.80 31

XVS		99.53 8	99.42 10	99.87 2	99.85 15	99.83 3	99.69 43	99.68 16	98.98 18	99.37 80	99.74 82	98.81 30	99.94 27	98.79 58	99.86 38	99.84 10

HPM-MVS_fast		99.51 10	99.40 13	99.85 13	99.91 1	99.79 11	99.76 26	99.56 43	97.72 105	99.76 20	99.75 79	99.13 5	99.92 47	99.07 35	99.92 8	99.85 6

HFP-MVS		99.49 11	99.37 15	99.86 8	99.87 8	99.80 8	99.66 52	99.67 19	98.15 64	99.68 26	99.69 97	99.06 7	99.96 11	98.69 66	99.87 28	99.84 10

ACMMPR		99.49 11	99.36 17	99.86 8	99.87 8	99.79 11	99.66 52	99.67 19	98.15 64	99.67 30	99.69 97	98.95 22	99.96 11	98.69 66	99.87 28	99.84 10

DeepC-MVS_fast	98.69 1	99.49 11	99.39 14	99.77 28	99.63 77	99.59 38	99.36 158	99.46 116	99.07 8	99.79 14	99.82 42	98.85 28	99.92 47	98.68 68	99.87 28	99.82 24
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
region2R		99.48 14	99.35 19	99.87 2	99.88 4	99.80 8	99.65 60	99.66 22	98.13 66	99.66 35	99.68 102	98.96 19	99.96 11	98.62 73	99.87 28	99.84 10

APD-MVS_3200maxsize		99.48 14	99.35 19	99.85 13	99.76 32	99.83 3	99.63 63	99.54 57	98.36 49	99.79 14	99.82 42	98.86 27	99.95 24	98.62 73	99.81 56	99.78 39

DELS-MVS		99.48 14	99.42 10	99.65 48	99.72 52	99.40 64	99.05 218	99.66 22	99.14 5	99.57 49	99.80 58	98.46 53	99.94 27	99.57 2	99.84 47	99.60 92
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
MSLP-MVS		99.46 17	99.47 7	99.44 84	99.60 84	99.16 81	99.41 142	99.71 11	98.98 18	99.45 66	99.78 69	99.19 3	99.54 159	99.28 18	99.84 47	99.63 88

PGM-MVS		99.45 18	99.31 27	99.86 8	99.87 8	99.78 15	99.58 76	99.65 27	97.84 93	99.71 22	99.80 58	99.12 6	99.97 6	98.33 101	99.87 28	99.83 20

CP-MVS		99.45 18	99.32 22	99.85 13	99.83 19	99.75 16	99.69 43	99.52 71	98.07 75	99.53 54	99.63 123	98.93 23	99.97 6	98.74 61	99.91 13	99.83 20

ACMMP		99.45 18	99.32 22	99.82 18	99.89 3	99.67 26	99.62 64	99.69 15	98.12 67	99.63 40	99.84 32	98.73 41	99.96 11	98.55 85	99.83 51	99.81 27
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
mPP-MVS		99.44 21	99.30 28	99.86 8	99.88 4	99.79 11	99.69 43	99.48 99	98.12 67	99.50 58	99.75 79	98.78 32	99.97 6	98.57 80	99.89 24	99.83 20

#test#		99.43 22	99.29 31	99.86 8	99.87 8	99.80 8	99.55 93	99.67 19	97.83 94	99.68 26	99.69 97	99.06 7	99.96 11	98.39 94	99.87 28	99.84 10

MCST-MVS		99.43 22	99.30 28	99.82 18	99.79 24	99.74 18	99.29 172	99.40 151	98.79 31	99.52 56	99.62 128	98.91 24	99.90 67	98.64 70	99.75 66	99.82 24

UA-Net		99.42 24	99.29 31	99.80 22	99.62 78	99.55 43	99.50 107	99.70 12	98.79 31	99.77 18	99.96 1	97.45 79	99.96 11	98.92 46	99.90 18	99.89 2

HPM-MVS		99.42 24	99.28 33	99.83 17	99.90 2	99.72 19	99.81 15	99.54 57	97.59 112	99.68 26	99.63 123	98.91 24	99.94 27	98.58 78	99.91 13	99.84 10

CNVR-MVS		99.42 24	99.30 28	99.78 26	99.62 78	99.71 20	99.26 183	99.52 71	98.82 28	99.39 77	99.71 89	98.96 19	99.85 86	98.59 77	99.80 58	99.77 41

SD-MVS		99.41 27	99.52 6	99.05 117	99.74 44	99.68 24	99.46 123	99.52 71	99.11 6	99.88 3	99.91 5	99.43 1	97.70 269	98.72 63	99.93 7	99.77 41

MVS_111021_LR		99.41 27	99.33 21	99.65 48	99.77 29	99.51 52	98.94 243	99.85 4	98.82 28	99.65 38	99.74 82	98.51 50	99.80 109	98.83 56	99.89 24	99.64 85

MVS_111021_HR		99.41 27	99.32 22	99.66 45	99.72 52	99.47 56	98.95 241	99.85 4	98.82 28	99.54 53	99.73 85	98.51 50	99.74 120	98.91 47	99.88 26	99.77 41

HPM-MVS++		99.39 30	99.23 35	99.87 2	99.75 38	99.84 2	99.43 132	99.51 79	98.68 34	99.27 106	99.53 149	98.64 47	99.96 11	98.44 93	99.80 58	99.79 35

TSAR-MVS		99.36 31	99.36 17	99.36 91	99.67 64	98.61 154	99.07 213	99.33 185	99.00 16	99.82 11	99.81 51	99.06 7	99.84 91	99.09 32	99.42 94	99.65 80

PVSNet_Blended_VisFu		99.36 31	99.28 33	99.61 56	99.86 12	99.07 89	99.47 121	99.93 1	97.66 110	99.71 22	99.86 21	97.73 74	99.96 11	99.47 6	99.82 55	99.79 35

NCCC		99.34 33	99.19 36	99.79 25	99.61 82	99.65 30	99.30 169	99.48 99	98.86 27	99.21 118	99.63 123	98.72 42	99.90 67	98.25 105	99.63 89	99.80 31

MP-MVS		99.33 34	99.15 39	99.87 2	99.88 4	99.82 6	99.66 52	99.46 116	98.09 71	99.48 62	99.74 82	98.29 62	99.96 11	97.93 126	99.87 28	99.82 24

PS-MVSNAJ		99.32 35	99.32 22	99.30 97	99.57 89	98.94 107	98.97 235	99.46 116	98.92 26	99.71 22	99.24 216	99.01 10	99.98 2	99.35 10	99.66 84	98.97 157

CSCG		99.32 35	99.32 22	99.32 93	99.85 15	98.29 170	99.71 40	99.66 22	98.11 69	99.41 73	99.80 58	98.37 59	99.96 11	98.99 41	99.96 3	99.72 62

PHI-MVS		99.30 37	99.17 38	99.70 41	99.56 91	99.52 50	99.58 76	99.80 6	97.12 150	99.62 43	99.73 85	98.58 49	99.90 67	98.61 75	99.91 13	99.68 74

DeepC-MVS	98.35 2	99.30 37	99.19 36	99.64 52	99.82 20	99.23 77	99.62 64	99.55 50	98.94 24	99.63 40	99.95 2	95.82 116	99.94 27	99.37 9	99.97 2	99.73 56
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APD-MVS		99.27 39	99.08 42	99.84 16	99.75 38	99.79 11	99.50 107	99.50 89	97.16 146	99.77 18	99.82 42	98.78 32	99.94 27	97.56 157	99.86 38	99.80 31
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
LS3D		99.27 39	99.12 40	99.74 35	99.18 155	99.75 16	99.56 88	99.57 40	98.45 43	99.49 61	99.85 24	97.77 73	99.94 27	98.33 101	99.84 47	99.52 108

3Dnovator	97.25 9	99.24 41	99.05 44	99.81 21	99.12 167	99.66 28	99.84 9	99.74 8	99.09 7	98.92 160	99.90 7	95.94 113	99.98 2	98.95 44	99.92 8	99.79 35

test_prior3		99.21 42	99.05 44	99.68 42	99.67 64	99.48 54	98.96 237	99.56 43	98.34 50	99.01 147	99.52 152	98.68 44	99.83 97	97.96 124	99.74 68	99.74 50

F-COLMAP		99.19 43	99.04 47	99.64 52	99.78 25	99.27 73	99.42 138	99.54 57	97.29 137	99.41 73	99.59 134	98.42 56	99.93 40	98.19 107	99.69 79	99.73 56

3Dnovator+	97.12 13	99.18 44	98.97 57	99.82 18	99.17 159	99.68 24	99.81 15	99.51 79	99.20 4	98.72 180	99.89 10	95.68 120	99.97 6	98.86 53	99.86 38	99.81 27

MVSFormer		99.17 45	99.12 40	99.29 100	99.51 95	98.94 107	99.88 1	99.46 116	97.55 116	99.80 12	99.65 113	97.39 80	99.28 198	99.03 37	99.85 42	99.65 80

sss		99.17 45	99.05 44	99.53 68	99.62 78	98.97 103	99.36 158	99.62 28	97.83 94	99.67 30	99.65 113	97.37 83	99.95 24	99.19 24	99.19 102	99.68 74

DP-MVS		99.16 47	98.95 62	99.78 26	99.77 29	99.53 47	99.41 142	99.50 89	97.03 158	99.04 144	99.88 13	97.39 80	99.92 47	98.66 69	99.90 18	99.87 3

CNLPA		99.14 48	98.99 54	99.59 58	99.58 87	99.41 62	99.16 197	99.44 133	98.45 43	99.19 125	99.49 160	98.08 65	99.89 75	97.73 143	99.75 66	99.48 113

CDPH-MVS		99.13 49	98.91 65	99.80 22	99.75 38	99.71 20	99.15 200	99.41 145	96.60 182	99.60 45	99.55 145	98.83 29	99.90 67	97.48 162	99.83 51	99.78 39

jason		99.13 49	99.03 49	99.45 81	99.46 105	98.87 114	99.12 206	99.26 208	98.03 82	99.79 14	99.65 113	97.02 90	99.85 86	99.02 39	99.90 18	99.65 80
jason: jason.
lupinMVS		99.13 49	99.01 53	99.46 80	99.51 95	98.94 107	99.05 218	99.16 218	97.86 89	99.80 12	99.56 142	97.39 80	99.86 83	98.94 45	99.85 42	99.58 98

EPP-MVSNet		99.13 49	98.99 54	99.53 68	99.65 74	99.06 90	99.81 15	99.33 185	97.43 125	99.60 45	99.88 13	97.14 87	99.84 91	99.13 30	98.94 118	99.69 70

MG-MVS		99.13 49	99.02 52	99.45 81	99.57 89	98.63 150	99.07 213	99.34 177	98.99 17	99.61 44	99.82 42	97.98 68	99.87 80	97.00 187	99.80 58	99.85 6

DP-MVS Recon		99.12 54	98.95 62	99.65 48	99.74 44	99.70 22	99.27 176	99.57 40	96.40 199	99.42 71	99.68 102	98.75 39	99.80 109	97.98 123	99.72 72	99.44 123

Vis-MVSNet		99.12 54	98.97 57	99.56 63	99.78 25	99.10 86	99.68 48	99.66 22	98.49 42	99.86 7	99.87 18	94.77 158	99.84 91	99.19 24	99.41 95	99.74 50
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAMVS		99.12 54	99.08 42	99.24 103	99.46 105	98.55 156	99.51 102	99.46 116	98.09 71	99.45 66	99.82 42	98.34 60	99.51 160	98.70 64	98.93 119	99.67 77

VNet		99.11 57	98.90 66	99.73 37	99.52 93	99.56 41	99.41 142	99.39 154	99.01 12	99.74 21	99.78 69	95.56 121	99.92 47	99.52 4	98.18 151	99.72 62

CPTT-MVS		99.11 57	98.90 66	99.74 35	99.80 23	99.46 57	99.59 73	99.49 92	97.03 158	99.63 40	99.69 97	97.27 85	99.96 11	97.82 133	99.84 47	99.81 27

MVS_Test		99.10 59	98.97 57	99.48 76	99.49 100	99.14 84	99.67 50	99.34 177	97.31 135	99.58 47	99.76 75	97.65 76	99.82 102	98.87 50	99.07 110	99.46 120

liao		99.09 60	98.87 69	99.75 30	99.74 44	99.60 36	99.27 176	99.48 99	96.82 169	99.25 110	99.65 113	98.38 57	99.93 40	97.53 158	99.67 83	99.73 56

HyFIR		99.09 60	98.97 57	99.45 81	99.68 62	98.78 138	99.14 205	99.62 28	97.97 85	99.20 121	99.83 34	96.26 107	99.82 102	99.08 33	99.98 1	99.74 50

CDS-MVSNet		99.09 60	99.03 49	99.25 102	99.42 110	98.73 141	99.45 124	99.46 116	98.11 69	99.46 65	99.77 73	98.01 67	99.37 177	98.70 64	98.92 122	99.66 78
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PVSNet_Blended		99.08 63	98.97 57	99.42 88	99.76 32	98.79 136	98.78 253	99.91 2	96.74 171	99.67 30	99.49 160	97.53 77	99.88 78	98.98 42	99.85 42	99.60 92

OMC-MVS		99.08 63	99.04 47	99.20 107	99.67 64	98.22 173	99.28 174	99.52 71	98.07 75	99.66 35	99.81 51	97.79 72	99.78 113	97.79 135	99.81 56	99.60 92

WTY-MVS		99.06 65	98.88 68	99.61 56	99.62 78	99.16 81	99.37 155	99.56 43	98.04 80	99.53 54	99.62 128	96.84 93	99.94 27	98.85 54	98.49 143	99.72 62

IS-MVSNet		99.05 66	98.87 69	99.57 61	99.73 49	99.32 67	99.75 33	99.20 214	98.02 83	99.56 50	99.86 21	96.54 100	99.67 142	98.09 114	99.13 105	99.73 56

PAPM_NR		99.04 67	98.84 73	99.66 45	99.74 44	99.44 59	99.39 149	99.38 159	97.70 108	99.28 102	99.28 212	98.34 60	99.85 86	96.96 191	99.45 93	99.69 70

API-MVS		99.04 67	99.03 49	99.06 115	99.40 116	99.31 70	99.55 93	99.56 43	98.54 39	99.33 91	99.39 185	98.76 37	99.78 113	96.98 189	99.78 62	98.07 254

mvs_anonymous		99.03 69	98.99 54	99.16 109	99.38 119	98.52 161	99.51 102	99.38 159	97.79 97	99.38 79	99.81 51	97.30 84	99.45 164	99.35 10	98.99 113	99.51 110

canonicalmvs		99.02 70	98.86 71	99.51 74	99.42 110	99.32 67	99.80 19	99.48 99	98.63 35	99.31 93	98.81 244	97.09 88	99.75 119	99.27 20	97.90 161	99.47 117

PLC	97.94 4	99.02 70	98.85 72	99.53 68	99.66 73	99.01 96	99.24 186	99.52 71	96.85 167	99.27 106	99.48 164	98.25 64	99.91 56	97.76 139	99.62 90	99.65 80
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
agg_prior1		99.01 72	98.76 79	99.76 29	99.67 64	99.62 32	98.99 229	99.40 151	96.26 205	98.87 166	99.49 160	98.77 35	99.91 56	97.69 149	99.72 72	99.75 45

AdaColmap		99.01 72	98.80 75	99.66 45	99.56 91	99.54 44	99.18 196	99.70 12	98.18 63	99.35 87	99.63 123	96.32 103	99.90 67	97.48 162	99.77 64	99.55 100

1112_ss		98.98 74	98.77 78	99.59 58	99.68 62	99.02 94	99.25 184	99.48 99	97.23 143	99.13 129	99.58 137	96.93 92	99.90 67	98.87 50	98.78 131	99.84 10

MSDG		98.98 74	98.80 75	99.53 68	99.76 32	99.19 78	98.75 256	99.55 50	97.25 140	99.47 63	99.77 73	97.82 71	99.87 80	96.93 194	99.90 18	99.54 102

agg_prior3		98.97 76	98.71 83	99.75 30	99.67 64	99.60 36	99.04 222	99.41 145	95.93 220	98.87 166	99.48 164	98.61 48	99.91 56	97.63 152	99.72 72	99.75 45

114514_t		98.93 77	98.67 87	99.72 39	99.85 15	99.53 47	99.62 64	99.59 35	92.65 263	99.71 22	99.78 69	98.06 66	99.90 67	98.84 55	99.91 13	99.74 50

PS-MVSNAJss		98.92 78	98.92 64	98.90 142	98.78 233	98.53 158	99.78 22	99.54 57	98.07 75	99.00 153	99.76 75	99.01 10	99.37 177	99.13 30	97.23 191	98.81 163

Test_1112_low_res		98.89 79	98.66 90	99.57 61	99.69 61	98.95 104	99.03 223	99.47 112	96.98 160	99.15 128	99.23 217	96.77 95	99.89 75	98.83 56	98.78 131	99.86 4

AllTest		98.87 80	98.72 81	99.31 94	99.86 12	98.48 165	99.56 88	99.61 30	97.85 91	99.36 84	99.85 24	95.95 111	99.85 86	96.66 207	99.83 51	99.59 96

UGNet		98.87 80	98.69 85	99.40 89	99.22 148	98.72 142	99.44 128	99.68 16	99.24 3	99.18 127	99.42 175	92.74 208	99.96 11	99.34 14	99.94 6	99.53 106
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
Vis-MVSNet (Re-imp)		98.87 80	98.72 81	99.31 94	99.71 54	98.88 113	99.80 19	99.44 133	97.91 87	99.36 84	99.78 69	95.49 123	99.43 172	97.91 127	99.11 106	99.62 90

EPNet		98.86 83	98.71 83	99.30 97	97.20 273	98.18 174	99.62 64	98.91 243	99.28 2	98.63 197	99.81 51	95.96 110	99.99 1	99.24 21	99.72 72	99.73 56
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		98.86 83	98.80 75	99.03 118	99.76 32	98.79 136	99.28 174	99.91 2	97.42 127	99.67 30	99.37 189	97.53 77	99.88 78	98.98 42	97.29 190	98.42 245

ab-mvs		98.86 83	98.63 92	99.54 64	99.64 75	99.19 78	99.44 128	99.54 57	97.77 99	99.30 94	99.81 51	94.20 178	99.93 40	99.17 27	98.82 129	99.49 111

MAR-MVS		98.86 83	98.63 92	99.54 64	99.37 121	99.66 28	99.45 124	99.54 57	96.61 180	99.01 147	99.40 181	97.09 88	99.86 83	97.68 151	99.53 92	99.10 143
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
COLMAP_ROB	97.56 6	98.86 83	98.75 80	99.17 108	99.88 4	98.53 158	99.34 162	99.59 35	97.55 116	98.70 186	99.89 10	95.83 115	99.90 67	98.10 113	99.90 18	99.08 148
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
HY-MVS	97.30 7	98.85 88	98.64 91	99.47 78	99.42 110	99.08 88	99.62 64	99.36 165	97.39 130	99.28 102	99.68 102	96.44 101	99.92 47	98.37 97	98.22 150	99.40 128

PVSNet	96.02 17	98.85 88	98.84 73	98.89 144	99.73 49	97.28 191	98.32 274	99.60 32	97.86 89	99.50 58	99.57 141	96.75 96	99.86 83	98.56 83	99.70 78	99.54 102

PatchMatch-RL		98.84 90	98.62 95	99.52 72	99.71 54	99.28 72	99.06 216	99.77 7	97.74 103	99.50 58	99.53 149	95.41 124	99.84 91	97.17 179	99.64 87	99.44 123

alignmvs		98.81 91	98.56 101	99.58 60	99.43 109	99.42 61	99.51 102	98.96 236	98.61 37	99.35 87	98.92 239	94.78 155	99.77 115	99.35 10	98.11 155	99.54 102

DeepPCF-MVS	98.18 3	98.81 91	99.37 15	97.12 248	99.60 84	91.75 273	98.61 265	99.44 133	99.35 1	99.83 8	99.85 24	98.70 43	99.81 107	99.02 39	99.91 13	99.81 27

PMMVS		98.80 93	98.62 95	99.34 92	99.27 141	98.70 143	98.76 255	99.31 192	97.34 132	99.21 118	99.07 228	97.20 86	99.82 102	98.56 83	98.87 126	99.52 108

FIs		98.78 94	98.63 92	99.23 105	99.18 155	99.54 44	99.83 12	99.59 35	98.28 54	98.79 175	99.81 51	96.75 96	99.37 177	99.08 33	96.38 206	98.78 166

FC-MVSNet-test		98.75 95	98.62 95	99.15 111	99.08 176	99.45 58	99.86 8	99.60 32	98.23 59	98.70 186	99.82 42	96.80 94	99.22 212	99.07 35	96.38 206	98.79 165

XVG-OURS		98.73 96	98.68 86	98.88 146	99.70 59	97.73 186	98.92 244	99.55 50	98.52 41	99.45 66	99.84 32	95.27 128	99.91 56	98.08 118	98.84 128	99.00 154

diffmvs		98.72 97	98.49 103	99.43 87	99.48 103	99.19 78	99.62 64	99.42 142	95.58 227	99.37 80	99.67 106	96.14 108	99.74 120	98.14 111	98.96 116	99.37 129

XVG-OURS-SEG-HR		98.69 98	98.62 95	98.89 144	99.71 54	97.74 185	99.12 206	99.54 57	98.44 46	99.42 71	99.71 89	94.20 178	99.92 47	98.54 87	98.90 124	99.00 154

liao1		98.68 99	98.54 102	99.11 113	98.89 217	98.65 148	99.27 176	99.49 92	96.89 165	97.99 228	99.56 142	97.72 75	99.83 97	97.74 142	99.27 100	98.84 162

EI-MVSNet		98.67 100	98.67 87	98.68 167	99.35 124	97.97 180	99.50 107	99.38 159	96.93 164	99.20 121	99.83 34	97.87 69	99.36 181	98.38 96	97.56 172	98.71 178

test_djsdf		98.67 100	98.57 100	98.98 124	98.70 244	98.91 112	99.88 1	99.46 116	97.55 116	99.22 117	99.88 13	95.73 119	99.28 198	99.03 37	97.62 168	98.75 172

QAPM		98.67 100	98.30 113	99.80 22	99.20 151	99.67 26	99.77 24	99.72 9	94.74 235	98.73 179	99.90 7	95.78 117	99.98 2	96.96 191	99.88 26	99.76 44

nrg030		98.64 103	98.42 105	99.28 101	99.05 181	99.69 23	99.81 15	99.46 116	98.04 80	99.01 147	99.82 42	96.69 98	99.38 174	99.34 14	94.59 240	98.78 166

PAPR		98.63 104	98.34 109	99.51 74	99.40 116	99.03 93	98.80 252	99.36 165	96.33 201	99.00 153	99.12 226	98.46 53	99.84 91	95.23 234	99.37 99	99.66 78

CVMVSNet		98.57 105	98.67 87	98.30 197	99.35 124	95.59 239	99.50 107	99.55 50	98.60 38	99.39 77	99.83 34	94.48 169	99.45 164	98.75 60	98.56 140	99.85 6

MVSTER		98.49 106	98.32 111	99.00 122	99.35 124	99.02 94	99.54 96	99.38 159	97.41 128	99.20 121	99.73 85	93.86 190	99.36 181	98.87 50	97.56 172	98.62 223

OpenMVS	96.50 16	98.47 107	98.12 119	99.52 72	99.04 182	99.53 47	99.82 13	99.72 9	94.56 240	98.08 223	99.88 13	94.73 160	99.98 2	97.47 164	99.76 65	99.06 150

IterMVS-LS		98.46 108	98.42 105	98.58 172	99.59 86	98.00 178	99.37 155	99.43 141	96.94 163	99.07 139	99.59 134	97.87 69	99.03 229	98.32 103	95.62 216	98.71 178
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
jajsoiax		98.43 109	98.28 114	98.88 146	98.60 251	98.43 167	99.82 13	99.53 67	98.19 60	98.63 197	99.80 58	93.22 198	99.44 169	99.22 22	97.50 176	98.77 169

BH-untuned		98.42 110	98.36 107	98.59 171	99.49 100	96.70 217	99.27 176	99.13 221	97.24 142	98.80 174	99.38 186	95.75 118	99.74 120	97.07 184	99.16 103	99.33 132

BH-RMVSNet		98.41 111	98.08 122	99.40 89	99.41 113	98.83 120	99.30 169	98.77 251	97.70 108	98.94 158	99.65 113	92.91 204	99.74 120	96.52 211	99.55 91	99.64 85

mvs_tets		98.40 112	98.23 115	98.91 138	98.67 247	98.51 162	99.66 52	99.53 67	98.19 60	98.65 195	99.81 51	92.75 206	99.44 169	99.31 16	97.48 180	98.77 169

XXY-MVS		98.38 113	98.09 121	99.24 103	99.26 143	99.32 67	99.56 88	99.55 50	97.45 124	98.71 181	99.83 34	93.23 197	99.63 151	98.88 48	96.32 208	98.76 171

ACMM	97.58 5	98.37 114	98.34 109	98.48 183	99.41 113	97.10 199	99.56 88	99.45 127	98.53 40	99.04 144	99.85 24	93.00 200	99.71 133	98.74 61	97.45 181	98.64 216
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		98.33 115	98.48 104	97.90 227	99.16 161	94.78 253	99.31 167	99.11 222	97.27 138	99.45 66	99.59 134	95.33 125	99.84 91	98.48 90	98.61 134	99.09 147

PatchmatchNet		98.31 116	98.36 107	98.19 212	99.16 161	95.32 245	99.27 176	98.92 240	97.37 131	99.37 80	99.58 137	94.90 149	99.70 138	97.43 167	99.21 101	99.54 102
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VPA-MVSNet		98.29 117	97.95 132	99.30 97	99.16 161	99.54 44	99.50 107	99.58 39	98.27 55	99.35 87	99.37 189	92.53 215	99.65 145	99.35 10	94.46 241	98.72 176

UniMVSNet (Re)		98.29 117	98.00 128	99.13 112	99.00 188	99.36 65	99.49 112	99.51 79	97.95 86	98.97 156	99.13 223	96.30 104	99.38 174	98.36 99	93.34 256	98.66 212

HQP_MVS		98.27 119	98.22 116	98.44 187	99.29 136	96.97 209	99.39 149	99.47 112	98.97 21	99.11 133	99.61 131	92.71 209	99.69 140	97.78 136	97.63 166	98.67 203

UniMVSNet_NR-MVSNet		98.22 120	97.97 130	98.96 126	98.92 211	98.98 100	99.48 117	99.53 67	97.76 100	98.71 181	99.46 169	96.43 102	99.22 212	98.57 80	92.87 262	98.69 187

LPG-MVS_test		98.22 120	98.13 118	98.49 181	99.33 128	97.05 203	99.58 76	99.55 50	97.46 121	99.24 111	99.83 34	92.58 213	99.72 128	98.09 114	97.51 174	98.68 192

RPSCF		98.22 120	98.62 95	96.99 249	99.82 20	91.58 274	99.72 38	99.44 133	96.61 180	99.66 35	99.89 10	95.92 114	99.82 102	97.46 165	99.10 107	99.57 99

ADS-MVSNet		98.20 123	98.08 122	98.56 175	99.33 128	96.48 225	99.23 187	99.15 219	96.24 207	99.10 135	99.67 106	94.11 182	99.71 133	96.81 197	99.05 111	99.48 113

CR-MVSNet		98.17 124	97.93 134	98.87 149	99.18 155	98.49 163	99.22 190	99.33 185	96.96 161	99.56 50	99.38 186	94.33 174	99.00 232	94.83 240	98.58 137	99.14 140

CLD-MVS		98.16 125	98.10 120	98.33 194	99.29 136	96.82 215	98.75 256	99.44 133	97.83 94	99.13 129	99.55 145	92.92 202	99.67 142	98.32 103	97.69 165	98.48 243
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
WR-MVS_H		98.13 126	97.87 139	98.90 142	99.02 186	98.84 117	99.70 41	99.59 35	97.27 138	98.40 210	99.19 220	95.53 122	99.23 209	98.34 100	93.78 254	98.61 232

v1neww		98.12 127	97.84 140	98.93 131	98.97 196	98.81 129	99.66 52	99.35 169	96.49 187	99.29 98	99.37 189	95.02 139	99.32 189	97.73 143	94.73 232	98.67 203

v7new		98.12 127	97.84 140	98.93 131	98.97 196	98.81 129	99.66 52	99.35 169	96.49 187	99.29 98	99.37 189	95.02 139	99.32 189	97.73 143	94.73 232	98.67 203

v6		98.12 127	97.84 140	98.94 129	98.94 204	98.83 120	99.66 52	99.34 177	96.49 187	99.30 94	99.37 189	94.95 143	99.34 186	97.77 138	94.74 231	98.67 203

ACMH	97.28 8	98.10 130	97.99 129	98.44 187	99.41 113	96.96 211	99.60 71	99.56 43	98.09 71	98.15 220	99.91 5	90.87 232	99.70 138	98.88 48	97.45 181	98.67 203
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CP-MVSNet		98.09 131	97.78 146	99.01 120	98.97 196	99.24 76	99.67 50	99.46 116	97.25 140	98.48 207	99.64 119	93.79 191	99.06 224	98.63 71	94.10 248	98.74 175

DU-MVS		98.08 132	97.79 144	98.96 126	98.87 220	98.98 100	99.41 142	99.45 127	97.87 88	98.71 181	99.50 157	94.82 153	99.22 212	98.57 80	92.87 262	98.68 192

divwei89l23v2f112		98.06 133	97.78 146	98.91 138	98.90 214	98.77 140	99.57 82	99.35 169	96.45 194	99.24 111	99.37 189	94.92 147	99.27 200	97.50 160	94.71 236	98.68 192

v2v482		98.06 133	97.77 150	98.92 136	98.90 214	98.82 127	99.57 82	99.36 165	96.65 177	99.19 125	99.35 200	94.20 178	99.25 206	97.72 147	94.97 228	98.69 187

V42		98.06 133	97.79 144	98.86 153	98.98 193	98.84 117	99.69 43	99.34 177	96.53 186	99.30 94	99.37 189	94.67 162	99.32 189	97.57 156	94.66 237	98.42 245

test-LLR		98.06 133	97.90 135	98.55 177	98.79 229	97.10 199	98.67 261	97.75 281	97.34 132	98.61 200	98.85 240	94.45 170	99.45 164	97.25 173	99.38 96	99.10 143

WR-MVS		98.06 133	97.73 157	99.06 115	98.86 223	99.25 75	99.19 195	99.35 169	97.30 136	98.66 189	99.43 174	93.94 187	99.21 215	98.58 78	94.28 244	98.71 178

ACMP	97.20 11	98.06 133	97.94 133	98.45 186	99.37 121	97.01 206	99.44 128	99.49 92	97.54 119	98.45 208	99.79 66	91.95 222	99.72 128	97.91 127	97.49 179	98.62 223
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v1141		98.05 139	97.76 153	98.91 138	98.91 213	98.78 138	99.57 82	99.35 169	96.41 198	99.23 115	99.36 196	94.93 146	99.27 200	97.38 169	94.72 234	98.68 192

v7		98.05 139	97.78 146	98.87 149	98.99 189	98.67 145	99.64 62	99.34 177	96.31 202	99.29 98	99.51 155	94.78 155	99.27 200	97.03 185	95.15 225	98.66 212

v1		98.05 139	97.76 153	98.93 131	98.92 211	98.80 134	99.57 82	99.35 169	96.39 200	99.28 102	99.36 196	94.86 152	99.32 189	97.38 169	94.72 234	98.68 192

EPNet_dtu		98.03 142	97.96 131	98.23 208	98.27 258	95.54 241	99.23 187	98.75 252	99.02 9	97.82 232	99.71 89	96.11 109	99.48 161	93.04 258	99.65 86	99.69 70
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet3		98.03 142	97.76 153	98.84 157	99.39 118	98.98 100	99.40 148	99.38 159	96.67 176	99.07 139	99.28 212	92.93 201	98.98 235	97.10 181	96.65 199	98.56 238

ADS-MVSNet2		98.02 144	98.07 124	97.87 228	99.33 128	95.19 248	99.23 187	99.08 224	96.24 207	99.10 135	99.67 106	94.11 182	98.93 243	96.81 197	99.05 111	99.48 113

HQP-MVS		98.02 144	97.90 135	98.37 192	99.19 152	96.83 213	98.98 232	99.39 154	98.24 56	98.66 189	99.40 181	92.47 217	99.64 147	97.19 177	97.58 170	98.64 216

LTVRE_ROB	97.16 12	98.02 144	97.90 135	98.40 190	99.23 146	96.80 216	99.70 41	99.60 32	97.12 150	98.18 219	99.70 92	91.73 224	99.72 128	98.39 94	97.45 181	98.68 192
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
PatchFormer-LS_test		98.01 147	98.05 125	97.87 228	99.15 164	94.76 254	99.42 138	98.93 238	97.12 150	98.84 171	98.59 251	93.74 195	99.80 109	98.55 85	98.17 152	99.06 150

BH-w/o		98.00 148	97.89 138	98.32 195	99.35 124	96.20 233	99.01 227	98.90 245	96.42 196	98.38 211	99.00 233	95.26 129	99.72 128	96.06 218	98.61 134	99.03 152

v1144		97.98 149	97.69 160	98.85 156	98.87 220	98.66 147	99.54 96	99.35 169	96.27 204	99.23 115	99.35 200	94.67 162	99.23 209	96.73 202	95.16 224	98.68 192

EU-MVSNet		97.98 149	98.03 126	97.81 233	98.72 241	96.65 220	99.66 52	99.66 22	98.09 71	98.35 213	99.82 42	95.25 130	98.01 264	97.41 168	95.30 221	98.78 166

tpmvs		97.98 149	98.02 127	97.84 231	99.04 182	94.73 255	99.31 167	99.20 214	96.10 218	98.76 178	99.42 175	94.94 144	99.81 107	96.97 190	98.45 144	98.97 157

NR-MVSNet		97.97 152	97.61 164	99.02 119	98.87 220	99.26 74	99.47 121	99.42 142	97.63 111	97.08 242	99.50 157	95.07 137	99.13 219	97.86 130	93.59 255	98.68 192

v8		97.95 153	97.63 163	98.93 131	98.95 201	98.81 129	99.80 19	99.41 145	96.03 219	99.10 135	99.42 175	94.92 147	99.30 195	96.94 193	94.08 249	98.66 212

PS-CasMVS		97.93 154	97.59 166	98.95 128	98.99 189	99.06 90	99.68 48	99.52 71	97.13 148	98.31 215	99.68 102	92.44 220	99.05 225	98.51 88	94.08 249	98.75 172

TranMVSNet+NR-MVSNet		97.93 154	97.66 161	98.76 164	98.78 233	98.62 152	99.65 60	99.49 92	97.76 100	98.49 206	99.60 133	94.23 177	98.97 242	98.00 122	92.90 260	98.70 182

v144192		97.92 156	97.60 165	98.87 149	98.83 226	98.65 148	99.55 93	99.34 177	96.20 210	99.32 92	99.40 181	94.36 173	99.26 205	96.37 215	95.03 227	98.70 182

ACMH+	97.24 10	97.92 156	97.78 146	98.32 195	99.46 105	96.68 219	99.56 88	99.54 57	98.41 47	97.79 234	99.87 18	90.18 239	99.66 144	98.05 121	97.18 194	98.62 223

LFMVS		97.90 158	97.35 192	99.54 64	99.52 93	99.01 96	99.39 149	98.24 272	97.10 154	99.65 38	99.79 66	84.79 271	99.91 56	99.28 18	98.38 147	99.69 70

OurMVSNet-221017-0		97.88 159	97.77 150	98.19 212	98.71 243	96.53 223	99.88 1	99.00 232	97.79 97	98.78 176	99.94 3	91.68 225	99.35 184	97.21 175	96.99 197	98.69 187

v7n		97.87 160	97.52 170	98.92 136	98.76 237	98.58 155	99.84 9	99.46 116	96.20 210	98.91 161	99.70 92	94.89 150	99.44 169	96.03 219	93.89 253	98.75 172

v10		97.85 161	97.52 170	98.86 153	98.99 189	98.67 145	99.75 33	99.41 145	95.70 225	98.98 155	99.41 178	94.75 159	99.23 209	96.01 220	94.63 239	98.67 203

GA-MVS		97.85 161	97.47 177	99.00 122	99.38 119	97.99 179	98.57 267	99.15 219	97.04 157	98.90 163	99.30 209	89.83 241	99.38 174	96.70 204	98.33 148	99.62 90

VPNet		97.84 163	97.44 182	99.01 120	99.21 149	98.94 107	99.48 117	99.57 40	98.38 48	99.28 102	99.73 85	88.89 248	99.39 173	99.19 24	93.27 257	98.71 178

LCM-MVSNet-Re		97.83 164	98.15 117	96.87 253	99.30 134	92.25 272	99.59 73	98.26 271	97.43 125	96.20 250	99.13 223	96.27 105	98.73 248	98.17 109	98.99 113	99.64 85

XVG-ACMP-BASELINE		97.83 164	97.71 159	98.20 211	99.11 169	96.33 229	99.41 142	99.52 71	98.06 79	99.05 143	99.50 157	89.64 243	99.73 126	97.73 143	97.38 187	98.53 240

IterMVS		97.83 164	97.77 150	98.02 218	99.58 87	96.27 231	99.02 225	99.48 99	97.22 144	98.71 181	99.70 92	92.75 206	99.13 219	97.46 165	96.00 212	98.67 203
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EPMVS		97.82 167	97.65 162	98.35 193	98.88 218	95.98 235	99.49 112	94.71 292	97.57 115	99.26 109	99.48 164	92.46 219	99.71 133	97.87 129	99.08 109	99.35 130

MV-PatchMatch		97.81 168	97.75 156	97.99 221	97.53 267	96.60 221	98.96 237	98.85 247	97.22 144	97.23 240	99.36 196	95.28 127	99.46 163	95.51 229	99.78 62	97.92 262

v1192		97.81 168	97.44 182	98.91 138	98.88 218	98.68 144	99.51 102	99.34 177	96.18 212	99.20 121	99.34 203	94.03 185	99.36 181	95.32 233	95.18 223	98.69 187

v1921920		97.80 170	97.45 179	98.84 157	98.80 227	98.53 158	99.52 100	99.34 177	96.15 214	99.24 111	99.47 168	93.98 186	99.29 197	95.40 231	95.13 226	98.69 187

V4		97.80 170	97.51 172	98.67 169	98.79 229	98.63 150	99.87 4	99.44 133	95.87 221	99.01 147	99.46 169	94.52 167	99.33 187	96.64 210	93.97 251	98.05 255

v148		97.79 172	97.55 167	98.50 179	98.74 238	97.72 187	99.54 96	99.33 185	96.26 205	98.90 163	99.51 155	94.68 161	99.14 218	97.83 132	93.15 259	98.63 222

v52		97.79 172	97.50 173	98.66 170	98.80 227	98.62 152	99.87 4	99.44 133	95.87 221	99.01 147	99.46 169	94.44 172	99.33 187	96.65 209	93.96 252	98.05 255

pm-mvs1		97.77 174	97.53 169	98.50 179	98.46 254	97.92 181	99.15 200	99.31 192	95.87 221	98.58 202	99.58 137	94.51 168	99.04 226	96.74 201	95.59 217	98.56 238

PEN-MVS		97.76 175	97.44 182	98.72 166	98.77 236	98.54 157	99.78 22	99.51 79	97.06 156	98.29 217	99.64 119	92.63 212	98.89 244	98.09 114	93.16 258	98.72 176

Baseline_NR-MVSNet		97.76 175	97.45 179	98.68 167	99.09 174	98.29 170	99.41 142	98.85 247	95.65 226	98.63 197	99.67 106	94.82 153	99.10 223	98.07 119	92.89 261	98.64 216

TR-MVS		97.76 175	97.41 187	98.82 159	99.06 179	97.87 182	98.87 249	98.56 265	96.63 179	98.68 188	99.22 218	92.49 216	99.65 145	95.40 231	97.79 163	98.95 159

Patchmtry		97.75 178	97.40 188	98.81 160	99.10 172	98.87 114	99.11 209	99.33 185	94.83 233	98.81 173	99.38 186	94.33 174	99.02 230	96.10 217	95.57 218	98.53 240

dp		97.75 178	97.80 143	97.59 240	99.10 172	93.71 264	99.32 164	98.88 246	96.48 193	99.08 138	99.55 145	92.67 211	99.82 102	96.52 211	98.58 137	99.24 137

TAPA-MVS	97.07 15	97.74 180	97.34 195	98.94 129	99.70 59	97.53 188	99.25 184	99.51 79	91.90 267	99.30 94	99.63 123	98.78 32	99.64 147	88.09 273	99.87 28	99.65 80
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VDD-MVS		97.73 181	97.35 192	98.88 146	99.47 104	97.12 198	99.34 162	98.85 247	98.19 60	99.67 30	99.85 24	82.98 275	99.92 47	99.49 5	98.32 149	99.60 92

MIMVSNet		97.73 181	97.45 179	98.57 173	99.45 108	97.50 189	99.02 225	98.98 234	96.11 216	99.41 73	99.14 222	90.28 235	98.74 247	95.74 224	98.93 119	99.47 117

CostFormer		97.72 183	97.73 157	97.71 238	99.15 164	94.02 260	99.54 96	99.02 231	94.67 236	99.04 144	99.35 200	92.35 221	99.77 115	98.50 89	97.94 160	99.34 131

FMVSNet2		97.72 183	97.36 190	98.80 161	99.51 95	98.84 117	99.45 124	99.42 142	96.49 187	98.86 170	99.29 211	90.26 236	98.98 235	96.44 213	96.56 202	98.58 237

test0.0.03 1		97.71 185	97.42 186	98.56 175	98.41 256	97.82 183	98.78 253	98.63 261	97.34 132	98.05 227	98.98 236	94.45 170	98.98 235	95.04 237	97.15 195	98.89 160

v1240		97.69 186	97.32 198	98.79 162	98.85 224	98.43 167	99.48 117	99.36 165	96.11 216	99.27 106	99.36 196	93.76 193	99.24 208	94.46 245	95.23 222	98.70 182

cascas		97.69 186	97.43 185	98.48 183	98.60 251	97.30 190	98.18 279	99.39 154	92.96 260	98.41 209	98.78 247	93.77 192	99.27 200	98.16 110	98.61 134	98.86 161

GBi-Net		97.68 188	97.48 175	98.29 198	99.51 95	97.26 193	99.43 132	99.48 99	96.49 187	99.07 139	99.32 206	90.26 236	98.98 235	97.10 181	96.65 199	98.62 223

test1		97.68 188	97.48 175	98.29 198	99.51 95	97.26 193	99.43 132	99.48 99	96.49 187	99.07 139	99.32 206	90.26 236	98.98 235	97.10 181	96.65 199	98.62 223

tpm		97.67 190	97.55 167	98.03 216	99.02 186	95.01 251	99.43 132	98.54 266	96.44 195	99.12 131	99.34 203	91.83 223	99.60 154	97.75 141	96.46 204	99.48 113

PCF-MVS	97.08 14	97.66 191	97.06 207	99.47 78	99.61 82	99.09 87	98.04 280	99.25 210	91.24 270	98.51 204	99.70 92	94.55 165	99.91 56	92.76 260	99.85 42	99.42 126
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
testgi		97.65 192	97.50 173	98.13 214	99.36 123	96.45 226	99.42 138	99.48 99	97.76 100	97.87 231	99.45 172	91.09 229	98.81 246	94.53 243	98.52 141	99.13 142

PAPM		97.59 193	97.09 206	99.07 114	99.06 179	98.26 172	98.30 275	99.10 223	94.88 232	98.08 223	99.34 203	96.27 105	99.64 147	89.87 268	98.92 122	99.31 133

VDDNet		97.55 194	97.02 208	99.16 109	99.49 100	98.12 177	99.38 153	99.30 195	95.35 229	99.68 26	99.90 7	82.62 277	99.93 40	99.31 16	98.13 154	99.42 126

TESTMET0.1,1		97.55 194	97.27 201	98.40 190	98.93 209	96.53 223	98.67 261	97.61 285	96.96 161	98.64 196	99.28 212	88.63 254	99.45 164	97.30 172	99.38 96	99.21 138

DWT-MVSNet_test		97.53 196	97.40 188	97.93 224	99.03 184	94.86 252	99.57 82	98.63 261	96.59 184	98.36 212	98.79 245	89.32 245	99.74 120	98.14 111	98.16 153	99.20 139

v748		97.52 197	97.23 202	98.41 189	98.69 245	97.23 196	99.87 4	99.45 127	95.72 224	98.51 204	99.53 149	94.13 181	99.30 195	96.78 199	92.39 265	98.70 182

LF4IMVS		97.52 197	97.46 178	97.70 239	98.98 193	95.55 240	99.29 172	98.82 250	98.07 75	98.66 189	99.64 119	89.97 240	99.61 153	97.01 186	96.68 198	97.94 260

DTE-MVSNet		97.51 199	97.19 204	98.46 185	98.63 250	98.13 176	99.84 9	99.48 99	96.68 175	97.97 229	99.67 106	92.92 202	98.56 250	96.88 196	92.60 264	98.70 182

SixPastTwentyTwo		97.50 200	97.33 197	98.03 216	98.65 248	96.23 232	99.77 24	98.68 259	97.14 147	97.90 230	99.93 4	90.45 234	99.18 217	97.00 187	96.43 205	98.67 203

JIA-IIPM		97.50 200	97.02 208	98.93 131	98.73 239	97.80 184	99.30 169	98.97 235	91.73 268	98.91 161	94.86 283	95.10 136	99.71 133	97.58 155	97.98 159	99.28 135

test-mter		97.49 202	97.13 205	98.55 177	98.79 229	97.10 199	98.67 261	97.75 281	96.65 177	98.61 200	98.85 240	88.23 259	99.45 164	97.25 173	99.38 96	99.10 143

DI_MVS_test_dynamic		97.45 203	96.79 212	99.44 84	97.76 265	99.04 92	99.21 192	98.61 263	97.74 103	94.01 266	98.83 242	87.38 263	99.83 97	98.63 71	98.90 124	99.44 123

DI_MVS_test_normal		97.44 204	96.77 214	99.44 84	97.75 266	99.00 98	99.10 211	98.64 260	97.71 106	93.93 269	98.82 243	87.39 262	99.83 97	98.61 75	98.97 115	99.49 111

tpm2		97.44 204	97.34 195	97.74 237	99.15 164	94.36 258	99.45 124	98.94 237	93.45 258	98.90 163	99.44 173	91.35 227	99.59 155	97.31 171	98.07 156	99.29 134

tpm cat1		97.39 206	97.36 190	97.50 243	99.17 159	93.73 262	99.43 132	99.31 192	91.27 269	98.71 181	99.08 227	94.31 176	99.77 115	96.41 214	98.50 142	99.00 154

tpmp4_e23		97.34 207	97.29 200	97.52 241	99.25 145	93.73 262	99.58 76	99.19 217	94.00 250	98.20 218	99.41 178	90.74 233	99.74 120	97.13 180	98.07 156	99.07 149

USDC		97.34 207	97.20 203	97.75 236	99.07 177	95.20 247	98.51 270	99.04 229	97.99 84	98.31 215	99.86 21	89.02 246	99.55 158	95.67 227	97.36 188	98.49 242

HC-MVS		97.28 209	96.55 216	99.48 76	98.78 233	98.95 104	99.27 176	99.39 154	83.53 284	98.08 223	99.54 148	96.97 91	99.87 80	94.23 252	99.16 103	99.63 88

DSMNet-mixed		97.25 210	97.35 192	96.95 251	97.84 263	93.61 266	99.57 82	96.63 288	96.13 215	98.87 166	98.61 250	94.59 164	97.70 269	95.08 236	98.86 127	99.55 100

MS-PatchMatch		97.24 211	97.32 198	96.99 249	98.45 255	93.51 267	98.82 251	99.32 191	97.41 128	98.13 221	99.30 209	88.99 247	99.56 156	95.68 226	99.80 58	97.90 263

TransMVSNet (Re)		97.15 212	96.58 215	98.86 153	99.12 167	98.85 116	99.49 112	98.91 243	95.48 228	97.16 241	99.80 58	93.38 196	99.11 222	94.16 254	91.73 266	98.62 223

TinyColmap		97.12 213	96.89 210	97.83 232	99.07 177	95.52 242	98.57 267	98.74 255	97.58 114	97.81 233	99.79 66	88.16 260	99.56 156	95.10 235	97.21 192	98.39 248

K. test v3		97.10 214	96.79 212	98.01 219	98.72 241	96.33 229	99.87 4	97.05 287	97.59 112	96.16 251	99.80 58	88.71 250	99.04 226	96.69 205	96.55 203	98.65 215

LP		97.04 215	96.80 211	97.77 235	98.90 214	95.23 246	98.97 235	99.06 227	94.02 249	98.09 222	99.41 178	93.88 188	98.82 245	90.46 265	98.42 146	99.26 136

PatchT		97.03 216	96.44 217	98.79 162	98.99 189	98.34 169	99.16 197	99.07 226	92.13 264	99.52 56	97.31 275	94.54 166	98.98 235	88.54 271	98.73 133	99.03 152

FMVSNet1		96.84 217	96.36 218	98.29 198	99.32 132	97.26 193	99.43 132	99.48 99	95.11 230	98.55 203	99.32 206	83.95 274	98.98 235	95.81 223	96.26 209	98.62 223

test_0402		96.64 218	96.24 219	97.85 230	98.85 224	96.43 227	99.44 128	99.26 208	93.52 256	96.98 244	99.52 152	88.52 255	99.20 216	92.58 262	97.50 176	97.93 261

RPMNet		96.61 219	95.85 225	98.87 149	99.18 155	98.49 163	99.22 190	99.08 224	88.72 280	99.56 50	97.38 274	94.08 184	99.00 232	86.87 277	98.58 137	99.14 140

X-MVStestdata		96.55 220	95.45 238	99.87 2	99.85 15	99.83 3	99.69 43	99.68 16	98.98 18	99.37 80	64.01 296	98.81 30	99.94 27	98.79 58	99.86 38	99.84 10

UnsupCasMVSNet_eth		96.44 221	96.12 221	97.40 245	98.65 248	95.65 237	99.36 158	99.51 79	97.13 148	96.04 254	98.99 234	88.40 257	98.17 253	96.71 203	90.27 268	98.40 247

FMVSNet5		96.43 222	96.19 220	97.15 247	99.11 169	95.89 236	99.32 164	99.52 71	94.47 243	98.34 214	99.07 228	87.54 261	97.07 272	92.61 261	95.72 214	98.47 244

v18		96.42 223	95.80 228	98.26 201	98.95 201	98.82 127	99.76 26	99.28 203	94.58 237	94.12 261	97.70 263	95.22 132	98.16 254	94.83 240	87.80 274	97.79 271

v17		96.42 223	95.81 227	98.25 205	98.94 204	98.80 134	99.76 26	99.28 203	94.57 238	94.18 260	97.71 262	95.23 131	98.16 254	94.86 238	87.73 276	97.80 266

v16		96.39 225	95.76 229	98.26 201	98.96 199	98.81 129	99.76 26	99.28 203	94.57 238	94.10 262	97.70 263	95.04 138	98.16 254	94.70 242	87.77 275	97.80 266

new_pmnet		96.38 226	96.03 222	97.41 244	98.13 261	95.16 250	99.05 218	99.20 214	93.94 251	97.39 238	98.79 245	91.61 226	99.04 226	90.43 266	95.77 213	98.05 255

v15		96.28 227	95.62 231	98.25 205	98.94 204	98.83 120	99.76 26	99.29 196	94.52 241	94.02 265	97.61 270	95.02 139	98.13 258	94.53 243	86.92 279	97.80 266

V14		96.26 228	95.60 232	98.26 201	98.94 204	98.83 120	99.76 26	99.29 196	94.49 242	93.96 267	97.66 267	94.99 142	98.13 258	94.41 246	86.90 280	97.80 266

V9		96.25 229	95.58 233	98.26 201	98.94 204	98.83 120	99.75 33	99.29 196	94.45 244	93.96 267	97.62 269	94.94 144	98.14 257	94.40 247	86.87 281	97.81 264

v13		96.24 230	95.58 233	98.25 205	98.98 193	98.83 120	99.75 33	99.29 196	94.35 246	93.89 270	97.60 271	95.17 134	98.11 260	94.27 251	86.86 282	97.81 264

v12		96.24 230	95.58 233	98.23 208	98.96 199	98.81 129	99.76 26	99.29 196	94.42 245	93.85 271	97.60 271	95.12 135	98.09 261	94.32 248	86.85 283	97.80 266

v11		96.23 232	95.57 236	98.21 210	98.93 209	98.83 120	99.72 38	99.29 196	94.29 247	94.05 264	97.64 268	94.88 151	98.04 262	92.89 259	88.43 273	97.77 272

IB-MVS	95.67 18	96.22 233	95.44 239	98.57 173	99.21 149	96.70 217	98.65 264	97.74 283	96.71 173	97.27 239	98.54 253	86.03 265	99.92 47	98.47 92	86.30 284	99.10 143
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
gg-mvs-nofinetune		96.17 234	95.32 240	98.73 165	98.79 229	98.14 175	99.38 153	94.09 293	91.07 272	98.07 226	91.04 289	89.62 244	99.35 184	96.75 200	99.09 108	98.68 192

test20.03		96.12 235	95.96 224	96.63 255	97.44 268	95.45 243	99.51 102	99.38 159	96.55 185	96.16 251	99.25 215	93.76 193	96.17 276	87.35 276	94.22 246	98.27 250

PVSNet_0	94.43 19	96.09 236	95.47 237	97.94 223	99.31 133	94.34 259	97.81 281	99.70 12	97.12 150	97.46 237	98.75 248	89.71 242	99.79 112	97.69 149	81.69 287	99.68 74

EG-PatchMatch MVS		95.97 237	95.69 230	96.81 254	97.78 264	92.79 270	99.16 197	98.93 238	96.16 213	94.08 263	99.22 218	82.72 276	99.47 162	95.67 227	97.50 176	98.17 252

MVS-HIRNet		95.75 238	95.16 242	97.51 242	99.30 134	93.69 265	98.88 248	95.78 289	85.09 283	98.78 176	92.65 285	91.29 228	99.37 177	94.85 239	99.85 42	99.46 120

testpf		95.66 239	96.02 223	94.58 261	98.35 257	92.32 271	97.25 286	97.91 279	92.83 261	97.03 243	98.99 234	88.69 251	98.61 249	95.72 225	97.40 185	92.80 285

MIMVSNet1		95.51 240	95.04 243	96.92 252	97.38 269	95.60 238	99.52 100	99.50 89	93.65 254	96.97 245	99.17 221	85.28 269	96.56 275	88.36 272	95.55 219	98.60 233

MDA-MVSNet_test_wron		95.45 241	94.60 245	98.01 219	98.16 260	97.21 197	99.11 209	99.24 211	93.49 257	80.73 288	98.98 236	93.02 199	98.18 252	94.22 253	94.45 242	98.64 216

TDRefinement		95.42 242	94.57 246	97.97 222	89.83 289	96.11 234	99.48 117	98.75 252	96.74 171	96.68 246	99.88 13	88.65 253	99.71 133	98.37 97	82.74 286	98.09 253

YYNet1		95.36 243	94.51 247	97.92 225	97.89 262	97.10 199	99.10 211	99.23 212	93.26 259	80.77 287	99.04 231	92.81 205	98.02 263	94.30 249	94.18 247	98.64 216

Test4		95.05 244	93.67 251	99.22 106	96.07 275	98.94 107	99.20 194	99.27 207	97.71 106	89.96 281	97.59 273	66.18 285	99.25 206	98.06 120	98.96 116	99.47 117

MDA-MVSNet-bldmvs		94.96 245	93.98 249	97.92 225	98.24 259	97.27 192	99.15 200	99.33 185	93.80 253	80.09 289	99.03 232	88.31 258	97.86 267	93.49 257	94.36 243	98.62 223

N_pmnet		94.95 246	95.83 226	92.31 267	98.47 253	79.33 290	99.12 206	92.81 297	93.87 252	97.68 236	99.13 223	93.87 189	99.01 231	91.38 263	96.19 210	98.59 234

testus		94.61 247	95.30 241	92.54 266	96.44 274	84.18 283	98.36 271	99.03 230	94.18 248	96.49 247	98.57 252	88.74 249	95.09 280	87.41 275	98.45 144	98.36 249

testing_2		94.44 248	92.93 254	98.98 124	94.16 281	99.00 98	99.42 138	99.28 203	96.60 182	84.86 283	96.84 276	70.91 280	99.27 200	98.23 106	96.08 211	98.68 192

OpenMVS_ROB	92.34 20	94.38 249	93.70 250	96.41 258	97.38 269	93.17 269	99.06 216	98.75 252	86.58 281	94.84 259	98.26 256	81.53 278	99.32 189	89.01 270	97.87 162	96.76 276

CMPMVS	69.68 23	94.13 250	94.90 244	91.84 268	97.24 272	80.01 289	98.52 269	99.48 99	89.01 278	91.99 275	99.67 106	85.67 267	99.13 219	95.44 230	97.03 196	96.39 278
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs3		94.09 251	93.25 253	96.60 256	94.76 280	94.49 256	98.92 244	98.18 275	89.66 275	96.48 248	98.06 257	86.28 264	97.33 271	89.68 269	87.20 278	97.97 259

test2356		94.07 252	94.46 248	92.89 264	95.18 279	86.13 281	97.60 284	99.06 227	93.61 255	96.15 253	98.28 254	85.60 268	93.95 282	86.68 278	98.00 158	98.59 234

HyFIR lowres test		93.82 253	92.65 256	97.33 246	99.03 184	93.48 268	98.72 260	97.91 279	90.29 274	97.72 235	98.28 254	62.59 288	98.99 234	90.37 267	98.93 119	99.53 106

UnsupCasMVSNet_bld		93.53 254	92.51 257	96.58 257	97.38 269	93.82 261	98.24 276	99.48 99	91.10 271	93.10 272	96.66 277	74.89 279	98.37 251	94.03 255	87.71 277	97.56 274

Patchmatch-RL test		93.33 255	92.66 255	95.32 259	95.61 276	90.57 276	98.24 276	98.39 268	95.10 231	95.20 256	97.70 263	67.41 284	97.77 268	96.28 216	90.02 270	97.62 273

PM-MVS		92.96 256	92.23 258	95.14 260	95.61 276	89.98 278	99.37 155	98.21 273	94.80 234	95.04 258	97.69 266	65.06 286	97.90 266	94.30 249	89.98 271	97.54 275

test1235678		92.91 257	93.30 252	91.71 270	93.14 284	83.01 285	98.75 256	98.58 264	92.80 262	92.45 273	97.91 259	88.51 256	93.54 283	82.26 282	95.35 220	98.59 234

1111		92.30 258	92.21 259	92.55 265	93.30 282	86.27 279	99.15 200	98.74 255	91.94 265	90.85 278	97.82 260	84.18 272	95.21 278	79.65 284	94.27 245	96.19 279

test12356		91.74 259	92.19 260	90.37 273	91.22 285	82.41 286	98.61 265	98.28 270	90.66 273	91.82 276	97.92 258	84.90 270	92.61 284	81.64 283	94.66 237	96.09 280

Gipuma		90.99 260	90.15 261	93.51 262	98.73 239	90.12 277	93.98 290	99.45 127	79.32 286	92.28 274	94.91 282	69.61 281	97.98 265	87.42 274	95.67 215	92.45 287
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testmv		87.91 261	87.80 262	88.24 274	87.68 292	77.50 292	99.07 213	97.66 284	89.27 276	86.47 282	96.22 280	68.35 282	92.49 286	76.63 288	88.82 272	94.72 283

PMMVS2		86.87 262	85.37 265	91.35 272	90.21 288	83.80 284	98.89 247	97.45 286	83.13 285	91.67 277	95.03 281	48.49 291	94.70 281	85.86 279	77.62 288	95.54 281

LCM-MVSNet		86.80 263	85.22 266	91.53 271	87.81 291	80.96 288	98.23 278	98.99 233	71.05 289	90.13 280	96.51 278	48.45 292	96.88 273	90.51 264	85.30 285	96.76 276

FPMVS		84.93 264	85.65 264	82.75 281	86.77 293	63.39 299	98.35 273	98.92 240	74.11 288	83.39 285	98.98 236	50.85 290	92.40 287	84.54 280	94.97 228	92.46 286

.test1245		83.42 265	86.17 263	75.15 284	93.30 282	86.27 279	99.15 200	98.74 255	91.94 265	90.85 278	97.82 260	84.18 272	95.21 278	79.65 284	39.90 297	43.98 296

no-one		83.04 266	80.12 268	91.79 269	89.44 290	85.65 282	99.32 164	98.32 269	89.06 277	79.79 291	89.16 291	44.86 293	96.67 274	84.33 281	46.78 295	93.05 284

DUST3R		82.80 267	81.52 267	86.66 275	66.61 300	68.44 298	92.79 292	97.92 277	68.96 291	80.04 290	99.85 24	85.77 266	96.15 277	97.86 130	43.89 296	95.39 282

E-PMN		80.61 268	79.88 269	82.81 280	90.75 287	76.38 294	97.69 282	95.76 290	66.44 293	83.52 284	92.25 286	62.54 289	87.16 291	68.53 292	61.40 291	84.89 294

EMVS		80.02 269	79.22 270	82.43 282	91.19 286	76.40 293	97.55 285	92.49 299	66.36 294	83.01 286	91.27 287	64.63 287	85.79 292	65.82 293	60.65 292	85.08 293

PNet_i23d		79.43 270	77.68 271	84.67 277	86.18 294	71.69 297	96.50 288	93.68 294	75.17 287	71.33 292	91.18 288	32.18 296	90.62 288	78.57 287	74.34 289	91.71 289

ANet_high		77.30 271	74.86 273	84.62 278	75.88 298	77.61 291	97.63 283	93.15 296	88.81 279	64.27 294	89.29 290	36.51 294	83.93 293	75.89 289	52.31 294	92.33 288

MVE	76.82 21	76.91 272	74.31 274	84.70 276	85.38 296	76.05 295	96.88 287	93.17 295	67.39 292	71.28 293	89.01 292	21.66 301	87.69 290	71.74 291	72.29 290	90.35 290
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 273	74.97 272	79.01 283	70.98 299	55.18 300	93.37 291	98.21 273	65.08 295	61.78 296	93.83 284	21.74 300	92.53 285	78.59 286	91.12 267	89.34 291
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuykxyi23d		74.42 274	71.19 275	84.14 279	76.16 297	74.29 296	96.00 289	92.57 298	69.57 290	63.84 295	87.49 293	21.98 298	88.86 289	75.56 290	57.50 293	89.26 292

pcd1.5k->3k		40.85 275	43.49 277	32.93 286	98.95 201	0.00 304	0.00 295	99.53 67	0.00 299	0.00 300	0.27 298	95.32 126	0.00 297	0.00 297	97.30 189	98.80 164

wuyk23d		40.18 276	41.29 279	36.84 285	86.18 294	49.12 301	79.73 294	22.81 301	27.64 296	25.46 299	28.45 297	21.98 298	48.89 294	55.80 294	23.56 300	12.51 298

testmvs		39.17 277	43.78 276	25.37 288	36.04 302	16.84 303	98.36 271	26.56 300	20.06 297	38.51 298	67.32 294	29.64 297	15.30 296	37.59 295	39.90 297	43.98 296

test123		39.01 278	42.50 278	28.53 287	39.17 301	20.91 302	98.75 256	19.17 302	19.83 298	38.57 297	66.67 295	33.16 295	15.42 295	37.50 296	29.66 299	49.26 295

cdsmvs_eth3d_5k		24.64 279	32.85 280	0.00 289	0.00 303	0.00 304	0.00 295	99.51 79	0.00 299	0.00 300	99.56 142	96.58 99	0.00 297	0.00 297	0.00 301	0.00 299

ab-mvs-re		8.30 280	11.06 281	0.00 289	0.00 303	0.00 304	0.00 295	0.00 303	0.00 299	0.00 300	99.58 137	0.00 302	0.00 297	0.00 297	0.00 301	0.00 299

pcd_1.5k_mvsjas		8.27 281	11.03 282	0.00 289	0.00 303	0.00 304	0.00 295	0.00 303	0.00 299	0.00 300	0.27 298	99.01 10	0.00 297	0.00 297	0.00 301	0.00 299

sosnet-low-res		0.02 282	0.03 283	0.00 289	0.00 303	0.00 304	0.00 295	0.00 303	0.00 299	0.00 300	0.27 298	0.00 302	0.00 297	0.00 297	0.00 301	0.00 299

sosnet		0.02 282	0.03 283	0.00 289	0.00 303	0.00 304	0.00 295	0.00 303	0.00 299	0.00 300	0.27 298	0.00 302	0.00 297	0.00 297	0.00 301	0.00 299

uncertanet		0.02 282	0.03 283	0.00 289	0.00 303	0.00 304	0.00 295	0.00 303	0.00 299	0.00 300	0.27 298	0.00 302	0.00 297	0.00 297	0.00 301	0.00 299

Regformer		0.02 282	0.03 283	0.00 289	0.00 303	0.00 304	0.00 295	0.00 303	0.00 299	0.00 300	0.27 298	0.00 302	0.00 297	0.00 297	0.00 301	0.00 299

uanet		0.02 282	0.03 283	0.00 289	0.00 303	0.00 304	0.00 295	0.00 303	0.00 299	0.00 300	0.27 298	0.00 302	0.00 297	0.00 297	0.00 301	0.00 299

test9_res														97.49 161	99.72 72	99.75 45

TEST9					99.67 64	99.65 30	99.05 218	99.41 145	96.22 209	98.95 157	99.49 160	98.77 35	99.91 56

train_agg														97.63 152	99.72 72	99.75 45

Patchmatch-test1					95.52 278	90.87 275	90.46 293	98.41 267		95.19 257	96.45 279	67.48 283			90.26 269

Patchmatch-test					99.09 174	96.59 222					98.70 249

test_8					99.67 64	99.61 34	99.03 223	99.41 145	96.28 203	98.93 159	99.48 164	98.76 37	99.91 56

agg_prior2														97.21 175	99.73 71	99.75 45

agg_prior					99.67 64	99.62 32		99.40 151		98.87 166			99.91 56

TestCases				99.31 94	99.86 12	98.48 165		99.61 30	97.85 91	99.36 84	99.85 24	95.95 111	99.85 86	96.66 207	99.83 51	99.59 96

test_prior4						99.56 41	98.99 229

test_prior2							98.96 237		98.34 50	99.01 147	99.52 152	98.68 44		97.96 124	99.74 68

test_prior				99.68 42	99.67 64	99.48 54		99.56 43					99.83 97			99.74 50

旧先验2							98.96 237		96.70 174	99.47 63			99.94 27	98.19 107

新几何2							99.01 227

新几何1				99.75 30	99.75 38	99.59 38		99.54 57	96.76 170	99.29 98	99.64 119	98.43 55	99.94 27	96.92 195	99.66 84	99.72 62

旧先验1					99.74 44	99.59 38		99.54 57			99.69 97	98.47 52			99.68 82	99.73 56

无先验							98.99 229	99.51 79	96.89 165				99.93 40	97.53 158		99.72 62

原ACMM2							98.95 241

原ACMM1				99.65 48	99.73 49	99.33 66		99.47 112	97.46 121	99.12 131	99.66 112	98.67 46	99.91 56	97.70 148	99.69 79	99.71 69

test222					99.75 38	99.49 53	98.91 246	99.49 92	96.42 196	99.34 90	99.65 113	98.28 63			99.69 79	99.72 62

testdata2													99.95 24	96.67 206

segment_acmp												98.96 19

testdata				99.54 64	99.75 38	98.95 104		99.51 79	97.07 155	99.43 70	99.70 92	98.87 26	99.94 27	97.76 139	99.64 87	99.72 62

testdata1							98.85 250		98.32 53

test12				99.75 30	99.64 75	99.61 34		99.29 196		99.21 118		98.38 57	99.89 75		99.74 68	99.74 50

plane_prior7					99.29 136	97.03 205

plane_prior6					99.27 141	96.98 208						92.71 209

plane_prior5								99.47 112					99.69 140	97.78 136	97.63 166	98.67 203

plane_prior4											99.61 131

plane_prior3						97.00 207			98.69 33	99.11 133

plane_prior2							99.39 149		98.97 21

plane_prior1					99.26 143

plane_prior						96.97 209	99.21 192		98.45 43						97.60 169

abl_6																99.79 35

n2								0.00 303

nn								0.00 303

door-mid								98.05 276

lessismore_v0				97.79 234	98.69 245	95.44 244		94.75 291		95.71 255	99.87 18	88.69 251	99.32 189	95.89 221	94.93 230	98.62 223

LGP-MVS_train				98.49 181	99.33 128	97.05 203		99.55 50	97.46 121	99.24 111	99.83 34	92.58 213	99.72 128	98.09 114	97.51 174	98.68 192

test11								99.35 169

door								97.92 277

HQP5-MVS						96.83 213

HQP-NCC					99.19 152		98.98 232		98.24 56	98.66 189

ACMP_Plane					99.19 152		98.98 232		98.24 56	98.66 189

BP-MVS														97.19 177

HQP4-MVS										98.66 189			99.64 147			98.64 216

HQP3-MVS								99.39 154							97.58 170

HQP2-MVS												92.47 217

NP-MVS					99.23 146	96.92 212					99.40 181

MDTV_nov1_ep13_2view						95.18 249	99.35 161

High-resolution multi-view benchmark