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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

Anonymous20231211		99.83 1	99.80 1	99.86 1	99.97 1	99.87 1	99.90 1	99.92 1	99.76 1	99.82 2	99.79 37	99.98 1	99.63 13	99.84 3	99.78 3	99.94 1	99.61 6

UA-Net		99.30 25	99.22 24	99.39 47	99.94 2	99.66 17	98.91 124	99.86 9	97.74 56	98.74 124	99.00 103	99.60 38	99.17 72	99.50 24	99.39 26	99.70 24	99.64 2

DTE-MVSNet		99.52 13	99.27 20	99.82 3	99.93 3	99.77 4	99.79 10	99.87 7	97.89 46	99.70 11	99.55 63	99.21 79	99.77 2	99.65 11	99.43 24	99.90 3	99.36 22

SixPastTwentyTwo		99.70 4	99.59 7	99.82 3	99.93 3	99.80 2	99.86 3	99.87 7	98.87 14	99.79 5	99.85 27	99.33 64	99.74 7	99.85 2	99.82 1	99.74 23	99.63 4

pmmvs6		99.74 3	99.75 2	99.73 15	99.92 5	99.67 16	99.76 15	99.84 11	99.59 2	99.52 27	99.87 18	99.91 2	99.43 40	99.87 1	99.81 2	99.89 6	99.52 10

PS-CasMVS		99.50 15	99.23 22	99.82 3	99.92 5	99.75 7	99.78 11	99.89 2	97.30 86	99.71 6	99.60 53	99.23 75	99.71 9	99.65 11	99.55 19	99.90 3	99.56 8

PEN-MVS		99.54 11	99.30 19	99.83 2	99.92 5	99.76 5	99.80 8	99.88 4	97.60 67	99.71 6	99.59 56	99.52 43	99.75 6	99.64 13	99.51 20	99.90 3	99.46 17

WR-MVS		99.61 10	99.44 11	99.82 3	99.92 5	99.80 2	99.80 8	99.89 2	98.54 19	99.66 15	99.78 40	99.16 87	99.68 10	99.70 6	99.63 7	99.94 1	99.49 16

v52		99.67 6	99.59 7	99.76 9	99.91 9	99.69 12	99.85 4	99.79 16	99.12 9	99.68 12	99.95 2	99.72 14	99.77 2	99.58 18	99.61 12	99.54 39	99.50 13

V4		99.67 6	99.60 6	99.76 9	99.91 9	99.69 12	99.85 4	99.79 16	99.13 8	99.68 12	99.95 2	99.72 14	99.77 2	99.58 18	99.61 12	99.54 39	99.50 13

CP-MVSNet		99.39 21	99.04 30	99.80 7	99.91 9	99.70 11	99.75 16	99.88 4	96.82 108	99.68 12	99.32 77	98.86 121	99.68 10	99.57 22	99.47 22	99.89 6	99.52 10

WR-MVS_H		99.48 16	99.23 22	99.76 9	99.91 9	99.76 5	99.75 16	99.88 4	97.27 89	99.58 20	99.56 60	99.24 73	99.56 19	99.60 16	99.60 15	99.88 8	99.58 7

gm-plane-assit		94.62 209	91.39 218	98.39 157	99.90 13	99.47 36	99.40 67	99.65 44	97.44 78	99.56 23	99.68 44	59.40 242	94.23 210	96.17 197	94.77 208	97.61 192	92.79 217

v7n		99.68 5	99.61 4	99.76 9	99.89 14	99.74 8	99.87 2	99.82 14	99.20 6	99.71 6	99.96 1	99.73 12	99.76 5	99.58 18	99.59 16	99.52 44	99.46 17

NR-MVSNet		99.10 40	98.68 57	99.58 22	99.89 14	99.23 60	99.35 73	99.63 48	96.58 123	99.36 38	99.05 97	98.67 133	99.46 33	99.63 14	98.73 74	99.80 16	98.88 69

Anonymous20240521		99.52 13	99.38 12	99.69 16	99.88 16	99.71 9	99.77 12	99.78 19	98.23 26	99.21 62	99.60 53	99.42 51	99.64 12	99.68 9	99.67 5	99.85 10	99.38 21

TransMVSNet (Re)		99.45 19	99.32 17	99.61 18	99.88 16	99.60 19	99.75 16	99.63 48	99.11 10	99.28 57	99.83 31	98.35 141	99.27 63	99.70 6	99.62 11	99.84 11	99.03 49

anonymousdsp		99.64 9	99.55 9	99.74 14	99.87 18	99.56 23	99.82 7	99.73 29	98.54 19	99.71 6	99.92 6	99.84 7	99.61 14	99.70 6	99.63 7	99.69 27	99.64 2

FC-MVSNet-train		99.13 38	99.05 29	99.21 75	99.87 18	99.57 22	99.67 21	99.60 55	96.75 115	98.28 156	99.48 68	99.52 43	98.10 136	99.47 27	99.37 28	99.76 22	99.21 33

FC-MVSNet-test		99.32 24	99.33 15	99.31 66	99.87 18	99.65 18	99.63 30	99.75 26	97.76 51	97.29 203	99.87 18	99.63 33	99.52 25	99.66 10	99.63 7	99.77 20	99.12 38

v748		99.67 6	99.61 4	99.75 13	99.87 18	99.68 14	99.84 6	99.79 16	99.14 7	99.64 17	99.89 12	99.88 5	99.72 8	99.58 18	99.57 18	99.62 31	99.50 13

LTVRE_ROB	98.82 1	99.76 2	99.75 2	99.77 8	99.87 18	99.71 9	99.77 12	99.76 23	99.52 3	99.80 3	99.79 37	99.91 2	99.56 19	99.83 4	99.75 4	99.86 9	99.75 1
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
EPP-MVSNet		98.61 96	98.19 105	99.11 88	99.86 23	99.60 19	99.44 64	99.53 71	97.37 84	96.85 211	98.69 113	93.75 187	99.18 69	99.22 37	99.35 30	99.82 14	99.32 24

MIMVSNet1		99.46 18	99.34 14	99.60 20	99.83 24	99.68 14	99.74 19	99.71 34	98.20 28	99.41 35	99.86 22	99.66 27	99.41 43	99.50 24	99.39 26	99.50 50	99.10 42

CSCG		99.23 28	99.15 26	99.32 65	99.83 24	99.45 37	98.97 116	99.21 140	98.83 15	99.04 94	99.43 72	99.64 31	99.26 64	98.85 66	98.20 104	99.62 31	99.62 5

conf0.05thres1000		97.44 161	95.93 182	99.20 78	99.82 26	99.56 23	99.41 65	99.61 53	97.42 80	98.01 171	94.34 206	82.73 221	98.68 102	99.33 33	99.42 25	99.67 28	98.74 85

pm-mvs1		99.47 17	99.38 12	99.57 23	99.82 26	99.49 33	99.63 30	99.65 44	98.88 13	99.31 47	99.85 27	99.02 113	99.23 66	99.60 16	99.58 17	99.80 16	99.22 32

IS_MVSNet		98.20 126	98.00 117	98.44 153	99.82 26	99.48 34	99.25 87	99.56 59	95.58 156	93.93 233	97.56 150	96.52 173	98.27 128	99.08 47	99.20 37	99.80 16	98.56 101

tfpnnormal		99.19 32	98.90 40	99.54 27	99.81 29	99.55 27	99.60 36	99.54 67	98.53 21	99.23 61	98.40 121	98.23 144	99.40 44	99.29 34	99.36 29	99.63 30	98.95 62

TranMVSNet+NR-MVSNet		99.23 28	98.91 39	99.61 18	99.81 29	99.45 37	99.47 59	99.68 38	97.28 88	99.39 36	99.54 64	99.08 108	99.45 35	99.09 44	98.84 62	99.83 12	99.04 47

Vis-MVSNet (Re-imp)		98.46 112	98.23 103	98.73 130	99.81 29	99.29 54	98.79 137	99.50 77	96.20 142	96.03 216	98.29 126	96.98 169	98.54 113	99.11 41	99.08 44	99.70 24	98.62 94

ACMH+	97.53 7	99.29 26	99.20 25	99.40 46	99.81 29	99.22 63	99.59 37	99.50 77	98.64 18	98.29 155	99.21 86	99.69 19	99.57 17	99.53 23	99.33 31	99.66 29	98.81 75

ACMH	97.81 6	99.44 20	99.33 15	99.56 24	99.81 29	99.42 39	99.73 20	99.58 56	99.02 11	99.10 82	99.41 74	99.69 19	99.60 15	99.45 28	99.26 36	99.55 38	99.05 46
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMMPR		99.05 43	98.72 52	99.44 37	99.79 34	99.12 81	99.35 73	99.56 59	97.74 56	99.21 62	97.72 145	99.55 41	99.29 61	98.90 65	98.81 64	99.41 65	99.19 34

SteuartSystems-ACMMP		98.94 54	98.52 70	99.43 40	99.79 34	99.13 79	99.33 77	99.55 61	96.17 143	99.04 94	97.53 151	99.65 30	99.46 33	99.04 53	98.76 70	99.44 57	99.35 23
Skip Steuart: Steuart Systems R&D Blog.
testgi		98.18 129	98.44 84	97.89 182	99.78 36	99.23 60	98.78 138	99.21 140	97.26 91	97.41 193	97.39 155	99.36 62	92.85 220	98.82 69	98.66 81	99.31 82	98.35 114

LGP-MVS_train		98.84 74	98.33 95	99.44 37	99.78 36	98.98 106	99.39 68	99.55 61	95.41 158	98.90 110	97.51 152	99.68 22	99.44 38	99.03 54	98.81 64	99.57 37	98.91 66

zzz-MVS		98.94 54	98.57 65	99.37 54	99.77 38	99.15 77	99.24 88	99.55 61	97.38 83	99.16 72	96.64 175	99.69 19	99.15 76	99.09 44	98.92 55	99.37 72	99.11 39

XVS					99.77 38	99.07 86	99.46 61			98.95 103		99.37 58				99.33 78

X-MVStestdata					99.77 38	99.07 86	99.46 61			98.95 103		99.37 58				99.33 78

APDe-MVS		99.15 37	98.95 33	99.39 47	99.77 38	99.28 55	99.52 52	99.54 67	97.22 94	99.06 89	99.20 87	99.64 31	99.05 83	99.14 39	99.02 53	99.39 70	99.17 36

test20.03		98.84 74	98.74 51	98.95 108	99.77 38	99.33 49	99.21 93	99.46 86	97.29 87	98.88 115	99.65 49	99.10 102	97.07 168	99.11 41	98.76 70	99.32 81	97.98 147

ACMMP		98.82 81	98.33 95	99.39 47	99.77 38	99.14 78	99.37 70	99.54 67	96.47 133	99.03 96	96.26 184	99.52 43	99.28 62	98.92 63	98.80 67	99.37 72	99.16 37
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
PGM-MVS		98.69 87	98.09 111	99.39 47	99.76 44	99.07 86	99.30 79	99.51 74	94.76 174	99.18 68	96.70 173	99.51 46	99.20 67	98.79 72	98.71 77	99.39 70	99.11 39

UniMVSNet_NR-MVSNet		98.97 50	98.46 74	99.56 24	99.76 44	99.34 47	99.29 80	99.61 53	96.55 127	99.55 24	99.05 97	97.96 155	99.36 56	98.84 67	98.50 91	99.81 15	98.97 56

PVSNet_Blended_VisFu		98.98 49	98.79 48	99.21 75	99.76 44	99.34 47	99.35 73	99.35 117	97.12 100	99.46 32	99.56 60	98.89 119	98.08 139	99.05 49	98.58 86	99.27 88	98.98 55

X-MVS		98.59 99	97.99 118	99.30 67	99.75 47	99.07 86	99.17 97	99.50 77	96.62 120	98.95 103	93.95 207	99.37 58	99.11 79	98.94 60	98.86 58	99.35 76	99.09 43

MP-MVS		98.78 84	98.30 97	99.34 63	99.75 47	98.95 115	99.26 85	99.46 86	95.78 154	99.17 69	96.98 168	99.72 14	99.06 82	98.84 67	98.74 73	99.33 78	99.11 39
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
UniMVSNet (Re)		99.08 42	98.69 56	99.54 27	99.75 47	99.33 49	99.29 80	99.64 47	96.75 115	99.48 31	99.30 79	98.69 129	99.26 64	98.94 60	98.76 70	99.78 19	99.02 52

mPP-MVS					99.75 47							99.49 50

DU-MVS		99.04 44	98.59 62	99.56 24	99.74 51	99.23 60	99.29 80	99.63 48	96.58 123	99.55 24	99.05 97	98.68 131	99.36 56	99.03 54	98.60 84	99.77 20	98.97 56

Baseline_NR-MVSNet		99.18 35	98.87 42	99.54 27	99.74 51	99.56 23	99.36 72	99.62 52	96.53 129	99.29 52	99.85 27	98.64 135	99.40 44	99.03 54	99.63 7	99.83 12	98.86 70

ACMP	96.54 13	98.87 67	98.40 89	99.41 43	99.74 51	98.88 126	99.29 80	99.50 77	96.85 104	98.96 101	97.05 164	99.66 27	99.43 40	98.98 58	98.60 84	99.52 44	98.81 75
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	96.66 11	98.90 62	98.44 84	99.44 37	99.74 51	98.95 115	99.47 59	99.55 61	97.66 63	99.09 86	96.43 180	99.41 52	99.35 59	98.95 59	98.67 79	99.45 55	99.03 49
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
COLMAP_ROB	98.29 2	99.37 22	99.25 21	99.51 31	99.74 51	99.12 81	99.56 41	99.39 94	98.96 12	99.17 69	99.44 71	99.63 33	99.58 16	99.48 26	99.27 34	99.60 35	98.81 75
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SMA-MVS		98.94 54	98.80 47	99.11 88	99.73 56	99.09 83	98.78 138	99.18 145	96.32 138	98.89 113	99.19 89	99.72 14	98.75 98	99.09 44	98.89 57	99.31 82	99.27 27

tfpn		94.97 205	91.60 217	98.90 111	99.73 56	99.33 49	99.11 104	99.51 74	95.05 164	97.19 208	89.03 222	62.62 239	98.37 121	98.53 81	98.97 54	99.48 53	97.70 155

DeepC-MVS	97.88 4	99.33 23	99.15 26	99.53 30	99.73 56	99.05 90	99.49 57	99.40 92	98.42 22	99.55 24	99.71 43	99.89 4	99.49 30	99.14 39	98.81 64	99.54 39	99.02 52
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MVS_0304		98.57 101	98.36 92	98.82 123	99.72 59	98.94 119	98.92 122	99.14 151	96.76 113	99.33 43	98.30 125	99.73 12	96.74 171	98.05 123	97.79 130	99.08 103	98.97 56

HyFIR lowres test		98.08 131	97.16 150	99.14 85	99.72 59	98.91 122	99.41 65	99.58 56	97.93 40	98.82 118	99.24 81	95.81 180	98.73 100	95.16 212	95.13 205	98.60 163	97.94 148

1111		94.22 216	92.26 213	96.51 217	99.71 61	98.75 134	99.03 108	99.83 12	95.01 166	93.39 235	99.54 64	60.23 240	89.58 230	97.90 133	97.62 150	97.50 195	96.75 183

.test1245		74.10 232	68.09 234	81.11 233	99.71 61	98.75 134	99.03 108	99.83 12	95.01 166	93.39 235	99.54 64	60.23 240	89.58 230	97.90 133	10.38 236	5.14 240	14.81 236

view800		96.48 181	94.42 193	98.87 115	99.70 63	99.26 56	99.05 107	99.45 90	94.77 173	97.32 200	88.21 223	83.40 219	98.28 127	98.37 93	99.33 31	99.44 57	97.58 160

TDRefinement		99.54 11	99.50 10	99.60 20	99.70 63	99.35 46	99.77 12	99.58 56	99.40 5	99.28 57	99.66 45	99.41 52	99.55 21	99.74 5	99.65 6	99.70 24	99.25 28

Gipuma		99.22 30	98.86 43	99.64 17	99.70 63	99.24 58	99.17 97	99.63 48	99.52 3	99.89 1	96.54 179	99.14 93	99.93 1	99.42 30	99.15 39	99.52 44	99.04 47
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
Fast-Effi-MVS+		98.42 113	97.79 125	99.15 82	99.69 66	98.66 142	98.94 119	99.68 38	94.49 178	99.05 91	98.06 137	98.86 121	98.48 116	98.18 112	97.78 131	99.05 109	98.54 102

v148		98.77 85	98.45 78	99.15 82	99.68 67	98.94 119	99.49 57	99.31 127	97.95 39	98.91 109	99.65 49	99.62 35	99.18 69	97.99 126	97.64 149	98.33 176	97.38 167

v13		99.22 30	98.99 32	99.49 32	99.68 67	99.58 21	99.67 21	99.77 22	98.10 30	99.36 38	99.88 13	99.37 58	99.54 23	98.50 83	98.51 90	98.92 122	99.03 49

CP-MVS		98.86 71	98.43 86	99.36 56	99.68 67	98.97 113	99.19 96	99.46 86	96.60 122	99.20 64	97.11 163	99.51 46	99.15 76	98.92 63	98.82 63	99.45 55	99.08 44

HSP-MVS		98.50 107	98.05 114	99.03 98	99.67 70	99.33 49	99.51 53	99.26 132	95.28 160	98.51 137	98.19 130	99.74 11	98.29 126	97.69 153	96.70 180	98.96 115	99.41 20

ACMMP_Plus		98.94 54	98.72 52	99.21 75	99.67 70	99.08 85	99.26 85	99.39 94	96.84 105	98.88 115	98.22 128	99.68 22	98.82 93	99.06 48	98.90 56	99.25 90	99.25 28

HFP-MVS		98.97 50	98.70 54	99.29 70	99.67 70	98.98 106	99.13 101	99.53 71	97.76 51	98.90 110	98.07 135	99.50 48	99.14 78	98.64 78	98.78 68	99.37 72	99.18 35

v12		99.19 32	98.95 33	99.48 33	99.67 70	99.56 23	99.66 23	99.76 23	98.06 32	99.33 43	99.88 13	99.34 63	99.53 24	98.42 90	98.43 95	98.91 125	98.97 56

tfpn_n400		97.59 153	96.36 171	99.01 102	99.66 74	99.19 69	99.21 93	99.55 61	97.62 64	97.77 178	94.60 201	87.78 200	98.27 128	98.44 86	98.72 75	99.62 31	98.21 129

tfpnconf		97.59 153	96.36 171	99.01 102	99.66 74	99.19 69	99.21 93	99.55 61	97.62 64	97.77 178	94.60 201	87.78 200	98.27 128	98.44 86	98.72 75	99.62 31	98.21 129

gg-mvs-nofinetune		96.77 177	96.52 167	97.06 200	99.66 74	97.82 188	97.54 214	99.86 9	98.69 17	98.61 128	99.94 4	89.62 195	88.37 234	97.55 164	96.67 182	98.30 177	95.35 200

v11		99.19 32	98.95 33	99.47 34	99.66 74	99.54 29	99.65 24	99.73 29	98.06 32	99.38 37	99.92 6	99.40 55	99.55 21	98.29 103	98.50 91	98.88 130	98.92 65

V9		99.16 36	98.90 40	99.46 35	99.66 74	99.54 29	99.65 24	99.75 26	98.01 35	99.31 47	99.87 18	99.31 67	99.51 26	98.34 97	98.34 98	98.90 127	98.91 66

thres600view7		96.35 186	94.27 195	98.79 126	99.66 74	99.18 71	98.94 119	99.38 101	94.37 186	97.21 205	87.19 226	84.10 218	98.10 136	98.16 113	99.47 22	99.42 62	97.43 164

view600		96.39 185	94.30 194	98.82 123	99.65 80	99.16 76	98.98 114	99.36 112	94.46 180	97.39 196	87.28 224	84.16 217	98.16 135	98.16 113	99.48 21	99.40 67	97.42 165

CANet		98.47 110	98.30 97	98.67 138	99.65 80	98.87 127	98.82 135	99.01 165	96.14 144	99.29 52	98.86 108	99.01 114	96.54 175	98.36 95	98.08 109	98.72 154	98.80 79

v1141		98.87 67	98.45 78	99.36 56	99.65 80	99.04 94	99.56 41	99.38 101	97.83 47	99.29 52	99.86 22	99.16 87	99.40 44	97.68 154	97.78 131	98.86 135	97.82 151

divwei89l23v2f112		98.87 67	98.45 78	99.36 56	99.65 80	99.04 94	99.56 41	99.38 101	97.83 47	99.29 52	99.86 22	99.15 91	99.40 44	97.68 154	97.78 131	98.86 135	97.82 151

V14		99.13 38	98.85 45	99.45 36	99.65 80	99.52 31	99.63 30	99.74 28	97.97 37	99.30 50	99.87 18	99.27 71	99.49 30	98.23 109	98.24 101	98.88 130	98.83 71

v2v482		98.85 73	98.40 89	99.38 52	99.65 80	98.98 106	99.55 44	99.39 94	97.92 41	99.35 41	99.85 27	99.14 93	99.39 54	97.50 166	97.78 131	98.98 114	97.60 158

v1		98.87 67	98.45 78	99.36 56	99.65 80	99.04 94	99.55 44	99.38 101	97.83 47	99.30 50	99.86 22	99.17 84	99.40 44	97.68 154	97.77 138	98.86 135	97.82 151

Vis-MVSNet		99.25 27	99.32 17	99.17 80	99.65 80	99.55 27	99.63 30	99.33 120	98.16 29	99.29 52	99.65 49	99.77 8	97.56 154	99.44 29	99.14 40	99.58 36	99.51 12
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tfpn1000		97.10 170	95.97 180	98.41 155	99.64 88	99.30 53	98.89 128	99.49 81	96.49 130	95.97 218	95.31 194	85.62 214	96.92 170	97.86 137	99.13 42	99.53 43	98.11 138

v15		99.09 41	98.79 48	99.43 40	99.64 88	99.50 32	99.61 34	99.73 29	97.92 41	99.28 57	99.86 22	99.24 73	99.47 32	98.12 120	98.14 106	98.87 132	98.76 82

APD-MVS		98.47 110	97.97 119	99.05 96	99.64 88	98.91 122	98.94 119	99.45 90	94.40 184	98.77 120	97.26 157	99.41 52	98.21 133	98.67 76	98.57 88	99.31 82	98.57 98
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EG-PatchMatch MVS		99.01 46	98.77 50	99.28 74	99.64 88	98.90 125	98.81 136	99.27 131	96.55 127	99.71 6	99.31 78	99.66 27	99.17 72	99.28 36	99.11 43	99.10 98	98.57 98

LS3D		98.79 83	98.52 70	99.12 86	99.64 88	99.09 83	99.24 88	99.46 86	97.75 54	98.93 107	97.47 153	98.23 144	97.98 142	99.36 31	99.30 33	99.46 54	98.42 110

tfpnview11		97.49 158	96.22 175	98.97 106	99.63 93	99.24 58	99.12 103	99.54 67	96.76 113	97.77 178	94.60 201	87.78 200	98.25 131	97.93 130	99.14 40	99.52 44	98.08 141

IterMVS-LS		98.23 123	97.66 130	98.90 111	99.63 93	99.38 44	99.07 106	99.48 82	97.75 54	98.81 119	99.37 76	94.57 185	97.88 146	96.54 193	97.04 174	98.53 168	98.97 56
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Effi-MVS+		98.11 130	97.29 142	99.06 93	99.62 95	98.55 151	98.16 188	99.80 15	94.64 175	99.15 75	96.59 176	97.43 162	98.44 117	97.46 168	97.90 120	99.17 95	98.45 107

v1144		98.94 54	98.53 68	99.42 42	99.62 95	99.03 99	99.58 38	99.36 112	97.99 36	99.49 30	99.91 11	99.20 81	99.51 26	97.61 160	97.85 128	98.95 117	98.10 139

3Dnovator+	97.85 5	98.61 96	98.14 107	99.15 82	99.62 95	98.37 162	99.10 105	99.51 74	98.04 34	98.98 98	96.07 188	98.75 127	98.55 111	98.51 82	98.40 96	99.17 95	98.82 73

v1192		98.91 60	98.48 73	99.41 43	99.61 98	99.03 99	99.64 27	99.25 135	97.91 43	99.58 20	99.92 6	99.07 110	99.45 35	97.55 164	97.68 145	98.93 119	98.23 126

v1240		98.86 71	98.41 87	99.38 52	99.59 99	99.05 90	99.65 24	99.14 151	97.68 62	99.66 15	99.93 5	98.72 128	99.45 35	97.38 175	97.72 143	98.79 148	98.35 114

3Dnovator	98.16 3	98.65 91	98.35 93	99.00 104	99.59 99	98.70 138	98.90 127	99.36 112	97.97 37	99.09 86	96.55 178	99.09 106	97.97 143	98.70 75	98.65 82	99.12 97	98.81 75

v1921920		98.89 64	98.46 74	99.39 47	99.58 101	99.04 94	99.64 27	99.17 147	97.91 43	99.64 17	99.92 6	98.99 117	99.44 38	97.44 171	97.57 155	98.84 139	98.35 114

thres400		96.22 191	94.08 198	98.72 131	99.58 101	99.05 90	98.83 132	99.22 138	94.01 193	97.40 194	86.34 232	84.91 216	97.93 144	97.85 140	99.08 44	99.37 72	97.28 170

CDPH-MVS		97.99 132	97.23 146	98.87 115	99.58 101	98.29 164	98.83 132	99.20 143	93.76 196	98.11 164	96.11 186	99.16 87	98.23 132	97.80 145	97.22 170	99.29 86	98.28 120

UGNet		98.52 106	99.00 31	97.96 181	99.58 101	99.26 56	99.27 84	99.40 92	98.07 31	98.28 156	98.76 111	99.71 18	92.24 224	98.94 60	98.85 60	99.00 113	99.43 19
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
QAPM		98.62 95	98.40 89	98.89 113	99.57 105	98.80 129	98.63 152	99.35 117	96.82 108	98.60 129	98.85 110	99.08 108	98.09 138	98.31 101	98.21 102	99.08 103	98.72 86

ESAPD		98.60 98	98.41 87	98.83 120	99.56 106	99.21 64	98.66 151	99.47 83	95.22 161	98.35 150	98.48 119	99.67 26	97.84 149	98.80 71	98.57 88	99.10 98	98.93 64

v144192		98.88 66	98.46 74	99.37 54	99.56 106	99.03 99	99.61 34	99.26 132	97.79 50	99.58 20	99.88 13	99.11 101	99.43 40	97.38 175	97.61 151	98.80 146	98.43 109

new-patchmatchnet		97.26 165	96.12 177	98.58 146	99.55 108	98.63 144	99.14 100	97.04 223	98.80 16	99.19 66	99.92 6	99.19 82	98.92 87	95.51 207	87.04 223	97.66 191	93.73 212

DI_MVS_plusplus_trai		97.57 156	96.55 166	98.77 127	99.55 108	98.76 132	99.22 91	99.00 166	97.08 101	97.95 174	97.78 144	91.35 194	98.02 141	96.20 196	96.81 179	98.87 132	97.87 150

CHOSEN 1792x2688		98.31 118	98.02 116	98.66 140	99.55 108	98.57 150	99.38 69	99.25 135	98.42 22	98.48 143	99.58 58	99.85 6	98.31 125	95.75 203	95.71 196	96.96 203	98.27 122

v1neww		98.84 74	98.45 78	99.29 70	99.54 111	98.98 106	99.54 48	99.37 109	97.48 74	99.10 82	99.80 35	99.12 97	99.40 44	97.85 140	97.89 122	98.81 141	98.04 142

v7new		98.84 74	98.45 78	99.29 70	99.54 111	98.98 106	99.54 48	99.37 109	97.48 74	99.10 82	99.80 35	99.12 97	99.40 44	97.85 140	97.89 122	98.81 141	98.04 142

v17		98.96 52	98.63 59	99.35 61	99.54 111	99.41 40	99.55 44	99.70 35	97.40 81	99.10 82	99.79 37	99.10 102	99.40 44	97.96 127	97.99 114	98.80 146	98.77 81

v8		98.94 54	98.60 61	99.35 61	99.54 111	99.39 42	99.55 44	99.67 41	97.48 74	99.13 77	99.81 32	99.10 102	99.39 54	97.86 137	97.89 122	98.81 141	98.66 92

v6		98.84 74	98.46 74	99.30 67	99.54 111	98.98 106	99.54 48	99.37 109	97.49 73	99.11 81	99.81 32	99.13 96	99.40 44	97.86 137	97.89 122	98.81 141	98.04 142

CPTT-MVS		98.28 119	97.51 137	99.16 81	99.54 111	98.78 131	98.96 117	99.36 112	96.30 139	98.89 113	93.10 212	99.30 68	99.20 67	98.35 96	97.96 119	99.03 111	98.82 73

FMVSNet1		98.90 62	99.10 28	98.67 138	99.54 111	99.48 34	99.22 91	99.66 42	98.39 25	97.50 191	99.66 45	99.04 111	96.58 174	99.05 49	99.03 50	99.52 44	99.08 44

HPM-MVS++		98.56 104	98.08 112	99.11 88	99.53 118	98.61 146	99.02 112	99.32 125	96.29 140	99.06 89	97.23 158	99.50 48	98.77 96	98.15 116	97.90 120	98.96 115	98.90 68

v16		98.95 53	98.62 60	99.34 63	99.53 118	99.41 40	99.54 48	99.70 35	97.34 85	99.07 88	99.76 41	99.10 102	99.40 44	97.96 127	98.00 113	98.79 148	98.76 82

v7		98.91 60	98.53 68	99.36 56	99.53 118	98.99 105	99.57 39	99.36 112	97.58 70	99.32 45	99.88 13	99.23 75	99.50 28	97.77 148	97.98 116	98.91 125	98.26 123

MCST-MVS		98.25 122	97.57 135	99.06 93	99.53 118	98.24 170	98.63 152	99.17 147	95.88 151	98.58 131	96.11 186	99.09 106	99.18 69	97.58 163	97.31 166	99.25 90	98.75 84

CLD-MVS		98.48 109	98.15 106	98.86 118	99.53 118	98.35 163	98.55 163	97.83 215	96.02 148	98.97 99	99.08 94	99.75 9	99.03 84	98.10 122	97.33 165	99.28 87	98.44 108
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
OPM-MVS		98.84 74	98.59 62	99.12 86	99.52 123	98.50 156	99.13 101	99.22 138	97.76 51	98.76 121	98.70 112	99.61 36	98.90 88	98.67 76	98.37 97	99.19 94	98.57 98

v10		99.01 46	98.66 58	99.41 43	99.52 123	99.39 42	99.57 39	99.66 42	97.59 68	99.32 45	99.88 13	99.23 75	99.50 28	97.77 148	97.98 116	98.92 122	98.78 80

V42		98.81 82	98.49 72	99.18 79	99.52 123	98.92 121	99.50 56	99.29 128	97.43 79	98.97 99	99.81 32	99.00 116	99.30 60	97.93 130	98.01 112	98.51 171	98.34 118

Anonymous20231206		98.50 107	98.03 115	99.05 96	99.50 126	99.01 103	99.15 99	99.26 132	96.38 135	99.12 79	99.50 67	99.12 97	98.60 106	97.68 154	97.24 169	98.66 157	97.30 169

v18		98.89 64	98.54 66	99.30 67	99.50 126	99.37 45	99.51 53	99.68 38	97.25 93	99.00 97	99.76 41	99.04 111	99.36 56	97.81 144	97.86 127	98.77 151	98.68 91

OpenMVS	97.26 9	97.88 138	97.17 149	98.70 134	99.50 126	98.55 151	98.34 179	99.11 156	93.92 194	98.90 110	95.04 197	98.23 144	97.38 162	98.11 121	98.12 107	98.95 117	98.23 126

pmmvs-eth3d		98.68 88	98.14 107	99.29 70	99.49 129	98.45 159	99.45 63	99.38 101	97.21 95	99.50 29	99.65 49	99.21 79	99.16 74	97.11 183	97.56 156	98.79 148	97.82 151

PHI-MVS		98.57 101	98.20 104	99.00 104	99.48 130	98.91 122	98.68 144	99.17 147	94.97 169	99.27 60	98.33 123	99.33 64	98.05 140	98.82 69	98.62 83	99.34 77	98.38 112

pmmvs5		98.37 115	97.81 124	99.03 98	99.46 131	98.97 113	99.03 108	98.96 169	95.85 152	99.05 91	99.45 70	98.66 134	98.79 95	96.02 200	97.52 157	98.87 132	98.21 129

ambc			97.89 122		99.45 132	97.88 186	97.78 201		97.27 89	99.80 3	98.99 104	98.48 139	98.55 111	97.80 145	96.68 181	98.54 167	98.10 139

canonicalmvs		98.34 117	97.92 121	98.83 120	99.45 132	99.21 64	98.37 175	99.53 71	97.06 102	97.74 182	96.95 170	95.05 183	98.36 122	98.77 73	98.85 60	99.51 49	99.53 9

IterMVS		97.40 162	96.67 160	98.25 164	99.45 132	98.66 142	98.87 130	98.73 180	96.40 134	98.94 106	99.56 60	95.26 182	97.58 153	95.38 208	94.70 209	95.90 212	96.72 184
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres200		96.23 190	94.13 196	98.69 136	99.44 135	99.18 71	98.58 161	99.38 101	93.52 199	97.35 198	86.33 233	85.83 213	97.93 144	98.16 113	98.78 68	99.42 62	97.10 179

PCF-MVS	95.58 16	97.60 151	96.67 160	98.69 136	99.44 135	98.23 171	98.37 175	98.81 176	93.01 206	98.22 158	97.97 141	99.59 39	98.20 134	95.72 205	95.08 206	99.08 103	97.09 181
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
train_agg		97.99 132	97.26 143	98.83 120	99.43 137	98.22 172	98.91 124	99.07 159	94.43 182	97.96 173	96.42 181	99.30 68	98.81 94	97.39 173	96.62 183	98.82 140	98.47 104

N_pmnet		96.68 179	95.70 187	97.84 184	99.42 138	98.00 181	99.35 73	98.21 203	98.40 24	98.13 163	99.42 73	99.30 68	97.44 161	94.00 222	88.79 220	94.47 218	91.96 220

USDC		98.26 121	97.57 135	99.06 93	99.42 138	97.98 184	98.83 132	98.85 173	97.57 71	99.59 19	99.15 90	98.59 136	98.99 85	97.42 172	96.08 195	98.69 156	96.23 191

NCCC		97.84 140	96.96 156	98.87 115	99.39 140	98.27 167	98.46 168	99.02 164	96.78 111	98.73 125	91.12 218	98.91 118	98.57 109	97.83 143	97.49 159	99.04 110	98.33 119

tfpn111		96.48 181	94.67 192	98.59 144	99.37 141	99.18 71	98.68 144	99.39 94	92.02 215	97.21 205	90.63 219	86.34 208	97.45 156	98.15 116	99.08 44	99.43 59	97.28 170

conf200view11		96.16 194	94.08 198	98.59 144	99.37 141	99.18 71	98.68 144	99.39 94	92.02 215	97.21 205	86.53 229	86.34 208	97.45 156	98.15 116	99.08 44	99.43 59	97.28 170

thres100view900		95.74 198	93.66 206	98.17 170	99.37 141	98.59 147	98.10 189	98.33 199	92.02 215	97.30 201	86.53 229	86.34 208	96.69 172	96.77 189	98.47 93	99.24 92	96.89 182

tfpn200view9		96.17 192	94.08 198	98.60 143	99.37 141	99.18 71	98.68 144	99.39 94	92.02 215	97.30 201	86.53 229	86.34 208	97.45 156	98.15 116	99.08 44	99.43 59	97.28 170

testmv		97.48 160	96.83 159	98.24 167	99.37 141	97.79 191	98.59 159	99.07 159	92.40 209	97.59 186	99.24 81	98.11 148	97.66 151	97.64 158	97.11 172	97.17 199	95.54 199

test1235678		97.49 158	96.84 158	98.24 167	99.37 141	97.79 191	98.59 159	99.07 159	92.41 208	97.59 186	99.24 81	98.15 147	97.66 151	97.64 158	97.12 171	97.17 199	95.55 198

RPSCF		98.84 74	98.81 46	98.89 113	99.37 141	98.95 115	98.51 165	98.85 173	97.73 58	98.33 152	98.97 105	99.14 93	98.95 86	99.18 38	98.68 78	99.31 82	98.99 54

MDA-MVSNet-bldmvs		97.75 142	97.26 143	98.33 160	99.35 148	98.45 159	99.32 78	97.21 221	97.90 45	99.05 91	99.01 102	96.86 171	99.08 80	99.36 31	92.97 215	95.97 211	96.25 190

CNVR-MVS		98.22 125	97.76 126	98.76 128	99.33 149	98.26 168	98.48 166	98.88 172	96.22 141	98.47 145	95.79 190	99.33 64	98.35 123	98.37 93	97.99 114	99.03 111	98.38 112

DeepC-MVS_fast	97.38 8	98.65 91	98.34 94	99.02 101	99.33 149	98.29 164	98.99 113	98.71 182	97.40 81	99.31 47	98.20 129	99.40 55	98.54 113	98.33 100	98.18 105	99.23 93	98.58 96
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSDG		98.20 126	97.88 123	98.56 148	99.33 149	97.74 194	98.27 183	98.10 206	97.20 97	98.06 166	98.59 117	99.16 87	98.76 97	98.39 92	97.71 144	98.86 135	96.38 188

thresconf0.02		95.49 200	92.74 211	98.70 134	99.32 152	98.70 138	98.87 130	99.21 140	95.95 149	97.57 188	90.63 219	73.55 233	97.86 148	96.09 199	97.03 175	99.40 67	97.22 175

EPNet		96.44 184	96.08 178	96.86 207	99.32 152	97.15 204	97.69 208	99.32 125	93.67 197	98.11 164	95.64 192	93.44 189	89.07 232	96.86 187	96.83 178	97.67 190	98.97 56
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVS_111021_HR		98.58 100	98.26 100	98.96 107	99.32 152	98.81 128	98.48 166	98.99 167	96.81 110	99.16 72	98.07 135	99.23 75	98.89 90	98.43 89	98.27 100	98.90 127	98.24 125

PVSNet_BlendedMVS		97.93 136	97.66 130	98.25 164	99.30 155	98.67 140	98.31 180	97.95 210	94.30 187	98.75 122	97.63 147	98.76 125	96.30 182	98.29 103	97.78 131	98.93 119	98.18 133

PVSNet_Blended		97.93 136	97.66 130	98.25 164	99.30 155	98.67 140	98.31 180	97.95 210	94.30 187	98.75 122	97.63 147	98.76 125	96.30 182	98.29 103	97.78 131	98.93 119	98.18 133

HQP-MVS		97.58 155	96.65 164	98.66 140	99.30 155	97.99 182	97.88 199	98.65 185	94.58 176	98.66 126	94.65 200	99.15 91	98.59 107	96.10 198	95.59 198	98.90 127	98.50 103

our_test_3					99.29 158	97.72 195	98.98 114

conf0.01		94.53 212	91.09 220	98.53 151	99.29 158	99.05 90	98.68 144	99.35 117	92.02 215	97.04 209	84.45 235	68.52 235	97.45 156	97.79 147	99.08 44	99.41 65	96.70 185

TinyColmap		98.27 120	97.62 134	99.03 98	99.29 158	97.79 191	98.92 122	98.95 170	97.48 74	99.52 27	98.65 115	97.86 157	98.90 88	98.34 97	97.27 167	98.64 160	95.97 194

TSAR-MVS + GP.		98.54 105	98.29 99	98.82 123	99.28 161	98.59 147	97.73 204	99.24 137	95.93 150	98.59 130	99.07 96	99.17 84	98.86 91	98.44 86	98.10 108	99.26 89	98.72 86

MVS_Test		97.69 146	97.15 151	98.33 160	99.27 162	98.43 161	98.25 184	99.29 128	95.00 168	97.39 196	98.86 108	98.00 153	97.14 166	95.38 208	96.22 189	98.62 161	98.15 137

conf0.002		93.97 217	90.06 224	98.52 152	99.26 163	99.02 102	98.68 144	99.33 120	92.02 215	97.01 210	83.82 236	63.41 238	97.45 156	97.73 151	97.98 116	99.40 67	96.47 187

PM-MVS		98.57 101	98.24 102	98.95 108	99.26 163	98.59 147	99.03 108	98.74 179	96.84 105	99.44 34	99.13 91	98.31 143	98.75 98	98.03 124	98.21 102	98.48 172	98.58 96

PMVS	92.51 17	98.66 90	98.86 43	98.43 154	99.26 163	98.98 106	98.60 158	98.59 189	97.73 58	99.45 33	99.38 75	98.54 138	95.24 195	99.62 15	99.61 12	99.42 62	98.17 135
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Effi-MVS+-dtu		97.78 141	97.37 140	98.26 163	99.25 166	98.50 156	97.89 198	99.19 144	94.51 177	98.16 161	95.93 189	98.80 124	95.97 186	98.27 108	97.38 162	99.10 98	98.23 126

AdaColmap		97.57 156	96.57 165	98.74 129	99.25 166	98.01 180	98.36 178	98.98 168	94.44 181	98.47 145	92.44 216	97.91 156	98.62 105	98.19 111	97.74 140	98.73 153	97.28 170

DELS-MVS		98.63 94	98.70 54	98.55 149	99.24 168	99.04 94	98.96 117	98.52 192	96.83 107	98.38 148	99.58 58	99.68 22	97.06 169	98.74 74	98.44 94	99.10 98	98.59 95
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
TSAR-MVS + MP.		99.02 45	98.95 33	99.11 88	99.23 169	98.79 130	99.51 53	98.73 180	97.50 72	98.56 132	99.03 100	99.59 39	99.16 74	99.29 34	99.17 38	99.50 50	99.24 31

pmmvs4		97.87 139	97.02 154	98.86 118	99.20 170	97.68 197	98.89 128	99.03 163	96.57 125	99.12 79	99.03 100	97.26 166	98.42 119	95.16 212	96.34 187	98.53 168	97.10 179

test-LLR		94.79 207	93.71 204	96.06 221	99.20 170	96.16 214	96.31 229	98.50 193	89.98 232	94.08 231	97.01 165	86.43 206	92.20 225	96.76 190	95.31 201	96.05 209	94.31 208

test0.0.03 1		95.81 197	95.77 186	95.85 225	99.20 170	98.15 175	97.49 218	98.50 193	92.24 210	92.74 238	96.82 172	92.70 191	88.60 233	97.31 179	97.01 177	98.57 166	96.19 192

CANet_DTU		97.65 149	97.50 138	97.82 186	99.19 173	98.08 177	98.41 171	98.67 184	94.40 184	99.16 72	98.32 124	98.69 129	93.96 213	97.87 136	97.61 151	97.51 194	97.56 161

EPNet_dtu		96.31 187	95.96 181	96.72 211	99.18 174	95.39 228	97.03 225	99.13 155	93.02 205	99.35 41	97.23 158	97.07 168	90.70 229	95.74 204	95.08 206	94.94 215	98.16 136
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tfpn_ndepth		96.69 178	95.49 189	98.09 175	99.17 175	99.13 79	98.61 157	99.38 101	94.90 172	95.85 220	92.85 214	88.19 199	96.07 185	97.28 180	98.67 79	99.49 52	97.44 163

TSAR-MVS + ACMM		98.64 93	98.58 64	98.72 131	99.17 175	98.63 144	98.69 143	99.10 158	97.69 61	98.30 154	99.12 93	99.38 57	98.70 101	98.45 85	97.51 158	98.35 175	99.25 28

GA-MVS		96.84 175	95.86 184	97.98 179	99.16 177	98.29 164	97.91 196	98.64 187	95.14 163	97.71 184	98.04 139	88.90 197	96.50 176	96.41 194	96.61 184	97.97 188	97.60 158

SD-MVS		98.73 86	98.54 66	98.95 108	99.14 178	98.76 132	98.46 168	99.14 151	97.71 60	98.56 132	98.06 137	99.61 36	98.85 92	98.56 80	97.74 140	99.54 39	99.32 24

EU-MVSNet		98.68 88	98.94 37	98.37 159	99.14 178	98.74 136	99.64 27	98.20 205	98.21 27	99.17 69	99.66 45	99.18 83	99.08 80	99.11 41	98.86 58	95.00 214	98.83 71

testus		96.13 195	95.13 190	97.28 195	99.13 180	97.00 205	96.84 227	97.89 214	90.48 231	97.40 194	93.60 209	96.47 174	95.39 193	96.21 195	96.19 191	97.05 201	95.99 193

MDTV_nov1_ep13_2view		97.12 168	96.19 176	98.22 169	99.13 180	98.05 178	99.24 88	99.47 83	97.61 66	99.15 75	99.59 56	99.01 114	98.40 120	94.87 214	90.14 218	93.91 219	94.04 211

PLC	95.63 15	97.73 145	97.01 155	98.57 147	99.10 182	97.80 190	97.72 205	98.77 178	96.34 136	98.38 148	93.46 211	98.06 150	98.66 103	97.90 133	97.65 148	98.77 151	97.90 149
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		96.80 176	96.30 173	97.39 192	99.09 183	96.52 208	98.76 140	99.29 128	93.88 195	97.65 185	98.34 122	93.66 188	96.29 184	98.28 106	97.73 142	93.27 223	95.70 196

IB-MVS	95.85 14	95.87 196	94.88 191	97.02 203	99.09 183	98.25 169	97.16 221	97.38 219	91.97 222	97.77 178	83.61 237	97.29 165	92.03 227	97.16 182	97.66 146	98.66 157	98.20 132
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
CDS-MVSNet		97.75 142	97.68 129	97.83 185	99.08 185	98.20 173	98.68 144	98.61 188	95.63 155	97.80 177	99.24 81	96.93 170	94.09 211	97.96 127	97.82 129	98.71 155	97.99 145
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS_111021_LR		98.39 114	98.11 109	98.71 133	99.08 185	98.54 154	98.23 186	98.56 191	96.57 125	99.13 77	98.41 120	98.86 121	98.65 104	98.23 109	97.87 126	98.65 159	98.28 120

TAMVS		96.95 173	96.94 157	96.97 206	99.07 187	97.67 198	97.98 194	97.12 222	95.04 165	95.41 225	99.27 80	95.57 181	94.09 211	97.32 177	97.11 172	98.16 184	96.59 186

abl_6				98.38 158	99.03 188	98.04 179	98.08 191	98.65 185	93.23 202	98.56 132	94.58 204	98.57 137	97.17 165			98.81 141	97.42 165

MIMVSNet		97.24 166	97.15 151	97.36 194	99.03 188	98.52 155	98.55 163	99.73 29	94.94 171	94.94 230	97.98 140	97.37 164	93.66 215	97.60 161	97.34 164	98.23 181	96.29 189

diffmvs		97.29 164	96.67 160	98.01 178	99.00 190	97.82 188	98.37 175	99.18 145	96.73 117	97.74 182	99.08 94	94.26 186	96.50 176	94.86 216	95.67 197	97.29 197	98.25 124

Fast-Effi-MVS+-dtu		96.99 171	96.46 168	97.61 190	98.98 191	97.89 185	97.54 214	99.76 23	93.43 200	96.55 214	94.93 198	98.06 150	94.32 209	96.93 186	96.50 186	98.53 168	97.47 162

no-one		99.01 46	98.94 37	99.09 92	98.97 192	98.55 151	99.37 70	99.04 162	97.59 68	99.36 38	99.66 45	99.75 9	99.57 17	98.47 84	99.27 34	98.21 182	99.30 26

MAR-MVS		97.12 168	96.28 174	98.11 174	98.94 193	97.22 202	97.65 209	99.38 101	90.93 230	98.15 162	95.17 195	97.13 167	96.48 178	97.71 152	97.40 161	98.06 185	98.40 111
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
MSLP-MVS++		97.99 132	97.64 133	98.40 156	98.91 194	98.47 158	97.12 223	98.78 177	96.49 130	98.48 143	93.57 210	99.12 97	98.51 115	98.31 101	98.58 86	98.58 165	98.95 62

ADS-MVSNet		94.41 215	92.13 215	97.07 199	98.86 195	96.60 207	98.38 174	98.47 196	96.13 146	98.02 168	96.98 168	87.50 204	95.87 188	89.89 227	87.58 222	92.79 227	90.27 226

OMC-MVS		98.35 116	98.10 110	98.64 142	98.85 196	97.99 182	98.56 162	98.21 203	97.26 91	98.87 117	98.54 118	99.27 71	98.43 118	98.34 97	97.66 146	98.92 122	97.65 157

MVSTER		95.38 202	93.99 202	97.01 204	98.83 197	98.95 115	96.62 228	99.14 151	92.17 212	97.44 192	97.29 156	77.88 228	91.63 228	97.45 169	96.18 192	98.41 174	97.99 145

TAPA-MVS	96.65 12	98.23 123	97.96 120	98.55 149	98.81 198	98.16 174	98.40 172	97.94 212	96.68 118	98.49 141	98.61 116	98.89 119	98.57 109	97.45 169	97.59 153	99.09 102	98.35 114
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CostFormer		92.75 222	89.49 225	96.55 215	98.78 199	95.83 225	97.55 213	98.59 189	91.83 223	97.34 199	96.31 183	78.53 227	94.50 205	86.14 232	84.92 228	92.54 228	92.84 216

PatchmatchNet		93.88 219	91.08 221	97.14 198	98.75 200	96.01 220	98.25 184	99.39 94	94.95 170	98.96 101	96.32 182	85.35 215	95.50 192	88.89 229	85.89 227	91.99 231	90.15 227
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
GBi-Net		97.69 146	97.75 127	97.62 188	98.71 201	99.21 64	98.62 154	99.33 120	94.09 190	95.60 222	98.17 132	95.97 177	94.39 206	99.05 49	99.03 50	99.08 103	98.70 88

test1		97.69 146	97.75 127	97.62 188	98.71 201	99.21 64	98.62 154	99.33 120	94.09 190	95.60 222	98.17 132	95.97 177	94.39 206	99.05 49	99.03 50	99.08 103	98.70 88

FMVSNet2		97.94 135	98.08 112	97.77 187	98.71 201	99.21 64	98.62 154	99.47 83	96.62 120	96.37 215	99.20 87	97.70 159	94.39 206	97.39 173	97.75 139	99.08 103	98.70 88

PatchMatch-RL		97.24 166	96.45 169	98.17 170	98.70 204	97.57 199	97.31 219	98.48 195	94.42 183	98.39 147	95.74 191	96.35 176	97.88 146	97.75 150	97.48 160	98.24 180	95.87 195

LP		95.33 204	93.45 207	97.54 191	98.68 205	97.40 200	98.73 141	98.41 197	96.33 137	98.92 108	97.84 143	88.30 198	95.92 187	92.98 223	89.38 219	94.56 217	91.90 221

MS-PatchMatch		97.60 151	97.22 147	98.04 177	98.67 206	97.18 203	97.91 196	98.28 200	95.82 153	98.34 151	97.66 146	98.38 140	97.77 150	97.10 184	97.25 168	97.27 198	97.18 177

PatchT		95.49 200	93.29 208	98.06 176	98.65 207	96.20 213	98.91 124	99.73 29	92.00 221	98.50 138	96.67 174	83.25 220	96.34 180	94.40 218	95.50 199	96.21 207	95.04 203

CR-MVSNet		95.38 202	93.01 209	98.16 172	98.63 208	95.85 223	97.64 210	99.78 19	91.27 226	98.50 138	96.84 171	82.16 222	96.34 180	94.40 218	95.50 199	98.05 186	95.04 203

EPMVS		93.67 220	90.82 222	96.99 205	98.62 209	96.39 212	98.40 172	99.11 156	95.54 157	97.87 176	97.14 161	81.27 226	94.97 199	88.54 231	86.80 224	92.95 225	90.06 228

CVMVSNet		97.38 163	97.39 139	97.37 193	98.58 210	97.72 195	98.70 142	97.42 218	97.21 95	95.95 219	99.46 69	93.31 190	97.38 162	97.60 161	97.78 131	96.18 208	98.66 92

CNLPA		97.75 142	97.26 143	98.32 162	98.58 210	97.86 187	97.80 200	98.09 207	96.49 130	98.49 141	96.15 185	98.08 149	98.35 123	98.00 125	97.03 175	98.61 162	97.21 176

E-PMN		92.28 227	90.12 223	94.79 229	98.56 212	90.90 236	95.16 234	93.68 233	95.36 159	95.10 229	96.56 177	89.05 196	95.24 195	95.21 211	81.84 233	90.98 233	81.94 234

RPMNet		94.72 208	92.01 216	97.88 183	98.56 212	95.85 223	97.78 201	99.70 35	91.27 226	98.33 152	93.69 208	81.88 223	94.91 200	92.60 225	94.34 211	98.01 187	94.46 207

MDTV_nov1_ep13		94.47 213	92.15 214	97.17 197	98.54 214	96.42 211	98.10 189	98.89 171	94.49 178	98.02 168	97.41 154	86.49 205	95.56 191	90.85 226	87.95 221	93.91 219	91.45 224

test2356		92.46 223	88.72 230	96.82 208	98.48 215	95.34 229	96.22 232	98.09 207	87.46 237	96.01 217	92.82 215	64.42 236	95.10 197	94.08 220	94.05 212	97.02 202	92.87 215

TSAR-MVS + COLMAP		97.62 150	97.31 141	97.98 179	98.47 216	97.39 201	98.29 182	98.25 201	96.68 118	97.54 190	98.87 107	98.04 152	97.08 167	96.78 188	96.26 188	98.26 179	97.12 178

tpmp4_e23		92.43 225	88.82 228	96.64 214	98.46 217	95.17 230	97.61 212	98.85 173	92.42 207	98.18 159	93.03 213	74.92 231	93.80 214	88.91 228	84.60 229	92.95 225	92.66 218

EMVS		91.84 228	89.39 227	94.70 230	98.44 218	90.84 237	95.27 233	93.53 234	95.18 162	95.26 227	95.62 193	87.59 203	94.77 202	94.87 214	80.72 234	90.95 234	80.88 235

tpmrst		92.45 224	89.48 226	95.92 223	98.43 219	95.03 231	97.14 222	97.92 213	94.16 189	97.56 189	97.86 142	81.63 225	93.56 216	85.89 234	82.86 230	90.91 235	88.95 233

tpm		93.89 218	91.21 219	97.03 202	98.36 220	96.07 218	97.53 217	99.65 44	92.24 210	98.64 127	97.23 158	74.67 232	94.64 204	92.68 224	90.73 217	93.37 222	94.82 206

tpm cat1		91.52 229	87.70 231	95.97 222	98.33 221	94.98 232	97.06 224	98.03 209	92.11 214	98.03 167	94.77 199	77.19 229	92.71 221	83.56 235	82.24 232	91.67 232	89.04 232

PMMVS2		96.29 189	97.05 153	95.40 226	98.32 222	96.16 214	98.18 187	97.46 217	97.20 97	84.51 240	99.60 53	98.68 131	96.37 179	98.59 79	97.38 162	97.58 193	91.76 222

DWT-MVSNet_training		91.07 230	86.55 232	96.35 218	98.28 223	95.82 226	98.00 192	95.03 230	91.24 228	97.99 172	90.35 221	63.43 237	95.25 194	86.06 233	86.62 225	93.55 221	92.30 219

test12356		95.71 199	95.55 188	95.89 224	98.27 224	96.48 209	96.90 226	97.35 220	92.13 213	95.64 221	99.13 91	97.97 154	92.34 223	96.94 185	96.55 185	94.87 216	89.61 229

new_pmnet		96.59 180	96.40 170	96.81 209	98.24 225	95.46 227	97.71 207	94.75 231	96.92 103	96.80 213	99.23 85	97.81 158	96.69 172	96.58 192	95.16 204	96.69 204	93.64 213

dps		92.35 226	88.78 229	96.52 216	98.21 226	95.94 222	97.78 201	98.38 198	89.88 234	96.81 212	95.07 196	75.31 230	94.70 203	88.62 230	86.21 226	93.21 224	90.41 225

FMVSNet5		94.57 211	92.77 210	96.67 213	97.88 227	98.72 137	97.54 214	98.70 183	88.64 236	95.11 228	86.90 227	81.77 224	93.27 217	97.92 132	98.07 110	97.50 195	97.34 168

TESTMET0.1,1		94.44 214	93.71 204	95.30 228	97.84 228	96.16 214	96.31 229	95.32 229	89.98 232	94.08 231	97.01 165	86.43 206	92.20 225	96.76 190	95.31 201	96.05 209	94.31 208

FPMVS		96.97 172	97.20 148	96.70 212	97.75 229	96.11 217	97.72 205	95.47 227	97.13 99	98.02 168	97.57 149	96.67 172	92.97 219	99.00 57	98.34 98	98.28 178	95.58 197

test-mter		94.62 209	94.02 201	95.32 227	97.72 230	96.75 206	96.23 231	95.67 226	89.83 235	93.23 237	96.99 167	85.94 212	92.66 222	97.32 177	96.11 194	96.44 205	95.22 202

pmmvs3		96.30 188	95.87 183	96.80 210	97.66 231	96.48 209	97.93 195	93.80 232	93.40 201	98.54 135	98.27 127	97.50 161	97.37 164	97.49 167	93.11 214	95.52 213	94.85 205

FMVSNet3		96.85 174	96.67 160	97.06 200	97.56 232	99.01 103	97.99 193	99.33 120	94.09 190	95.60 222	98.17 132	95.97 177	93.26 218	94.76 217	96.22 189	98.59 164	98.46 105

CMPMVS	74.71 19	96.17 192	96.06 179	96.30 219	97.41 233	94.52 233	94.83 235	95.46 228	91.57 224	97.26 204	94.45 205	98.33 142	94.98 198	98.28 106	97.59 153	97.86 189	97.68 156
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PMMVS		96.47 183	95.81 185	97.23 196	97.38 234	95.96 221	97.31 219	96.91 224	93.21 203	97.93 175	97.14 161	97.64 160	95.70 189	95.24 210	96.18 192	98.17 183	95.33 201

MVS-HIRNet		94.86 206	93.83 203	96.07 220	97.07 235	94.00 234	94.31 236	99.17 147	91.23 229	98.17 160	98.69 113	97.43 162	95.66 190	94.05 221	91.92 216	92.04 230	89.46 230

DeepPCF-MVS	96.68 10	98.20 126	98.26 100	98.12 173	97.03 236	98.11 176	98.44 170	97.70 216	96.77 112	98.52 136	98.91 106	99.17 84	98.58 108	98.41 91	98.02 111	98.46 173	98.46 105

testpf		87.81 231	83.90 233	92.37 231	96.76 237	88.65 238	93.04 238	98.24 202	85.20 238	95.28 226	86.82 228	72.43 234	82.35 235	82.62 236	82.30 231	88.55 236	89.29 231

MVE	82.47 18	93.12 221	94.09 197	91.99 232	90.79 238	82.50 240	93.93 237	96.30 225	96.06 147	88.81 239	98.19 130	96.38 175	97.56 154	97.24 181	95.18 203	84.58 237	93.07 214
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				65.28 234	82.24 239	71.50 241	70.81 241	23.21 236	96.14 144	81.70 241	85.98 234	92.44 192	49.84 236	95.81 202	94.36 210	83.86 238

testmvs		9.73 234	13.38 235	5.48 237	3.62 240	4.12 242	6.40 243	3.19 238	14.92 239	7.68 244	22.10 238	13.89 244	6.83 237	13.47 237	10.38 236	5.14 240	14.81 236

test123		9.37 235	12.26 236	6.00 236	3.32 241	4.06 243	6.39 244	3.41 237	13.20 240	10.48 243	16.43 239	16.22 243	6.76 238	11.37 238	10.40 235	5.62 239	14.10 238

GG-mvs-BLEND		65.66 233	92.62 212	34.20 235	1.45 242	93.75 235	85.40 240	1.64 239	91.37 225	17.21 242	87.25 225	94.78 184	3.25 239	95.64 206	93.80 213	96.27 206	91.74 223

sosnet-low-res		0.00 236	0.00 237	0.00 238	0.00 243	0.00 244	0.00 245	0.00 240	0.00 241	0.00 245	0.00 240	0.00 245	0.00 240	0.00 239	0.00 238	0.00 242	0.00 239

sosnet		0.00 236	0.00 237	0.00 238	0.00 243	0.00 244	0.00 245	0.00 240	0.00 241	0.00 245	0.00 240	0.00 245	0.00 240	0.00 239	0.00 238	0.00 242	0.00 239

MTAPA										99.19 66		99.68 22

MTMP										99.20 64		99.54 42

Patchmatch-RL test							32.47 242

NP-MVS									93.07 204

Patchmtry						96.05 219	97.64 210	99.78 19		98.50 138

DeepMVS_CX						87.86 239	92.27 239	61.98 235	93.64 198	93.62 234	91.17 217	91.67 193	94.90 201	95.99 201		92.48 229	94.18 210

High-resolution multi-view benchmark