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.

TDRefinement		97.59 2	98.32 2	96.73 4	95.90 66	98.10 2	99.08 2	93.92 32	98.24 3	96.44 12	98.12 19	97.86 50	96.06 2	99.24 1	98.93 1	99.00 2	97.77 4

LTVRE_ROB	95.06 1	97.73 1	98.39 1	96.95 1	96.33 50	96.94 33	98.30 21	94.90 15	98.61 1	97.73 3	97.97 23	98.57 21	95.74 4	99.24 1	98.70 4	98.72 7	98.70 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
WR-MVS		97.53 3	98.20 3	96.76 3	96.93 29	98.17 1	98.60 10	96.67 7	96.39 13	94.46 31	99.14 1	98.92 9	94.57 15	99.06 3	98.80 2	99.32 1	96.92 24

PS-CasMVS		97.22 5	97.84 6	96.50 5	97.08 25	97.92 6	98.17 29	97.02 2	94.71 25	95.32 20	98.52 12	98.97 8	92.91 40	99.04 4	98.47 5	98.49 18	97.24 11

SixPastTwentyTwo		97.36 4	97.73 9	96.92 2	97.36 13	96.15 53	98.29 22	94.43 24	96.50 11	96.96 6	98.74 5	98.74 16	96.04 3	99.03 5	97.74 17	98.44 22	97.22 12

PEN-MVS		97.16 6	97.87 5	96.33 12	97.20 21	97.97 4	98.25 25	96.86 6	95.09 23	94.93 25	98.66 7	99.16 5	92.27 50	98.98 6	98.39 7	98.49 18	96.83 29

DTE-MVSNet		97.16 6	97.75 8	96.47 6	97.40 12	97.95 5	98.20 28	96.89 5	95.30 18	95.15 23	98.66 7	98.80 14	92.77 44	98.97 7	98.27 9	98.44 22	96.28 40

CP-MVSNet		96.97 10	97.42 13	96.44 7	97.06 26	97.82 8	98.12 31	96.98 3	93.50 44	95.21 22	97.98 22	98.44 23	92.83 43	98.93 8	98.37 8	98.46 21	96.91 25

WR-MVS_H		97.06 9	97.78 7	96.23 14	96.74 37	98.04 3	98.25 25	97.32 1	94.40 32	93.71 51	98.55 10	98.89 10	92.97 37	98.91 9	98.45 6	98.38 27	97.19 13

PMVS	87.16 16	95.88 35	96.47 29	95.19 38	97.00 28	96.02 56	96.70 60	91.57 78	94.43 31	95.33 19	97.16 47	95.37 109	92.39 46	98.89 10	98.72 3	98.17 33	94.71 68
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
COLMAP_ROB	93.74 2	97.09 8	97.98 4	96.05 18	95.97 62	97.78 9	98.56 11	91.72 76	97.53 7	96.01 14	98.14 18	98.76 15	95.28 5	98.76 11	98.23 10	98.77 5	96.67 34
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	89.90 10	96.27 17	97.52 12	94.81 45	95.19 83	97.18 30	97.97 34	92.52 51	96.72 9	90.50 116	97.31 43	99.11 6	94.10 20	98.67 12	97.90 14	98.56 15	95.79 48

UniMVSNet_ETH3D		96.15 22	97.71 10	94.33 52	97.31 17	96.71 38	95.06 104	96.91 4	97.86 5	90.42 117	98.55 10	99.60 1	88.01 112	98.51 13	97.81 16	98.26 28	94.95 63

LS3D		95.83 38	96.35 32	95.22 37	96.47 47	97.49 15	97.99 32	92.35 56	94.92 24	94.58 30	94.88 92	95.11 118	91.52 61	98.48 14	98.05 12	98.42 24	95.49 53

UA-Net		96.56 12	96.73 22	96.36 10	98.99 1	97.90 7	97.79 41	95.64 10	92.78 56	92.54 72	96.23 65	95.02 120	94.31 18	98.43 15	98.12 11	98.89 3	98.58 2

ACMH	90.17 8	96.61 11	97.69 11	95.35 31	95.29 80	96.94 33	98.43 15	92.05 68	98.04 4	95.38 18	98.07 20	99.25 4	93.23 33	98.35 16	97.16 38	97.72 49	96.00 44
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
RPSCF		95.46 42	96.95 19	93.73 75	95.72 73	95.94 59	95.58 95	88.08 134	95.31 17	91.34 99	96.26 62	98.04 40	93.63 28	98.28 17	97.67 18	98.01 40	97.13 16

LGP-MVS_train		96.10 25	96.29 34	95.87 20	96.72 38	97.35 24	98.43 15	93.83 35	90.81 101	92.67 71	95.05 86	98.86 12	95.01 7	98.11 18	97.37 34	98.52 16	96.50 36

TSAR-MVS + MP.		95.99 29	96.57 26	95.31 33	96.87 30	96.50 45	98.71 5	91.58 77	93.25 49	92.71 68	96.86 53	96.57 82	93.92 21	98.09 19	97.91 13	98.08 36	96.81 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
zzz-MVS		96.18 20	96.01 43	96.38 8	98.30 2	96.18 52	98.51 13	94.48 23	94.56 27	94.81 29	91.73 128	96.96 69	94.30 19	98.09 19	97.83 15	97.91 44	96.73 31

ACMM	90.06 9	96.31 16	96.42 30	96.19 15	97.21 20	97.16 31	98.71 5	93.79 36	94.35 33	93.81 45	92.80 118	98.23 31	95.11 6	98.07 21	97.45 28	98.51 17	96.86 28
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	89.62 11	95.96 31	96.28 35	95.59 24	96.58 43	97.23 28	98.26 24	93.22 46	92.33 66	92.31 80	94.29 102	98.73 17	94.68 12	98.04 22	97.14 39	98.47 20	96.17 43
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Gipuma		95.86 36	96.17 39	95.50 28	95.92 65	94.59 97	94.77 110	92.50 52	97.82 6	97.90 2	95.56 75	97.88 48	94.71 11	98.02 23	94.81 87	97.23 65	94.48 75
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SteuartSystems-ACMMP		95.96 31	96.13 42	95.76 22	97.06 26	97.36 22	98.40 19	94.24 27	91.49 81	91.91 88	94.50 97	96.89 72	94.99 8	98.01 24	97.44 29	97.97 42	97.25 9
Skip Steuart: Steuart Systems R&D Blog.
CP-MVS		96.21 19	96.16 41	96.27 13	97.56 8	97.13 32	98.43 15	94.70 18	92.62 59	94.13 40	92.71 119	98.03 41	94.54 16	98.00 25	97.60 21	98.23 30	97.05 20

ACMMP		96.12 24	96.27 37	95.93 19	97.20 21	97.60 12	98.64 7	93.74 37	92.47 61	93.13 65	93.23 113	98.06 38	94.51 17	97.99 26	97.57 23	98.39 26	96.99 21
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
pmmvs6		94.58 58	97.30 14	91.40 113	94.84 90	94.61 96	93.40 138	92.43 55	98.51 2	85.61 156	98.73 6	99.53 2	84.40 134	97.88 27	97.03 40	97.72 49	94.79 66

ACMMP_NAP		95.86 36	96.18 38	95.47 29	97.11 24	97.26 26	98.37 20	93.48 44	93.49 45	93.99 43	95.61 72	94.11 130	92.49 45	97.87 28	97.44 29	97.40 57	97.52 7

X-MVS		95.33 47	95.13 62	95.57 26	97.35 14	97.48 17	98.43 15	94.28 25	92.30 67	93.28 58	86.89 175	96.82 75	91.87 55	97.85 29	97.59 22	98.19 31	96.95 23

ACMMPR		96.54 13	96.71 23	96.35 11	97.55 9	97.63 11	98.62 9	94.54 19	94.45 29	94.19 37	95.04 88	97.35 61	94.92 10	97.85 29	97.50 26	98.26 28	97.17 14

v7n		96.49 14	97.20 17	95.65 23	95.57 76	96.04 55	97.93 36	92.49 53	96.40 12	97.13 5	98.99 2	99.41 3	93.79 26	97.84 31	96.15 57	97.00 73	95.60 52

FC-MVSNet-test		91.49 123	94.43 75	88.07 158	94.97 87	90.53 158	95.42 98	91.18 84	93.24 50	72.94 199	98.37 15	93.86 133	78.78 165	97.82 32	96.13 59	95.13 126	91.05 131

APDe-MVS		96.23 18	97.22 16	95.08 40	96.66 41	97.56 14	98.63 8	93.69 40	94.62 26	89.80 125	97.73 31	98.13 35	93.84 25	97.79 33	97.63 19	97.87 45	97.08 19

anonymousdsp		95.45 44	96.70 24	93.99 63	88.43 191	92.05 140	99.18 1	85.42 168	94.29 34	96.10 13	98.63 9	99.08 7	96.11 1	97.77 34	97.41 32	98.70 8	97.69 5

MP-MVS		96.13 23	95.93 46	96.37 9	98.19 4	97.31 25	98.49 14	94.53 22	91.39 87	94.38 34	94.32 101	96.43 84	94.59 14	97.75 35	97.44 29	98.04 39	96.88 27
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DVP-MVS		96.10 25	97.23 15	94.79 47	96.28 53	97.49 15	97.90 37	93.60 42	95.47 16	89.57 130	97.32 42	97.72 53	93.89 23	97.74 36	97.53 24	97.51 54	97.34 8

PGM-MVS		95.90 34	95.72 49	96.10 16	97.53 10	97.45 21	98.55 12	94.12 29	90.25 104	93.71 51	93.20 114	97.18 64	94.63 13	97.68 37	97.34 35	98.08 36	96.97 22

DCV-MVSNet		93.49 83	95.15 61	91.55 109	94.05 107	95.92 60	95.15 102	91.21 82	92.76 58	87.01 149	89.71 147	97.16 65	83.90 138	97.65 38	96.87 42	97.99 41	95.95 46

EPP-MVSNet		93.63 78	93.95 85	93.26 84	95.15 84	96.54 43	96.18 81	91.97 69	91.74 75	85.76 153	94.95 90	84.27 176	91.60 60	97.61 39	97.38 33	98.87 4	95.18 60

SMA-MVS		95.99 29	96.48 28	95.41 30	97.43 11	97.36 22	97.55 46	93.70 39	94.05 39	93.79 46	97.02 51	94.53 125	92.28 49	97.53 40	97.19 36	97.73 48	97.67 6

DPE-MVS		96.00 28	96.80 20	95.06 41	95.87 69	97.47 20	98.25 25	93.73 38	92.38 63	91.57 97	97.55 37	97.97 43	92.98 36	97.49 41	97.61 20	97.96 43	97.16 15

IS_MVSNet		92.76 100	93.25 106	92.19 101	94.91 89	95.56 69	95.86 85	92.12 64	88.10 127	82.71 173	93.15 115	88.30 163	88.86 100	97.29 42	96.95 41	98.66 10	93.38 94

HFP-MVS		96.18 20	96.53 27	95.77 21	97.34 16	97.26 26	98.16 30	94.54 19	94.45 29	92.52 73	95.05 86	96.95 70	93.89 23	97.28 43	97.46 27	98.19 31	97.25 9

TranMVSNet+NR-MVSNet		95.72 40	96.42 30	94.91 44	96.21 54	96.77 37	96.90 56	94.99 13	92.62 59	91.92 87	98.51 13	98.63 19	90.82 75	97.27 44	96.83 43	98.63 12	94.31 76

Anonymous20231211		93.19 88	95.50 55	90.49 126	93.77 118	95.29 77	94.36 122	90.04 104	91.44 85	84.59 163	96.72 56	97.65 56	82.45 148	97.25 45	96.32 53	97.74 47	93.79 86

APD-MVS		95.38 45	95.68 50	95.03 42	97.30 18	96.90 35	97.83 40	93.92 32	89.40 116	90.35 118	95.41 79	97.69 55	92.97 37	97.24 46	97.17 37	97.83 46	95.96 45
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CSCG		96.07 27	97.15 18	94.81 45	96.06 60	97.58 13	96.52 70	90.98 89	96.51 10	93.60 53	97.13 48	98.55 22	93.01 35	97.17 47	95.36 73	98.68 9	97.78 3

OPM-MVS		95.96 31	96.59 25	95.23 36	96.67 40	96.52 44	97.86 39	93.28 45	95.27 21	93.46 55	96.26 62	98.85 13	92.89 41	97.09 48	96.37 52	97.22 66	95.78 49

DU-MVS		95.51 41	95.68 50	95.33 32	96.45 48	96.44 47	96.61 67	95.32 11	89.97 109	93.78 47	97.46 39	98.07 37	91.19 68	97.03 49	96.53 47	98.61 13	94.22 77

Baseline_NR-MVSNet		94.85 53	95.35 58	94.26 54	96.45 48	93.86 112	96.70 60	94.54 19	90.07 107	90.17 122	98.77 4	97.89 45	90.64 80	97.03 49	96.16 56	97.04 72	93.67 89

ETV-MVS		92.65 103	91.68 123	93.79 72	96.20 55	93.41 124	96.66 65	91.10 86	85.28 148	91.19 105	89.89 145	87.36 166	90.20 90	96.98 51	96.20 55	97.40 57	92.61 111

PHI-MVS		94.65 57	94.84 67	94.44 48	94.95 88	96.55 40	96.46 73	91.10 86	88.96 119	96.00 15	94.55 96	95.32 112	90.67 78	96.97 52	96.69 46	97.44 55	94.84 64

CPTT-MVS		95.00 52	94.52 73	95.57 26	96.84 34	96.78 36	97.88 38	93.67 41	92.20 68	92.35 79	85.87 183	97.56 58	94.98 9	96.96 53	96.07 60	97.70 51	96.18 42

Vis-MVSNet		94.39 61	95.85 48	92.68 94	90.91 174	95.88 61	97.62 45	91.41 79	91.95 73	89.20 132	97.29 44	96.26 87	90.60 85	96.95 54	95.91 61	96.32 92	96.71 32
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UniMVSNet (Re)		95.46 42	95.86 47	95.00 43	96.09 57	96.60 39	96.68 64	94.99 13	90.36 103	92.13 83	97.64 35	98.13 35	91.38 62	96.90 55	96.74 44	98.73 6	94.63 71

FC-MVSNet-train		92.75 101	95.40 57	89.66 140	95.21 82	94.82 89	97.00 52	89.40 118	91.13 92	81.71 179	97.72 32	96.43 84	77.57 177	96.89 56	96.72 45	97.05 70	94.09 80

EG-PatchMatch MVS		94.81 54	95.53 53	93.97 64	95.89 68	94.62 95	95.55 97	88.18 132	92.77 57	94.88 27	97.04 50	98.61 20	93.31 30	96.89 56	95.19 77	95.99 104	93.56 92

MDA-MVSNet-bldmvs		89.75 137	91.67 124	87.50 163	74.25 210	90.88 152	94.68 113	85.89 162	91.64 77	91.03 106	95.86 68	94.35 128	89.10 99	96.87 58	86.37 174	90.04 171	85.72 167

NR-MVSNet		94.55 60	95.66 52	93.25 86	94.26 102	96.44 47	96.69 62	95.32 11	89.97 109	91.79 93	97.46 39	98.39 25	82.85 143	96.87 58	96.48 50	98.57 14	93.98 83

DeepC-MVS	92.47 4	96.44 15	96.75 21	96.08 17	97.57 7	97.19 29	97.96 35	94.28 25	95.29 19	94.92 26	98.31 17	96.92 71	93.69 27	96.81 60	96.50 49	98.06 38	96.27 41
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SD-MVS		95.77 39	96.17 39	95.30 34	96.72 38	96.19 51	97.01 51	93.04 47	94.03 40	92.71 68	96.45 60	96.78 79	93.91 22	96.79 61	95.89 63	98.42 24	97.09 18
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
TransMVSNet (Re)		93.55 82	96.32 33	90.32 129	94.38 99	94.05 105	93.30 141	89.53 114	97.15 8	85.12 159	98.83 3	97.89 45	82.21 149	96.75 62	96.14 58	97.35 61	93.46 93

UniMVSNet_NR-MVSNet		95.34 46	95.51 54	95.14 39	95.80 71	96.55 40	96.61 67	94.79 16	90.04 108	93.78 47	97.51 38	97.25 62	91.19 68	96.68 63	96.31 54	98.65 11	94.22 77

3Dnovator+	92.82 3	95.22 49	95.16 60	95.29 35	96.17 56	96.55 40	97.64 43	94.02 31	94.16 37	94.29 36	92.09 125	93.71 135	91.90 53	96.68 63	96.51 48	97.70 51	96.40 37

TSAR-MVS + ACMM		95.17 51	95.95 44	94.26 54	96.07 59	96.46 46	95.67 92	94.21 28	93.84 42	90.99 108	97.18 46	95.24 117	93.55 29	96.60 65	95.61 70	95.06 130	96.69 33

MSLP-MVS++		93.91 68	94.30 80	93.45 78	95.51 77	95.83 63	93.12 144	91.93 72	91.45 84	91.40 98	87.42 170	96.12 94	93.27 31	96.57 66	96.40 51	95.49 115	96.29 39

Anonymous202405211			94.63 71		94.51 98	94.96 87	93.94 128	91.35 81	90.82 99		95.60 74	95.85 99	81.74 156	96.47 67	95.84 65	97.39 59	92.85 102

pm-mvs1		93.27 87	95.94 45	90.16 130	94.13 105	93.66 115	92.61 154	89.91 107	95.73 15	84.28 168	98.51 13	98.29 28	82.80 144	96.44 68	95.76 66	97.25 64	93.21 97

FPMVS		90.81 125	91.60 126	89.88 135	92.52 147	88.18 168	93.31 140	83.62 179	91.59 79	88.45 141	88.96 155	89.73 158	86.96 116	96.42 69	95.69 68	94.43 142	90.65 135

TSAR-MVS + GP.		94.25 62	94.81 68	93.60 76	96.52 46	95.80 64	94.37 118	92.47 54	90.89 97	88.92 134	95.34 81	94.38 127	92.85 42	96.36 70	95.62 69	96.47 84	95.28 58

CNVR-MVS		94.24 63	94.47 74	93.96 65	96.56 44	95.67 67	96.43 74	91.95 70	92.08 71	91.28 101	90.51 136	95.35 110	91.20 67	96.34 71	95.50 72	96.34 90	95.88 47

OMC-MVS		94.74 55	95.46 56	93.91 67	94.62 94	96.26 50	96.64 66	89.36 120	94.20 35	94.15 39	94.02 107	97.73 52	91.34 64	96.15 72	95.04 81	97.37 60	94.80 65

MIMVSNet1		92.52 106	94.88 66	89.77 136	96.09 57	91.99 141	96.92 54	89.68 112	95.92 14	84.55 164	96.64 58	98.21 33	78.44 171	96.08 73	95.10 78	92.91 163	90.22 140

HPM-MVS++		95.21 50	94.89 65	95.59 24	97.79 6	95.39 75	97.68 42	94.05 30	91.91 74	94.35 35	93.38 112	95.07 119	92.94 39	96.01 74	95.88 64	96.73 76	96.61 35

MVS_111021_HR		93.82 75	94.26 82	93.31 81	95.01 86	93.97 110	95.73 89	89.75 110	92.06 72	92.49 74	94.01 108	96.05 96	90.61 84	95.95 75	94.78 90	96.28 93	93.04 99

NCCC		93.87 73	93.42 102	94.40 50	96.84 34	95.42 72	96.47 72	92.62 50	92.36 65	92.05 84	83.83 189	95.55 103	91.84 56	95.89 76	95.23 76	96.56 81	95.63 51

Vis-MVSNet (Re-imp)		90.68 126	92.18 118	88.92 147	94.63 93	92.75 129	92.91 148	91.20 83	89.21 118	75.01 196	93.96 109	89.07 161	82.72 146	95.88 77	95.30 74	97.08 69	89.08 148

CS-MVS		92.04 119	90.08 139	94.32 53	95.94 64	94.95 88	96.72 59	91.36 80	80.81 176	94.18 38	81.09 197	90.28 155	90.30 89	95.84 78	95.57 71	97.41 56	92.05 119

AdaColmap		92.41 110	91.49 127	93.48 77	95.96 63	95.02 84	95.37 100	91.73 75	87.97 130	91.28 101	82.82 193	91.04 150	90.62 82	95.82 79	95.07 79	95.95 105	92.67 107

canonicalmvs		93.38 85	94.36 77	92.24 100	93.94 113	96.41 49	94.18 125	90.47 96	93.07 53	88.47 140	88.66 157	93.78 134	88.80 101	95.74 80	95.75 67	97.57 53	97.13 16

DeepC-MVS_fast	91.38 6	94.73 56	94.98 63	94.44 48	96.83 36	96.12 54	96.69 62	92.17 62	92.98 54	93.72 49	94.14 103	95.45 107	90.49 86	95.73 81	95.30 74	96.71 77	95.13 61
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EIA-MVS		91.95 120	90.36 135	93.81 71	96.54 45	94.65 93	95.38 99	90.40 97	78.01 194	93.72 49	86.70 178	91.95 145	89.93 93	95.67 82	94.72 94	96.89 75	90.79 134

CDPH-MVS		93.96 65	93.86 88	94.08 59	96.31 51	95.84 62	96.92 54	91.85 73	87.21 135	91.25 103	92.83 116	96.06 95	91.05 72	95.57 83	94.81 87	97.12 67	94.72 67

tfpnnormal		92.45 107	94.77 69	89.74 137	93.95 112	93.44 123	93.25 142	88.49 131	95.27 21	83.20 171	96.51 59	96.23 89	83.17 142	95.47 84	94.52 96	96.38 87	91.97 121

CNLPA		93.14 91	93.67 94	92.53 96	94.62 94	94.73 91	95.00 106	86.57 158	92.85 55	92.43 76	90.94 131	94.67 122	90.35 88	95.41 85	93.70 107	96.23 96	93.37 95

CLD-MVS		92.81 99	94.32 78	91.05 117	95.39 78	95.31 76	95.82 86	81.44 191	89.40 116	91.94 86	95.86 68	97.36 60	85.83 125	95.35 86	94.59 95	95.85 108	92.34 115
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GBi-Net		89.35 142	90.58 131	87.91 159	91.22 169	94.05 105	92.88 149	90.05 101	79.40 181	78.60 187	90.58 133	87.05 168	78.54 168	95.32 87	94.98 82	96.17 99	92.67 107

test1		89.35 142	90.58 131	87.91 159	91.22 169	94.05 105	92.88 149	90.05 101	79.40 181	78.60 187	90.58 133	87.05 168	78.54 168	95.32 87	94.98 82	96.17 99	92.67 107

FMVSNet1		92.86 98	95.26 59	90.06 132	92.40 151	95.16 78	94.37 118	92.22 58	93.18 52	82.16 178	96.76 55	97.48 59	81.85 153	95.32 87	94.98 82	97.34 62	93.93 84

TinyColmap		93.17 89	93.33 105	93.00 92	93.84 116	92.76 128	94.75 112	88.90 125	93.97 41	97.48 4	95.28 85	95.29 113	88.37 106	95.31 90	91.58 134	94.65 138	89.10 147

3Dnovator	91.81 5	93.36 86	94.27 81	92.29 99	92.99 137	95.03 82	95.76 87	87.79 137	93.82 43	92.38 78	92.19 124	93.37 139	88.14 110	95.26 91	94.85 86	96.69 78	95.40 54

UGNet		92.31 115	94.70 70	89.53 142	90.99 173	95.53 70	96.19 80	92.10 66	91.35 88	85.76 153	95.31 82	95.48 106	76.84 182	95.22 92	94.79 89	95.32 117	95.19 59
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
DeepPCF-MVS	90.68 7	94.56 59	94.92 64	94.15 57	94.11 106	95.71 66	97.03 50	90.65 93	93.39 48	94.08 41	95.29 83	94.15 129	93.21 34	95.22 92	94.92 85	95.82 110	95.75 50

MAR-MVS		91.86 121	91.14 130	92.71 93	94.29 100	94.24 103	94.91 107	91.82 74	81.66 171	93.32 57	84.51 187	93.42 138	86.86 118	95.16 94	94.44 97	95.05 131	94.53 74
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
MVS_111021_LR		93.15 90	93.65 95	92.56 95	93.89 115	92.28 135	95.09 103	86.92 153	91.26 91	92.99 67	94.46 99	96.22 90	90.64 80	95.11 95	93.45 111	95.85 108	92.74 106

PLC	87.27 15	93.08 92	92.92 109	93.26 84	94.67 91	95.03 82	94.38 117	90.10 99	91.69 76	92.14 82	87.24 171	93.91 132	91.61 59	95.05 96	94.73 93	96.67 79	92.80 103
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSDG		92.09 118	92.84 110	91.22 116	92.55 146	92.97 125	93.42 137	85.43 167	90.24 105	91.83 90	94.70 93	94.59 123	88.48 105	94.91 97	93.31 114	95.59 114	89.15 146

Fast-Effi-MVS+		92.93 95	92.64 113	93.27 83	93.81 117	93.88 111	95.90 83	90.61 94	83.98 159	92.71 68	92.81 117	96.22 90	90.67 78	94.90 98	93.92 103	95.92 106	92.77 105

train_agg		93.89 70	93.46 101	94.40 50	97.35 14	93.78 114	97.63 44	92.19 61	88.12 126	90.52 115	93.57 111	95.78 100	92.31 48	94.78 99	93.46 110	96.36 88	94.70 70

ambc			94.61 72		98.09 5	95.14 79	91.71 167		94.18 36	96.46 11	96.26 62	96.30 86	91.26 66	94.70 100	92.00 128	93.45 153	93.67 89

PVSNet_Blended_VisFu		93.60 79	93.41 103	93.83 68	96.31 51	95.65 68	95.71 90	90.58 95	88.08 128	93.17 63	95.29 83	92.20 143	90.72 77	94.69 101	93.41 112	96.51 83	94.54 73

MVS_0304		93.92 67	93.81 92	94.05 60	96.06 60	96.00 57	96.43 74	92.76 49	85.99 145	94.43 33	94.04 106	97.08 66	88.12 111	94.65 102	94.20 100	96.47 84	94.71 68

thisisatest0515		93.79 76	94.41 76	93.06 91	94.14 103	92.50 133	95.56 96	88.55 129	91.61 78	92.45 75	96.84 54	95.71 101	90.62 82	94.58 103	95.07 79	97.05 70	94.58 72

QAPM		92.57 105	93.51 98	91.47 111	92.91 139	94.82 89	93.01 146	87.51 141	91.49 81	91.21 104	92.24 122	91.70 146	88.74 102	94.54 104	94.39 98	95.41 116	95.37 57

DELS-MVS		92.33 113	93.61 97	90.83 120	92.84 141	95.13 80	94.76 111	87.22 149	87.78 131	88.42 142	95.78 70	95.28 114	85.71 128	94.44 105	93.91 104	96.01 103	92.97 101
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
MSP-MVS		95.32 48	96.28 35	94.19 56	96.87 30	97.77 10	98.27 23	93.88 34	94.15 38	89.63 129	95.36 80	98.37 26	90.73 76	94.37 106	97.53 24	95.77 111	96.40 37

CANet		93.07 93	93.05 108	93.10 89	95.90 66	95.41 73	95.88 84	91.94 71	84.77 153	93.36 56	94.05 105	95.25 116	86.25 123	94.33 107	93.94 102	95.30 118	93.58 91

TAPA-MVS	88.94 13	93.78 77	94.31 79	93.18 88	94.14 103	95.99 58	95.74 88	86.98 151	93.43 47	93.88 44	90.16 143	96.88 73	91.05 72	94.33 107	93.95 101	97.28 63	95.40 54
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
tfpn200view9		87.94 159	87.51 166	88.44 152	92.28 155	93.63 117	93.35 139	88.11 133	80.90 174	80.89 181	78.25 202	82.25 178	79.65 164	94.27 109	94.76 91	96.36 88	88.48 153

thres600view7		89.14 144	88.83 150	89.51 143	93.71 122	93.55 119	93.93 129	88.02 135	87.30 134	82.40 174	81.18 196	80.63 186	82.69 147	94.27 109	95.90 62	96.27 94	88.94 149

thres200		88.29 153	87.88 162	88.76 149	92.50 148	93.55 119	92.47 157	88.02 135	84.80 152	81.44 180	79.28 201	82.20 180	81.83 154	94.27 109	93.67 108	96.27 94	87.40 160

Effi-MVS+-dtu		92.32 114	91.66 125	93.09 90	95.13 85	94.73 91	94.57 115	92.14 63	81.74 170	90.33 119	88.13 163	95.91 98	89.24 97	94.23 112	93.65 109	97.12 67	93.23 96

EU-MVSNet		91.63 122	92.73 112	90.35 128	88.36 192	87.89 172	96.53 69	81.51 190	92.45 62	91.82 91	96.44 61	97.05 67	93.26 32	94.10 113	88.94 163	90.61 170	92.24 116

OpenMVS	89.22 12	91.09 124	91.42 128	90.71 122	92.79 143	93.61 118	92.74 153	85.47 166	86.10 144	90.73 109	85.71 184	93.07 141	86.69 119	94.07 114	93.34 113	95.86 107	94.02 82

MCST-MVS		93.60 79	93.40 104	93.83 68	95.30 79	95.40 74	96.49 71	90.87 90	90.08 106	91.72 94	90.28 141	95.99 97	91.69 58	93.94 115	92.99 115	96.93 74	95.13 61

Effi-MVS+		92.93 95	92.16 120	93.83 68	94.29 100	93.53 121	95.04 105	92.98 48	85.27 150	94.46 31	90.24 142	95.34 111	89.99 92	93.72 116	94.23 99	96.22 97	92.79 104

tttt0517		89.64 138	88.05 159	91.49 110	93.52 123	91.65 144	93.67 131	87.53 139	82.77 166	89.39 131	90.37 140	70.05 200	88.21 108	93.71 117	93.79 105	96.63 80	94.04 81

PM-MVS		92.65 103	93.20 107	92.00 103	92.11 159	90.16 161	95.99 82	84.81 173	91.31 89	92.41 77	95.87 67	96.64 81	92.35 47	93.65 118	92.91 116	94.34 144	91.85 123

IB-MVS	86.01 17	88.24 154	87.63 164	88.94 146	92.03 160	91.77 142	92.40 159	85.58 165	78.24 191	84.85 161	71.99 206	93.45 137	83.96 137	93.48 119	92.33 121	94.84 135	92.15 117
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
thisisatest0530		89.54 141	87.99 161	91.35 114	93.17 131	91.31 148	93.45 136	87.53 139	82.96 164	89.17 133	90.45 137	70.32 199	88.21 108	93.37 120	93.79 105	96.54 82	93.71 88

TSAR-MVS + COLMAP		93.06 94	93.65 95	92.36 97	94.62 94	94.28 102	95.36 101	89.46 117	92.18 69	91.64 95	95.55 76	95.27 115	88.60 104	93.24 121	92.50 120	94.46 141	92.55 113

PatchMatch-RL		89.59 139	88.80 152	90.51 125	92.20 157	88.00 171	91.72 166	86.64 155	84.75 154	88.25 143	87.10 173	90.66 153	89.85 95	93.23 122	92.28 122	94.41 143	85.60 168

thres400		88.54 149	88.15 158	88.98 145	93.17 131	92.84 127	93.56 134	86.93 152	86.45 141	82.37 175	79.96 199	81.46 184	81.83 154	93.21 123	94.76 91	96.04 102	88.39 154

casdiffmvs		92.42 109	93.99 84	90.60 124	93.25 129	93.82 113	94.28 124	88.73 127	91.53 80	84.53 166	97.74 30	98.64 18	86.60 120	93.21 123	91.20 139	96.21 98	91.76 128

CDS-MVSNet		88.41 150	89.79 141	86.79 168	94.55 97	90.82 153	92.50 156	89.85 108	83.26 163	80.52 183	91.05 129	89.93 156	69.11 196	93.17 125	92.71 118	94.21 146	87.63 158
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test20.03		88.20 156	91.26 129	84.63 181	96.64 42	89.39 163	90.73 175	89.97 106	91.07 94	72.02 201	94.98 89	95.45 107	69.35 195	92.70 126	91.19 140	89.06 175	84.02 170

V42		92.67 102	93.50 99	91.71 107	91.41 165	92.96 126	95.71 90	85.00 169	89.67 114	93.22 61	97.67 34	98.01 42	91.02 74	92.65 127	92.12 125	93.86 149	91.42 130

PVSNet_BlendedMVS		90.09 134	90.12 137	90.05 133	92.40 151	92.74 130	91.74 164	85.89 162	80.54 177	90.30 120	88.54 158	95.51 104	84.69 132	92.64 128	90.25 148	95.28 119	90.61 136

PVSNet_Blended		90.09 134	90.12 137	90.05 133	92.40 151	92.74 130	91.74 164	85.89 162	80.54 177	90.30 120	88.54 158	95.51 104	84.69 132	92.64 128	90.25 148	95.28 119	90.61 136

CMPMVS	66.55 18	85.55 170	87.46 167	83.32 184	84.99 200	81.97 193	79.19 207	75.93 197	79.32 184	88.82 136	85.09 185	91.07 149	82.12 150	92.56 130	89.63 154	88.84 176	92.56 112
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v10		93.96 65	94.12 83	93.77 74	93.37 126	95.45 71	96.83 58	91.13 85	89.70 113	95.02 24	97.88 27	98.23 31	91.27 65	92.39 131	92.18 124	94.99 132	93.00 100

v8		93.60 79	93.82 90	93.34 79	93.13 133	95.06 81	96.39 76	90.75 91	89.90 111	94.03 42	97.70 33	98.21 33	91.08 71	92.36 132	91.47 136	94.63 139	92.07 118

EPNet		90.17 133	89.07 148	91.45 112	97.25 19	90.62 157	94.84 108	93.54 43	80.96 173	91.85 89	86.98 174	85.88 172	77.79 174	92.30 133	92.58 119	93.41 154	94.20 79
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HQP-MVS		92.87 97	92.49 114	93.31 81	95.75 72	95.01 85	95.64 93	91.06 88	88.54 123	91.62 96	88.16 162	96.25 88	89.47 96	92.26 134	91.81 129	96.34 90	95.40 54

v144192		93.89 70	93.85 89	93.94 66	93.50 124	94.33 99	97.12 47	89.49 115	90.89 97	96.49 10	97.78 29	98.27 29	91.89 54	92.17 135	91.70 132	95.19 124	91.78 126

v1192		93.98 64	93.94 86	94.01 61	93.91 114	94.63 94	97.00 52	89.75 110	91.01 95	96.50 9	97.93 24	98.26 30	91.74 57	92.06 136	92.05 126	95.18 125	91.66 129

v148		92.38 111	92.78 111	91.91 104	92.86 140	92.13 138	94.84 108	87.03 150	91.47 83	93.07 66	96.92 52	98.89 10	90.10 91	92.05 137	89.69 152	93.56 152	88.27 156

USDC		92.17 116	92.17 119	92.18 102	92.93 138	92.22 136	93.66 132	87.41 144	93.49 45	97.99 1	94.10 104	96.68 80	86.46 121	92.04 138	89.18 158	94.61 140	87.47 159

v1144		93.83 74	93.87 87	93.78 73	93.72 121	94.57 98	96.85 57	89.98 105	91.31 89	95.90 16	97.89 26	98.40 24	91.13 70	92.01 139	92.01 127	95.10 128	90.94 133

v1921920		93.90 69	93.82 90	94.00 62	93.74 120	94.31 100	97.12 47	89.33 121	91.13 92	96.77 8	97.90 25	98.06 38	91.95 52	91.93 140	91.54 135	95.10 128	91.85 123

testgi		86.49 167	90.31 136	82.03 186	95.63 75	88.18 168	93.47 135	84.89 171	93.23 51	69.54 205	87.16 172	97.96 44	60.66 203	91.90 141	89.90 150	87.99 178	83.84 171

baseline1		86.96 164	87.58 165	86.24 171	93.07 135	90.44 159	89.24 187	86.85 154	85.14 151	77.26 193	90.45 137	76.09 191	75.79 187	91.80 142	91.81 129	95.20 123	87.35 161

ET-MVSNet_ETH3D		88.06 158	85.75 174	90.74 121	92.82 142	90.68 154	93.77 130	88.59 128	81.22 172	89.78 126	89.15 154	66.79 207	84.29 135	91.72 143	91.34 138	95.22 122	89.36 145

v2v482		93.42 84	93.49 100	93.32 80	93.44 125	94.05 105	96.36 79	89.76 109	91.41 86	95.24 21	97.63 36	98.34 27	90.44 87	91.65 144	91.76 131	94.69 136	89.62 143

FMVSNet2		90.28 130	92.04 121	88.23 156	91.22 169	94.05 105	92.88 149	90.69 92	86.53 140	79.89 185	94.38 100	92.73 142	78.54 168	91.64 145	92.26 123	96.17 99	92.67 107

v1240		93.89 70	93.72 93	94.09 58	93.98 111	94.31 100	97.12 47	89.37 119	90.74 102	96.92 7	98.05 21	97.89 45	92.15 51	91.53 146	91.60 133	94.99 132	91.93 122

CANet_DTU		88.95 146	89.51 145	88.29 155	93.12 134	91.22 150	93.61 133	83.47 182	80.07 180	90.71 113	89.19 153	93.68 136	76.27 186	91.44 147	91.17 141	92.59 165	89.83 142

PCF-MVS	87.46 14	92.44 108	91.80 122	93.19 87	94.66 92	95.80 64	96.37 77	90.19 98	87.57 132	92.23 81	89.26 152	93.97 131	89.24 97	91.32 148	90.82 144	96.46 86	93.86 85
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CVMVSNet		88.97 145	89.73 142	88.10 157	87.33 198	85.22 181	94.68 113	78.68 193	88.94 120	86.98 150	95.55 76	85.71 173	89.87 94	91.19 149	89.69 152	91.05 168	91.78 126

gg-mvs-nofinetune		88.32 151	88.81 151	87.75 161	93.07 135	89.37 164	89.06 188	95.94 8	95.29 19	87.15 147	97.38 41	76.38 189	68.05 199	91.04 150	89.10 160	93.24 157	83.10 176

Fast-Effi-MVS+-dtu		89.57 140	88.42 156	90.92 119	93.35 127	91.57 145	93.01 146	95.71 9	78.94 189	87.65 145	84.68 186	93.14 140	82.00 151	90.84 151	91.01 142	93.78 151	88.77 152

MVSTER		84.79 173	83.79 177	85.96 173	89.14 185	89.80 162	89.39 185	82.99 184	74.16 203	82.78 172	85.97 182	66.81 206	76.84 182	90.77 152	88.83 164	94.66 137	90.19 141

DPM-MVS		90.67 128	89.86 140	91.63 108	95.29 80	94.16 104	94.52 116	89.63 113	89.59 115	89.67 128	81.95 195	88.64 162	85.75 127	90.46 153	90.43 146	94.91 134	93.77 87

new-patchmatchnet		84.45 176	88.75 153	79.43 192	93.28 128	81.87 194	81.68 204	83.48 181	94.47 28	71.53 202	98.33 16	97.88 48	58.61 206	90.35 154	77.33 194	87.99 178	81.05 182

pmmvs-eth3d		92.34 112	92.33 115	92.34 98	92.67 144	90.67 155	96.37 77	89.06 122	90.98 96	93.60 53	97.13 48	97.02 68	88.29 107	90.20 155	91.42 137	94.07 147	88.89 151

thres100view900		86.46 168	86.00 173	86.99 166	92.28 155	91.03 151	91.09 171	84.49 175	80.90 174	80.89 181	78.25 202	82.25 178	77.57 177	90.17 156	92.84 117	95.63 112	86.57 165

FMVSNet5		79.08 195	78.83 192	79.38 194	87.52 197	86.78 175	87.64 193	78.15 194	69.54 209	70.64 203	65.97 209	65.44 209	63.87 202	90.17 156	90.46 145	88.48 177	83.45 173

E-PMN		77.81 199	77.88 199	77.73 201	88.26 193	70.48 208	80.19 206	71.20 201	86.66 139	72.89 200	88.09 164	81.74 183	78.75 166	90.02 158	68.30 206	75.10 206	59.85 209

diffmvs		90.44 129	92.23 117	88.35 154	91.36 167	91.38 147	92.45 158	84.84 172	89.88 112	85.09 160	96.69 57	97.71 54	83.33 141	90.01 159	88.96 162	93.03 161	91.00 132

DI_MVS_plusplus_trai		90.68 126	90.40 134	91.00 118	92.43 150	92.61 132	94.17 126	88.98 123	88.32 125	88.76 138	93.67 110	87.58 165	86.44 122	89.74 160	90.33 147	95.24 121	90.56 138

Anonymous20231206		87.45 162	89.66 144	84.87 178	94.00 108	87.73 174	91.36 170	86.41 160	88.89 121	75.03 195	92.59 120	96.82 75	72.48 193	89.72 161	88.06 165	89.93 172	83.81 172

IterMVS-LS		92.10 117	92.33 115	91.82 106	93.18 130	93.66 115	92.80 152	92.27 57	90.82 99	90.59 114	97.19 45	90.97 151	87.76 113	89.60 162	90.94 143	94.34 144	93.16 98
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EMVS		77.65 200	77.49 201	77.83 199	87.75 195	71.02 207	81.13 205	70.54 202	86.38 142	74.52 197	89.38 151	80.19 187	78.22 173	89.48 163	67.13 207	74.83 208	58.84 210

GA-MVS		88.76 147	88.04 160	89.59 141	92.32 154	91.46 146	92.28 160	86.62 156	83.82 161	89.84 124	92.51 121	81.94 181	83.53 140	89.41 164	89.27 157	92.95 162	87.90 157

MS-PatchMatch		87.72 161	88.62 155	86.66 169	90.81 176	88.18 168	90.92 172	82.25 185	85.86 146	80.40 184	90.14 144	89.29 160	84.93 129	89.39 165	89.12 159	90.67 169	88.34 155

EPNet_dtu		87.40 163	86.27 171	88.72 150	95.68 74	83.37 188	92.09 162	90.08 100	78.11 193	91.29 100	86.33 179	89.74 157	75.39 188	89.07 166	87.89 166	87.81 180	89.38 144
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IterMVS-SCA-FT		90.24 131	89.37 146	91.26 115	92.50 148	92.11 139	91.69 168	87.48 142	87.05 137	91.82 91	95.76 71	87.25 167	91.36 63	89.02 167	85.53 178	92.68 164	88.90 150

TAMVS		82.96 179	86.15 172	79.24 195	90.57 177	83.12 191	87.29 194	75.12 199	84.06 156	65.81 206	92.22 123	88.27 164	69.11 196	88.72 168	87.26 170	87.56 184	79.38 190

PMMVS2		69.86 204	82.14 183	55.52 205	75.19 209	63.08 211	75.52 210	60.97 205	88.50 124	25.11 213	91.77 126	96.44 83	25.43 208	88.70 169	79.34 188	70.93 209	67.17 207

MVS_Test		90.19 132	90.58 131	89.74 137	92.12 158	91.74 143	92.51 155	88.54 130	82.80 165	87.50 146	94.62 94	95.02 120	83.97 136	88.69 170	89.32 156	93.79 150	91.85 123

CHOSEN 280x420		79.24 192	78.26 196	80.38 190	79.60 206	68.80 210	89.32 186	75.38 198	77.25 195	78.02 192	75.57 205	76.17 190	81.19 158	88.61 171	81.39 185	78.79 202	80.03 187

test0.0.03 1		81.51 186	83.30 180	79.42 193	93.99 109	86.50 177	85.93 202	87.32 146	78.16 192	61.62 207	80.78 198	81.78 182	59.87 204	88.40 172	87.27 169	87.78 182	80.19 185

MIMVSNet		84.76 174	86.75 168	82.44 185	91.71 163	85.95 178	89.74 183	89.49 115	85.28 148	69.69 204	87.93 165	90.88 152	64.85 201	88.26 173	87.74 167	89.18 174	81.24 180

baseline2		84.95 172	82.68 181	87.59 162	92.64 145	88.41 167	90.09 178	84.25 176	75.88 197	85.23 158	82.49 194	71.15 197	80.14 161	88.21 174	87.21 171	93.21 160	85.39 169

FMVSNet3		87.90 160	88.63 154	87.04 165	89.78 182	93.46 122	91.62 169	90.05 101	79.40 181	78.60 187	90.58 133	87.05 168	77.07 181	88.03 175	89.86 151	95.12 127	92.04 120

gm-plane-assit		86.15 169	82.51 182	90.40 127	95.81 70	92.29 134	97.99 32	84.66 174	92.15 70	93.15 64	97.84 28	44.65 215	78.60 167	88.02 176	85.95 175	92.20 166	76.69 197

pmmvs3		81.69 184	83.83 176	79.19 196	78.33 207	78.57 198	89.53 184	58.71 207	78.88 190	84.34 167	88.36 160	91.96 144	77.69 176	87.48 177	82.42 183	86.54 187	79.18 191

IterMVS		88.32 151	88.25 157	88.41 153	90.83 175	91.24 149	93.07 145	81.69 188	86.77 138	88.55 139	95.61 72	86.91 171	87.01 115	87.38 178	83.77 180	89.29 173	86.06 166
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
pmmvs5		88.63 148	89.70 143	87.39 164	89.24 184	90.64 156	91.87 163	82.13 186	83.34 162	87.86 144	94.58 95	96.15 93	79.87 162	87.33 179	89.07 161	93.39 155	86.76 163

MDTV_nov1_ep13_2view		88.22 155	87.85 163	88.65 151	91.40 166	86.75 176	94.07 127	84.97 170	88.86 122	93.20 62	96.11 66	96.21 92	83.70 139	87.29 180	80.29 187	84.56 192	79.46 189

new_pmnet		76.65 202	83.52 178	68.63 203	82.60 202	72.08 206	76.76 209	64.17 203	84.41 155	49.73 210	91.77 126	91.53 147	56.16 207	86.59 181	83.26 182	82.37 198	75.02 199

PMMVS		81.93 183	83.48 179	80.12 191	72.35 211	75.05 204	88.54 190	64.01 204	77.02 196	82.22 177	87.51 169	91.12 148	79.70 163	86.59 181	86.64 172	93.88 148	80.41 183

baseline		86.71 165	88.89 149	84.16 183	87.85 194	85.23 180	89.82 181	77.69 195	84.03 158	84.75 162	94.91 91	94.59 123	77.19 180	86.57 183	86.51 173	87.66 183	90.36 139

pmmvs4		89.95 136	89.32 147	90.69 123	91.60 164	89.17 165	94.37 118	87.63 138	88.07 129	91.02 107	94.50 97	90.50 154	86.13 124	86.33 184	89.40 155	93.39 155	87.29 162

MVE	60.41 19	73.21 203	80.84 187	64.30 204	56.34 212	57.24 212	75.28 211	72.76 200	87.14 136	41.39 211	86.31 180	85.30 175	80.66 159	86.17 185	83.36 181	59.35 210	80.38 184
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CHOSEN 1792x2688		86.64 166	86.62 169	86.65 170	90.33 179	87.86 173	93.19 143	83.30 183	83.95 160	82.32 176	87.93 165	89.34 159	86.92 117	85.64 186	84.95 179	83.85 195	86.68 164

HyFIR lowres test		88.19 157	86.56 170	90.09 131	91.24 168	92.17 137	94.30 123	88.79 126	84.06 156	85.45 157	89.52 150	85.64 174	88.64 103	85.40 187	87.28 168	92.14 167	81.87 179

N_pmnet		79.33 190	84.22 175	73.62 202	91.72 162	73.72 205	86.11 200	76.36 196	92.38 63	53.38 208	95.54 78	95.62 102	59.14 205	84.23 188	74.84 201	75.03 207	73.25 204

CR-MVSNet		85.32 171	81.58 184	89.69 139	90.36 178	84.79 183	86.72 198	92.22 58	75.38 199	90.73 109	90.41 139	67.88 204	84.86 130	83.76 189	85.74 176	93.24 157	83.14 174

PatchT		83.44 177	81.10 185	86.18 172	77.92 208	82.58 192	89.87 180	87.39 145	75.88 197	90.73 109	89.86 146	66.71 208	84.86 130	83.76 189	85.74 176	86.33 188	83.14 174

GG-mvs-BLEND		54.28 205	77.89 198	26.72 207	0.37 216	83.31 189	70.04 212	0.39 213	74.71 201	5.36 214	68.78 207	83.06 177	0.62 212	83.73 191	78.99 191	83.55 196	72.68 206

test-mter		78.71 197	78.35 195	79.12 197	84.03 201	76.58 200	88.51 191	59.06 206	71.06 205	78.87 186	83.73 190	71.83 194	76.44 185	83.41 192	80.61 186	87.79 181	81.24 180

test-LLR		80.62 188	77.20 202	84.62 182	93.99 109	75.11 202	87.04 195	87.32 146	70.11 207	78.59 190	83.17 191	71.60 195	73.88 191	82.32 193	79.20 189	86.91 185	78.87 192

TESTMET0.1,1		77.47 201	77.20 202	77.78 200	81.94 203	75.11 202	87.04 195	58.33 208	70.11 207	78.59 190	83.17 191	71.60 195	73.88 191	82.32 193	79.20 189	86.91 185	78.87 192

RPMNet		83.42 178	78.40 194	89.28 144	89.79 181	84.79 183	90.64 176	92.11 65	75.38 199	87.10 148	79.80 200	61.99 213	82.79 145	81.88 195	82.07 184	93.23 159	82.87 177

dps		81.42 187	77.88 199	85.56 174	87.67 196	85.17 182	88.37 192	87.46 143	74.37 202	84.55 164	86.80 177	62.18 212	80.20 160	81.13 196	77.52 192	85.10 189	77.98 194

SCA		84.69 175	81.10 185	88.87 148	89.02 186	90.31 160	92.21 161	92.09 67	82.72 167	89.68 127	86.83 176	73.08 193	85.80 126	80.50 197	77.51 193	84.45 194	76.80 196

tpm		81.58 185	78.84 191	84.79 180	91.11 172	79.50 196	89.79 182	83.75 177	79.30 185	92.05 84	90.98 130	64.78 210	74.54 189	80.50 197	76.67 196	77.49 204	80.15 186

MDTV_nov1_ep13		82.33 181	79.66 188	85.45 175	88.83 188	83.88 186	90.09 178	81.98 187	79.07 188	88.82 136	88.70 156	73.77 192	78.41 172	80.29 199	76.08 197	84.56 192	75.83 198

ADS-MVSNet		79.11 194	79.38 190	78.80 198	81.90 204	75.59 201	84.36 203	83.69 178	87.31 133	76.76 194	87.58 168	76.90 188	68.55 198	78.70 200	75.56 198	77.53 203	74.07 202

PatchmatchNet		82.44 180	78.69 193	86.83 167	89.81 180	81.55 195	90.78 174	87.27 148	82.39 169	88.85 135	88.31 161	70.96 198	81.90 152	78.58 201	74.33 202	82.35 199	74.69 200
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		79.26 191	78.20 197	80.49 189	87.04 199	78.86 197	86.08 201	83.51 180	82.63 168	73.94 198	89.59 148	68.67 203	72.03 194	78.17 202	75.08 200	80.37 201	74.37 201

MVS-HIRNet		78.28 198	75.28 206	81.79 188	80.33 205	69.38 209	76.83 208	86.59 157	70.76 206	86.66 151	89.57 149	81.04 185	77.74 175	77.81 203	71.65 203	82.62 197	66.73 208

CostFormer		82.15 182	79.54 189	85.20 177	88.92 187	85.70 179	90.87 173	86.26 161	79.19 187	83.87 169	87.89 167	69.20 202	76.62 184	77.50 204	75.28 199	84.69 191	82.02 178

DWT-MVSNet_training		79.22 193	73.99 207	85.33 176	88.57 189	84.41 185	90.56 177	80.96 192	73.90 204	85.72 155	75.62 204	50.09 214	81.30 157	76.91 205	77.02 195	84.88 190	79.97 188

tpm cat1		80.03 189	75.93 205	84.81 179	89.31 183	83.26 190	88.86 189	86.55 159	79.24 186	86.10 152	84.22 188	63.62 211	77.37 179	73.43 206	70.88 205	80.67 200	76.87 195

tpmrst		78.81 196	76.18 204	81.87 187	88.56 190	77.45 199	86.74 197	81.52 189	80.08 179	83.48 170	90.84 132	66.88 205	74.54 189	73.04 207	71.02 204	76.38 205	73.95 203

DeepMVS_CX						47.68 213	53.20 213	19.21 209	63.24 210	26.96 212	66.50 208	69.82 201	66.91 200	64.27 208		54.91 211	72.72 205

tmp_tt				28.44 206	36.05 213	15.86 214	21.29 214	6.40 210	54.52 211	51.96 209	50.37 210	38.68 216	9.55 209	61.75 209	59.66 208	45.36 212

testmvs		2.38 206	3.35 208	1.26 209	0.83 214	0.96 216	1.53 216	0.83 211	3.59 212	1.63 216	6.03 211	2.93 217	1.55 211	3.49 210	2.51 210	1.21 214	3.92 212

test123		2.16 207	2.82 209	1.41 208	0.62 215	1.18 215	1.53 216	0.82 212	2.78 213	2.27 215	4.18 212	1.98 218	1.64 210	2.58 211	3.01 209	1.56 213	4.00 211

sosnet-low-res		0.00 208	0.00 210	0.00 210	0.00 217	0.00 217	0.00 218	0.00 214	0.00 214	0.00 217	0.00 213	0.00 219	0.00 213	0.00 212	0.00 211	0.00 215	0.00 213

sosnet		0.00 208	0.00 210	0.00 210	0.00 217	0.00 217	0.00 218	0.00 214	0.00 214	0.00 217	0.00 213	0.00 219	0.00 213	0.00 212	0.00 211	0.00 215	0.00 213

SR-MVS					97.13 23			94.77 17				97.77 51

our_test_3					91.78 161	88.87 166	94.37 118

test_part1																	96.89 26

MTAPA										94.88 27		96.88 73

MTMP										95.43 17		97.25 62

Patchmatch-RL test							8.96 215

XVS					96.86 32	97.48 17	98.73 3			93.28 58		96.82 75				98.17 33

X-MVStestdata					96.86 32	97.48 17	98.73 3			93.28 58		96.82 75				98.17 33

abl_6				91.88 105	93.76 119	94.98 86	95.64 93	88.97 124	86.20 143	90.00 123	86.31 180	94.50 126	87.31 114			95.60 113	92.48 114

mPP-MVS					98.24 3							97.65 56

NP-MVS									85.48 147

Patchmtry						83.74 187	86.72 198	92.22 58		90.73 109

High-resolution multi-view benchmark