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.

LTVRE_ROB	97.71 1	99.33 1	99.47 2	99.16 7	99.16 41	99.11 12	99.39 13	99.16 11	99.26 3	99.22 5	99.51 19	99.75 3	98.54 15	99.71 2	99.47 4	99.52 13	99.46 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
SixPastTwentyTwo		99.25 2	99.20 4	99.32 1	99.53 15	99.32 9	99.64 2	99.19 10	98.05 11	99.19 6	99.74 4	98.96 50	99.03 2	99.69 3	99.58 2	99.32 25	99.06 6

WR-MVS		99.22 3	99.15 6	99.30 2	99.54 11	99.62 1	99.63 4	99.45 1	97.75 15	98.47 22	99.71 6	99.05 41	98.88 4	99.54 6	99.49 3	99.81 1	98.87 9

test_part1		99.20 4	99.62 1	98.72 16	98.92 66	99.62 1	99.52 12	99.01 13	99.39 1	97.87 37	99.74 4	99.75 3	97.29 61	99.73 1	99.71 1	99.69 2	99.41 2

PS-CasMVS		99.08 5	98.90 11	99.28 3	99.65 3	99.56 5	99.59 6	99.39 3	96.36 34	98.83 14	99.46 22	99.09 34	98.62 10	99.51 8	99.36 9	99.63 4	98.97 7

PEN-MVS		99.08 5	98.95 9	99.23 5	99.65 3	99.59 3	99.64 2	99.34 6	96.68 27	98.65 17	99.43 24	99.33 16	98.47 17	99.50 9	99.32 10	99.60 6	98.79 11

v7n		99.03 7	99.03 8	99.02 9	99.09 53	99.11 12	99.57 9	98.82 19	98.21 10	99.25 3	99.84 2	99.59 6	98.76 6	99.23 17	98.83 28	98.63 67	98.40 34

DTE-MVSNet		99.03 7	98.88 12	99.21 6	99.66 2	99.59 3	99.62 5	99.34 6	96.92 23	98.52 19	99.36 30	98.98 46	98.57 13	99.49 10	99.23 13	99.56 10	98.55 25

TDRefinement		99.00 9	99.13 7	98.86 10	98.99 63	99.05 17	99.58 7	98.29 44	98.96 5	97.96 35	99.40 27	98.67 74	98.87 5	99.60 4	99.46 5	99.46 19	98.74 14

WR-MVS_H		98.97 10	98.82 14	99.14 8	99.56 9	99.56 5	99.54 11	99.42 2	96.07 39	98.37 24	99.34 31	99.09 34	98.43 18	99.45 11	99.41 6	99.53 11	98.86 10

UniMVSNet_ETH3D		98.93 11	99.20 4	98.63 21	99.54 11	99.33 8	98.73 61	99.37 4	98.87 6	97.86 38	99.27 35	99.78 2	96.59 81	99.52 7	99.40 7	99.67 3	98.21 41

CP-MVSNet		98.91 12	98.61 19	99.25 4	99.63 5	99.50 7	99.55 10	99.36 5	95.53 63	98.77 16	99.11 41	98.64 77	98.57 13	99.42 12	99.28 12	99.61 5	98.78 12

anonymousdsp		98.85 13	98.88 12	98.83 11	98.69 82	98.20 73	99.68 1	97.35 118	97.09 22	98.98 10	99.86 1	99.43 10	98.94 3	99.28 15	99.19 14	99.33 23	99.08 5

pmmvs6		98.77 14	99.35 3	98.09 42	98.32 98	98.92 22	98.57 67	99.03 12	99.36 2	96.86 84	99.77 3	99.86 1	96.20 96	99.56 5	99.39 8	99.59 7	98.61 22

ACMH	95.26 7	98.75 15	98.93 10	98.54 25	98.86 69	99.01 19	99.58 7	98.10 63	98.67 7	97.30 62	99.18 39	99.42 11	98.40 19	99.19 19	98.86 26	98.99 42	98.19 42
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
COLMAP_ROB	96.84 2	98.75 15	98.82 14	98.66 20	99.14 45	98.79 33	99.30 16	97.67 90	98.33 9	97.82 40	99.20 38	99.18 32	98.76 6	99.27 16	98.96 20	99.29 27	98.03 46
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UA-Net		98.66 17	98.60 22	98.73 15	99.83 1	99.28 10	98.56 69	99.24 8	96.04 40	97.12 71	98.44 75	98.95 51	98.17 26	99.15 22	99.00 19	99.48 18	99.33 3

DeepC-MVS	96.08 5	98.58 18	98.49 24	98.68 18	99.37 27	98.52 60	99.01 33	98.17 57	97.17 21	98.25 27	99.56 16	99.62 5	98.29 22	98.40 57	98.09 66	98.97 44	98.08 45
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TranMVSNet+NR-MVSNet		98.45 19	98.22 31	98.72 16	99.32 32	99.06 15	98.99 34	98.89 15	95.52 64	97.53 50	99.42 26	98.83 62	98.01 32	98.55 49	98.34 52	99.57 9	97.80 56

CSCG		98.45 19	98.61 19	98.26 36	99.11 49	99.06 15	98.17 87	97.49 103	97.93 13	97.37 59	98.88 52	99.29 19	98.10 27	98.40 57	97.51 83	99.32 25	99.16 4

Gipuma		98.43 21	98.15 34	98.76 14	99.00 62	98.29 70	97.91 102	98.06 65	99.02 4	99.50 1	96.33 123	98.67 74	99.22 1	99.02 25	98.02 71	98.88 57	97.66 65
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ACMH+	94.90 8	98.40 22	98.71 17	98.04 53	98.93 65	98.84 28	99.30 16	97.86 82	97.78 14	94.19 169	98.77 62	99.39 13	98.61 11	99.33 14	99.07 15	99.33 23	97.81 55

ACMMPR		98.31 23	98.07 38	98.60 22	99.58 6	98.83 29	99.09 25	98.48 28	96.25 36	97.03 75	96.81 113	99.09 34	98.39 20	98.55 49	98.45 44	99.01 39	98.53 28

APDe-MVS		98.29 24	98.42 26	98.14 39	99.45 22	98.90 23	99.18 22	98.30 42	95.96 45	95.13 148	98.79 59	99.25 27	97.92 36	98.80 33	98.71 31	98.85 59	98.54 26

DVP-MVS		98.27 25	98.61 19	97.87 63	99.17 40	99.03 18	99.07 27	98.17 57	96.75 26	94.35 164	98.92 48	99.58 7	97.86 39	98.67 42	98.70 32	98.63 67	98.63 20
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
TransMVSNet (Re)		98.23 26	98.72 16	97.66 74	98.22 107	98.73 44	98.66 63	98.03 70	98.60 8	96.40 102	99.60 13	98.24 98	95.26 118	99.19 19	99.05 18	99.36 20	97.64 66

DU-MVS		98.23 26	97.74 55	98.81 12	99.23 34	98.77 35	98.76 55	98.88 16	94.10 112	98.50 20	98.87 54	98.32 95	97.99 33	98.40 57	98.08 69	99.49 17	97.64 66

UniMVSNet (Re)		98.23 26	97.85 47	98.67 19	99.15 42	98.87 25	98.74 58	98.84 18	94.27 110	97.94 36	99.01 43	98.39 91	97.82 40	98.35 62	98.29 57	99.51 16	97.78 57

MIMVSNet1		98.22 29	98.51 23	97.87 63	99.40 26	98.82 31	99.31 15	98.53 26	97.39 18	96.59 93	99.31 33	99.23 29	94.76 128	98.93 29	98.67 34	98.63 67	97.25 89

HFP-MVS		98.17 30	98.02 39	98.35 34	99.36 28	98.62 50	98.79 54	98.46 32	96.24 37	96.53 95	97.13 110	98.98 46	98.02 31	98.20 65	98.42 46	98.95 48	98.54 26

Baseline_NR-MVSNet		98.17 30	97.90 44	98.48 28	99.23 34	98.59 52	98.83 51	98.73 23	93.97 117	96.95 78	99.66 8	98.23 100	97.90 37	98.40 57	99.06 17	99.25 28	97.42 81

TSAR-MVS + MP.		98.15 32	98.23 30	98.06 51	98.47 89	98.16 79	99.23 19	96.87 133	95.58 58	96.72 87	98.41 76	99.06 38	98.05 30	98.99 26	98.90 23	99.00 40	98.51 29
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
zzz-MVS		98.14 33	97.78 52	98.55 24	99.58 6	98.58 54	98.98 36	98.48 28	95.98 43	97.39 57	94.73 152	99.27 23	97.98 35	98.81 32	98.64 38	98.90 52	98.46 30

pm-mvs1		98.14 33	98.66 18	97.53 82	97.93 128	98.49 62	98.14 89	98.19 53	97.95 12	96.17 113	99.63 11	98.85 59	95.41 116	98.91 30	98.89 24	99.34 22	97.86 54

SMA-MVS		98.13 35	98.22 31	98.02 56	99.44 24	98.73 44	98.24 84	97.87 81	95.22 71	96.76 86	98.66 68	99.35 15	97.03 69	98.53 52	98.39 48	98.80 62	98.69 16
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
ACMMP_NAP		98.12 36	98.08 37	98.18 38	99.34 29	98.74 43	98.97 37	98.00 72	95.13 75	96.90 79	97.54 98	99.27 23	97.18 63	98.72 38	98.45 44	98.68 66	98.69 16

UniMVSNet_NR-MVSNet		98.12 36	97.56 62	98.78 13	99.13 47	98.89 24	98.76 55	98.78 20	93.81 120	98.50 20	98.81 58	97.64 120	97.99 33	98.18 68	97.92 74	99.53 11	97.64 66

ACMM	94.29 11	98.12 36	97.71 56	98.59 23	99.51 17	98.58 54	99.24 18	98.25 46	96.22 38	96.90 79	95.01 146	98.89 56	98.52 16	98.66 43	98.32 55	99.13 32	98.28 40
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SteuartSystems-ACMMP		98.06 39	97.78 52	98.39 32	99.54 11	98.79 33	98.94 41	98.42 34	93.98 116	95.85 122	96.66 118	99.25 27	98.61 11	98.71 40	98.38 49	98.97 44	98.67 19
Skip Steuart: Steuart Systems R&D Blog.
SED-MVS		98.05 40	98.46 25	97.57 78	99.01 59	98.99 20	98.82 53	98.24 47	95.76 53	94.70 157	98.96 45	99.49 9	96.19 97	98.74 34	98.65 36	98.46 81	98.63 20

OPM-MVS		98.01 41	98.01 40	98.00 58	99.11 49	98.12 82	98.68 62	97.72 88	96.65 28	96.68 91	98.40 77	99.28 22	97.44 53	98.20 65	97.82 80	98.40 87	97.58 71

Vis-MVSNet		98.01 41	98.42 26	97.54 81	96.89 175	98.82 31	99.14 23	97.59 93	96.30 35	97.04 74	99.26 36	98.83 62	96.01 102	98.73 36	98.21 59	98.58 73	98.75 13
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
NR-MVSNet		98.00 43	97.88 45	98.13 40	98.33 96	98.77 35	98.83 51	98.88 16	94.10 112	97.46 55	98.87 54	98.58 82	95.78 105	99.13 23	98.16 63	99.52 13	97.53 74

CP-MVS		98.00 43	97.57 61	98.50 26	99.47 21	98.56 57	98.91 43	98.38 37	94.71 91	97.01 76	95.20 142	99.06 38	98.20 24	98.61 46	98.46 41	99.02 37	98.40 34

DPE-MVS		97.99 45	98.12 35	97.84 66	98.65 84	98.86 26	98.86 48	98.05 68	94.18 111	95.49 141	98.90 50	99.33 16	97.11 65	98.53 52	98.65 36	98.86 58	98.39 36
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ACMMP		97.99 45	97.60 60	98.45 30	99.53 15	98.83 29	99.13 24	98.30 42	94.57 97	96.39 106	95.32 140	98.95 51	98.37 21	98.61 46	98.47 40	99.00 40	98.45 31
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
MP-MVS		97.98 47	97.53 64	98.50 26	99.56 9	98.58 54	98.97 37	98.39 36	93.49 123	97.14 68	96.08 129	99.23 29	98.06 29	98.50 54	98.38 49	98.90 52	98.44 32
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
EG-PatchMatch MVS		97.98 47	97.92 42	98.04 53	98.84 72	98.04 90	97.90 103	96.83 136	95.07 77	98.79 15	99.07 42	99.37 14	97.88 38	98.74 34	98.16 63	98.01 109	96.96 96

ACMP	94.03 12	97.97 49	97.61 59	98.39 32	99.43 25	98.51 61	98.97 37	98.06 65	94.63 95	96.10 115	96.12 128	99.20 31	98.63 9	98.68 41	98.20 62	99.14 31	97.93 51
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LGP-MVS_train		97.96 50	97.53 64	98.45 30	99.45 22	98.64 49	99.09 25	98.27 45	92.99 135	96.04 117	96.57 119	99.29 19	98.66 8	98.73 36	98.42 46	99.19 30	98.09 44

LS3D		97.93 51	97.80 49	98.08 46	99.20 37	98.77 35	98.89 45	97.92 77	96.59 29	96.99 77	96.71 116	97.14 133	96.39 90	99.04 24	98.96 20	99.10 36	97.39 82

SD-MVS		97.84 52	97.78 52	97.90 61	98.33 96	98.06 87	97.95 99	97.80 87	96.03 42	96.72 87	97.57 96	99.18 32	97.50 51	97.88 71	97.08 96	99.11 34	98.68 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
RPSCF		97.83 53	98.27 28	97.31 93	98.23 105	98.06 87	97.44 128	95.79 166	96.90 24	95.81 124	98.76 63	98.61 81	97.70 45	98.90 31	98.36 51	98.90 52	98.29 37

thisisatest0515		97.82 54	97.67 57	97.99 59	98.49 88	98.07 86	98.48 72	98.06 65	95.35 69	97.74 43	98.83 57	97.61 121	96.74 75	97.53 90	98.30 56	98.43 86	98.01 48

PGM-MVS		97.82 54	97.25 72	98.48 28	99.54 11	98.75 42	99.02 29	98.35 40	92.41 139	96.84 85	95.39 139	98.99 45	98.24 23	98.43 56	98.34 52	98.90 52	98.41 33

PMVS	90.51 17	97.77 56	97.98 41	97.53 82	98.68 83	98.14 81	97.67 113	97.03 128	96.43 30	98.38 23	98.72 65	97.03 135	94.44 133	99.37 13	99.30 11	98.98 43	96.86 102
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MSP-MVS		97.67 57	97.88 45	97.43 88	99.34 29	98.99 20	98.87 47	98.12 60	95.63 55	94.16 170	97.45 99	99.50 8	96.44 89	96.35 126	98.70 32	97.65 125	98.57 24
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
tfpnnormal		97.66 58	97.79 50	97.52 84	98.32 98	98.53 59	98.45 75	97.69 89	97.59 17	96.12 114	97.79 91	96.70 139	95.69 110	98.35 62	98.34 52	98.85 59	97.22 92

FC-MVSNet-train		97.65 59	98.16 33	97.05 105	98.85 70	98.85 27	99.34 14	98.08 64	94.50 102	94.41 162	99.21 37	98.80 66	92.66 158	98.98 27	98.85 27	98.96 46	97.94 50

v10		97.64 60	97.26 71	98.08 46	98.07 118	98.56 57	98.86 48	98.18 55	94.48 103	98.24 28	99.56 16	98.98 46	97.72 44	96.05 136	96.26 123	97.42 134	96.93 97

X-MVS		97.60 61	97.00 87	98.29 35	99.50 18	98.76 38	98.90 44	98.37 38	94.67 94	96.40 102	91.47 191	98.78 68	97.60 50	98.55 49	98.50 39	98.96 46	98.29 37

3Dnovator+	96.20 4	97.58 62	97.14 79	98.10 41	98.98 64	97.85 102	98.60 66	98.33 41	96.41 32	97.23 66	94.66 155	97.26 129	96.91 72	97.91 70	97.87 76	98.53 76	98.03 46

DCV-MVSNet		97.56 63	97.63 58	97.47 86	98.41 93	99.12 11	98.63 64	98.57 24	95.71 54	95.60 138	93.79 170	98.01 109	94.25 136	99.16 21	98.88 25	99.35 21	98.74 14

HPM-MVS++		97.56 63	97.11 83	98.09 42	99.18 39	97.95 97	98.57 67	98.20 51	94.08 114	97.25 65	95.96 133	98.81 65	97.13 64	97.51 91	97.30 93	98.21 97	98.15 43

FC-MVSNet-test		97.54 65	98.26 29	96.70 122	98.87 68	97.79 110	98.49 71	98.56 25	96.04 40	90.39 198	99.65 9	98.67 74	95.15 120	99.23 17	99.07 15	98.73 65	97.39 82

TSAR-MVS + ACMM		97.54 65	97.79 50	97.26 94	98.23 105	98.10 85	97.71 111	97.88 80	95.97 44	95.57 140	98.71 66	98.57 83	97.36 56	97.74 78	96.81 105	96.83 159	98.59 23

DeepC-MVS_fast	95.38 6	97.53 67	97.30 70	97.79 70	98.83 73	97.64 113	98.18 85	97.14 124	95.57 59	97.83 39	97.10 111	98.80 66	96.53 86	97.41 94	97.32 91	98.24 96	97.26 88
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
v1192		97.52 68	97.03 86	98.09 42	98.31 101	98.01 92	98.96 40	97.25 121	95.22 71	98.89 12	99.64 10	98.83 62	97.68 46	95.63 143	95.91 133	97.47 130	95.97 129

v1144		97.51 69	97.05 85	98.04 53	98.26 103	97.98 94	98.88 46	97.42 112	95.38 68	98.56 18	99.59 15	99.01 44	97.65 47	95.77 140	96.06 130	97.47 130	95.56 141

v8		97.51 69	97.16 77	97.91 60	97.99 124	98.48 63	98.76 55	98.17 57	94.54 101	97.69 45	99.48 21	98.76 71	97.63 49	96.10 135	96.14 125	97.20 144	96.64 109

v1921920		97.50 71	97.00 87	98.07 49	98.20 109	97.94 100	99.03 28	97.06 126	95.29 70	99.01 9	99.62 12	98.73 73	97.74 43	95.52 146	95.78 138	97.39 136	96.12 125

Anonymous20231211		97.49 72	97.91 43	97.00 109	98.31 101	98.72 46	98.27 81	97.84 84	94.76 90	94.77 156	98.14 84	98.38 93	93.60 146	98.96 28	98.66 35	99.22 29	97.77 60

v144192		97.49 72	96.99 89	98.07 49	98.11 117	97.95 97	99.02 29	97.21 122	94.90 86	98.88 13	99.53 18	98.89 56	97.75 42	95.59 144	95.90 134	97.43 133	96.16 123

GeoE		97.48 74	96.84 95	98.22 37	99.01 59	98.39 66	98.85 50	98.76 21	92.37 140	97.53 50	97.58 95	98.23 100	97.11 65	97.57 89	96.98 99	98.10 105	96.78 105

APD-MVS		97.47 75	97.16 77	97.84 66	99.32 32	98.39 66	98.47 74	98.21 50	92.08 144	95.23 145	96.68 117	98.90 54	96.99 70	98.20 65	98.21 59	98.80 62	97.67 64
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PVSNet_Blended_VisFu		97.44 76	97.14 79	97.79 70	99.15 42	98.44 64	98.32 79	97.66 91	93.74 122	97.73 44	98.79 59	96.93 138	95.64 115	97.69 80	96.91 102	98.25 95	97.50 77

PHI-MVS		97.44 76	97.17 76	97.74 73	98.14 114	98.41 65	98.03 95	97.50 101	92.07 145	98.01 34	97.33 104	98.62 80	96.02 101	98.34 64	98.21 59	98.76 64	97.24 91

v1240		97.43 78	96.87 94	98.09 42	98.25 104	97.92 101	99.02 29	97.06 126	94.77 89	99.09 8	99.68 7	98.51 86	97.78 41	95.25 151	95.81 136	97.32 140	96.13 124

FMVSNet1		97.40 79	98.09 36	96.60 126	97.80 142	98.76 38	98.26 82	98.50 27	96.79 25	93.13 186	99.28 34	98.64 77	92.90 156	97.67 82	97.86 77	99.02 37	97.64 66

v2v482		97.33 80	96.84 95	97.90 61	98.19 110	97.83 103	98.74 58	97.44 109	95.42 67	98.23 29	99.46 22	98.84 61	97.46 52	95.51 147	96.10 128	97.36 138	94.72 150

xxxxxxxxxxxxxcwj		97.32 81	97.55 63	97.05 105	98.80 75	97.83 103	96.02 176	97.44 109	94.98 80	95.74 128	97.16 107	99.30 18	95.72 107	97.85 72	97.97 72	98.60 70	97.78 57

EPP-MVSNet		97.29 82	96.88 92	97.76 72	98.70 79	99.10 14	98.92 42	98.36 39	95.12 76	93.36 184	97.39 101	91.00 183	97.65 47	98.72 38	98.91 22	99.58 8	97.92 52

MVS_111021_HR		97.27 83	97.11 83	97.46 87	98.46 90	97.82 107	97.50 124	96.86 134	94.97 82	97.13 70	96.99 112	98.39 91	96.82 74	97.65 85	97.38 86	98.02 108	96.56 112

SF-MVS		97.26 84	97.43 66	97.05 105	98.80 75	97.83 103	96.02 176	97.44 109	94.98 80	95.74 128	97.16 107	98.45 90	95.72 107	97.85 72	97.97 72	98.60 70	97.78 57

TSAR-MVS + GP.		97.26 84	97.33 69	97.18 99	98.21 108	98.06 87	96.38 167	97.66 91	93.92 119	95.23 145	98.48 73	98.33 94	97.41 54	97.63 87	97.35 87	98.18 99	97.57 72

OMC-MVS		97.23 86	97.21 74	97.25 97	97.85 133	97.52 122	97.92 101	95.77 167	95.83 49	97.09 73	97.86 89	98.52 85	96.62 79	97.51 91	96.65 110	98.26 93	96.57 110

3Dnovator	96.31 3	97.22 87	97.19 75	97.25 97	98.14 114	97.95 97	98.03 95	96.77 139	96.42 31	97.14 68	95.11 143	97.59 122	95.14 122	97.79 76	97.72 81	98.26 93	97.76 62

MVS_0304		97.18 88	96.84 95	97.58 77	99.15 42	98.19 74	98.11 90	97.81 86	92.36 141	98.06 32	97.43 100	99.06 38	94.24 137	96.80 115	96.54 114	98.12 103	97.52 75

canonicalmvs		97.11 89	96.88 92	97.38 89	98.34 95	98.72 46	97.52 123	97.94 75	95.60 56	95.01 153	94.58 156	94.50 164	96.59 81	97.84 74	98.03 70	98.90 52	98.91 8

V42		97.10 90	96.97 90	97.26 94	97.64 148	97.60 115	98.45 75	95.99 156	94.44 104	97.35 60	99.40 27	98.63 79	97.34 58	96.33 129	96.38 120	96.82 161	96.00 127

CPTT-MVS		97.08 91	96.25 109	98.05 52	99.21 36	98.30 69	98.54 70	97.98 73	94.28 108	95.89 121	89.57 200	98.54 84	98.18 25	97.82 75	97.32 91	98.54 74	97.91 53

DeepPCF-MVS	94.55 10	97.05 92	97.13 82	96.95 111	96.06 189	97.12 139	98.01 97	95.44 173	95.18 73	97.50 52	97.86 89	98.08 105	97.31 60	97.23 99	97.00 98	97.36 138	97.45 79

QAPM		97.04 93	97.14 79	96.93 113	97.78 145	98.02 91	97.36 133	96.72 140	94.68 93	96.23 108	97.21 106	97.68 118	95.70 109	97.37 95	97.24 95	97.78 118	97.77 60

CNVR-MVS		97.03 94	96.77 100	97.34 90	98.89 67	97.67 112	97.64 116	97.17 123	94.40 106	95.70 134	94.02 165	98.76 71	96.49 88	97.78 77	97.29 94	98.12 103	97.47 78

casdiffmvs		97.00 95	97.36 68	96.59 127	97.65 147	97.98 94	98.06 92	96.81 137	95.78 51	92.77 192	99.40 27	99.26 26	95.65 114	96.70 118	96.39 119	98.59 72	95.99 128

v148		96.99 96	96.70 102	97.34 90	97.89 131	97.23 131	98.33 78	96.96 129	95.57 59	97.12 71	98.99 44	99.40 12	97.23 62	96.22 132	95.45 143	96.50 166	94.02 162

DELS-MVS		96.90 97	97.24 73	96.50 132	97.85 133	98.18 75	97.88 106	95.92 159	93.48 124	95.34 143	98.86 56	98.94 53	94.03 140	97.33 97	97.04 97	98.00 110	96.85 103
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
MVS_111021_LR		96.86 98	96.72 101	97.03 108	97.80 142	97.06 142	97.04 147	95.51 172	94.55 98	97.47 53	97.35 103	97.68 118	96.66 77	97.11 104	96.73 107	97.69 122	96.57 110

PM-MVS		96.85 99	96.62 104	97.11 101	97.13 170	96.51 155	98.29 80	94.65 190	94.84 87	98.12 30	98.59 69	97.20 130	97.41 54	96.24 131	96.41 118	97.09 149	96.56 112

pmmvs-eth3d		96.84 100	96.22 111	97.56 79	97.63 150	96.38 162	98.74 58	96.91 132	94.63 95	98.26 26	99.43 24	98.28 96	96.58 83	94.52 161	95.54 141	97.24 142	94.75 149

CANet		96.81 101	96.50 105	97.17 100	99.10 51	97.96 96	97.86 107	97.51 99	91.30 150	97.75 42	97.64 93	97.89 112	93.39 150	96.98 111	96.73 107	97.40 135	96.99 95

Fast-Effi-MVS+		96.80 102	95.92 122	97.84 66	98.57 86	97.46 125	98.06 92	98.24 47	89.64 172	97.57 49	96.45 121	97.35 127	96.73 76	97.22 100	96.64 111	97.86 115	96.65 108

MCST-MVS		96.79 103	96.08 115	97.62 75	98.78 77	97.52 122	98.01 97	97.32 119	93.20 127	95.84 123	93.97 167	98.12 103	97.34 58	96.34 127	95.88 135	98.45 82	97.51 76

UGNet		96.79 103	97.82 48	95.58 155	97.57 153	98.39 66	98.48 72	97.84 84	95.85 48	94.68 158	97.91 88	99.07 37	87.12 197	97.71 79	97.51 83	97.80 116	98.29 37
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
TAPA-MVS	93.96 13	96.79 103	96.70 102	96.90 115	97.64 148	97.58 116	97.54 122	94.50 192	95.14 74	96.64 92	96.76 115	97.90 111	96.63 78	95.98 137	96.14 125	98.45 82	97.39 82
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CLD-MVS		96.73 106	96.92 91	96.51 131	98.70 79	97.57 118	97.64 116	92.07 199	93.10 133	96.31 107	98.29 79	99.02 43	95.99 103	97.20 101	96.47 116	98.37 89	96.81 104
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
train_agg		96.68 107	95.93 121	97.56 79	99.08 54	97.16 135	98.44 77	97.37 115	91.12 154	95.18 147	95.43 138	98.48 88	97.36 56	96.48 123	95.52 142	97.95 113	97.34 86

CDPH-MVS		96.68 107	95.99 118	97.48 85	99.13 47	97.64 113	98.08 91	97.46 105	90.56 160	95.13 148	94.87 150	98.27 97	96.56 84	97.09 105	96.45 117	98.54 74	97.08 94

MSLP-MVS++		96.66 109	96.46 108	96.89 116	98.02 120	97.71 111	95.57 184	96.96 129	94.36 107	96.19 112	91.37 192	98.24 98	97.07 67	97.69 80	97.89 75	97.52 128	97.95 49

TinyColmap		96.64 110	96.07 116	97.32 92	97.84 138	96.40 159	97.63 118	96.25 150	95.86 47	98.98 10	97.94 87	96.34 146	96.17 98	97.30 98	95.38 146	97.04 151	93.24 169

IS_MVSNet		96.62 111	96.48 107	96.78 120	98.46 90	98.68 48	98.61 65	98.24 47	92.23 142	89.63 202	95.90 134	94.40 165	96.23 93	98.65 44	98.77 29	99.52 13	96.76 106

NCCC		96.56 112	95.68 124	97.59 76	99.04 58	97.54 121	97.67 113	97.56 97	94.84 87	96.10 115	87.91 204	98.09 104	96.98 71	97.20 101	96.80 106	98.21 97	97.38 85

ETV-MVS		96.54 113	95.27 131	98.02 56	99.07 56	97.48 124	98.16 88	98.19 53	87.33 192	97.58 48	92.67 179	95.93 153	96.22 94	98.49 55	98.46 41	98.91 51	96.50 115

Effi-MVS+		96.46 114	95.28 130	97.85 65	98.64 85	97.16 135	97.15 145	98.75 22	90.27 164	98.03 33	93.93 168	96.21 147	96.55 85	96.34 127	96.69 109	97.97 112	96.33 119

IterMVS-LS		96.35 115	95.85 123	96.93 113	97.53 154	98.00 93	97.37 131	97.97 74	95.49 66	96.71 90	98.94 47	93.23 171	94.82 127	93.15 180	95.05 149	97.17 146	97.12 93
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
USDC		96.30 116	95.64 126	97.07 103	97.62 151	96.35 164	97.17 143	95.71 168	95.52 64	99.17 7	98.11 85	97.46 124	95.67 111	95.44 149	93.60 169	97.09 149	92.99 173

Vis-MVSNet (Re-imp)		96.29 117	96.50 105	96.05 141	97.96 127	97.83 103	97.30 135	97.86 82	93.14 129	88.90 205	96.80 114	95.28 157	95.15 120	98.37 61	98.25 58	99.12 33	95.84 131

MSDG		96.27 118	96.17 114	96.38 137	97.85 133	96.27 165	96.55 164	94.41 193	94.55 98	95.62 137	97.56 97	97.80 113	96.22 94	97.17 103	96.27 122	97.67 124	93.60 166

CS-MVS		96.24 119	94.67 146	98.08 46	99.10 51	98.62 50	98.25 83	98.12 60	87.70 187	97.76 41	88.13 203	96.08 150	96.39 90	97.64 86	98.10 65	98.84 61	96.39 117

CNLPA		96.24 119	95.97 119	96.57 129	97.48 159	97.10 141	96.75 157	94.95 184	94.92 85	96.20 111	94.81 151	96.61 141	96.25 92	96.94 112	95.64 139	97.79 117	95.74 137

EIA-MVS		96.23 121	94.85 143	97.84 66	99.08 54	98.21 72	97.69 112	98.03 70	85.68 202	98.09 31	91.75 189	97.07 134	95.66 113	97.58 88	97.72 81	98.47 80	95.91 130

PLC	92.55 15	96.10 122	95.36 127	96.96 110	98.13 116	96.88 146	96.49 165	96.67 144	94.07 115	95.71 133	91.14 193	96.09 149	96.84 73	96.70 118	96.58 113	97.92 114	96.03 126
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test20.03		96.08 123	96.80 98	95.25 164	99.19 38	97.58 116	97.24 140	97.56 97	94.95 84	91.91 193	98.58 70	98.03 107	87.88 193	97.43 93	96.94 101	97.69 122	94.05 161

TSAR-MVS + COLMAP		96.05 124	95.94 120	96.18 140	97.46 160	96.41 158	97.26 139	95.83 163	94.69 92	95.30 144	98.31 78	96.52 142	94.71 129	95.48 148	94.87 151	96.54 165	95.33 144

EU-MVSNet		96.03 125	96.23 110	95.80 149	95.48 202	94.18 183	98.99 34	91.51 201	97.22 20	97.66 46	99.15 40	98.51 86	98.08 28	95.92 138	92.88 176	93.09 189	95.72 138

PCF-MVS	92.69 14	95.98 126	95.05 138	97.06 104	98.43 92	97.56 119	97.76 109	96.65 145	89.95 169	95.70 134	96.18 127	98.48 88	95.74 106	93.64 172	93.35 173	98.09 107	96.18 122
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HQP-MVS		95.97 127	95.01 140	97.08 102	98.72 78	97.19 133	97.07 146	96.69 143	91.49 148	95.77 127	92.19 185	97.93 110	96.15 99	94.66 158	94.16 160	98.10 105	97.45 79

Effi-MVS+-dtu		95.94 128	95.08 137	96.94 112	98.54 87	97.38 126	96.66 161	97.89 79	88.68 177	95.92 119	92.90 178	97.28 128	94.18 139	96.68 120	96.13 127	98.45 82	96.51 114

diffmvs		95.86 129	96.21 112	95.44 158	97.25 168	96.85 149	96.99 149	95.23 178	94.96 83	92.82 191	98.89 51	98.85 59	93.52 148	94.21 167	94.25 159	96.84 158	95.49 142

AdaColmap		95.85 130	94.65 147	97.26 94	98.70 79	97.20 132	97.33 134	97.30 120	91.28 152	95.90 120	88.16 202	96.17 148	96.60 80	97.34 96	96.82 104	97.71 119	95.60 140

FMVSNet2		95.77 131	96.20 113	95.27 162	96.77 178	98.18 75	97.28 136	97.90 78	93.12 130	91.37 195	98.25 81	96.05 151	90.04 178	94.96 156	95.94 132	98.28 90	96.90 98

OpenMVS	94.63 9	95.75 132	95.04 139	96.58 128	97.85 133	97.55 120	96.71 159	96.07 153	90.15 167	96.47 97	90.77 198	95.95 152	94.41 134	97.01 110	96.95 100	98.00 110	96.90 98

pmmvs5		95.70 133	95.22 132	96.26 138	96.55 184	97.24 130	97.50 124	94.99 183	90.95 156	96.87 81	98.47 74	97.40 125	94.45 132	92.86 181	94.98 150	97.23 143	94.64 152

Anonymous20231206		95.69 134	95.68 124	95.70 151	98.32 98	96.95 144	97.37 131	96.65 145	93.33 125	93.61 178	98.70 67	98.03 107	91.04 167	95.07 154	94.59 158	97.20 144	93.09 172

MAR-MVS		95.51 135	94.49 151	96.71 121	97.92 129	96.40 159	96.72 158	98.04 69	86.74 196	96.72 87	92.52 182	95.14 159	94.02 141	96.81 114	96.54 114	96.85 156	97.25 89
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
DI_MVS_plusplus_trai		95.48 136	94.51 149	96.61 125	97.13 170	97.30 128	98.05 94	96.79 138	93.75 121	95.08 151	96.38 122	89.76 186	94.95 123	93.97 171	94.82 155	97.64 126	95.63 139

MDA-MVSNet-bldmvs		95.45 137	95.20 133	95.74 150	94.24 207	96.38 162	97.93 100	94.80 185	95.56 62	96.87 81	98.29 79	95.24 158	96.50 87	98.65 44	90.38 188	94.09 183	91.93 177

PVSNet_BlendedMVS		95.44 138	95.09 135	95.86 147	97.31 165	97.13 137	96.31 170	95.01 181	88.55 180	96.23 108	94.55 159	97.75 114	92.56 160	96.42 124	95.44 144	97.71 119	95.81 132

PVSNet_Blended		95.44 138	95.09 135	95.86 147	97.31 165	97.13 137	96.31 170	95.01 181	88.55 180	96.23 108	94.55 159	97.75 114	92.56 160	96.42 124	95.44 144	97.71 119	95.81 132

pmmvs4		95.37 140	94.25 152	96.67 124	97.01 173	95.28 177	97.60 119	96.07 153	93.11 131	97.29 63	98.09 86	94.23 167	95.21 119	91.56 192	93.91 166	96.82 161	93.59 167

MVS_Test		95.34 141	94.88 142	95.89 146	96.93 174	96.84 150	96.66 161	97.08 125	90.06 168	94.02 171	97.61 94	96.64 140	93.59 147	92.73 184	94.02 164	97.03 152	96.24 120

GBi-Net		95.21 142	95.35 128	95.04 167	96.77 178	98.18 75	97.28 136	97.58 94	88.43 182	90.28 199	96.01 130	92.43 174	90.04 178	97.67 82	97.86 77	98.28 90	96.90 98

test1		95.21 142	95.35 128	95.04 167	96.77 178	98.18 75	97.28 136	97.58 94	88.43 182	90.28 199	96.01 130	92.43 174	90.04 178	97.67 82	97.86 77	98.28 90	96.90 98

IterMVS-SCA-FT		95.16 144	93.95 156	96.56 130	97.89 131	96.69 152	96.94 151	96.05 155	93.06 134	97.35 60	98.79 59	91.45 179	95.93 104	92.78 182	91.00 186	95.22 179	93.91 164

HyFIR lowres test		95.05 145	93.54 161	96.81 119	97.81 141	96.88 146	98.18 85	97.46 105	94.28 108	94.98 154	96.57 119	92.89 173	96.15 99	90.90 197	91.87 182	96.28 171	91.35 178

CHOSEN 1792x2688		94.98 146	94.69 145	95.31 160	97.27 167	95.58 174	97.90 103	95.56 171	95.03 78	93.77 177	95.65 136	99.29 19	95.30 117	91.51 193	91.28 185	92.05 197	94.50 154

CANet_DTU		94.96 147	94.62 148	95.35 159	98.03 119	96.11 167	96.92 153	95.60 170	88.59 179	97.27 64	95.27 141	96.50 143	88.77 189	95.53 145	95.59 140	95.54 177	94.78 148

CDS-MVSNet		94.91 148	95.17 134	94.60 175	97.85 133	96.21 166	96.90 155	96.39 148	90.81 157	93.40 182	97.24 105	94.54 163	85.78 203	96.25 130	96.15 124	97.26 141	95.01 147
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
DPM-MVS		94.86 149	93.90 158	95.99 143	98.19 110	96.52 154	96.29 172	95.95 157	93.11 131	94.61 160	88.17 201	96.44 144	93.77 145	93.33 175	93.54 171	97.11 148	96.22 121

MS-PatchMatch		94.84 150	94.76 144	94.94 170	96.38 185	94.69 182	95.90 179	94.03 195	92.49 138	93.81 175	95.79 135	96.38 145	94.54 130	94.70 157	94.85 152	94.97 181	94.43 156

thisisatest0530		94.81 151	93.06 167	96.85 118	98.01 121	97.18 134	96.93 152	97.36 116	89.73 171	95.80 125	94.98 147	77.88 207	94.89 124	96.73 117	97.35 87	98.13 102	97.54 73

tttt0517		94.81 151	93.04 168	96.88 117	98.15 113	97.37 127	96.99 149	97.36 116	89.51 173	95.74 128	94.89 149	77.53 209	94.89 124	96.94 112	97.35 87	98.17 100	97.70 63

testgi		94.81 151	96.05 117	93.35 186	99.06 57	96.87 148	97.57 121	96.70 142	95.77 52	88.60 207	93.19 176	98.87 58	81.21 211	97.03 109	96.64 111	96.97 155	93.99 163

PatchMatch-RL		94.79 154	93.75 160	96.00 142	96.80 177	95.00 179	95.47 189	95.25 177	90.68 159	95.80 125	92.97 177	93.64 169	95.67 111	96.13 134	95.81 136	96.99 154	92.01 176

FPMVS		94.70 155	94.99 141	94.37 177	95.84 195	93.20 188	96.00 178	91.93 200	95.03 78	94.64 159	94.68 153	93.29 170	90.95 168	98.07 69	97.34 90	96.85 156	93.29 168

new-patchmatchnet		94.48 156	94.02 154	95.02 169	97.51 158	95.00 179	95.68 183	94.26 194	97.32 19	95.73 131	99.60 13	98.22 102	91.30 163	94.13 168	84.41 198	95.65 176	89.45 189

IterMVS		94.48 156	93.46 163	95.66 152	97.52 155	96.43 156	97.20 141	94.73 188	92.91 137	96.44 98	98.75 64	91.10 181	94.53 131	92.10 188	90.10 190	93.51 186	92.84 175
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MDTV_nov1_ep13_2view		94.39 158	93.34 164	95.63 153	97.23 169	95.33 176	97.76 109	96.84 135	94.55 98	97.47 53	98.96 45	97.70 116	93.88 142	92.27 186	86.81 196	90.56 199	87.73 197

Fast-Effi-MVS+-dtu		94.34 159	93.26 166	95.62 154	97.82 139	95.97 170	95.86 180	99.01 13	86.88 194	93.39 183	90.83 196	95.46 156	90.61 172	94.46 163	94.68 156	97.01 153	94.51 153

thres600view7		94.34 159	92.31 176	96.70 122	98.19 110	98.12 82	97.85 108	97.45 107	91.49 148	93.98 173	84.27 207	82.02 198	94.24 137	97.04 106	98.76 30	98.49 78	94.47 155

EPNet		94.33 161	93.52 162	95.27 162	98.81 74	94.71 181	96.77 156	98.20 51	88.12 185	96.53 95	92.53 181	91.19 180	85.25 207	95.22 152	95.26 147	96.09 174	97.63 70
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GA-MVS		94.18 162	92.98 169	95.58 155	97.36 162	96.42 157	96.21 173	95.86 160	90.29 163	95.08 151	96.19 126	85.37 190	92.82 157	94.01 170	94.14 161	96.16 173	94.41 157

gg-mvs-nofinetune		94.13 163	93.93 157	94.37 177	97.99 124	95.86 171	95.45 192	99.22 9	97.61 16	95.10 150	99.50 20	84.50 191	81.73 210	95.31 150	94.12 162	96.71 164	90.59 182

baseline		94.07 164	94.50 150	93.57 184	96.34 186	93.40 187	95.56 187	92.39 198	92.07 145	94.00 172	98.24 82	97.51 123	89.19 184	91.75 190	92.72 177	93.96 185	95.79 134

FMVSNet3		94.06 165	93.85 159	94.31 180	95.46 203	97.80 109	96.34 168	97.58 94	88.43 182	90.28 199	96.01 130	92.43 174	88.67 190	91.82 189	93.96 165	97.53 127	96.50 115

thres400		94.04 166	91.94 179	96.50 132	97.98 126	97.82 107	97.66 115	96.96 129	90.96 155	94.20 167	83.24 208	82.82 196	93.80 143	96.50 122	98.09 66	98.38 88	94.15 159

CVMVSNet		94.01 167	94.25 152	93.73 183	94.36 206	92.44 191	97.45 127	88.56 204	95.59 57	93.06 189	98.88 52	90.03 185	94.84 126	94.08 169	93.45 172	94.09 183	95.31 145

thres200		93.98 168	91.90 180	96.40 136	97.66 146	98.12 82	97.20 141	97.45 107	90.16 166	93.82 174	83.08 209	83.74 194	93.80 143	97.04 106	97.48 85	98.49 78	93.70 165

baseline1		93.89 169	92.82 171	95.14 166	97.62 151	96.97 143	96.12 174	96.36 149	91.30 150	91.53 194	94.68 153	80.72 200	90.80 170	95.71 141	96.29 121	98.44 85	94.09 160

tfpn200view9		93.80 170	91.75 181	96.20 139	97.52 155	98.15 80	97.48 126	97.47 104	87.65 188	93.56 180	83.03 210	84.12 192	92.62 159	97.04 106	98.09 66	98.52 77	94.17 158

MIMVSNet		93.68 171	93.96 155	93.35 186	97.82 139	96.08 168	96.34 168	98.46 32	91.28 152	86.67 212	94.95 148	94.87 161	84.39 208	94.53 159	94.65 157	96.45 168	91.34 179

pmnet_mix02		93.59 172	92.65 172	94.69 173	96.76 181	94.16 184	97.03 148	93.00 197	95.79 50	96.03 118	98.91 49	97.69 117	92.99 153	90.03 200	84.10 200	92.35 195	87.89 196

EPNet_dtu		93.45 173	92.51 174	94.55 176	98.39 94	91.67 200	95.46 190	97.50 101	86.56 197	97.38 58	93.52 171	94.20 168	85.82 202	93.31 177	92.53 178	92.72 191	95.76 136
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IB-MVS	92.44 16	93.33 174	92.15 178	94.70 172	97.42 161	96.39 161	95.57 184	94.67 189	86.40 200	93.59 179	78.28 214	95.76 155	89.59 183	95.88 139	95.98 131	97.39 136	96.34 118
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
ET-MVSNet_ETH3D		93.18 175	90.80 186	95.95 144	96.05 190	96.07 169	96.92 153	96.51 147	89.34 174	95.63 136	94.08 164	72.31 218	93.13 151	94.33 165	94.83 153	97.44 132	94.65 151

thres100view900		92.93 176	90.89 185	95.31 160	97.52 155	96.82 151	96.41 166	95.08 179	87.65 188	93.56 180	83.03 210	84.12 192	91.12 166	94.53 159	96.91 102	98.17 100	93.21 170

N_pmnet		92.46 177	92.38 175	92.55 192	97.91 130	93.47 186	97.42 129	94.01 196	96.40 33	88.48 208	98.50 72	98.07 106	88.14 192	91.04 196	84.30 199	89.35 204	84.85 203

TAMVS		92.46 177	93.34 164	91.44 200	97.03 172	93.84 185	94.68 202	90.60 202	90.44 162	85.31 213	97.14 109	93.03 172	85.78 203	94.34 164	93.67 168	95.22 179	90.93 181

CMPMVS	71.81 19	92.34 179	92.85 170	91.75 198	92.70 211	90.43 205	88.84 214	88.56 204	85.87 201	94.35 164	90.98 194	95.89 154	91.14 165	96.14 133	94.83 153	94.93 182	95.78 135
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
baseline2		92.06 180	89.82 189	94.68 174	97.32 163	95.72 172	94.97 199	95.08 179	84.75 205	94.34 166	90.68 199	77.75 208	90.13 177	93.38 173	93.58 170	96.25 172	92.90 174

MVSTER		91.97 181	90.31 187	93.91 181	96.81 176	96.91 145	94.22 203	95.64 169	84.98 203	92.98 190	93.42 172	72.56 216	86.64 201	95.11 153	93.89 167	97.16 147	95.31 145

CR-MVSNet		91.94 182	88.50 192	95.94 145	96.14 188	92.08 195	95.23 195	98.47 30	84.30 207	96.44 98	94.58 156	75.57 210	92.92 154	90.22 198	92.22 179	96.43 169	90.56 183

gm-plane-assit		91.85 183	87.91 194	96.44 135	99.14 45	98.25 71	99.02 29	97.38 114	95.57 59	98.31 25	99.34 31	51.00 223	88.93 187	93.16 179	91.57 183	95.85 175	86.50 200

PMMVS		91.67 184	91.47 183	91.91 197	89.43 216	88.61 211	94.99 198	85.67 209	87.50 190	93.80 176	94.42 162	94.88 160	90.71 171	92.26 187	92.96 175	96.83 159	89.65 187

CHOSEN 280x420		91.55 185	90.27 188	93.05 189	94.61 205	88.01 212	96.56 163	94.62 191	88.04 186	94.20 167	92.66 180	86.60 188	90.82 169	95.06 155	91.89 181	87.49 209	89.61 188

PatchT		91.40 186	88.54 191	94.74 171	91.48 215	92.18 194	97.42 129	97.51 99	84.96 204	96.44 98	94.16 163	75.47 211	92.92 154	90.22 198	92.22 179	92.66 194	90.56 183

pmmvs3		91.20 187	91.40 184	90.96 202	91.71 214	91.08 201	95.41 193	81.34 213	87.36 191	94.57 161	95.02 145	94.30 166	90.42 173	94.28 166	89.26 192	92.30 196	88.49 194

test0.0.03 1		91.17 188	91.50 182	90.80 203	98.01 121	95.46 175	94.22 203	95.80 164	86.55 198	81.75 215	90.83 196	87.93 187	78.48 212	94.51 162	94.11 163	96.50 166	91.08 180

SCA		91.15 189	87.65 196	95.23 165	96.15 187	95.68 173	96.68 160	98.18 55	90.46 161	97.21 67	92.44 183	80.17 202	93.51 149	86.04 207	83.58 203	89.68 203	85.21 202

new_pmnet		90.85 190	92.26 177	89.21 206	93.68 210	89.05 210	93.20 211	84.16 212	92.99 135	84.25 214	97.72 92	94.60 162	86.80 200	93.20 178	91.30 184	93.21 187	86.94 199

RPMNet		90.52 191	86.27 205	95.48 157	95.95 193	92.08 195	95.55 188	98.12 60	84.30 207	95.60 138	87.49 205	72.78 215	91.24 164	87.93 202	89.34 191	96.41 170	89.98 186

MDTV_nov1_ep13		90.30 192	87.32 200	93.78 182	96.00 192	92.97 189	95.46 190	95.39 174	88.61 178	95.41 142	94.45 161	80.39 201	89.87 181	86.58 205	83.54 204	90.56 199	84.71 204

PatchmatchNet		89.98 193	86.23 206	94.36 179	96.56 183	91.90 199	96.07 175	96.72 140	90.18 165	96.87 81	93.36 175	78.06 206	91.46 162	84.71 211	81.40 208	88.45 206	83.97 208
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ADS-MVSNet		89.89 194	87.70 195	92.43 194	95.52 200	90.91 203	95.57 184	95.33 175	93.19 128	91.21 196	93.41 173	82.12 197	89.05 185	86.21 206	83.77 202	87.92 207	84.31 205

tpm		89.84 195	86.81 202	93.36 185	96.60 182	91.92 198	95.02 197	97.39 113	86.79 195	96.54 94	95.03 144	69.70 219	87.66 194	88.79 201	86.19 197	86.95 211	89.27 190

test-LLR		89.77 196	87.47 198	92.45 193	98.01 121	89.77 207	93.25 209	95.80 164	81.56 212	89.19 203	92.08 186	79.59 203	85.77 205	91.47 194	89.04 194	92.69 192	88.75 191

FMVSNet5		89.65 197	87.60 197	92.04 196	95.63 199	96.61 153	94.82 201	94.75 186	80.11 216	87.72 210	77.73 215	73.81 214	83.81 209	95.64 142	96.08 129	95.49 178	93.21 170

EPMVS		89.28 198	86.28 204	92.79 191	96.01 191	92.00 197	95.83 181	95.85 162	90.78 158	91.00 197	94.58 156	74.65 212	88.93 187	85.00 209	82.88 206	89.09 205	84.09 207

test-mter		89.16 199	88.14 193	90.37 204	94.79 204	91.05 202	93.60 208	85.26 210	81.65 211	88.32 209	92.22 184	79.35 205	87.03 198	92.28 185	90.12 189	93.19 188	90.29 185

CostFormer		89.06 200	85.65 207	93.03 190	95.88 194	92.40 192	95.30 194	95.86 160	86.49 199	93.12 188	93.40 174	74.18 213	88.25 191	82.99 212	81.46 207	89.77 202	88.66 193

MVS-HIRNet		88.72 201	86.49 203	91.33 201	91.81 213	85.66 213	87.02 216	96.25 150	81.48 214	94.82 155	96.31 125	92.14 177	90.32 175	87.60 203	83.82 201	87.74 208	78.42 212

TESTMET0.1,1		88.60 202	87.47 198	89.93 205	94.23 208	89.77 207	93.25 209	84.47 211	81.56 212	89.19 203	92.08 186	79.59 203	85.77 205	91.47 194	89.04 194	92.69 192	88.75 191

dps		88.36 203	84.32 210	93.07 188	93.86 209	92.29 193	94.89 200	95.93 158	83.50 209	93.13 186	91.87 188	67.79 221	90.32 175	85.99 208	83.22 205	90.28 201	85.56 201

tpmrst		87.60 204	84.13 211	91.66 199	95.65 198	89.73 209	93.77 206	94.74 187	88.85 176	93.35 185	95.60 137	72.37 217	87.40 195	81.24 213	78.19 210	85.02 214	82.90 211

tpm cat1		87.19 205	82.78 212	92.33 195	95.66 197	90.61 204	94.19 205	95.27 176	86.97 193	94.38 163	90.91 195	69.40 220	87.21 196	79.57 215	77.82 211	87.25 210	84.18 206

E-PMN		86.94 206	85.10 208	89.09 208	95.77 196	83.54 216	89.89 213	86.55 206	92.18 143	87.34 211	94.02 165	83.42 195	89.63 182	93.32 176	77.11 212	85.33 212	72.09 213

EMVS		86.63 207	84.48 209	89.15 207	95.51 201	83.66 215	90.19 212	86.14 208	91.78 147	88.68 206	93.83 169	81.97 199	89.05 185	92.76 183	76.09 213	85.31 213	71.28 214

PMMVS2		86.47 208	92.62 173	79.29 210	92.01 212	85.63 214	93.74 207	86.37 207	93.95 118	54.18 220	98.19 83	97.39 126	58.46 213	96.57 121	93.07 174	90.99 198	83.55 210

MVE	72.99 18	85.37 209	89.43 190	80.63 209	74.43 217	71.94 218	88.25 215	89.81 203	93.27 126	67.32 218	96.32 124	91.83 178	90.40 174	93.36 174	90.79 187	73.55 217	88.49 194
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		61.30 210	70.45 213	50.62 211	22.69 219	30.92 220	68.31 219	25.76 215	80.56 215	68.71 216	82.80 212	91.08 182	44.64 214	80.50 214	56.70 214	73.64 216	70.58 215

GG-mvs-BLEND		61.03 211	87.02 201	30.71 213	0.74 222	90.01 206	78.90 218	0.74 219	84.56 206	9.46 221	79.17 213	90.69 184	1.37 218	91.74 191	89.13 193	93.04 190	83.83 209

testmvs		4.99 212	6.88 214	2.78 215	1.73 220	2.04 222	3.10 222	1.71 217	7.27 218	3.92 223	12.18 217	6.71 224	3.31 217	6.94 216	5.51 216	2.94 219	7.51 216

test123		4.41 213	5.71 215	2.88 214	1.28 221	2.21 221	3.09 223	1.65 218	6.35 219	4.98 222	8.53 218	3.88 225	3.46 216	5.79 217	5.71 215	2.85 220	7.50 217

uanet_test		0.00 214	0.00 216	0.00 216	0.00 223	0.00 223	0.00 224	0.00 220	0.00 220	0.00 224	0.00 219	0.00 226	0.00 219	0.00 218	0.00 217	0.00 221	0.00 218

sosnet-low-res		0.00 214	0.00 216	0.00 216	0.00 223	0.00 223	0.00 224	0.00 220	0.00 220	0.00 224	0.00 219	0.00 226	0.00 219	0.00 218	0.00 217	0.00 221	0.00 218

sosnet		0.00 214	0.00 216	0.00 216	0.00 223	0.00 223	0.00 224	0.00 220	0.00 220	0.00 224	0.00 219	0.00 226	0.00 219	0.00 218	0.00 217	0.00 221	0.00 218

RE-MVS-def										99.38 2

9.14												96.98 137

SR-MVS					99.33 31			98.40 35				98.90 54

Anonymous202405211			97.39 67		98.85 70	98.59 52	97.89 105	97.93 76	94.41 105		97.37 102	96.99 136	93.09 152	98.61 46	98.46 41	99.11 34	97.27 87

our_test_3					97.32 163	95.13 178	97.59 120

ambc			96.78 99		99.01 59	97.11 140	95.73 182		95.91 46	99.25 3	98.56 71	97.17 131	97.04 68	96.76 116	95.22 148	96.72 163	96.73 107

MTAPA										97.43 56		99.27 23

MTMP										97.63 47		99.03 42

Patchmatch-RL test							17.42 221

tmp_tt				45.72 212	60.00 218	38.74 219	45.50 220	12.18 216	79.58 217	68.42 217	67.62 216	65.04 222	22.12 215	84.83 210	78.72 209	66.08 218

XVS					99.48 19	98.76 38	99.22 20			96.40 102		98.78 68				98.94 49

X-MVStestdata					99.48 19	98.76 38	99.22 20			96.40 102		98.78 68				98.94 49

abl_6				96.45 134	97.79 144	97.28 129	97.16 144	96.16 152	89.92 170	95.72 132	91.59 190	97.16 132	94.37 135			97.51 129	95.49 142

mPP-MVS					99.58 6							98.98 46

NP-MVS									89.27 175

Patchmtry						92.70 190	95.23 195	98.47 30		96.44 98

DeepMVS_CX						72.99 217	80.14 217	37.34 214	83.46 210	60.13 219	84.40 206	85.48 189	86.93 199	87.22 204		79.61 215	87.32 198

High-resolution multi-view benchmark