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	95.06 1	97.73 1	98.39 2	96.95 1	96.33 51	96.94 35	98.30 22	94.90 15	98.61 2	97.73 3	97.97 24	98.57 23	95.74 4	99.24 1	98.70 4	98.72 8	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
TDRefinement		97.59 2	98.32 3	96.73 4	95.90 66	98.10 2	99.08 2	93.92 32	98.24 4	96.44 13	98.12 20	97.86 52	96.06 2	99.24 1	98.93 1	99.00 2	97.77 4

WR-MVS		97.53 3	98.20 4	96.76 3	96.93 29	98.17 1	98.60 10	96.67 7	96.39 14	94.46 33	99.14 1	98.92 11	94.57 15	99.06 3	98.80 2	99.32 1	96.92 26

SixPastTwentyTwo		97.36 4	97.73 10	96.92 2	97.36 13	96.15 55	98.29 23	94.43 24	96.50 12	96.96 7	98.74 6	98.74 18	96.04 3	99.03 5	97.74 18	98.44 24	97.22 14

PS-CasMVS		97.22 5	97.84 7	96.50 5	97.08 25	97.92 6	98.17 31	97.02 2	94.71 26	95.32 21	98.52 13	98.97 9	92.91 40	99.04 4	98.47 6	98.49 19	97.24 13

PEN-MVS		97.16 6	97.87 6	96.33 12	97.20 21	97.97 4	98.25 26	96.86 6	95.09 24	94.93 26	98.66 8	99.16 6	92.27 51	98.98 6	98.39 8	98.49 19	96.83 30

DTE-MVSNet		97.16 6	97.75 9	96.47 6	97.40 12	97.95 5	98.20 29	96.89 5	95.30 19	95.15 24	98.66 8	98.80 16	92.77 44	98.97 7	98.27 10	98.44 24	96.28 41

COLMAP_ROB	93.74 2	97.09 8	97.98 5	96.05 18	95.97 63	97.78 9	98.56 11	91.72 82	97.53 8	96.01 15	98.14 19	98.76 17	95.28 5	98.76 12	98.23 11	98.77 6	96.67 35
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
WR-MVS_H		97.06 9	97.78 8	96.23 14	96.74 37	98.04 3	98.25 26	97.32 1	94.40 33	93.71 52	98.55 11	98.89 12	92.97 37	98.91 9	98.45 7	98.38 29	97.19 15

CP-MVSNet		96.97 10	97.42 14	96.44 7	97.06 26	97.82 8	98.12 33	96.98 3	93.50 46	95.21 23	97.98 23	98.44 25	92.83 43	98.93 8	98.37 9	98.46 23	96.91 27

test_part1		96.91 11	98.63 1	94.90 45	94.62 98	97.75 11	98.33 21	93.88 34	98.92 1	93.11 67	99.06 2	99.66 1	90.49 91	98.84 11	98.61 5	98.97 3	97.60 7

ACMH	90.17 8	96.61 12	97.69 12	95.35 31	95.29 82	96.94 35	98.43 15	92.05 70	98.04 5	95.38 19	98.07 21	99.25 5	93.23 33	98.35 17	97.16 41	97.72 51	96.00 47
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UA-Net		96.56 13	96.73 24	96.36 10	98.99 1	97.90 7	97.79 44	95.64 10	92.78 60	92.54 76	96.23 69	95.02 129	94.31 18	98.43 16	98.12 12	98.89 4	98.58 2

ACMMPR		96.54 14	96.71 25	96.35 11	97.55 9	97.63 12	98.62 9	94.54 19	94.45 30	94.19 39	95.04 94	97.35 65	94.92 10	97.85 30	97.50 28	98.26 30	97.17 16

v7n		96.49 15	97.20 18	95.65 23	95.57 76	96.04 57	97.93 38	92.49 55	96.40 13	97.13 6	98.99 3	99.41 4	93.79 26	97.84 32	96.15 62	97.00 78	95.60 55

DeepC-MVS	92.47 4	96.44 16	96.75 23	96.08 17	97.57 7	97.19 31	97.96 37	94.28 25	95.29 20	94.92 27	98.31 18	96.92 77	93.69 27	96.81 63	96.50 52	98.06 40	96.27 42
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMM	90.06 9	96.31 17	96.42 32	96.19 15	97.21 20	97.16 33	98.71 5	93.79 38	94.35 34	93.81 46	92.80 126	98.23 33	95.11 6	98.07 22	97.45 30	98.51 18	96.86 29
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	89.90 10	96.27 18	97.52 13	94.81 46	95.19 85	97.18 32	97.97 36	92.52 53	96.72 10	90.50 123	97.31 44	99.11 7	94.10 20	98.67 13	97.90 15	98.56 16	95.79 51

APDe-MVS		96.23 19	97.22 17	95.08 40	96.66 41	97.56 15	98.63 8	93.69 42	94.62 27	89.80 132	97.73 32	98.13 37	93.84 25	97.79 35	97.63 20	97.87 47	97.08 21

CP-MVS		96.21 20	96.16 43	96.27 13	97.56 8	97.13 34	98.43 15	94.70 18	92.62 63	94.13 41	92.71 127	98.03 43	94.54 16	98.00 26	97.60 22	98.23 32	97.05 22

zzz-MVS		96.18 21	96.01 46	96.38 8	98.30 2	96.18 54	98.51 13	94.48 23	94.56 28	94.81 30	91.73 136	96.96 75	94.30 19	98.09 20	97.83 16	97.91 46	96.73 32

HFP-MVS		96.18 21	96.53 29	95.77 21	97.34 16	97.26 28	98.16 32	94.54 19	94.45 30	92.52 77	95.05 92	96.95 76	93.89 23	97.28 46	97.46 29	98.19 33	97.25 11

UniMVSNet_ETH3D		96.15 23	97.71 11	94.33 54	97.31 17	96.71 40	95.06 109	96.91 4	97.86 6	90.42 124	98.55 11	99.60 2	88.01 119	98.51 14	97.81 17	98.26 30	94.95 67

MP-MVS		96.13 24	95.93 49	96.37 9	98.19 4	97.31 27	98.49 14	94.53 22	91.39 92	94.38 36	94.32 107	96.43 90	94.59 14	97.75 37	97.44 31	98.04 41	96.88 28
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ACMMP		96.12 25	96.27 39	95.93 19	97.20 21	97.60 13	98.64 7	93.74 39	92.47 65	93.13 66	93.23 120	98.06 40	94.51 17	97.99 27	97.57 25	98.39 28	96.99 23
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
DVP-MVS		96.10 26	97.23 16	94.79 48	96.28 54	97.49 16	97.90 39	93.60 44	95.47 17	89.57 138	97.32 43	97.72 56	93.89 23	97.74 38	97.53 26	97.51 56	97.34 9
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
LGP-MVS_train		96.10 26	96.29 36	95.87 20	96.72 38	97.35 26	98.43 15	93.83 36	90.81 106	92.67 75	95.05 92	98.86 14	95.01 7	98.11 19	97.37 37	98.52 17	96.50 37

CSCG		96.07 28	97.15 19	94.81 46	96.06 61	97.58 14	96.52 72	90.98 93	96.51 11	93.60 54	97.13 50	98.55 24	93.01 35	97.17 50	95.36 78	98.68 10	97.78 3

DPE-MVS		96.00 29	96.80 22	95.06 41	95.87 69	97.47 21	98.25 26	93.73 40	92.38 67	91.57 104	97.55 38	97.97 45	92.98 36	97.49 44	97.61 21	97.96 45	97.16 17
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SMA-MVS		95.99 30	96.48 30	95.41 30	97.43 11	97.36 24	97.55 49	93.70 41	94.05 41	93.79 47	97.02 53	94.53 134	92.28 50	97.53 43	97.19 39	97.73 50	97.67 6
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
TSAR-MVS + MP.		95.99 30	96.57 28	95.31 33	96.87 30	96.50 47	98.71 5	91.58 83	93.25 51	92.71 71	96.86 55	96.57 88	93.92 21	98.09 20	97.91 14	98.08 38	96.81 31
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
OPM-MVS		95.96 32	96.59 27	95.23 36	96.67 40	96.52 46	97.86 42	93.28 47	95.27 22	93.46 56	96.26 66	98.85 15	92.89 41	97.09 51	96.37 57	97.22 71	95.78 52

SteuartSystems-ACMMP		95.96 32	96.13 45	95.76 22	97.06 26	97.36 24	98.40 19	94.24 27	91.49 86	91.91 95	94.50 103	96.89 78	94.99 8	98.01 25	97.44 31	97.97 44	97.25 11
Skip Steuart: Steuart Systems R&D Blog.
ACMP	89.62 11	95.96 32	96.28 37	95.59 24	96.58 43	97.23 30	98.26 25	93.22 48	92.33 70	92.31 84	94.29 108	98.73 19	94.68 12	98.04 23	97.14 42	98.47 21	96.17 44
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PGM-MVS		95.90 35	95.72 54	96.10 16	97.53 10	97.45 22	98.55 12	94.12 29	90.25 110	93.71 52	93.20 121	97.18 69	94.63 13	97.68 40	97.34 38	98.08 38	96.97 24

PMVS	87.16 16	95.88 36	96.47 31	95.19 38	97.00 28	96.02 58	96.70 63	91.57 84	94.43 32	95.33 20	97.16 49	95.37 117	92.39 46	98.89 10	98.72 3	98.17 35	94.71 72
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ACMMP_NAP		95.86 37	96.18 40	95.47 29	97.11 24	97.26 28	98.37 20	93.48 46	93.49 47	93.99 44	95.61 78	94.11 139	92.49 45	97.87 29	97.44 31	97.40 61	97.52 8

Gipuma		95.86 37	96.17 41	95.50 28	95.92 65	94.59 102	94.77 117	92.50 54	97.82 7	97.90 2	95.56 81	97.88 50	94.71 11	98.02 24	94.81 92	97.23 70	94.48 79
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LS3D		95.83 39	96.35 34	95.22 37	96.47 47	97.49 16	97.99 34	92.35 58	94.92 25	94.58 31	94.88 98	95.11 127	91.52 62	98.48 15	98.05 13	98.42 26	95.49 56

SD-MVS		95.77 40	96.17 41	95.30 34	96.72 38	96.19 53	97.01 55	93.04 49	94.03 42	92.71 71	96.45 64	96.78 85	93.91 22	96.79 64	95.89 68	98.42 26	97.09 20
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
SED-MVS		95.73 41	96.98 20	94.28 55	96.08 59	97.39 23	98.18 30	93.80 37	94.20 36	89.61 137	97.29 45	97.49 62	90.69 81	97.74 38	97.41 34	97.32 67	97.34 9

TranMVSNet+NR-MVSNet		95.72 42	96.42 32	94.91 44	96.21 55	96.77 39	96.90 60	94.99 13	92.62 63	91.92 94	98.51 14	98.63 21	90.82 78	97.27 47	96.83 46	98.63 13	94.31 80

DU-MVS		95.51 43	95.68 55	95.33 32	96.45 48	96.44 49	96.61 69	95.32 11	89.97 115	93.78 48	97.46 40	98.07 39	91.19 69	97.03 53	96.53 50	98.61 14	94.22 81

UniMVSNet (Re)		95.46 44	95.86 52	95.00 43	96.09 57	96.60 41	96.68 67	94.99 13	90.36 109	92.13 87	97.64 36	98.13 37	91.38 63	96.90 58	96.74 47	98.73 7	94.63 75

RPSCF		95.46 44	96.95 21	93.73 78	95.72 73	95.94 61	95.58 100	88.08 140	95.31 18	91.34 107	96.26 66	98.04 42	93.63 28	98.28 18	97.67 19	98.01 42	97.13 18

anonymousdsp		95.45 46	96.70 26	93.99 66	88.43 198	92.05 147	99.18 1	85.42 175	94.29 35	96.10 14	98.63 10	99.08 8	96.11 1	97.77 36	97.41 34	98.70 9	97.69 5

APD-MVS		95.38 47	95.68 55	95.03 42	97.30 18	96.90 37	97.83 43	93.92 32	89.40 122	90.35 125	95.41 85	97.69 58	92.97 37	97.24 49	97.17 40	97.83 48	95.96 48
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
UniMVSNet_NR-MVSNet		95.34 48	95.51 59	95.14 39	95.80 71	96.55 42	96.61 69	94.79 16	90.04 114	93.78 48	97.51 39	97.25 66	91.19 69	96.68 66	96.31 59	98.65 12	94.22 81

X-MVS		95.33 49	95.13 67	95.57 26	97.35 14	97.48 18	98.43 15	94.28 25	92.30 71	93.28 59	86.89 183	96.82 81	91.87 56	97.85 30	97.59 23	98.19 33	96.95 25

MSP-MVS		95.32 50	96.28 37	94.19 58	96.87 30	97.77 10	98.27 24	93.88 34	94.15 40	89.63 136	95.36 86	98.37 28	90.73 79	94.37 113	97.53 26	95.77 118	96.40 38
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
CS-MVS-test		95.28 51	95.87 50	94.60 49	94.78 93	95.80 68	97.88 40	89.55 119	90.46 108	94.57 32	96.56 61	97.80 53	92.34 48	97.84 32	97.59 23	98.47 21	95.03 66

3Dnovator+	92.82 3	95.22 52	95.16 65	95.29 35	96.17 56	96.55 42	97.64 46	94.02 31	94.16 39	94.29 38	92.09 133	93.71 144	91.90 54	96.68 66	96.51 51	97.70 53	96.40 38

HPM-MVS++		95.21 53	94.89 70	95.59 24	97.79 6	95.39 80	97.68 45	94.05 30	91.91 78	94.35 37	93.38 119	95.07 128	92.94 39	96.01 79	95.88 69	96.73 81	96.61 36

TSAR-MVS + ACMM		95.17 54	95.95 47	94.26 56	96.07 60	96.46 48	95.67 97	94.21 28	93.84 44	90.99 115	97.18 48	95.24 126	93.55 29	96.60 70	95.61 76	95.06 137	96.69 34

xxxxxxxxxxxxxcwj		95.03 55	96.14 44	93.73 78	95.30 79	95.93 62	94.80 115	91.76 79	93.11 55	91.93 92	95.83 74	98.96 10	91.11 72	96.62 68	96.44 54	97.46 57	96.13 45

CPTT-MVS		95.00 56	94.52 78	95.57 26	96.84 34	96.78 38	97.88 40	93.67 43	92.20 72	92.35 83	85.87 191	97.56 61	94.98 9	96.96 56	96.07 65	97.70 53	96.18 43

SF-MVS		94.88 57	95.87 50	93.73 78	95.30 79	95.93 62	94.80 115	91.76 79	93.11 55	91.93 92	95.83 74	97.07 72	91.11 72	96.62 68	96.44 54	97.46 57	96.13 45

Baseline_NR-MVSNet		94.85 58	95.35 63	94.26 56	96.45 48	93.86 119	96.70 63	94.54 19	90.07 113	90.17 129	98.77 5	97.89 47	90.64 85	97.03 53	96.16 61	97.04 77	93.67 93

EG-PatchMatch MVS		94.81 59	95.53 58	93.97 67	95.89 68	94.62 100	95.55 102	88.18 138	92.77 61	94.88 28	97.04 52	98.61 22	93.31 30	96.89 59	95.19 82	95.99 110	93.56 96

OMC-MVS		94.74 60	95.46 61	93.91 70	94.62 98	96.26 52	96.64 68	89.36 126	94.20 36	94.15 40	94.02 113	97.73 55	91.34 65	96.15 77	95.04 86	97.37 64	94.80 69

DeepC-MVS_fast	91.38 6	94.73 61	94.98 68	94.44 50	96.83 36	96.12 56	96.69 65	92.17 64	92.98 58	93.72 50	94.14 109	95.45 115	90.49 91	95.73 86	95.30 79	96.71 82	95.13 64
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PHI-MVS		94.65 62	94.84 72	94.44 50	94.95 90	96.55 42	96.46 75	91.10 91	88.96 125	96.00 16	94.55 102	95.32 121	90.67 82	96.97 55	96.69 49	97.44 60	94.84 68

pmmvs6		94.58 63	97.30 15	91.40 120	94.84 92	94.61 101	93.40 145	92.43 57	98.51 3	85.61 163	98.73 7	99.53 3	84.40 141	97.88 28	97.03 43	97.72 51	94.79 70

DeepPCF-MVS	90.68 7	94.56 64	94.92 69	94.15 59	94.11 111	95.71 71	97.03 54	90.65 97	93.39 50	94.08 42	95.29 89	94.15 138	93.21 34	95.22 97	94.92 90	95.82 117	95.75 53

NR-MVSNet		94.55 65	95.66 57	93.25 92	94.26 107	96.44 49	96.69 65	95.32 11	89.97 115	91.79 100	97.46 40	98.39 27	82.85 150	96.87 61	96.48 53	98.57 15	93.98 87

Vis-MVSNet		94.39 66	95.85 53	92.68 100	90.91 181	95.88 65	97.62 48	91.41 85	91.95 77	89.20 140	97.29 45	96.26 93	90.60 90	96.95 57	95.91 66	96.32 97	96.71 33
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TSAR-MVS + GP.		94.25 67	94.81 73	93.60 81	96.52 46	95.80 68	94.37 125	92.47 56	90.89 102	88.92 142	95.34 87	94.38 136	92.85 42	96.36 75	95.62 75	96.47 89	95.28 61

CNVR-MVS		94.24 68	94.47 79	93.96 68	96.56 44	95.67 72	96.43 76	91.95 73	92.08 75	91.28 109	90.51 144	95.35 118	91.20 68	96.34 76	95.50 77	96.34 95	95.88 50

v1192		93.98 69	93.94 91	94.01 64	93.91 119	94.63 99	97.00 56	89.75 115	91.01 100	96.50 10	97.93 25	98.26 32	91.74 58	92.06 143	92.05 133	95.18 132	91.66 135

v10		93.96 70	94.12 88	93.77 77	93.37 133	95.45 76	96.83 62	91.13 90	89.70 119	95.02 25	97.88 28	98.23 33	91.27 66	92.39 138	92.18 131	94.99 139	93.00 105

CDPH-MVS		93.96 70	93.86 93	94.08 61	96.31 52	95.84 66	96.92 58	91.85 76	87.21 141	91.25 111	92.83 123	96.06 102	91.05 75	95.57 88	94.81 92	97.12 72	94.72 71

MVS_0304		93.92 72	93.81 97	94.05 63	96.06 61	96.00 59	96.43 76	92.76 51	85.99 152	94.43 35	94.04 112	97.08 71	88.12 118	94.65 109	94.20 105	96.47 89	94.71 72

MSLP-MVS++		93.91 73	94.30 85	93.45 83	95.51 77	95.83 67	93.12 151	91.93 75	91.45 89	91.40 106	87.42 178	96.12 101	93.27 31	96.57 71	96.40 56	95.49 122	96.29 40

v1921920		93.90 74	93.82 95	94.00 65	93.74 127	94.31 105	97.12 51	89.33 127	91.13 97	96.77 9	97.90 26	98.06 40	91.95 53	91.93 147	91.54 142	95.10 135	91.85 128

train_agg		93.89 75	93.46 107	94.40 52	97.35 14	93.78 121	97.63 47	92.19 63	88.12 132	90.52 122	93.57 118	95.78 108	92.31 49	94.78 106	93.46 117	96.36 93	94.70 74

v144192		93.89 75	93.85 94	93.94 69	93.50 131	94.33 104	97.12 51	89.49 121	90.89 102	96.49 11	97.78 30	98.27 31	91.89 55	92.17 142	91.70 139	95.19 131	91.78 132

v1240		93.89 75	93.72 98	94.09 60	93.98 116	94.31 105	97.12 51	89.37 125	90.74 107	96.92 8	98.05 22	97.89 47	92.15 52	91.53 153	91.60 140	94.99 139	91.93 127

NCCC		93.87 78	93.42 108	94.40 52	96.84 34	95.42 77	96.47 74	92.62 52	92.36 69	92.05 89	83.83 198	95.55 111	91.84 57	95.89 81	95.23 81	96.56 86	95.63 54

v1144		93.83 79	93.87 92	93.78 76	93.72 128	94.57 103	96.85 61	89.98 110	91.31 94	95.90 17	97.89 27	98.40 26	91.13 71	92.01 146	92.01 134	95.10 135	90.94 139

MVS_111021_HR		93.82 80	94.26 87	93.31 86	95.01 88	93.97 116	95.73 94	89.75 115	92.06 76	92.49 78	94.01 114	96.05 103	90.61 89	95.95 80	94.78 95	96.28 98	93.04 104

thisisatest0515		93.79 81	94.41 81	93.06 97	94.14 108	92.50 140	95.56 101	88.55 135	91.61 82	92.45 79	96.84 56	95.71 109	90.62 87	94.58 110	95.07 84	97.05 75	94.58 76

TAPA-MVS	88.94 13	93.78 82	94.31 84	93.18 94	94.14 108	95.99 60	95.74 93	86.98 157	93.43 49	93.88 45	90.16 151	96.88 79	91.05 75	94.33 114	93.95 107	97.28 68	95.40 57
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		93.72 83	93.62 102	93.84 71	94.75 94	94.90 93	97.24 50	91.81 78	86.97 144	92.74 70	93.83 116	97.24 68	90.46 93	95.10 101	94.09 106	96.08 107	93.18 102

EPP-MVSNet		93.63 84	93.95 90	93.26 90	95.15 86	96.54 45	96.18 84	91.97 72	91.74 79	85.76 161	94.95 96	84.27 185	91.60 61	97.61 42	97.38 36	98.87 5	95.18 63

v8		93.60 85	93.82 95	93.34 84	93.13 140	95.06 86	96.39 78	90.75 95	89.90 117	94.03 43	97.70 34	98.21 35	91.08 74	92.36 139	91.47 143	94.63 146	92.07 123

MCST-MVS		93.60 85	93.40 110	93.83 72	95.30 79	95.40 79	96.49 73	90.87 94	90.08 112	91.72 101	90.28 149	95.99 104	91.69 59	93.94 122	92.99 122	96.93 79	95.13 64

PVSNet_Blended_VisFu		93.60 85	93.41 109	93.83 72	96.31 52	95.65 73	95.71 95	90.58 100	88.08 134	93.17 64	95.29 89	92.20 153	90.72 80	94.69 108	93.41 119	96.51 88	94.54 77

TransMVSNet (Re)		93.55 88	96.32 35	90.32 136	94.38 104	94.05 111	93.30 148	89.53 120	97.15 9	85.12 166	98.83 4	97.89 47	82.21 156	96.75 65	96.14 63	97.35 65	93.46 97

DCV-MVSNet		93.49 89	95.15 66	91.55 116	94.05 112	95.92 64	95.15 107	91.21 87	92.76 62	87.01 157	89.71 154	97.16 70	83.90 145	97.65 41	96.87 45	97.99 43	95.95 49

v2v482		93.42 90	93.49 106	93.32 85	93.44 132	94.05 111	96.36 81	89.76 114	91.41 91	95.24 22	97.63 37	98.34 29	90.44 94	91.65 151	91.76 138	94.69 143	89.62 149

canonicalmvs		93.38 91	94.36 82	92.24 107	93.94 118	96.41 51	94.18 132	90.47 101	93.07 57	88.47 148	88.66 165	93.78 143	88.80 108	95.74 85	95.75 73	97.57 55	97.13 18

3Dnovator	91.81 5	93.36 92	94.27 86	92.29 106	92.99 144	95.03 87	95.76 92	87.79 143	93.82 45	92.38 82	92.19 132	93.37 148	88.14 117	95.26 96	94.85 91	96.69 83	95.40 57

pm-mvs1		93.27 93	95.94 48	90.16 137	94.13 110	93.66 122	92.61 161	89.91 112	95.73 16	84.28 175	98.51 14	98.29 30	82.80 151	96.44 73	95.76 72	97.25 69	93.21 101

Anonymous20231211		93.19 94	95.50 60	90.49 133	93.77 125	95.29 82	94.36 129	90.04 109	91.44 90	84.59 170	96.72 58	97.65 59	82.45 155	97.25 48	96.32 58	97.74 49	93.79 90

TinyColmap		93.17 95	93.33 111	93.00 98	93.84 121	92.76 135	94.75 119	88.90 131	93.97 43	97.48 4	95.28 91	95.29 122	88.37 113	95.31 95	91.58 141	94.65 145	89.10 153

MVS_111021_LR		93.15 96	93.65 100	92.56 101	93.89 120	92.28 142	95.09 108	86.92 159	91.26 96	92.99 69	94.46 105	96.22 96	90.64 85	95.11 100	93.45 118	95.85 115	92.74 112

CNLPA		93.14 97	93.67 99	92.53 102	94.62 98	94.73 96	95.00 111	86.57 164	92.85 59	92.43 80	90.94 139	94.67 131	90.35 95	95.41 90	93.70 114	96.23 101	93.37 99

PLC	87.27 15	93.08 98	92.92 115	93.26 90	94.67 95	95.03 87	94.38 124	90.10 104	91.69 80	92.14 86	87.24 179	93.91 141	91.61 60	95.05 102	94.73 98	96.67 84	92.80 108
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CANet		93.07 99	93.05 114	93.10 95	95.90 66	95.41 78	95.88 89	91.94 74	84.77 159	93.36 57	94.05 111	95.25 125	86.25 130	94.33 114	93.94 108	95.30 125	93.58 95

TSAR-MVS + COLMAP		93.06 100	93.65 100	92.36 104	94.62 98	94.28 108	95.36 106	89.46 123	92.18 73	91.64 102	95.55 82	95.27 124	88.60 111	93.24 128	92.50 127	94.46 148	92.55 118

Effi-MVS+		92.93 101	92.16 127	93.83 72	94.29 105	93.53 129	95.04 110	92.98 50	85.27 156	94.46 33	90.24 150	95.34 119	89.99 98	93.72 123	94.23 104	96.22 102	92.79 109

Fast-Effi-MVS+		92.93 101	92.64 119	93.27 88	93.81 122	93.88 117	95.90 87	90.61 98	83.98 165	92.71 71	92.81 124	96.22 96	90.67 82	94.90 104	93.92 109	95.92 112	92.77 110

DROMVSNet		92.93 101	92.64 119	93.27 88	93.81 122	93.88 117	95.90 87	90.61 98	83.98 165	92.71 71	92.81 124	96.22 96	90.67 82	94.90 104	93.92 109	95.92 112	92.77 110

HQP-MVS		92.87 104	92.49 121	93.31 86	95.75 72	95.01 90	95.64 98	91.06 92	88.54 129	91.62 103	88.16 170	96.25 94	89.47 103	92.26 141	91.81 136	96.34 95	95.40 57

FMVSNet1		92.86 105	95.26 64	90.06 139	92.40 158	95.16 83	94.37 125	92.22 60	93.18 54	82.16 185	96.76 57	97.48 63	81.85 160	95.32 92	94.98 87	97.34 66	93.93 88

CLD-MVS		92.81 106	94.32 83	91.05 124	95.39 78	95.31 81	95.82 91	81.44 198	89.40 122	91.94 91	95.86 72	97.36 64	85.83 132	95.35 91	94.59 100	95.85 115	92.34 120
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
IS_MVSNet		92.76 107	93.25 112	92.19 108	94.91 91	95.56 74	95.86 90	92.12 66	88.10 133	82.71 180	93.15 122	88.30 173	88.86 107	97.29 45	96.95 44	98.66 11	93.38 98

FC-MVSNet-train		92.75 108	95.40 62	89.66 147	95.21 84	94.82 94	97.00 56	89.40 124	91.13 97	81.71 186	97.72 33	96.43 90	77.57 183	96.89 59	96.72 48	97.05 75	94.09 84

V42		92.67 109	93.50 105	91.71 114	91.41 172	92.96 133	95.71 95	85.00 176	89.67 120	93.22 62	97.67 35	98.01 44	91.02 77	92.65 134	92.12 132	93.86 156	91.42 136

PM-MVS		92.65 110	93.20 113	92.00 110	92.11 166	90.16 168	95.99 86	84.81 180	91.31 94	92.41 81	95.87 71	96.64 87	92.35 47	93.65 125	92.91 123	94.34 151	91.85 128

QAPM		92.57 111	93.51 104	91.47 118	92.91 146	94.82 94	93.01 153	87.51 147	91.49 86	91.21 112	92.24 130	91.70 156	88.74 109	94.54 111	94.39 103	95.41 123	95.37 60

MIMVSNet1		92.52 112	94.88 71	89.77 143	96.09 57	91.99 148	96.92 58	89.68 117	95.92 15	84.55 171	96.64 60	98.21 35	78.44 177	96.08 78	95.10 83	92.91 170	90.22 146

tfpnnormal		92.45 113	94.77 74	89.74 144	93.95 117	93.44 131	93.25 149	88.49 137	95.27 22	83.20 178	96.51 62	96.23 95	83.17 149	95.47 89	94.52 101	96.38 92	91.97 126

PCF-MVS	87.46 14	92.44 114	91.80 129	93.19 93	94.66 96	95.80 68	96.37 79	90.19 103	87.57 138	92.23 85	89.26 159	93.97 140	89.24 104	91.32 155	90.82 151	96.46 91	93.86 89
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		92.42 115	93.99 89	90.60 131	93.25 136	93.82 120	94.28 131	88.73 133	91.53 84	84.53 173	97.74 31	98.64 20	86.60 127	93.21 130	91.20 146	96.21 103	91.76 134

AdaColmap		92.41 116	91.49 134	93.48 82	95.96 64	95.02 89	95.37 105	91.73 81	87.97 136	91.28 109	82.82 202	91.04 160	90.62 87	95.82 84	95.07 84	95.95 111	92.67 113

v148		92.38 117	92.78 117	91.91 111	92.86 147	92.13 145	94.84 113	87.03 156	91.47 88	93.07 68	96.92 54	98.89 12	90.10 97	92.05 144	89.69 159	93.56 159	88.27 162

pmmvs-eth3d		92.34 118	92.33 122	92.34 105	92.67 151	90.67 162	96.37 79	89.06 128	90.98 101	93.60 54	97.13 50	97.02 74	88.29 114	90.20 162	91.42 144	94.07 154	88.89 157

DELS-MVS		92.33 119	93.61 103	90.83 127	92.84 148	95.13 85	94.76 118	87.22 155	87.78 137	88.42 150	95.78 76	95.28 123	85.71 135	94.44 112	93.91 111	96.01 109	92.97 106
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
Effi-MVS+-dtu		92.32 120	91.66 132	93.09 96	95.13 87	94.73 96	94.57 122	92.14 65	81.74 177	90.33 126	88.13 171	95.91 105	89.24 104	94.23 119	93.65 116	97.12 72	93.23 100

UGNet		92.31 121	94.70 75	89.53 149	90.99 180	95.53 75	96.19 83	92.10 68	91.35 93	85.76 161	95.31 88	95.48 114	76.84 188	95.22 97	94.79 94	95.32 124	95.19 62
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
USDC		92.17 122	92.17 126	92.18 109	92.93 145	92.22 143	93.66 139	87.41 150	93.49 47	97.99 1	94.10 110	96.68 86	86.46 128	92.04 145	89.18 165	94.61 147	87.47 165

ETV-MVS		92.12 123	90.44 141	94.08 61	96.36 50	93.63 124	96.27 82	92.00 71	78.90 197	92.13 87	85.29 193	89.85 166	90.26 96	97.07 52	96.29 60	97.46 57	92.04 124

IterMVS-LS		92.10 124	92.33 122	91.82 113	93.18 137	93.66 122	92.80 159	92.27 59	90.82 104	90.59 121	97.19 47	90.97 161	87.76 120	89.60 169	90.94 150	94.34 151	93.16 103
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		92.09 125	92.84 116	91.22 123	92.55 153	92.97 132	93.42 144	85.43 174	90.24 111	91.83 97	94.70 99	94.59 132	88.48 112	94.91 103	93.31 121	95.59 121	89.15 152

CS-MVS		92.07 126	91.69 130	92.52 103	93.80 124	94.30 107	96.15 85	86.55 165	79.55 187	91.47 105	89.10 162	95.33 120	89.78 102	95.88 82	95.85 70	97.40 61	91.81 131

EIA-MVS		91.95 127	90.36 143	93.81 75	96.54 45	94.65 98	95.38 104	90.40 102	78.01 202	93.72 50	86.70 186	91.95 155	89.93 99	95.67 87	94.72 99	96.89 80	90.79 140

MAR-MVS		91.86 128	91.14 137	92.71 99	94.29 105	94.24 109	94.91 112	91.82 77	81.66 178	93.32 58	84.51 196	93.42 147	86.86 125	95.16 99	94.44 102	95.05 138	94.53 78
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
EU-MVSNet		91.63 129	92.73 118	90.35 135	88.36 199	87.89 179	96.53 71	81.51 197	92.45 66	91.82 98	96.44 65	97.05 73	93.26 32	94.10 120	88.94 170	90.61 177	92.24 121

FC-MVSNet-test		91.49 130	94.43 80	88.07 165	94.97 89	90.53 165	95.42 103	91.18 89	93.24 52	72.94 207	98.37 16	93.86 142	78.78 171	97.82 34	96.13 64	95.13 133	91.05 137

OpenMVS	89.22 12	91.09 131	91.42 135	90.71 129	92.79 150	93.61 126	92.74 160	85.47 173	86.10 151	90.73 116	85.71 192	93.07 151	86.69 126	94.07 121	93.34 120	95.86 114	94.02 86

FPMVS		90.81 132	91.60 133	89.88 142	92.52 154	88.18 175	93.31 147	83.62 186	91.59 83	88.45 149	88.96 163	89.73 168	86.96 123	96.42 74	95.69 74	94.43 149	90.65 141

DI_MVS_plusplus_trai		90.68 133	90.40 142	91.00 125	92.43 157	92.61 139	94.17 133	88.98 129	88.32 131	88.76 146	93.67 117	87.58 175	86.44 129	89.74 167	90.33 154	95.24 128	90.56 144

Vis-MVSNet (Re-imp)		90.68 133	92.18 125	88.92 154	94.63 97	92.75 136	92.91 155	91.20 88	89.21 124	75.01 204	93.96 115	89.07 171	82.72 153	95.88 82	95.30 79	97.08 74	89.08 154

DPM-MVS		90.67 135	89.86 147	91.63 115	95.29 82	94.16 110	94.52 123	89.63 118	89.59 121	89.67 135	81.95 204	88.64 172	85.75 134	90.46 160	90.43 153	94.91 141	93.77 91

diffmvs		90.44 136	92.23 124	88.35 161	91.36 174	91.38 154	92.45 165	84.84 179	89.88 118	85.09 167	96.69 59	97.71 57	83.33 148	90.01 166	88.96 169	93.03 168	91.00 138

FMVSNet2		90.28 137	92.04 128	88.23 163	91.22 176	94.05 111	92.88 156	90.69 96	86.53 147	79.89 193	94.38 106	92.73 152	78.54 174	91.64 152	92.26 130	96.17 104	92.67 113

IterMVS-SCA-FT		90.24 138	89.37 153	91.26 122	92.50 155	92.11 146	91.69 175	87.48 148	87.05 143	91.82 98	95.76 77	87.25 176	91.36 64	89.02 174	85.53 185	92.68 171	88.90 156

MVS_Test		90.19 139	90.58 138	89.74 144	92.12 165	91.74 150	92.51 162	88.54 136	82.80 172	87.50 154	94.62 100	95.02 129	83.97 143	88.69 177	89.32 163	93.79 157	91.85 128

EPNet		90.17 140	89.07 155	91.45 119	97.25 19	90.62 164	94.84 113	93.54 45	80.96 180	91.85 96	86.98 182	85.88 181	77.79 180	92.30 140	92.58 126	93.41 161	94.20 83
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		90.09 141	90.12 145	90.05 140	92.40 158	92.74 137	91.74 171	85.89 169	80.54 183	90.30 127	88.54 166	95.51 112	84.69 139	92.64 135	90.25 155	95.28 126	90.61 142

PVSNet_Blended		90.09 141	90.12 145	90.05 140	92.40 158	92.74 137	91.74 171	85.89 169	80.54 183	90.30 127	88.54 166	95.51 112	84.69 139	92.64 135	90.25 155	95.28 126	90.61 142

pmmvs4		89.95 143	89.32 154	90.69 130	91.60 171	89.17 172	94.37 125	87.63 144	88.07 135	91.02 114	94.50 103	90.50 164	86.13 131	86.33 191	89.40 162	93.39 162	87.29 168

MDA-MVSNet-bldmvs		89.75 144	91.67 131	87.50 170	74.25 217	90.88 159	94.68 120	85.89 169	91.64 81	91.03 113	95.86 72	94.35 137	89.10 106	96.87 61	86.37 181	90.04 178	85.72 173

tttt0517		89.64 145	88.05 166	91.49 117	93.52 130	91.65 151	93.67 138	87.53 145	82.77 173	89.39 139	90.37 148	70.05 210	88.21 115	93.71 124	93.79 112	96.63 85	94.04 85

PatchMatch-RL		89.59 146	88.80 159	90.51 132	92.20 164	88.00 178	91.72 173	86.64 161	84.75 160	88.25 151	87.10 181	90.66 163	89.85 101	93.23 129	92.28 129	94.41 150	85.60 174

Fast-Effi-MVS+-dtu		89.57 147	88.42 163	90.92 126	93.35 134	91.57 152	93.01 153	95.71 9	78.94 196	87.65 153	84.68 195	93.14 150	82.00 158	90.84 158	91.01 149	93.78 158	88.77 158

thisisatest0530		89.54 148	87.99 168	91.35 121	93.17 138	91.31 155	93.45 143	87.53 145	82.96 171	89.17 141	90.45 145	70.32 209	88.21 115	93.37 127	93.79 112	96.54 87	93.71 92

GBi-Net		89.35 149	90.58 138	87.91 166	91.22 176	94.05 111	92.88 156	90.05 106	79.40 188	78.60 195	90.58 141	87.05 177	78.54 174	95.32 92	94.98 87	96.17 104	92.67 113

test1		89.35 149	90.58 138	87.91 166	91.22 176	94.05 111	92.88 156	90.05 106	79.40 188	78.60 195	90.58 141	87.05 177	78.54 174	95.32 92	94.98 87	96.17 104	92.67 113

thres600view7		89.14 151	88.83 157	89.51 150	93.71 129	93.55 127	93.93 136	88.02 141	87.30 140	82.40 181	81.18 205	80.63 196	82.69 154	94.27 116	95.90 67	96.27 99	88.94 155

CVMVSNet		88.97 152	89.73 149	88.10 164	87.33 205	85.22 188	94.68 120	78.68 199	88.94 126	86.98 158	95.55 82	85.71 182	89.87 100	91.19 156	89.69 159	91.05 175	91.78 132

CANet_DTU		88.95 153	89.51 152	88.29 162	93.12 141	91.22 157	93.61 140	83.47 189	80.07 186	90.71 120	89.19 160	93.68 145	76.27 192	91.44 154	91.17 148	92.59 172	89.83 148

GA-MVS		88.76 154	88.04 167	89.59 148	92.32 161	91.46 153	92.28 167	86.62 162	83.82 168	89.84 131	92.51 129	81.94 190	83.53 147	89.41 171	89.27 164	92.95 169	87.90 163

pmmvs5		88.63 155	89.70 150	87.39 171	89.24 192	90.64 163	91.87 170	82.13 193	83.34 169	87.86 152	94.58 101	96.15 100	79.87 168	87.33 186	89.07 168	93.39 162	86.76 169

thres400		88.54 156	88.15 165	88.98 152	93.17 138	92.84 134	93.56 141	86.93 158	86.45 148	82.37 182	79.96 207	81.46 193	81.83 161	93.21 130	94.76 96	96.04 108	88.39 160

CDS-MVSNet		88.41 157	89.79 148	86.79 175	94.55 102	90.82 160	92.50 163	89.85 113	83.26 170	80.52 190	91.05 137	89.93 165	69.11 203	93.17 132	92.71 125	94.21 153	87.63 164
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gg-mvs-nofinetune		88.32 158	88.81 158	87.75 168	93.07 142	89.37 171	89.06 194	95.94 8	95.29 20	87.15 155	97.38 42	76.38 199	68.05 206	91.04 157	89.10 167	93.24 164	83.10 182

IterMVS		88.32 158	88.25 164	88.41 160	90.83 182	91.24 156	93.07 152	81.69 195	86.77 145	88.55 147	95.61 78	86.91 180	87.01 122	87.38 185	83.77 187	89.29 180	86.06 172
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres200		88.29 160	87.88 169	88.76 156	92.50 155	93.55 127	92.47 164	88.02 141	84.80 158	81.44 187	79.28 209	82.20 189	81.83 161	94.27 116	93.67 115	96.27 99	87.40 166

IB-MVS	86.01 17	88.24 161	87.63 171	88.94 153	92.03 167	91.77 149	92.40 166	85.58 172	78.24 199	84.85 168	71.99 213	93.45 146	83.96 144	93.48 126	92.33 128	94.84 142	92.15 122
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
MDTV_nov1_ep13_2view		88.22 162	87.85 170	88.65 158	91.40 173	86.75 183	94.07 134	84.97 177	88.86 128	93.20 63	96.11 70	96.21 99	83.70 146	87.29 187	80.29 194	84.56 198	79.46 195

test20.03		88.20 163	91.26 136	84.63 187	96.64 42	89.39 170	90.73 182	89.97 111	91.07 99	72.02 209	94.98 95	95.45 115	69.35 202	92.70 133	91.19 147	89.06 182	84.02 176

HyFIR lowres test		88.19 164	86.56 178	90.09 138	91.24 175	92.17 144	94.30 130	88.79 132	84.06 162	85.45 164	89.52 157	85.64 183	88.64 110	85.40 194	87.28 175	92.14 174	81.87 185

ET-MVSNet_ETH3D		88.06 165	85.75 182	90.74 128	92.82 149	90.68 161	93.77 137	88.59 134	81.22 179	89.78 133	89.15 161	66.79 217	84.29 142	91.72 150	91.34 145	95.22 129	89.36 151

tfpn200view9		87.94 166	87.51 173	88.44 159	92.28 162	93.63 124	93.35 146	88.11 139	80.90 181	80.89 188	78.25 210	82.25 187	79.65 170	94.27 116	94.76 96	96.36 93	88.48 159

FMVSNet3		87.90 167	88.63 161	87.04 172	89.78 190	93.46 130	91.62 176	90.05 106	79.40 188	78.60 195	90.58 141	87.05 177	77.07 187	88.03 182	89.86 158	95.12 134	92.04 124

MS-PatchMatch		87.72 168	88.62 162	86.66 176	90.81 183	88.18 175	90.92 179	82.25 192	85.86 153	80.40 191	90.14 152	89.29 170	84.93 136	89.39 172	89.12 166	90.67 176	88.34 161

Anonymous20231206		87.45 169	89.66 151	84.87 184	94.00 113	87.73 181	91.36 177	86.41 167	88.89 127	75.03 203	92.59 128	96.82 81	72.48 200	89.72 168	88.06 172	89.93 179	83.81 178

EPNet_dtu		87.40 170	86.27 179	88.72 157	95.68 74	83.37 194	92.09 169	90.08 105	78.11 201	91.29 108	86.33 187	89.74 167	75.39 195	89.07 173	87.89 173	87.81 187	89.38 150
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
baseline1		86.96 171	87.58 172	86.24 178	93.07 142	90.44 166	89.24 193	86.85 160	85.14 157	77.26 201	90.45 145	76.09 201	75.79 193	91.80 149	91.81 136	95.20 130	87.35 167

baseline		86.71 172	88.89 156	84.16 189	87.85 201	85.23 187	89.82 187	77.69 202	84.03 164	84.75 169	94.91 97	94.59 132	77.19 186	86.57 190	86.51 180	87.66 190	90.36 145

CHOSEN 1792x2688		86.64 173	86.62 176	86.65 177	90.33 186	87.86 180	93.19 150	83.30 190	83.95 167	82.32 183	87.93 173	89.34 169	86.92 124	85.64 193	84.95 186	83.85 202	86.68 170

testgi		86.49 174	90.31 144	82.03 193	95.63 75	88.18 175	93.47 142	84.89 178	93.23 53	69.54 213	87.16 180	97.96 46	60.66 210	91.90 148	89.90 157	87.99 185	83.84 177

thres100view900		86.46 175	86.00 181	86.99 173	92.28 162	91.03 158	91.09 178	84.49 182	80.90 181	80.89 188	78.25 210	82.25 187	77.57 183	90.17 163	92.84 124	95.63 119	86.57 171

gm-plane-assit		86.15 176	82.51 190	90.40 134	95.81 70	92.29 141	97.99 34	84.66 181	92.15 74	93.15 65	97.84 29	44.65 224	78.60 173	88.02 183	85.95 182	92.20 173	76.69 203

CMPMVS	66.55 18	85.55 177	87.46 174	83.32 190	84.99 207	81.97 199	79.19 214	75.93 204	79.32 191	88.82 144	85.09 194	91.07 159	82.12 157	92.56 137	89.63 161	88.84 183	92.56 117
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CR-MVSNet		85.32 178	81.58 192	89.69 146	90.36 185	84.79 190	86.72 205	92.22 60	75.38 207	90.73 116	90.41 147	67.88 214	84.86 137	83.76 197	85.74 183	93.24 164	83.14 180

baseline2		84.95 179	82.68 189	87.59 169	92.64 152	88.41 174	90.09 184	84.25 183	75.88 205	85.23 165	82.49 203	71.15 207	80.14 167	88.21 181	87.21 178	93.21 167	85.39 175

pmnet_mix02		84.85 180	86.58 177	82.83 191	90.19 187	81.10 202	88.52 197	78.58 200	91.50 85	80.32 192	96.48 63	95.86 106	75.42 194	85.17 195	76.44 203	83.91 201	79.51 194

MVSTER		84.79 181	83.79 185	85.96 180	89.14 193	89.80 169	89.39 191	82.99 191	74.16 211	82.78 179	85.97 190	66.81 216	76.84 188	90.77 159	88.83 171	94.66 144	90.19 147

MIMVSNet		84.76 182	86.75 175	82.44 192	91.71 170	85.95 185	89.74 189	89.49 121	85.28 155	69.69 212	87.93 173	90.88 162	64.85 208	88.26 180	87.74 174	89.18 181	81.24 186

SCA		84.69 183	81.10 193	88.87 155	89.02 194	90.31 167	92.21 168	92.09 69	82.72 174	89.68 134	86.83 184	73.08 203	85.80 133	80.50 205	77.51 200	84.45 200	76.80 202

new-patchmatchnet		84.45 184	88.75 160	79.43 199	93.28 135	81.87 200	81.68 211	83.48 188	94.47 29	71.53 210	98.33 17	97.88 50	58.61 213	90.35 161	77.33 201	87.99 185	81.05 188

PatchT		83.44 185	81.10 193	86.18 179	77.92 215	82.58 198	89.87 186	87.39 151	75.88 205	90.73 116	89.86 153	66.71 218	84.86 137	83.76 197	85.74 183	86.33 195	83.14 180

RPMNet		83.42 186	78.40 202	89.28 151	89.79 189	84.79 190	90.64 183	92.11 67	75.38 207	87.10 156	79.80 208	61.99 223	82.79 152	81.88 203	82.07 191	93.23 166	82.87 183

TAMVS		82.96 187	86.15 180	79.24 202	90.57 184	83.12 197	87.29 201	75.12 206	84.06 162	65.81 214	92.22 131	88.27 174	69.11 203	88.72 175	87.26 177	87.56 191	79.38 196

PatchmatchNet		82.44 188	78.69 201	86.83 174	89.81 188	81.55 201	90.78 181	87.27 154	82.39 176	88.85 143	88.31 169	70.96 208	81.90 159	78.58 209	74.33 209	82.35 206	74.69 206
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13		82.33 189	79.66 196	85.45 182	88.83 196	83.88 192	90.09 184	81.98 194	79.07 195	88.82 144	88.70 164	73.77 202	78.41 178	80.29 207	76.08 204	84.56 198	75.83 204

CostFormer		82.15 190	79.54 197	85.20 183	88.92 195	85.70 186	90.87 180	86.26 168	79.19 194	83.87 176	87.89 175	69.20 212	76.62 190	77.50 212	75.28 206	84.69 197	82.02 184

PMMVS		81.93 191	83.48 187	80.12 198	72.35 218	75.05 211	88.54 196	64.01 211	77.02 204	82.22 184	87.51 177	91.12 158	79.70 169	86.59 188	86.64 179	93.88 155	80.41 189

pmmvs3		81.69 192	83.83 184	79.19 203	78.33 214	78.57 205	89.53 190	58.71 214	78.88 198	84.34 174	88.36 168	91.96 154	77.69 182	87.48 184	82.42 190	86.54 194	79.18 197

tpm		81.58 193	78.84 199	84.79 186	91.11 179	79.50 203	89.79 188	83.75 184	79.30 192	92.05 89	90.98 138	64.78 220	74.54 196	80.50 205	76.67 202	77.49 211	80.15 192

test0.0.03 1		81.51 194	83.30 188	79.42 200	93.99 114	86.50 184	85.93 209	87.32 152	78.16 200	61.62 215	80.78 206	81.78 191	59.87 211	88.40 179	87.27 176	87.78 189	80.19 191

dps		81.42 195	77.88 207	85.56 181	87.67 203	85.17 189	88.37 199	87.46 149	74.37 210	84.55 171	86.80 185	62.18 222	80.20 166	81.13 204	77.52 199	85.10 196	77.98 200

test-LLR		80.62 196	77.20 210	84.62 188	93.99 114	75.11 209	87.04 202	87.32 152	70.11 214	78.59 198	83.17 200	71.60 205	73.88 198	82.32 201	79.20 196	86.91 192	78.87 198

tpm cat1		80.03 197	75.93 213	84.81 185	89.31 191	83.26 196	88.86 195	86.55 165	79.24 193	86.10 160	84.22 197	63.62 221	77.37 185	73.43 213	70.88 212	80.67 207	76.87 201

N_pmnet		79.33 198	84.22 183	73.62 209	91.72 169	73.72 212	86.11 207	76.36 203	92.38 67	53.38 216	95.54 84	95.62 110	59.14 212	84.23 196	74.84 208	75.03 214	73.25 210

EPMVS		79.26 199	78.20 205	80.49 196	87.04 206	78.86 204	86.08 208	83.51 187	82.63 175	73.94 206	89.59 155	68.67 213	72.03 201	78.17 210	75.08 207	80.37 208	74.37 207

CHOSEN 280x420		79.24 200	78.26 204	80.38 197	79.60 213	68.80 217	89.32 192	75.38 205	77.25 203	78.02 200	75.57 212	76.17 200	81.19 164	88.61 178	81.39 192	78.79 209	80.03 193

ADS-MVSNet		79.11 201	79.38 198	78.80 205	81.90 211	75.59 208	84.36 210	83.69 185	87.31 139	76.76 202	87.58 176	76.90 198	68.55 205	78.70 208	75.56 205	77.53 210	74.07 208

FMVSNet5		79.08 202	78.83 200	79.38 201	87.52 204	86.78 182	87.64 200	78.15 201	69.54 216	70.64 211	65.97 216	65.44 219	63.87 209	90.17 163	90.46 152	88.48 184	83.45 179

tpmrst		78.81 203	76.18 212	81.87 194	88.56 197	77.45 206	86.74 204	81.52 196	80.08 185	83.48 177	90.84 140	66.88 215	74.54 196	73.04 214	71.02 211	76.38 212	73.95 209

test-mter		78.71 204	78.35 203	79.12 204	84.03 208	76.58 207	88.51 198	59.06 213	71.06 212	78.87 194	83.73 199	71.83 204	76.44 191	83.41 200	80.61 193	87.79 188	81.24 186

MVS-HIRNet		78.28 205	75.28 214	81.79 195	80.33 212	69.38 216	76.83 215	86.59 163	70.76 213	86.66 159	89.57 156	81.04 194	77.74 181	77.81 211	71.65 210	82.62 204	66.73 214

E-PMN		77.81 206	77.88 207	77.73 208	88.26 200	70.48 215	80.19 213	71.20 208	86.66 146	72.89 208	88.09 172	81.74 192	78.75 172	90.02 165	68.30 213	75.10 213	59.85 215

EMVS		77.65 207	77.49 209	77.83 206	87.75 202	71.02 214	81.13 212	70.54 209	86.38 149	74.52 205	89.38 158	80.19 197	78.22 179	89.48 170	67.13 214	74.83 215	58.84 216

TESTMET0.1,1		77.47 208	77.20 210	77.78 207	81.94 210	75.11 209	87.04 202	58.33 215	70.11 214	78.59 198	83.17 200	71.60 205	73.88 198	82.32 201	79.20 196	86.91 192	78.87 198

new_pmnet		76.65 209	83.52 186	68.63 210	82.60 209	72.08 213	76.76 216	64.17 210	84.41 161	49.73 218	91.77 134	91.53 157	56.16 214	86.59 188	83.26 189	82.37 205	75.02 205

MVE	60.41 19	73.21 210	80.84 195	64.30 211	56.34 219	57.24 219	75.28 218	72.76 207	87.14 142	41.39 220	86.31 188	85.30 184	80.66 165	86.17 192	83.36 188	59.35 217	80.38 190
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		69.86 211	82.14 191	55.52 212	75.19 216	63.08 218	75.52 217	60.97 212	88.50 130	25.11 222	91.77 134	96.44 89	25.43 216	88.70 176	79.34 195	70.93 216	67.17 213

GG-mvs-BLEND		54.28 212	77.89 206	26.72 215	0.37 224	83.31 195	70.04 219	0.39 221	74.71 209	5.36 223	68.78 214	83.06 186	0.62 220	83.73 199	78.99 198	83.55 203	72.68 212

test_method		43.16 213	51.13 215	33.85 213	7.35 221	12.38 222	51.70 221	11.91 217	62.51 218	47.64 219	62.49 217	80.78 195	28.84 215	59.55 217	34.48 216	55.68 218	45.72 217

testmvs		2.38 214	3.35 216	1.26 217	0.83 222	0.96 224	1.53 224	0.83 219	3.59 220	1.63 225	6.03 219	2.93 226	1.55 219	3.49 218	2.51 218	1.21 222	3.92 219

test123		2.16 215	2.82 217	1.41 216	0.62 223	1.18 223	1.53 224	0.82 220	2.78 221	2.27 224	4.18 220	1.98 227	1.64 218	2.58 219	3.01 217	1.56 221	4.00 218

uanet_test		0.00 216	0.00 218	0.00 218	0.00 225	0.00 225	0.00 226	0.00 222	0.00 222	0.00 226	0.00 221	0.00 228	0.00 221	0.00 220	0.00 219	0.00 223	0.00 220

sosnet-low-res		0.00 216	0.00 218	0.00 218	0.00 225	0.00 225	0.00 226	0.00 222	0.00 222	0.00 226	0.00 221	0.00 228	0.00 221	0.00 220	0.00 219	0.00 223	0.00 220

sosnet		0.00 216	0.00 218	0.00 218	0.00 225	0.00 225	0.00 226	0.00 222	0.00 222	0.00 226	0.00 221	0.00 228	0.00 221	0.00 220	0.00 219	0.00 223	0.00 220

RE-MVS-def										97.21 5

9.14												93.19 149

SR-MVS					97.13 23			94.77 17				97.77 54

Anonymous202405211			94.63 76		94.51 103	94.96 92	93.94 135	91.35 86	90.82 104		95.60 80	95.85 107	81.74 163	96.47 72	95.84 71	97.39 63	92.85 107

our_test_3					91.78 168	88.87 173	94.37 125

ambc			94.61 77		98.09 5	95.14 84	91.71 174		94.18 38	96.46 12	96.26 66	96.30 92	91.26 67	94.70 107	92.00 135	93.45 160	93.67 93

MTAPA										94.88 28		96.88 79

MTMP										95.43 18		97.25 66

Patchmatch-RL test							8.96 223

tmp_tt				28.44 214	36.05 220	15.86 221	21.29 222	6.40 218	54.52 219	51.96 217	50.37 218	38.68 225	9.55 217	61.75 216	59.66 215	45.36 220

XVS					96.86 32	97.48 18	98.73 3			93.28 59		96.82 81				98.17 35

X-MVStestdata					96.86 32	97.48 18	98.73 3			93.28 59		96.82 81				98.17 35

abl_6				91.88 112	93.76 126	94.98 91	95.64 98	88.97 130	86.20 150	90.00 130	86.31 188	94.50 135	87.31 121			95.60 120	92.48 119

mPP-MVS					98.24 3							97.65 59

NP-MVS									85.48 154

Patchmtry						83.74 193	86.72 205	92.22 60		90.73 116

DeepMVS_CX						47.68 220	53.20 220	19.21 216	63.24 217	26.96 221	66.50 215	69.82 211	66.91 207	64.27 215		54.91 219	72.72 211

High-resolution multi-view benchmark