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		93.16 1	95.57 1	90.36 1	88.79 52	93.57 1	97.27 1	78.23 22	95.55 1	93.00 1	93.98 15	96.01 38	87.53 1	97.69 1	96.81 1	97.33 1	95.34 3

COLMAP_ROB	85.66 2	91.85 2	95.01 2	88.16 12	88.98 51	92.86 2	95.51 20	72.17 58	94.95 4	91.27 3	94.11 14	97.77 11	84.22 8	96.49 4	95.27 5	96.79 2	93.60 11
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UA-Net		89.02 33	91.44 37	86.20 28	94.88 1	89.84 33	94.76 28	77.45 29	85.41 70	74.79 100	88.83 75	88.90 131	78.67 40	96.06 7	95.45 4	96.66 3	95.58 1

SD-MVS		89.91 18	92.23 28	87.19 22	91.31 24	89.79 34	94.31 31	75.34 46	89.26 36	81.79 67	92.68 29	95.08 61	83.88 11	93.10 39	92.69 26	96.54 4	93.02 23
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
WR-MVS		89.79 23	93.66 4	85.27 37	91.32 23	88.27 44	93.49 37	79.86 10	92.75 8	75.37 96	96.86 1	98.38 5	75.10 68	95.93 8	94.07 15	96.46 5	89.39 57

anonymousdsp		85.62 59	90.53 46	79.88 90	64.64 199	76.35 136	96.28 13	53.53 185	85.63 67	81.59 69	92.81 28	97.71 13	86.88 2	94.56 26	92.83 25	96.35 6	93.84 8

ACMMP		90.63 8	92.40 19	88.56 9	91.24 28	91.60 6	96.49 9	77.53 27	87.89 47	86.87 30	87.24 89	96.46 25	82.87 16	95.59 15	94.50 9	96.35 6	93.51 17
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
LGP-MVS_train		90.56 9	92.38 20	88.43 10	90.88 32	91.15 11	95.35 22	77.65 26	86.26 63	87.23 24	90.45 52	97.35 17	83.20 14	95.44 16	93.41 21	96.28 8	92.63 26

ACMM	80.67 7	90.67 7	92.46 18	88.57 8	91.35 22	89.93 31	96.34 12	77.36 31	90.17 27	86.88 29	87.32 87	96.63 23	83.32 13	95.79 10	94.49 10	96.19 9	92.91 25
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	80.00 8	90.12 16	92.30 24	87.58 19	90.83 34	91.10 12	94.96 27	76.06 41	87.47 51	85.33 39	88.91 74	97.65 15	82.13 20	95.31 17	93.44 20	96.14 10	92.22 33
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMMPR		91.30 4	92.88 10	89.46 4	91.92 11	91.61 5	96.60 5	79.46 14	90.08 29	88.53 14	89.54 63	95.57 47	84.25 7	95.24 20	94.27 13	95.97 11	93.85 7

CSCG		88.12 44	91.45 36	84.23 47	88.12 61	90.59 25	90.57 59	68.60 85	91.37 14	83.45 52	89.94 56	95.14 60	78.71 38	91.45 57	88.21 72	95.96 12	93.44 19

LS3D		89.02 33	91.69 34	85.91 30	89.72 43	90.81 20	92.56 43	71.69 62	90.83 20	87.24 23	89.71 61	92.07 103	78.37 41	94.43 28	92.59 28	95.86 13	91.35 42

X-MVS		89.36 28	90.73 45	87.77 17	91.50 20	91.23 8	96.76 4	78.88 18	87.29 53	87.14 26	78.98 137	94.53 71	76.47 54	95.25 19	94.28 12	95.85 14	93.55 15

XVS					91.28 25	91.23 8	96.89 2			87.14 26		94.53 71				95.84 15

X-MVStestdata					91.28 25	91.23 8	96.89 2			87.14 26		94.53 71				95.84 15

HFP-MVS		90.32 13	92.37 21	87.94 14	91.46 21	90.91 18	95.69 18	79.49 12	89.94 32	83.50 50	89.06 70	94.44 74	81.68 23	94.17 31	94.19 14	95.81 17	93.87 6

CP-MVS		91.09 5	92.33 23	89.65 2	92.16 10	90.41 27	96.46 10	80.38 8	88.26 44	89.17 11	87.00 92	96.34 30	83.95 10	95.77 11	94.72 8	95.81 17	93.78 9

PGM-MVS		90.42 10	91.58 35	89.05 6	91.77 14	91.06 13	96.51 7	78.94 17	85.41 70	87.67 19	87.02 91	95.26 55	83.62 12	95.01 24	93.94 16	95.79 19	93.40 20

EPP-MVSNet		82.76 89	86.47 78	78.45 100	86.00 78	84.47 75	85.39 111	68.42 87	84.17 78	62.97 157	89.26 68	76.84 174	72.13 92	92.56 47	90.40 50	95.76 20	87.56 73

DeepC-MVS	83.59 4	90.37 12	92.56 17	87.82 15	91.26 27	92.33 3	94.72 29	80.04 9	90.01 30	84.61 42	93.33 20	94.22 77	80.59 28	92.90 42	92.52 29	95.69 21	92.57 27
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMH+	79.05 11	89.62 26	93.08 7	85.58 32	88.58 54	89.26 37	92.18 44	74.23 51	93.55 7	82.66 58	92.32 34	98.35 7	80.29 29	95.28 18	92.34 32	95.52 22	90.43 49

LTVRE_ROB	86.82 1	91.55 3	94.43 3	88.19 11	83.19 107	86.35 65	93.60 36	78.79 19	95.48 3	91.79 2	93.08 24	97.21 20	86.34 3	97.06 2	96.27 3	95.46 23	95.56 2
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
MP-MVS		90.84 6	91.95 32	89.55 3	92.92 5	90.90 19	96.56 6	79.60 11	86.83 58	88.75 13	89.00 71	94.38 76	84.01 9	94.94 25	94.34 11	95.45 24	93.24 22
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
3Dnovator+	83.71 3	88.13 43	90.00 50	85.94 29	86.82 70	91.06 13	94.26 32	75.39 45	88.85 40	85.76 37	85.74 105	86.92 140	78.02 43	93.03 40	92.21 35	95.39 25	92.21 34

CPTT-MVS		89.63 25	90.52 47	88.59 7	90.95 31	90.74 21	95.71 17	79.13 15	87.70 49	85.68 38	80.05 132	95.74 45	84.77 6	94.28 30	92.68 27	95.28 26	92.45 31

zzz-MVS		90.38 11	91.35 39	89.25 5	93.08 3	86.59 62	96.45 11	79.00 16	90.23 26	89.30 10	85.87 103	94.97 64	82.54 18	95.05 23	94.83 7	95.14 27	91.94 36

SixPastTwentyTwo		89.14 29	92.19 29	85.58 32	84.62 87	82.56 90	90.53 62	71.93 59	91.95 11	85.89 35	94.22 13	97.25 19	85.42 5	95.73 12	91.71 41	95.08 28	91.89 37

PMVS	79.51 9	90.23 14	92.67 13	87.39 21	90.16 39	88.75 40	93.64 35	75.78 43	90.00 31	83.70 47	92.97 26	92.22 100	86.13 4	97.01 3	96.79 2	94.94 29	90.96 46
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
TSAR-MVS + MP.		89.67 24	92.25 26	86.65 26	91.53 18	90.98 17	96.15 14	73.30 55	87.88 48	81.83 66	92.92 27	95.15 59	82.23 19	93.58 35	92.25 34	94.87 30	93.01 24
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
OMC-MVS		88.16 42	91.34 40	84.46 45	86.85 69	90.63 23	93.01 40	67.00 98	90.35 25	87.40 22	86.86 94	96.35 29	77.66 48	92.63 46	90.84 45	94.84 31	91.68 39

IS_MVSNet		81.72 97	85.01 95	77.90 103	86.19 75	82.64 89	85.56 109	70.02 70	80.11 117	63.52 155	87.28 88	81.18 159	67.26 120	91.08 66	89.33 63	94.82 32	83.42 100

SMA-MVS		90.13 15	92.26 25	87.64 18	91.68 16	90.44 26	95.22 24	77.34 33	90.79 21	87.80 17	90.42 53	92.05 105	79.05 35	93.89 33	93.59 19	94.77 33	94.62 4

APDe-MVS		89.85 20	92.91 9	86.29 27	90.47 38	91.34 7	96.04 15	76.41 40	91.11 16	78.50 86	93.44 19	95.82 42	81.55 24	93.16 38	91.90 39	94.77 33	93.58 14

SteuartSystems-ACMMP		90.00 17	91.73 33	87.97 13	91.21 29	90.29 28	96.51 7	78.00 24	86.33 61	85.32 40	88.23 79	94.67 69	82.08 21	95.13 22	93.88 17	94.72 35	93.59 12
Skip Steuart: Steuart Systems R&D Blog.
DPE-MVS		89.81 22	92.34 22	86.86 24	89.69 44	91.00 16	95.53 19	76.91 34	88.18 45	83.43 53	93.48 18	95.19 56	81.07 27	92.75 44	92.07 37	94.55 36	93.74 10

ACMMP_NAP		89.86 19	91.96 31	87.42 20	91.00 30	90.08 29	96.00 16	76.61 37	89.28 33	87.73 18	90.04 55	91.80 108	78.71 38	94.36 29	93.82 18	94.48 37	94.32 5

APD-MVS		89.14 29	91.25 42	86.67 25	91.73 15	91.02 15	95.50 21	77.74 25	84.04 81	79.47 81	91.48 42	94.85 66	81.14 26	92.94 41	92.20 36	94.47 38	92.24 32
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
RPSCF		88.05 45	92.61 16	82.73 65	84.24 92	88.40 42	90.04 72	66.29 103	91.46 12	82.29 60	88.93 73	96.01 38	79.38 32	95.15 21	94.90 6	94.15 39	93.40 20

OPM-MVS		89.82 21	92.24 27	86.99 23	90.86 33	89.35 36	95.07 26	75.91 42	91.16 15	86.87 30	91.07 48	97.29 18	79.13 34	93.32 36	91.99 38	94.12 40	91.49 41

TAPA-MVS	78.00 13	85.88 58	88.37 61	82.96 60	84.69 86	88.62 41	90.62 57	64.22 123	89.15 37	88.05 15	78.83 139	93.71 81	76.20 58	90.11 76	88.22 71	94.00 41	89.97 52
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
UniMVSNet (Re)		84.95 67	88.53 58	80.78 79	87.82 63	84.21 76	88.03 88	76.50 38	81.18 107	69.29 133	92.63 32	96.83 22	69.07 111	91.23 61	89.60 60	93.97 42	84.00 96

xxxxxxxxxxxxxcwj		88.03 46	91.29 41	84.22 48	88.17 59	87.90 51	90.80 54	71.80 60	89.28 33	82.70 56	89.90 57	97.72 12	77.91 45	91.69 52	90.04 53	93.95 43	92.47 28

SF-MVS		87.85 48	90.95 44	84.22 48	88.17 59	87.90 51	90.80 54	71.80 60	89.28 33	82.70 56	89.90 57	95.37 53	77.91 45	91.69 52	90.04 53	93.95 43	92.47 28

UniMVSNet_NR-MVSNet		84.62 71	88.00 67	80.68 83	88.18 58	83.83 78	87.06 100	76.47 39	81.46 103	70.49 127	93.24 21	95.56 48	68.13 115	90.43 72	88.47 68	93.78 45	83.02 103

ACMH	78.40 12	88.94 37	92.62 15	84.65 41	86.45 73	87.16 58	91.47 47	68.79 83	95.49 2	89.74 6	93.55 17	98.50 2	77.96 44	94.14 32	89.57 61	93.49 46	89.94 53
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CDPH-MVS		86.66 54	88.52 59	84.48 44	89.61 45	88.27 44	92.86 41	72.69 57	80.55 114	82.71 55	86.92 93	93.32 88	75.55 64	91.00 67	89.85 56	93.47 47	89.71 54

DeepC-MVS_fast	81.78 5	87.38 49	89.64 51	84.75 40	89.89 42	90.70 22	92.74 42	74.45 49	86.02 64	82.16 64	86.05 101	91.99 107	75.84 62	91.16 62	90.44 48	93.41 48	91.09 44
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PLC	76.06 15	85.38 63	87.46 71	82.95 61	85.79 79	88.84 39	88.86 82	68.70 84	87.06 56	83.60 48	79.02 135	90.05 122	77.37 51	90.88 69	89.66 59	93.37 49	86.74 76
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSP-MVS		89.40 27	92.69 12	85.56 34	89.01 50	89.85 32	93.72 34	75.42 44	92.28 10	80.49 72	94.36 12	94.87 65	81.46 25	92.49 48	91.42 42	93.27 50	93.54 16

TranMVSNet+NR-MVSNet		85.23 65	89.38 53	80.39 88	88.78 53	83.77 79	87.40 95	76.75 35	85.47 68	68.99 135	95.18 7	97.55 16	67.13 122	91.61 55	89.13 65	93.26 51	82.95 106

DU-MVS		84.88 68	88.27 64	80.92 77	88.30 56	83.59 82	87.06 100	78.35 20	80.64 112	70.49 127	92.67 30	96.91 21	68.13 115	91.79 49	89.29 64	93.20 52	83.02 103

DTE-MVSNet		88.99 35	92.77 11	84.59 42	93.31 2	88.10 47	90.96 51	83.09 2	91.38 13	76.21 91	96.03 2	98.04 8	70.78 103	95.65 14	92.32 33	93.18 53	87.84 70

HPM-MVS++		88.74 39	89.54 52	87.80 16	92.58 7	85.69 70	95.10 25	78.01 23	87.08 55	87.66 20	87.89 82	92.07 103	80.28 30	90.97 68	91.41 44	93.17 54	91.69 38

NR-MVSNet		82.89 86	87.43 72	77.59 106	83.91 98	83.59 82	87.10 99	78.35 20	80.64 112	68.85 136	92.67 30	96.50 24	54.19 172	87.19 101	88.68 67	93.16 55	82.75 108

WR-MVS_H		88.99 35	93.28 5	83.99 53	91.92 11	89.13 38	91.95 45	83.23 1	90.14 28	71.92 119	95.85 4	98.01 10	71.83 94	95.82 9	93.19 23	93.07 56	90.83 48

PEN-MVS		88.86 38	92.92 8	84.11 52	92.92 5	88.05 49	90.83 53	82.67 5	91.04 17	74.83 99	95.97 3	98.47 3	70.38 104	95.70 13	92.43 31	93.05 57	88.78 63

PS-CasMVS		89.07 32	93.23 6	84.21 50	92.44 8	88.23 46	90.54 61	82.95 3	90.50 23	75.31 97	95.80 5	98.37 6	71.16 97	96.30 5	93.32 22	92.88 58	90.11 51

CP-MVSNet		88.71 40	92.63 14	84.13 51	92.39 9	88.09 48	90.47 66	82.86 4	88.79 41	75.16 98	94.87 8	97.68 14	71.05 99	96.16 6	93.18 24	92.85 59	89.64 55

Effi-MVS+-dtu		82.04 95	83.39 118	80.48 87	85.48 82	86.57 64	88.40 86	68.28 89	69.04 163	73.13 113	76.26 157	91.11 116	74.74 72	88.40 88	87.76 73	92.84 60	84.57 90

PCF-MVS	76.59 14	84.11 74	85.27 91	82.76 64	86.12 76	88.30 43	91.24 49	69.10 78	82.36 91	84.45 43	77.56 147	90.40 121	72.91 86	85.88 110	83.88 108	92.72 61	88.53 64
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CS-MVS		79.35 117	77.74 142	81.22 74	85.59 81	79.85 107	88.78 84	66.61 100	67.63 166	80.41 73	67.82 196	75.07 183	73.27 85	88.31 90	84.36 104	92.63 62	81.18 120

MCST-MVS		84.79 69	86.48 77	82.83 63	87.30 66	87.03 60	90.46 67	69.33 77	83.14 84	82.21 63	81.69 128	92.14 102	75.09 69	87.27 98	84.78 100	92.58 63	89.30 58

PHI-MVS		86.37 56	88.14 65	84.30 46	86.65 72	87.56 54	90.76 56	70.16 69	82.55 88	89.65 7	84.89 112	92.40 97	75.97 60	90.88 69	89.70 58	92.58 63	89.03 61

NCCC		86.74 52	87.97 68	85.31 36	90.64 35	87.25 57	93.27 38	74.59 48	86.50 59	83.72 46	75.92 162	92.39 98	77.08 52	91.72 51	90.68 47	92.57 65	91.30 43

thisisatest0515		81.18 104	84.32 105	77.52 108	76.73 161	74.84 150	85.06 115	61.37 150	81.05 109	73.95 106	88.79 76	89.25 128	75.49 65	85.98 109	84.78 100	92.53 66	85.56 85

train_agg		86.67 53	87.73 69	85.43 35	91.51 19	82.72 87	94.47 30	74.22 52	81.71 96	81.54 70	89.20 69	92.87 92	78.33 42	90.12 75	88.47 68	92.51 67	89.04 60

DeepPCF-MVS	81.61 6	87.95 47	90.29 49	85.22 38	87.48 65	90.01 30	93.79 33	73.54 53	88.93 38	83.89 45	89.40 65	90.84 117	80.26 31	90.62 71	90.19 52	92.36 68	92.03 35

ETV-MVS		79.01 121	77.98 140	80.22 89	86.69 71	79.73 110	88.80 83	68.27 90	63.22 187	71.56 121	70.25 192	73.63 185	73.66 81	90.30 74	86.77 82	92.33 69	81.95 116

HQP-MVS		85.02 66	86.41 79	83.40 54	89.19 48	86.59 62	91.28 48	71.60 63	82.79 87	83.48 51	78.65 141	93.54 85	72.55 87	86.49 105	85.89 90	92.28 70	90.95 47

CNVR-MVS		86.93 51	88.98 56	84.54 43	90.11 40	87.41 56	93.23 39	73.47 54	86.31 62	82.25 61	82.96 120	92.15 101	76.04 59	91.69 52	90.69 46	92.17 71	91.64 40

CNLPA		85.50 61	88.58 57	81.91 68	84.55 89	87.52 55	90.89 52	63.56 133	88.18 45	84.06 44	83.85 117	91.34 114	76.46 55	91.27 59	89.00 66	91.96 72	88.88 62

MVS_0304		84.73 70	86.19 81	83.02 57	88.32 55	86.71 61	91.55 46	70.87 66	73.79 141	82.88 54	85.13 109	93.35 87	72.55 87	88.62 85	87.69 74	91.93 73	88.05 69

AdaColmap		84.15 73	85.14 94	83.00 59	89.08 49	87.14 59	90.56 60	70.90 65	82.40 90	80.41 73	73.82 173	84.69 149	75.19 67	91.58 56	89.90 55	91.87 74	86.48 77

3Dnovator	79.41 10	82.21 92	86.07 84	77.71 104	79.31 135	84.61 74	87.18 97	61.02 153	85.65 66	76.11 92	85.07 111	85.38 147	70.96 101	87.22 99	86.47 83	91.66 75	88.12 68

tttt0517		75.86 140	76.23 155	75.42 116	75.55 167	74.06 154	82.73 128	60.31 156	69.24 159	70.24 129	79.18 134	58.79 203	72.17 90	84.49 125	83.08 118	91.54 76	84.80 87

TSAR-MVS + GP.		85.32 64	87.41 73	82.89 62	90.07 41	85.69 70	89.07 80	72.99 56	82.45 89	74.52 103	85.09 110	87.67 137	79.24 33	91.11 63	90.41 49	91.45 77	89.45 56

PVSNet_Blended_VisFu		83.00 85	84.16 109	81.65 71	82.17 117	86.01 66	88.03 88	71.23 64	76.05 134	79.54 80	83.88 116	83.44 150	77.49 50	87.38 96	84.93 98	91.41 78	87.40 74

EIA-MVS		78.57 122	77.90 141	79.35 94	87.24 68	80.71 103	86.16 107	64.03 127	62.63 192	73.49 110	73.60 174	76.12 178	73.83 79	88.49 87	84.93 98	91.36 79	78.78 140

TSAR-MVS + ACMM		89.14 29	92.11 30	85.67 31	89.27 47	90.61 24	90.98 50	79.48 13	88.86 39	79.80 78	93.01 25	93.53 86	83.17 15	92.75 44	92.45 30	91.32 80	93.59 12

thisisatest0530		75.54 142	75.95 159	75.05 120	75.08 168	73.56 155	82.15 133	60.31 156	69.17 160	69.32 132	79.02 135	58.78 204	72.17 90	83.88 128	83.08 118	91.30 81	84.20 93

v7n		87.11 50	90.46 48	83.19 56	85.22 83	83.69 81	90.03 73	68.20 91	91.01 18	86.71 33	94.80 9	98.46 4	77.69 47	91.10 64	85.98 87	91.30 81	88.19 66

Effi-MVS+		82.33 91	83.87 112	80.52 86	84.51 90	81.32 98	87.53 93	68.05 92	74.94 139	79.67 79	82.37 125	92.31 99	72.21 89	85.06 117	86.91 79	91.18 83	84.20 93

canonicalmvs		81.22 103	86.04 85	75.60 115	83.17 108	83.18 85	80.29 144	65.82 111	85.97 65	67.98 143	77.74 145	91.51 111	65.17 131	88.62 85	86.15 86	91.17 84	89.09 59

DVP-MVS		88.51 41	91.36 38	85.19 39	90.63 36	92.01 4	95.29 23	77.52 28	90.48 24	80.21 77	90.21 54	96.08 34	76.38 56	88.30 91	91.42 42	91.12 85	91.01 45

Gipuma		86.47 55	89.25 54	83.23 55	83.88 99	78.78 117	85.35 112	68.42 87	92.69 9	89.03 12	91.94 35	96.32 32	81.80 22	94.45 27	86.86 80	90.91 86	83.69 97
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVS_111021_HR		83.95 75	86.10 83	81.44 73	84.62 87	80.29 105	90.51 63	68.05 92	84.07 80	80.38 75	84.74 113	91.37 113	74.23 74	90.37 73	87.25 76	90.86 87	84.59 89

abl_6				79.30 95	84.98 85	85.78 68	90.50 64	66.88 99	77.08 130	74.02 105	73.29 177	89.34 126	68.94 112			90.49 88	85.98 80

DCV-MVSNet		80.04 108	85.67 89	73.48 130	82.91 110	81.11 102	80.44 143	66.06 106	85.01 73	62.53 160	78.84 138	94.43 75	58.51 153	88.66 84	85.91 88	90.41 89	85.73 83

MVS_111021_LR		83.20 83	85.33 90	80.73 82	82.88 111	78.23 121	89.61 74	65.23 115	82.08 93	81.19 71	85.31 107	92.04 106	75.22 66	89.50 78	85.90 89	90.24 90	84.23 92

DPM-MVS		81.42 99	82.11 124	80.62 84	87.54 64	85.30 72	90.18 71	68.96 80	81.00 110	79.15 83	70.45 190	83.29 152	67.67 119	82.81 135	83.46 111	90.19 91	88.48 65

Fast-Effi-MVS+		81.42 99	83.82 113	78.62 99	82.24 116	80.62 104	87.72 91	63.51 134	73.01 143	74.75 101	83.80 118	92.70 94	73.44 83	88.15 93	85.26 94	90.05 92	83.17 101

FC-MVSNet-train		79.20 119	86.29 80	70.94 143	84.06 93	77.67 124	85.68 108	64.11 125	82.90 86	52.22 186	92.57 33	93.69 82	49.52 187	88.30 91	86.93 78	90.03 93	81.95 116

MSDG		81.39 101	84.23 108	78.09 102	82.40 115	82.47 91	85.31 114	60.91 154	79.73 120	80.26 76	86.30 97	88.27 135	69.67 107	87.20 100	84.98 97	89.97 94	80.67 125

Anonymous20231211		79.37 115	85.78 87	71.89 137	82.87 112	79.66 111	78.77 156	63.93 131	83.36 82	59.39 164	90.54 50	94.66 70	56.46 160	87.38 96	84.12 106	89.92 95	80.74 124

CANet		82.84 87	84.60 102	80.78 79	87.30 66	85.20 73	90.23 69	69.00 79	72.16 149	78.73 85	84.49 114	90.70 119	69.54 109	87.65 94	86.17 85	89.87 96	85.84 82

DELS-MVS		79.71 111	83.74 114	75.01 122	79.31 135	82.68 88	84.79 117	60.06 160	75.43 137	69.09 134	86.13 99	89.38 125	67.16 121	85.12 116	83.87 109	89.65 97	83.57 98
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
TSAR-MVS + COLMAP		85.51 60	88.36 62	82.19 66	86.05 77	87.69 53	90.50 64	70.60 68	86.40 60	82.33 59	89.69 62	92.52 96	74.01 78	87.53 95	86.84 81	89.63 98	87.80 71

EG-PatchMatch MVS		84.35 72	87.55 70	80.62 84	86.38 74	82.24 92	86.75 103	64.02 128	84.24 77	78.17 88	89.38 66	95.03 63	78.78 37	89.95 77	86.33 84	89.59 99	85.65 84

MAR-MVS		81.98 96	82.92 120	80.88 78	85.18 84	85.85 67	89.13 79	69.52 72	71.21 153	82.25 61	71.28 184	88.89 132	69.69 106	88.71 83	86.96 77	89.52 100	87.57 72
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
Vis-MVSNet		83.32 81	88.12 66	77.71 104	77.91 150	83.44 84	90.58 58	69.49 74	81.11 108	67.10 147	89.85 59	91.48 112	71.71 95	91.34 58	89.37 62	89.48 101	90.26 50
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UniMVSNet_ETH3D		85.39 62	91.12 43	78.71 97	90.48 37	83.72 80	81.76 135	82.41 6	93.84 5	64.43 153	95.41 6	98.76 1	63.72 137	93.63 34	89.74 57	89.47 102	82.74 109

MSLP-MVS++		86.29 57	89.10 55	83.01 58	85.71 80	89.79 34	87.04 102	74.39 50	85.17 72	78.92 84	77.59 146	93.57 84	82.60 17	93.23 37	91.88 40	89.42 103	92.46 30

TinyColmap		83.79 76	86.12 82	81.07 76	83.42 104	81.44 97	85.42 110	68.55 86	88.71 42	89.46 8	87.60 84	92.72 93	70.34 105	89.29 80	81.94 125	89.20 104	81.12 122

Vis-MVSNet (Re-imp)		76.15 136	80.84 129	70.68 144	83.66 102	74.80 151	81.66 137	69.59 71	80.48 115	46.94 195	87.44 85	80.63 161	53.14 177	86.87 102	84.56 103	89.12 105	71.12 165

ET-MVSNet_ETH3D		74.71 146	74.19 166	75.31 118	79.22 137	75.29 145	82.70 129	64.05 126	65.45 177	70.96 126	77.15 151	57.70 205	65.89 128	84.40 126	81.65 127	89.03 106	77.67 146

USDC		81.39 101	83.07 119	79.43 93	81.48 121	78.95 116	82.62 130	66.17 105	87.45 52	90.73 4	82.40 124	93.65 83	66.57 125	83.63 130	77.97 148	89.00 107	77.45 147

Anonymous202405211			84.68 101		83.92 97	79.45 112	79.03 154	67.79 94	82.01 94		88.77 77	92.58 95	55.93 163	86.68 103	84.26 105	88.92 108	78.98 138

v1192		83.61 77	85.23 92	81.72 70	84.05 94	82.15 93	89.54 75	66.20 104	81.38 105	86.76 32	91.79 39	96.03 36	74.88 71	81.81 143	80.92 132	88.91 109	82.50 111

v144192		83.43 80	84.97 97	81.63 72	83.43 103	81.23 100	89.42 78	66.04 108	81.45 104	86.40 34	91.46 43	95.70 46	75.76 63	82.14 139	80.23 139	88.74 110	82.57 110

OpenMVS	75.38 16	78.44 123	81.39 128	74.99 123	80.46 126	79.85 107	79.99 146	58.31 168	77.34 129	73.85 107	77.19 150	82.33 157	68.60 114	84.67 124	81.95 124	88.72 111	86.40 79

v1144		83.22 82	85.01 95	81.14 75	83.76 101	81.60 96	88.95 81	65.58 113	81.89 95	85.80 36	91.68 41	95.84 41	74.04 77	82.12 140	80.56 135	88.70 112	81.41 119

v1921920		83.49 79	84.94 98	81.80 69	83.78 100	81.20 101	89.50 76	65.91 109	81.64 98	87.18 25	91.70 40	95.39 52	75.85 61	81.56 146	80.27 138	88.60 113	82.80 107

casdiffmvs		79.93 109	84.11 110	75.05 120	81.41 123	78.99 115	82.95 127	62.90 141	81.53 100	68.60 140	91.94 35	96.03 36	65.84 129	82.89 133	77.07 156	88.59 114	80.34 131

v10		83.17 84	85.22 93	80.78 79	83.26 106	82.99 86	88.66 85	66.49 102	79.24 123	83.60 48	91.46 43	95.47 50	74.12 75	82.60 138	80.66 133	88.53 115	84.11 95

v1240		83.57 78	84.94 98	81.97 67	84.05 94	81.27 99	89.46 77	66.06 106	81.31 106	87.50 21	91.88 38	95.46 51	76.25 57	81.16 148	80.51 136	88.52 116	82.98 105

QAPM		80.43 106	84.34 104	75.86 113	79.40 134	82.06 94	79.86 149	61.94 147	83.28 83	74.73 102	81.74 127	85.44 146	70.97 100	84.99 122	84.71 102	88.29 117	88.14 67

UGNet		79.62 113	85.91 86	72.28 136	73.52 171	83.91 77	86.64 104	69.51 73	79.85 119	62.57 159	85.82 104	89.63 123	53.18 176	88.39 89	87.35 75	88.28 118	86.43 78
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
DI_MVS_plusplus_trai		77.64 126	79.64 132	75.31 118	79.87 131	76.89 133	81.55 138	63.64 132	76.21 133	72.03 118	85.59 106	82.97 154	66.63 124	79.27 159	77.78 150	88.14 119	78.76 141

FMVSNet1		78.20 125	84.83 100	70.46 147	78.62 142	79.03 114	77.90 158	67.53 97	83.02 85	55.10 175	87.19 90	93.18 90	55.65 165	85.57 111	83.39 113	87.98 120	82.40 112

FPMVS		81.56 98	84.04 111	78.66 98	82.92 109	75.96 140	86.48 106	65.66 112	84.67 76	71.47 122	77.78 144	83.22 153	77.57 49	91.24 60	90.21 51	87.84 121	85.21 86

v2v482		82.20 93	84.26 106	79.81 91	82.67 113	80.18 106	87.67 92	63.96 130	81.69 97	84.73 41	91.27 46	96.33 31	72.05 93	81.94 142	79.56 142	87.79 122	78.84 139

v8		82.20 93	84.56 103	79.45 92	82.42 114	81.65 95	87.26 96	64.27 122	79.36 122	81.70 68	91.04 49	95.75 44	73.30 84	82.82 134	79.18 145	87.74 123	82.09 114

PVSNet_BlendedMVS		76.45 134	78.12 138	74.49 126	76.76 155	78.46 118	79.65 150	63.26 137	65.42 178	73.15 111	75.05 167	88.96 129	66.51 126	82.73 136	77.66 151	87.61 124	78.60 142

PVSNet_Blended		76.45 134	78.12 138	74.49 126	76.76 155	78.46 118	79.65 150	63.26 137	65.42 178	73.15 111	75.05 167	88.96 129	66.51 126	82.73 136	77.66 151	87.61 124	78.60 142

tfpn200view9		72.01 159	75.40 161	68.06 162	77.97 148	76.44 135	77.04 163	62.67 142	66.81 169	50.82 191	67.30 197	75.67 180	52.46 183	85.06 117	82.64 121	87.41 126	73.86 158

pmmvs6		80.46 105	88.34 63	71.26 139	81.96 118	77.51 125	77.54 159	68.83 82	93.72 6	55.92 172	93.94 16	98.03 9	55.94 162	89.21 81	85.61 91	87.36 127	80.38 127

thres600view7		74.34 148	78.43 137	69.56 153	80.47 125	76.28 137	78.65 157	62.56 143	77.39 128	52.53 182	74.03 171	76.78 175	55.90 164	85.06 117	85.19 95	87.25 128	74.29 156

thres200		72.41 158	76.00 158	68.21 161	78.28 144	76.28 137	74.94 177	62.56 143	72.14 150	51.35 190	69.59 194	76.51 176	54.89 167	85.06 117	80.51 136	87.25 128	71.92 164

IB-MVS	71.28 17	75.21 143	77.00 149	73.12 134	76.76 155	77.45 126	83.05 125	58.92 165	63.01 188	64.31 154	59.99 206	87.57 138	68.64 113	86.26 108	82.34 123	87.05 130	82.36 113
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
TransMVSNet (Re)		79.05 120	86.66 75	70.18 149	83.32 105	75.99 139	77.54 159	63.98 129	90.68 22	55.84 173	94.80 9	96.06 35	53.73 175	86.27 107	83.22 117	86.65 131	79.61 136

pm-mvs1		78.21 124	85.68 88	69.50 154	80.38 127	75.73 142	76.25 167	65.04 116	87.59 50	54.47 177	93.16 23	95.99 40	54.20 171	86.37 106	82.98 120	86.64 132	77.96 145

MVSTER		68.08 175	69.73 176	66.16 171	66.33 197	70.06 166	75.71 174	52.36 188	55.18 206	58.64 166	70.23 193	56.72 208	57.34 157	79.68 157	76.03 161	86.61 133	80.20 133

thres400		73.13 154	76.99 150	68.62 158	79.46 133	74.93 149	77.23 161	61.23 152	75.54 135	52.31 185	72.20 179	77.10 173	54.89 167	82.92 132	82.62 122	86.57 134	73.66 161

EPNet		79.36 116	79.44 133	79.27 96	89.51 46	77.20 130	88.35 87	77.35 32	68.27 165	74.29 104	76.31 155	79.22 164	59.63 149	85.02 121	85.45 93	86.49 135	84.61 88
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PatchMatch-RL		76.05 137	76.64 151	75.36 117	77.84 151	69.87 168	81.09 140	63.43 135	71.66 151	68.34 142	71.70 180	81.76 158	74.98 70	84.83 123	83.44 112	86.45 136	73.22 162

CLD-MVS		82.75 90	87.22 74	77.54 107	88.01 62	85.76 69	90.23 69	54.52 179	82.28 92	82.11 65	88.48 78	95.27 54	63.95 135	89.41 79	88.29 70	86.45 136	81.01 123
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
IterMVS-LS		79.79 110	82.56 122	76.56 112	81.83 119	77.85 123	79.90 148	69.42 76	78.93 124	71.21 123	90.47 51	85.20 148	70.86 102	80.54 153	80.57 134	86.15 138	84.36 91
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
V42		79.59 114	83.59 116	74.93 125	69.61 184	77.05 132	86.59 105	55.84 174	78.42 126	77.29 89	89.84 60	95.08 61	74.12 75	83.05 131	80.11 140	86.12 139	81.59 118

GBi-Net		73.17 152	77.64 143	67.95 163	76.76 155	77.36 127	75.77 171	64.57 119	62.99 189	51.83 187	76.05 158	77.76 170	52.73 180	85.57 111	83.39 113	86.04 140	80.37 128

test1		73.17 152	77.64 143	67.95 163	76.76 155	77.36 127	75.77 171	64.57 119	62.99 189	51.83 187	76.05 158	77.76 170	52.73 180	85.57 111	83.39 113	86.04 140	80.37 128

FMVSNet2		74.43 147	79.70 131	68.27 160	76.76 155	77.36 127	75.77 171	65.36 114	72.28 147	52.97 181	81.92 126	85.61 145	52.73 180	80.66 152	79.73 141	86.04 140	80.37 128

ambc			88.38 60		91.62 17	87.97 50	84.48 119		88.64 43	87.93 16	87.38 86	94.82 68	74.53 73	89.14 82	83.86 110	85.94 143	86.84 75

Fast-Effi-MVS+-dtu		76.92 129	77.18 147	76.62 111	79.55 132	79.17 113	84.80 116	77.40 30	64.46 182	68.75 138	70.81 188	86.57 141	63.36 142	81.74 144	81.76 126	85.86 144	75.78 151

PM-MVS		80.42 107	83.63 115	76.67 110	78.04 147	72.37 160	87.14 98	60.18 159	80.13 116	71.75 120	86.12 100	93.92 80	77.08 52	86.56 104	85.12 96	85.83 145	81.18 120

Baseline_NR-MVSNet		82.79 88	86.51 76	78.44 101	88.30 56	75.62 144	87.81 90	74.97 47	81.53 100	66.84 148	94.71 11	96.46 25	66.90 123	91.79 49	83.37 116	85.83 145	82.09 114

thres100view900		69.86 166	72.97 173	66.24 170	77.97 148	72.49 159	73.29 181	59.12 163	66.81 169	50.82 191	67.30 197	75.67 180	50.54 186	78.24 162	79.40 143	85.71 147	70.88 166

pmmvs-eth3d		79.64 112	82.06 125	76.83 109	80.05 129	72.64 158	87.47 94	66.59 101	80.83 111	73.50 109	89.32 67	93.20 89	67.78 117	80.78 151	81.64 128	85.58 148	76.01 149

MVS_Test		76.72 131	79.40 134	73.60 129	78.85 141	74.99 148	79.91 147	61.56 149	69.67 157	72.44 114	85.98 102	90.78 118	63.50 140	78.30 161	75.74 163	85.33 149	80.31 132

v148		79.33 118	82.32 123	75.84 114	80.14 128	75.74 141	81.98 134	57.06 171	81.51 102	79.36 82	89.42 64	96.42 27	71.32 96	81.54 147	75.29 165	85.20 150	76.32 148

tfpnnormal		77.16 128	84.26 106	68.88 157	81.02 124	75.02 147	76.52 166	63.30 136	87.29 53	52.40 184	91.24 47	93.97 78	54.85 169	85.46 114	81.08 130	85.18 151	75.76 152

FC-MVSNet-test		75.91 139	83.59 116	66.95 168	76.63 163	69.07 170	85.33 113	64.97 117	84.87 75	41.95 199	93.17 22	87.04 139	47.78 190	91.09 65	85.56 92	85.06 152	74.34 155

CANet_DTU		75.04 144	78.45 136	71.07 140	77.27 152	77.96 122	83.88 122	58.00 169	64.11 183	68.67 139	75.65 164	88.37 134	53.92 174	82.05 141	81.11 129	84.67 153	79.88 134

FMVSNet3		71.40 163	75.20 164	66.97 167	75.00 169	76.59 134	74.29 178	64.57 119	62.99 189	51.83 187	76.05 158	77.76 170	51.49 185	76.58 169	77.03 157	84.62 154	79.43 137

pmmvs4		75.92 138	77.48 146	74.10 128	78.21 146	70.94 162	84.06 120	64.78 118	75.13 138	68.47 141	84.12 115	83.32 151	64.74 134	75.93 173	79.14 146	84.31 155	73.77 159

baseline2		68.71 172	68.34 180	69.14 155	75.69 165	69.70 169	76.60 165	55.53 176	60.13 197	62.07 162	66.76 199	60.35 198	60.77 146	76.53 171	74.03 167	84.19 156	70.88 166

GA-MVS		75.01 145	76.39 153	73.39 131	78.37 143	75.66 143	80.03 145	58.40 167	70.51 155	75.85 94	83.24 119	76.14 177	63.75 136	77.28 165	76.62 159	83.97 157	75.30 154

CDS-MVSNet		73.07 155	77.02 148	68.46 159	81.62 120	72.89 157	79.56 152	70.78 67	69.56 158	52.52 183	77.37 149	81.12 160	42.60 195	84.20 127	83.93 107	83.65 158	70.07 170
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
RPMNet		67.02 177	63.99 191	70.56 146	71.55 179	67.63 174	75.81 169	69.44 75	59.93 198	63.24 156	64.32 201	47.51 215	59.68 148	70.37 189	69.64 181	83.64 159	68.49 175

CR-MVSNet		69.56 168	68.34 180	70.99 142	72.78 176	67.63 174	64.47 200	67.74 95	59.93 198	72.30 115	80.10 130	56.77 207	65.04 132	71.64 185	72.91 171	83.61 160	69.40 172

PMMVS		61.98 190	65.61 186	57.74 189	45.03 211	51.76 203	69.54 193	35.05 204	55.49 205	55.32 174	68.23 195	78.39 168	58.09 154	70.21 190	71.56 176	83.42 161	63.66 183

IterMVS-SCA-FT		77.23 127	79.18 135	74.96 124	76.67 162	79.85 107	75.58 176	61.34 151	73.10 142	73.79 108	86.23 98	79.61 163	79.00 36	80.28 155	75.50 164	83.41 162	79.70 135

diffmvs		76.74 130	81.61 127	71.06 141	75.64 166	74.45 153	80.68 142	57.57 170	77.48 127	67.62 146	88.95 72	93.94 79	61.98 144	79.74 156	76.18 160	82.85 163	80.50 126

EU-MVSNet		76.48 133	80.53 130	71.75 138	67.62 190	70.30 165	81.74 136	54.06 182	75.47 136	71.01 125	80.10 130	93.17 91	73.67 80	83.73 129	77.85 149	82.40 164	83.07 102

baseline1		69.62 167	73.55 170	65.02 179	78.95 140	70.39 164	71.38 187	62.03 146	70.97 154	47.95 194	78.47 142	68.19 191	47.77 191	79.65 158	76.94 158	82.05 165	70.27 168

HyFIR lowres test		73.29 151	74.14 167	72.30 135	73.08 173	78.33 120	83.12 124	62.41 145	63.81 184	62.13 161	76.67 154	78.50 167	71.09 98	74.13 177	77.47 154	81.98 166	70.10 169

CVMVSNet		75.65 141	77.62 145	73.35 133	71.95 177	69.89 167	83.04 126	60.84 155	69.12 161	68.76 137	79.92 133	78.93 166	73.64 82	81.02 149	81.01 131	81.86 167	83.43 99

pmmvs5		68.91 170	74.35 165	62.56 182	67.45 192	66.78 178	71.70 184	51.47 191	67.17 168	56.25 171	82.41 123	88.59 133	47.21 192	73.21 183	74.23 166	81.30 168	68.03 176

gg-mvs-nofinetune		72.68 157	75.21 163	69.73 151	81.48 121	69.04 171	70.48 188	76.67 36	86.92 57	67.80 145	88.06 81	64.67 193	42.12 197	77.60 163	73.65 168	79.81 169	66.57 177

IterMVS		73.62 149	76.53 152	70.23 148	71.83 178	77.18 131	80.69 141	53.22 186	72.23 148	66.62 149	85.21 108	78.96 165	69.54 109	76.28 172	71.63 175	79.45 170	74.25 157
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MS-PatchMatch		71.18 164	73.99 168	67.89 165	77.16 153	71.76 161	77.18 162	56.38 173	67.35 167	55.04 176	74.63 169	75.70 179	62.38 143	76.62 168	75.97 162	79.22 171	75.90 150

gm-plane-assit		71.56 161	69.99 175	73.39 131	84.43 91	73.21 156	90.42 68	51.36 192	84.08 79	76.00 93	91.30 45	37.09 216	59.01 151	73.65 180	70.24 179	79.09 172	60.37 194

MDA-MVSNet-bldmvs		76.51 132	82.87 121	69.09 156	50.71 210	74.72 152	84.05 121	60.27 158	81.62 99	71.16 124	88.21 80	91.58 109	69.62 108	92.78 43	77.48 153	78.75 173	73.69 160

EPNet_dtu		71.90 160	73.03 172	70.59 145	78.28 144	61.64 189	82.44 131	64.12 124	63.26 186	69.74 130	71.47 182	82.41 155	51.89 184	78.83 160	78.01 147	77.07 174	75.60 153
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CMPMVS	55.74 18	71.56 161	76.26 154	66.08 173	68.11 188	63.91 186	63.17 202	50.52 194	68.79 164	75.49 95	70.78 189	85.67 144	63.54 139	81.58 145	77.20 155	75.63 175	85.86 81
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test-mter		59.39 194	61.59 198	56.82 191	53.21 206	54.82 197	73.12 183	26.57 209	53.19 207	56.31 170	64.71 200	60.47 197	56.36 161	68.69 193	64.27 189	75.38 176	65.00 179

test-LLR		62.15 189	59.46 205	65.29 177	79.07 138	52.66 201	69.46 194	62.93 139	50.76 209	53.81 179	63.11 203	58.91 201	52.87 178	66.54 198	62.34 191	73.59 177	61.87 190

TESTMET0.1,1		57.21 197	59.46 205	54.60 197	50.95 208	52.66 201	69.46 194	26.91 208	50.76 209	53.81 179	63.11 203	58.91 201	52.87 178	66.54 198	62.34 191	73.59 177	61.87 190

pmmvs3		62.72 187	68.71 179	55.74 193	50.74 209	57.10 194	70.05 190	28.82 207	61.57 196	57.39 168	71.19 186	85.73 143	53.96 173	73.36 182	69.43 182	73.47 179	62.55 188

CostFormer		66.81 178	66.94 183	66.67 169	72.79 175	68.25 173	79.55 153	55.57 175	65.52 176	62.77 158	76.98 152	60.09 199	56.73 159	65.69 200	62.35 190	72.59 180	69.71 171

MDTV_nov1_ep13_2view		72.96 156	75.59 160	69.88 150	71.15 181	64.86 183	82.31 132	54.45 180	76.30 132	78.32 87	86.52 95	91.58 109	61.35 145	76.80 166	66.83 186	71.70 181	66.26 178

MDTV_nov1_ep13		64.96 181	64.77 188	65.18 178	67.08 193	62.46 188	75.80 170	51.10 193	62.27 193	69.74 130	74.12 170	62.65 194	55.64 166	68.19 194	62.16 194	71.70 181	61.57 192

PatchT		66.25 179	66.76 184	65.67 176	55.87 205	60.75 190	70.17 189	59.00 164	59.80 200	72.30 115	78.68 140	54.12 212	65.04 132	71.64 185	72.91 171	71.63 183	69.40 172

baseline		69.33 169	75.37 162	62.28 183	66.54 195	66.67 179	73.95 180	48.07 195	66.10 172	59.26 165	82.45 122	86.30 142	54.44 170	74.42 176	73.25 170	71.42 184	78.43 144

dps		65.14 180	64.50 189	65.89 175	71.41 180	65.81 182	71.44 186	61.59 148	58.56 201	61.43 163	75.45 165	52.70 214	58.06 155	69.57 191	64.65 188	71.39 185	64.77 180

SCA		68.54 173	67.52 182	69.73 151	67.79 189	75.04 146	76.96 164	68.94 81	66.41 171	67.86 144	74.03 171	60.96 196	65.55 130	68.99 192	65.67 187	71.30 186	61.54 193

MVS-HIRNet		59.74 192	58.74 208	60.92 185	57.74 204	45.81 208	56.02 208	58.69 166	55.69 204	65.17 152	70.86 187	71.66 187	56.75 158	61.11 205	53.74 204	71.17 187	52.28 204

MIMVSNet1		73.40 150	81.85 126	63.55 180	72.90 174	64.37 184	84.58 118	53.60 184	90.84 19	53.92 178	87.75 83	96.10 33	45.31 193	85.37 115	79.32 144	70.98 188	69.18 174

test20.03		69.91 165	76.20 156	62.58 181	84.01 96	67.34 176	75.67 175	65.88 110	79.98 118	40.28 203	82.65 121	89.31 127	39.63 199	77.41 164	73.28 169	69.98 189	63.40 185

Anonymous20231206		67.28 176	73.41 171	60.12 186	76.45 164	63.61 187	74.21 179	56.52 172	76.35 131	42.23 198	75.81 163	90.47 120	41.51 198	74.52 174	69.97 180	69.83 190	63.17 186

CHOSEN 1792x2688		68.80 171	71.09 174	66.13 172	69.11 186	68.89 172	78.98 155	54.68 177	61.63 194	56.69 169	71.56 181	78.39 168	67.69 118	72.13 184	72.01 174	69.63 191	73.02 163

testgi		68.20 174	76.05 157	59.04 187	79.99 130	67.32 177	81.16 139	51.78 190	84.91 74	39.36 204	73.42 175	95.19 56	32.79 205	76.54 170	70.40 178	69.14 192	64.55 181

TAMVS		63.02 184	69.30 177	55.70 194	70.12 182	56.89 195	69.63 192	45.13 197	70.23 156	38.00 205	77.79 143	75.15 182	42.60 195	74.48 175	72.81 173	68.70 193	57.75 200

test0.0.03 1		61.79 191	65.33 187	57.65 190	79.07 138	64.09 185	68.51 197	62.93 139	61.59 195	33.71 207	61.58 205	71.58 189	33.43 204	70.95 188	68.68 183	68.26 194	58.82 196

tpm cat1		64.79 183	62.74 196	67.17 166	74.61 170	65.91 181	76.18 168	59.32 162	64.88 181	66.41 150	71.21 185	53.56 213	59.17 150	61.53 204	58.16 199	67.33 195	63.95 182

PatchmatchNet		64.81 182	63.74 192	66.06 174	69.21 185	58.62 193	73.16 182	60.01 161	65.92 173	66.19 151	76.27 156	59.09 200	60.45 147	66.58 197	61.47 196	67.33 195	58.24 198
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MIMVSNet		63.02 184	69.02 178	56.01 192	68.20 187	59.26 192	70.01 191	53.79 183	71.56 152	41.26 202	71.38 183	82.38 156	36.38 201	71.43 187	67.32 185	66.45 197	59.83 195

FMVSNet5		56.37 200	60.14 202	51.98 201	60.83 201	59.58 191	66.85 199	42.37 200	52.68 208	41.33 201	47.09 209	54.68 211	35.28 202	73.88 178	70.77 177	65.24 198	62.26 189

CHOSEN 280x420		56.32 201	58.85 207	53.36 198	51.63 207	39.91 211	69.12 196	38.61 203	56.29 203	36.79 206	48.84 208	62.59 195	63.39 141	73.61 181	67.66 184	60.61 199	63.07 187

GG-mvs-BLEND		41.63 206	60.36 201	19.78 207	0.14 217	66.04 180	55.66 209	0.17 214	57.64 202	2.42 215	51.82 207	69.42 190	0.28 213	64.11 203	58.29 198	60.02 200	55.18 202

tpm		62.79 186	63.25 193	62.26 184	70.09 183	53.78 198	71.65 185	47.31 196	65.72 175	76.70 90	80.62 129	56.40 210	48.11 189	64.20 202	58.54 197	59.70 201	63.47 184

tpmrst		59.42 193	60.02 203	58.71 188	67.56 191	53.10 200	66.99 198	51.88 189	63.80 185	57.68 167	76.73 153	56.49 209	48.73 188	56.47 208	55.55 201	59.43 202	58.02 199

new-patchmatchnet		62.59 188	73.79 169	49.53 202	76.98 154	53.57 199	53.46 210	54.64 178	85.43 69	28.81 208	91.94 35	96.41 28	25.28 207	76.80 166	53.66 205	57.99 203	58.69 197

EPMVS		56.62 199	59.77 204	52.94 199	62.41 200	50.55 204	60.66 204	52.83 187	65.15 180	41.80 200	77.46 148	57.28 206	42.68 194	59.81 206	54.82 202	57.23 204	53.35 203

new_pmnet		52.29 203	63.16 194	39.61 205	58.89 203	44.70 209	48.78 212	34.73 205	65.88 174	17.85 211	73.42 175	80.00 162	23.06 208	67.00 196	62.28 193	54.36 205	48.81 206

E-PMN		59.07 195	62.79 195	54.72 195	67.01 194	47.81 207	60.44 205	43.40 198	72.95 144	44.63 197	70.42 191	73.17 186	58.73 152	80.97 150	51.98 206	54.14 206	42.26 209

EMVS		58.97 196	62.63 197	54.70 196	66.26 198	48.71 205	61.74 203	42.71 199	72.80 146	46.00 196	73.01 178	71.66 187	57.91 156	80.41 154	50.68 208	53.55 207	41.11 210

ADS-MVSNet		56.89 198	61.09 199	52.00 200	59.48 202	48.10 206	58.02 206	54.37 181	72.82 145	49.19 193	75.32 166	65.97 192	37.96 200	59.34 207	54.66 203	52.99 208	51.42 205

N_pmnet		54.95 202	65.90 185	42.18 203	66.37 196	43.86 210	57.92 207	39.79 202	79.54 121	17.24 212	86.31 96	87.91 136	25.44 206	64.68 201	51.76 207	46.33 209	47.23 207

MVE	41.12 19	51.80 204	60.92 200	41.16 204	35.21 213	34.14 213	48.45 213	41.39 201	69.11 162	19.53 210	63.33 202	73.80 184	63.56 138	67.19 195	61.51 195	38.85 210	57.38 201
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		48.13 205	64.06 190	29.55 206	44.06 212	36.69 212	51.95 211	29.97 206	74.75 140	8.90 214	76.02 161	91.24 115	7.53 209	73.78 179	55.91 200	34.87 211	40.01 211

DeepMVS_CX						17.78 214	20.40 214	6.69 210	31.41 211	9.80 213	38.61 210	34.88 217	33.78 203	28.41 210		23.59 212	45.77 208

tmp_tt				13.54 208	16.73 214	6.42 215	8.49 215	2.36 211	28.69 212	27.44 209	18.40 211	13.51 218	3.70 210	33.23 209	36.26 209	22.54 213

testmvs		0.93 208	1.37 210	0.41 210	0.36 216	0.36 217	0.62 217	0.39 212	1.48 213	0.18 217	2.41 212	1.31 220	0.41 212	1.25 212	1.08 211	0.48 214	1.68 212

test123		1.06 207	1.41 209	0.64 209	0.39 215	0.48 216	0.52 218	0.25 213	1.11 214	1.37 216	2.01 213	1.98 219	0.87 211	1.43 211	1.27 210	0.46 215	1.62 213

uanet_test		0.00 209	0.00 211	0.00 211	0.00 218	0.00 218	0.00 219	0.00 215	0.00 215	0.00 218	0.00 214	0.00 221	0.00 214	0.00 213	0.00 212	0.00 216	0.00 214

sosnet-low-res		0.00 209	0.00 211	0.00 211	0.00 218	0.00 218	0.00 219	0.00 215	0.00 215	0.00 218	0.00 214	0.00 221	0.00 214	0.00 213	0.00 212	0.00 216	0.00 214

sosnet		0.00 209	0.00 211	0.00 211	0.00 218	0.00 218	0.00 219	0.00 215	0.00 215	0.00 218	0.00 214	0.00 221	0.00 214	0.00 213	0.00 212	0.00 216	0.00 214

9.14												89.43 124

SR-MVS					91.82 13			80.80 7				95.53 49

our_test_3					73.27 172	70.91 163	83.26 123

test_part1																	93.49 18

MTAPA										89.37 9		94.85 66

MTMP										90.54 5		95.16 58

Patchmatch-RL test							4.13 216

mPP-MVS					93.05 4							95.77 43

NP-MVS									78.65 125

Patchmtry						56.88 196	64.47 200	67.74 95		72.30 115

High-resolution multi-view benchmark