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 53	93.57 1	97.27 1	78.23 22	95.55 2	93.00 1	93.98 18	96.01 40	87.53 1	97.69 1	96.81 1	97.33 1	95.34 4

COLMAP_ROB	85.66 2	91.85 2	95.01 2	88.16 12	88.98 52	92.86 2	95.51 20	72.17 60	94.95 5	91.27 3	94.11 17	97.77 12	84.22 8	96.49 4	95.27 5	96.79 2	93.60 12
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 34	91.44 40	86.20 29	94.88 1	89.84 34	94.76 30	77.45 29	85.41 73	74.79 107	88.83 78	88.90 139	78.67 40	96.06 7	95.45 4	96.66 3	95.58 2

SD-MVS		89.91 19	92.23 31	87.19 22	91.31 25	89.79 35	94.31 33	75.34 48	89.26 39	81.79 70	92.68 32	95.08 63	83.88 11	93.10 40	92.69 26	96.54 4	93.02 24
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 24	93.66 5	85.27 38	91.32 24	88.27 46	93.49 39	79.86 10	92.75 10	75.37 103	96.86 1	98.38 6	75.10 73	95.93 8	94.07 15	96.46 5	89.39 59

anonymousdsp		85.62 62	90.53 49	79.88 95	64.64 206	76.35 142	96.28 13	53.53 191	85.63 70	81.59 72	92.81 31	97.71 14	86.88 2	94.56 26	92.83 25	96.35 6	93.84 9

ACMMP		90.63 8	92.40 21	88.56 9	91.24 29	91.60 6	96.49 9	77.53 27	87.89 50	86.87 31	87.24 93	96.46 27	82.87 16	95.59 15	94.50 9	96.35 6	93.51 18
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 22	88.43 10	90.88 33	91.15 11	95.35 22	77.65 26	86.26 66	87.23 24	90.45 55	97.35 19	83.20 14	95.44 16	93.41 21	96.28 8	92.63 27

ACMM	80.67 7	90.67 7	92.46 20	88.57 8	91.35 23	89.93 32	96.34 12	77.36 31	90.17 30	86.88 30	87.32 91	96.63 25	83.32 13	95.79 10	94.49 10	96.19 9	92.91 26
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	80.00 8	90.12 17	92.30 27	87.58 19	90.83 35	91.10 12	94.96 29	76.06 41	87.47 54	85.33 40	88.91 77	97.65 16	82.13 20	95.31 17	93.44 20	96.14 10	92.22 34
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMMPR		91.30 4	92.88 12	89.46 4	91.92 12	91.61 5	96.60 5	79.46 14	90.08 32	88.53 14	89.54 66	95.57 49	84.25 7	95.24 20	94.27 13	95.97 11	93.85 8

CSCG		88.12 46	91.45 39	84.23 49	88.12 63	90.59 25	90.57 62	68.60 90	91.37 16	83.45 53	89.94 59	95.14 62	78.71 38	91.45 61	88.21 76	95.96 12	93.44 19

LS3D		89.02 34	91.69 37	85.91 31	89.72 44	90.81 20	92.56 45	71.69 66	90.83 22	87.24 23	89.71 64	92.07 109	78.37 41	94.43 28	92.59 28	95.86 13	91.35 43

X-MVS		89.36 29	90.73 48	87.77 17	91.50 21	91.23 8	96.76 4	78.88 18	87.29 56	87.14 26	78.98 145	94.53 73	76.47 59	95.25 19	94.28 12	95.85 14	93.55 16

XVS					91.28 26	91.23 8	96.89 2			87.14 26		94.53 73				95.84 15

X-MVStestdata					91.28 26	91.23 8	96.89 2			87.14 26		94.53 73				95.84 15

HFP-MVS		90.32 14	92.37 23	87.94 14	91.46 22	90.91 18	95.69 18	79.49 12	89.94 35	83.50 51	89.06 73	94.44 77	81.68 23	94.17 31	94.19 14	95.81 17	93.87 7

CP-MVS		91.09 5	92.33 26	89.65 2	92.16 11	90.41 27	96.46 10	80.38 8	88.26 47	89.17 11	87.00 96	96.34 32	83.95 10	95.77 11	94.72 8	95.81 17	93.78 10

PGM-MVS		90.42 11	91.58 38	89.05 6	91.77 15	91.06 13	96.51 7	78.94 17	85.41 73	87.67 19	87.02 95	95.26 57	83.62 12	95.01 24	93.94 16	95.79 19	93.40 20

EPP-MVSNet		82.76 95	86.47 81	78.45 106	86.00 83	84.47 78	85.39 117	68.42 92	84.17 81	62.97 164	89.26 71	76.84 182	72.13 96	92.56 50	90.40 53	95.76 20	87.56 76

DeepC-MVS	83.59 4	90.37 13	92.56 19	87.82 15	91.26 28	92.33 3	94.72 31	80.04 9	90.01 33	84.61 43	93.33 23	94.22 80	80.59 28	92.90 45	92.52 29	95.69 21	92.57 28
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 27	93.08 9	85.58 33	88.58 56	89.26 39	92.18 46	74.23 53	93.55 9	82.66 61	92.32 37	98.35 8	80.29 29	95.28 18	92.34 32	95.52 22	90.43 51

LTVRE_ROB	86.82 1	91.55 3	94.43 3	88.19 11	83.19 113	86.35 68	93.60 38	78.79 19	95.48 4	91.79 2	93.08 27	97.21 22	86.34 3	97.06 2	96.27 3	95.46 23	95.56 3
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 35	89.55 3	92.92 5	90.90 19	96.56 6	79.60 11	86.83 61	88.75 13	89.00 74	94.38 79	84.01 9	94.94 25	94.34 11	95.45 24	93.24 23
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
3Dnovator+	83.71 3	88.13 45	90.00 53	85.94 30	86.82 74	91.06 13	94.26 34	75.39 47	88.85 43	85.76 38	85.74 109	86.92 148	78.02 45	93.03 41	92.21 35	95.39 25	92.21 35

CPTT-MVS		89.63 26	90.52 50	88.59 7	90.95 32	90.74 21	95.71 17	79.13 15	87.70 52	85.68 39	80.05 140	95.74 47	84.77 6	94.28 30	92.68 27	95.28 26	92.45 32

zzz-MVS		90.38 12	91.35 42	89.25 5	93.08 3	86.59 65	96.45 11	79.00 16	90.23 29	89.30 10	85.87 107	94.97 66	82.54 18	95.05 23	94.83 7	95.14 27	91.94 37

SixPastTwentyTwo		89.14 30	92.19 32	85.58 33	84.62 93	82.56 94	90.53 65	71.93 63	91.95 13	85.89 36	94.22 15	97.25 21	85.42 5	95.73 12	91.71 41	95.08 28	91.89 38

test_part1		87.86 50	93.26 7	81.56 77	87.23 72	86.76 63	90.91 54	70.06 74	96.50 1	76.74 94	96.63 2	98.62 2	69.45 116	92.93 44	90.92 47	94.98 29	90.46 50

PMVS	79.51 9	90.23 15	92.67 15	87.39 21	90.16 40	88.75 42	93.64 37	75.78 45	90.00 34	83.70 48	92.97 29	92.22 106	86.13 4	97.01 3	96.79 2	94.94 30	90.96 47
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
TSAR-MVS + MP.		89.67 25	92.25 29	86.65 26	91.53 19	90.98 17	96.15 14	73.30 57	87.88 51	81.83 69	92.92 30	95.15 61	82.23 19	93.58 35	92.25 34	94.87 31	93.01 25
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 44	91.34 43	84.46 47	86.85 73	90.63 23	93.01 42	67.00 103	90.35 28	87.40 22	86.86 98	96.35 31	77.66 50	92.63 49	90.84 48	94.84 32	91.68 40

IS_MVSNet		81.72 104	85.01 99	77.90 109	86.19 80	82.64 93	85.56 113	70.02 75	80.11 120	63.52 162	87.28 92	81.18 167	67.26 126	91.08 70	89.33 66	94.82 33	83.42 106

SMA-MVS		90.13 16	92.26 28	87.64 18	91.68 17	90.44 26	95.22 25	77.34 33	90.79 23	87.80 17	90.42 56	92.05 111	79.05 35	93.89 33	93.59 19	94.77 34	94.62 5
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
APDe-MVS		89.85 21	92.91 11	86.29 27	90.47 39	91.34 7	96.04 15	76.41 40	91.11 18	78.50 89	93.44 22	95.82 44	81.55 24	93.16 38	91.90 39	94.77 34	93.58 15

SteuartSystems-ACMMP		90.00 18	91.73 36	87.97 13	91.21 30	90.29 28	96.51 7	78.00 24	86.33 64	85.32 41	88.23 82	94.67 71	82.08 21	95.13 22	93.88 17	94.72 36	93.59 13
Skip Steuart: Steuart Systems R&D Blog.
CS-MVS-test		83.73 80	84.09 116	83.31 57	86.38 78	80.24 110	85.50 114	72.00 61	65.58 182	83.11 55	84.64 120	92.52 100	78.14 43	90.40 77	88.92 70	94.71 37	86.34 83

DPE-MVS		89.81 23	92.34 25	86.86 24	89.69 45	91.00 16	95.53 19	76.91 34	88.18 48	83.43 54	93.48 21	95.19 58	81.07 27	92.75 47	92.07 37	94.55 38	93.74 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CS-MVS		83.23 87	85.14 97	81.00 81	85.59 86	79.28 118	89.80 77	63.29 142	73.02 148	75.70 101	85.28 112	92.81 96	77.09 54	91.92 52	87.93 77	94.53 39	85.76 87

ACMMP_NAP		89.86 20	91.96 34	87.42 20	91.00 31	90.08 30	96.00 16	76.61 37	89.28 36	87.73 18	90.04 58	91.80 114	78.71 38	94.36 29	93.82 18	94.48 40	94.32 6

APD-MVS		89.14 30	91.25 45	86.67 25	91.73 16	91.02 15	95.50 21	77.74 25	84.04 84	79.47 84	91.48 45	94.85 68	81.14 26	92.94 42	92.20 36	94.47 41	92.24 33
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
RPSCF		88.05 47	92.61 18	82.73 68	84.24 98	88.40 44	90.04 75	66.29 107	91.46 14	82.29 63	88.93 76	96.01 40	79.38 32	95.15 21	94.90 6	94.15 42	93.40 20

OPM-MVS		89.82 22	92.24 30	86.99 23	90.86 34	89.35 38	95.07 28	75.91 44	91.16 17	86.87 31	91.07 51	97.29 20	79.13 34	93.32 36	91.99 38	94.12 43	91.49 42
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DROMVSNet		83.70 81	84.77 105	82.46 69	87.47 68	82.79 90	85.50 114	72.00 61	69.81 163	77.66 92	85.02 117	89.63 130	78.14 43	90.40 77	87.56 80	94.00 44	88.16 69

TAPA-MVS	78.00 13	85.88 61	88.37 64	82.96 63	84.69 91	88.62 43	90.62 60	64.22 128	89.15 40	88.05 15	78.83 147	93.71 84	76.20 63	90.11 82	88.22 75	94.00 44	89.97 54
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
UniMVSNet (Re)		84.95 70	88.53 61	80.78 84	87.82 65	84.21 79	88.03 92	76.50 38	81.18 110	69.29 140	92.63 35	96.83 24	69.07 117	91.23 65	89.60 63	93.97 46	84.00 101

xxxxxxxxxxxxxcwj		88.03 48	91.29 44	84.22 50	88.17 61	87.90 53	90.80 57	71.80 64	89.28 36	82.70 59	89.90 60	97.72 13	77.91 47	91.69 56	90.04 56	93.95 47	92.47 29

SF-MVS		87.85 51	90.95 47	84.22 50	88.17 61	87.90 53	90.80 57	71.80 64	89.28 36	82.70 59	89.90 60	95.37 55	77.91 47	91.69 56	90.04 56	93.95 47	92.47 29

DVP-MVS++.		90.50 10	94.18 4	86.21 28	92.52 8	90.29 28	95.29 23	76.02 42	94.24 6	82.82 57	95.84 6	97.56 17	76.82 57	93.13 39	91.20 45	93.78 49	97.01 1

UniMVSNet_NR-MVSNet		84.62 74	88.00 70	80.68 88	88.18 60	83.83 81	87.06 104	76.47 39	81.46 106	70.49 134	93.24 24	95.56 50	68.13 121	90.43 76	88.47 72	93.78 49	83.02 109

ACMH	78.40 12	88.94 39	92.62 17	84.65 43	86.45 77	87.16 60	91.47 49	68.79 88	95.49 3	89.74 6	93.55 20	98.50 3	77.96 46	94.14 32	89.57 64	93.49 51	89.94 55
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CDPH-MVS		86.66 57	88.52 62	84.48 46	89.61 46	88.27 46	92.86 43	72.69 59	80.55 117	82.71 58	86.92 97	93.32 91	75.55 69	91.00 71	89.85 59	93.47 52	89.71 56

SED-MVS		88.96 38	92.37 23	84.99 41	88.64 55	89.65 37	95.11 26	75.98 43	90.73 24	80.15 80	94.21 16	94.51 76	76.59 58	92.94 42	91.17 46	93.46 53	93.37 22

DeepC-MVS_fast	81.78 5	87.38 52	89.64 54	84.75 42	89.89 43	90.70 22	92.74 44	74.45 51	86.02 67	82.16 67	86.05 105	91.99 113	75.84 67	91.16 66	90.44 51	93.41 54	91.09 45
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 66	87.46 74	82.95 64	85.79 84	88.84 41	88.86 87	68.70 89	87.06 59	83.60 49	79.02 143	90.05 129	77.37 53	90.88 73	89.66 62	93.37 55	86.74 79
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
DVP-MVS		89.40 28	92.69 14	85.56 35	89.01 51	89.85 33	93.72 36	75.42 46	92.28 12	80.49 75	94.36 14	94.87 67	81.46 25	92.49 51	91.42 42	93.27 56	93.54 17
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
TranMVSNet+NR-MVSNet		85.23 68	89.38 56	80.39 93	88.78 54	83.77 82	87.40 99	76.75 35	85.47 71	68.99 142	95.18 9	97.55 18	67.13 128	91.61 59	89.13 68	93.26 57	82.95 112

DU-MVS		84.88 71	88.27 67	80.92 82	88.30 58	83.59 85	87.06 104	78.35 20	80.64 115	70.49 134	92.67 33	96.91 23	68.13 121	91.79 53	89.29 67	93.20 58	83.02 109

DTE-MVSNet		88.99 36	92.77 13	84.59 44	93.31 2	88.10 49	90.96 53	83.09 2	91.38 15	76.21 96	96.03 3	98.04 9	70.78 108	95.65 14	92.32 33	93.18 59	87.84 73

HPM-MVS++		88.74 41	89.54 55	87.80 16	92.58 7	85.69 73	95.10 27	78.01 23	87.08 58	87.66 20	87.89 85	92.07 109	80.28 30	90.97 72	91.41 44	93.17 60	91.69 39

NR-MVSNet		82.89 92	87.43 75	77.59 112	83.91 104	83.59 85	87.10 103	78.35 20	80.64 115	68.85 143	92.67 33	96.50 26	54.19 178	87.19 106	88.68 71	93.16 61	82.75 114

WR-MVS_H		88.99 36	93.28 6	83.99 55	91.92 12	89.13 40	91.95 47	83.23 1	90.14 31	71.92 126	95.85 5	98.01 11	71.83 99	95.82 9	93.19 23	93.07 62	90.83 49

PEN-MVS		88.86 40	92.92 10	84.11 54	92.92 5	88.05 51	90.83 56	82.67 5	91.04 19	74.83 106	95.97 4	98.47 4	70.38 109	95.70 13	92.43 31	93.05 63	88.78 65

PS-CasMVS		89.07 33	93.23 8	84.21 52	92.44 9	88.23 48	90.54 64	82.95 3	90.50 26	75.31 104	95.80 7	98.37 7	71.16 102	96.30 5	93.32 22	92.88 64	90.11 53

CP-MVSNet		88.71 42	92.63 16	84.13 53	92.39 10	88.09 50	90.47 69	82.86 4	88.79 44	75.16 105	94.87 10	97.68 15	71.05 104	96.16 6	93.18 24	92.85 65	89.64 57

Effi-MVS+-dtu		82.04 101	83.39 125	80.48 92	85.48 87	86.57 67	88.40 90	68.28 94	69.04 170	73.13 120	76.26 165	91.11 122	74.74 77	88.40 94	87.76 78	92.84 66	84.57 95

PCF-MVS	76.59 14	84.11 77	85.27 94	82.76 67	86.12 81	88.30 45	91.24 51	69.10 83	82.36 94	84.45 44	77.56 155	90.40 128	72.91 90	85.88 116	83.88 113	92.72 67	88.53 66
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MCST-MVS		84.79 72	86.48 80	82.83 66	87.30 69	87.03 62	90.46 70	69.33 82	83.14 87	82.21 66	81.69 136	92.14 108	75.09 74	87.27 103	84.78 106	92.58 68	89.30 60

PHI-MVS		86.37 59	88.14 68	84.30 48	86.65 76	87.56 56	90.76 59	70.16 73	82.55 91	89.65 7	84.89 118	92.40 102	75.97 65	90.88 73	89.70 61	92.58 68	89.03 63

NCCC		86.74 55	87.97 71	85.31 37	90.64 36	87.25 59	93.27 40	74.59 50	86.50 62	83.72 47	75.92 170	92.39 103	77.08 55	91.72 55	90.68 50	92.57 70	91.30 44

thisisatest0515		81.18 111	84.32 110	77.52 114	76.73 167	74.84 156	85.06 121	61.37 156	81.05 112	73.95 113	88.79 79	89.25 136	75.49 70	85.98 115	84.78 106	92.53 71	85.56 90

train_agg		86.67 56	87.73 72	85.43 36	91.51 20	82.72 91	94.47 32	74.22 54	81.71 99	81.54 73	89.20 72	92.87 95	78.33 42	90.12 81	88.47 72	92.51 72	89.04 62

DeepPCF-MVS	81.61 6	87.95 49	90.29 52	85.22 39	87.48 67	90.01 31	93.79 35	73.54 55	88.93 41	83.89 46	89.40 68	90.84 123	80.26 31	90.62 75	90.19 55	92.36 73	92.03 36

ETV-MVS		79.01 127	77.98 147	80.22 94	86.69 75	79.73 115	88.80 88	68.27 95	63.22 194	71.56 128	70.25 200	73.63 192	73.66 86	90.30 80	86.77 88	92.33 74	81.95 122

HQP-MVS		85.02 69	86.41 82	83.40 56	89.19 49	86.59 65	91.28 50	71.60 67	82.79 90	83.48 52	78.65 149	93.54 88	72.55 91	86.49 111	85.89 96	92.28 75	90.95 48

CNVR-MVS		86.93 54	88.98 59	84.54 45	90.11 41	87.41 58	93.23 41	73.47 56	86.31 65	82.25 64	82.96 128	92.15 107	76.04 64	91.69 56	90.69 49	92.17 76	91.64 41

CNLPA		85.50 64	88.58 60	81.91 72	84.55 95	87.52 57	90.89 55	63.56 138	88.18 48	84.06 45	83.85 125	91.34 120	76.46 60	91.27 63	89.00 69	91.96 77	88.88 64

MVS_0304		84.73 73	86.19 84	83.02 60	88.32 57	86.71 64	91.55 48	70.87 70	73.79 146	82.88 56	85.13 114	93.35 90	72.55 91	88.62 91	87.69 79	91.93 78	88.05 72

AdaColmap		84.15 76	85.14 97	83.00 62	89.08 50	87.14 61	90.56 63	70.90 69	82.40 93	80.41 76	73.82 181	84.69 157	75.19 72	91.58 60	89.90 58	91.87 79	86.48 80

3Dnovator	79.41 10	82.21 98	86.07 87	77.71 110	79.31 141	84.61 77	87.18 101	61.02 159	85.65 69	76.11 97	85.07 116	85.38 155	70.96 106	87.22 104	86.47 89	91.66 80	88.12 71

tttt0517		75.86 146	76.23 161	75.42 122	75.55 173	74.06 160	82.73 134	60.31 162	69.24 166	70.24 136	79.18 142	58.79 210	72.17 94	84.49 131	83.08 124	91.54 81	84.80 92

TSAR-MVS + GP.		85.32 67	87.41 76	82.89 65	90.07 42	85.69 73	89.07 85	72.99 58	82.45 92	74.52 110	85.09 115	87.67 145	79.24 33	91.11 67	90.41 52	91.45 82	89.45 58

PVSNet_Blended_VisFu		83.00 91	84.16 114	81.65 75	82.17 123	86.01 69	88.03 92	71.23 68	76.05 139	79.54 83	83.88 124	83.44 158	77.49 52	87.38 101	84.93 104	91.41 83	87.40 77

EIA-MVS		78.57 128	77.90 148	79.35 100	87.24 71	80.71 107	86.16 111	64.03 132	62.63 199	73.49 117	73.60 182	76.12 186	73.83 84	88.49 93	84.93 104	91.36 84	78.78 145

TSAR-MVS + ACMM		89.14 30	92.11 33	85.67 32	89.27 48	90.61 24	90.98 52	79.48 13	88.86 42	79.80 81	93.01 28	93.53 89	83.17 15	92.75 47	92.45 30	91.32 85	93.59 13

thisisatest0530		75.54 148	75.95 165	75.05 126	75.08 174	73.56 161	82.15 139	60.31 162	69.17 167	69.32 139	79.02 143	58.78 211	72.17 94	83.88 134	83.08 124	91.30 86	84.20 98

v7n		87.11 53	90.46 51	83.19 59	85.22 88	83.69 84	90.03 76	68.20 96	91.01 20	86.71 34	94.80 11	98.46 5	77.69 49	91.10 68	85.98 93	91.30 86	88.19 68

Effi-MVS+		82.33 97	83.87 118	80.52 91	84.51 96	81.32 102	87.53 97	68.05 97	74.94 144	79.67 82	82.37 133	92.31 104	72.21 93	85.06 123	86.91 85	91.18 88	84.20 98

canonicalmvs		81.22 110	86.04 88	75.60 121	83.17 114	83.18 88	80.29 150	65.82 116	85.97 68	67.98 150	77.74 153	91.51 117	65.17 137	88.62 91	86.15 92	91.17 89	89.09 61

MSP-MVS		88.51 43	91.36 41	85.19 40	90.63 37	92.01 4	95.29 23	77.52 28	90.48 27	80.21 79	90.21 57	96.08 36	76.38 61	88.30 96	91.42 42	91.12 90	91.01 46
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
Gipuma		86.47 58	89.25 57	83.23 58	83.88 105	78.78 123	85.35 118	68.42 92	92.69 11	89.03 12	91.94 38	96.32 34	81.80 22	94.45 27	86.86 86	90.91 91	83.69 103
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVS_111021_HR		83.95 78	86.10 86	81.44 78	84.62 93	80.29 109	90.51 66	68.05 97	84.07 83	80.38 77	84.74 119	91.37 119	74.23 79	90.37 79	87.25 82	90.86 92	84.59 94

abl_6				79.30 101	84.98 90	85.78 71	90.50 67	66.88 104	77.08 134	74.02 112	73.29 185	89.34 134	68.94 118			90.49 93	85.98 84

DCV-MVSNet		80.04 115	85.67 92	73.48 136	82.91 116	81.11 106	80.44 149	66.06 110	85.01 76	62.53 167	78.84 146	94.43 78	58.51 159	88.66 90	85.91 94	90.41 94	85.73 88

MVS_111021_LR		83.20 89	85.33 93	80.73 87	82.88 117	78.23 127	89.61 79	65.23 120	82.08 96	81.19 74	85.31 111	92.04 112	75.22 71	89.50 84	85.90 95	90.24 95	84.23 97

DPM-MVS		81.42 106	82.11 131	80.62 89	87.54 66	85.30 75	90.18 74	68.96 85	81.00 113	79.15 86	70.45 198	83.29 160	67.67 125	82.81 141	83.46 117	90.19 96	88.48 67

Fast-Effi-MVS+		81.42 106	83.82 120	78.62 105	82.24 122	80.62 108	87.72 95	63.51 139	73.01 149	74.75 108	83.80 126	92.70 98	73.44 88	88.15 98	85.26 100	90.05 97	83.17 107

FC-MVSNet-train		79.20 125	86.29 83	70.94 149	84.06 99	77.67 130	85.68 112	64.11 130	82.90 89	52.22 193	92.57 36	93.69 85	49.52 193	88.30 96	86.93 84	90.03 98	81.95 122

MSDG		81.39 108	84.23 113	78.09 108	82.40 121	82.47 95	85.31 120	60.91 160	79.73 123	80.26 78	86.30 101	88.27 143	69.67 112	87.20 105	84.98 103	89.97 99	80.67 130

Anonymous20231211		79.37 122	85.78 90	71.89 143	82.87 118	79.66 116	78.77 162	63.93 136	83.36 85	59.39 171	90.54 53	94.66 72	56.46 166	87.38 101	84.12 111	89.92 100	80.74 129

CANet		82.84 93	84.60 107	80.78 84	87.30 69	85.20 76	90.23 72	69.00 84	72.16 155	78.73 88	84.49 122	90.70 126	69.54 114	87.65 99	86.17 91	89.87 101	85.84 86

GeoE		81.92 103	83.87 118	79.66 97	84.64 92	79.87 112	89.75 78	65.90 114	76.12 138	75.87 99	84.62 121	92.23 105	71.96 98	86.83 108	83.60 116	89.83 102	83.81 102

DELS-MVS		79.71 118	83.74 121	75.01 128	79.31 141	82.68 92	84.79 123	60.06 166	75.43 142	69.09 141	86.13 103	89.38 133	67.16 127	85.12 122	83.87 114	89.65 103	83.57 104
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 63	88.36 65	82.19 70	86.05 82	87.69 55	90.50 67	70.60 72	86.40 63	82.33 62	89.69 65	92.52 100	74.01 83	87.53 100	86.84 87	89.63 104	87.80 74

EG-PatchMatch MVS		84.35 75	87.55 73	80.62 89	86.38 78	82.24 96	86.75 107	64.02 133	84.24 80	78.17 91	89.38 69	95.03 65	78.78 37	89.95 83	86.33 90	89.59 105	85.65 89

MAR-MVS		81.98 102	82.92 127	80.88 83	85.18 89	85.85 70	89.13 84	69.52 77	71.21 159	82.25 64	71.28 192	88.89 140	69.69 111	88.71 89	86.96 83	89.52 106	87.57 75
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 86	88.12 69	77.71 110	77.91 156	83.44 87	90.58 61	69.49 79	81.11 111	67.10 154	89.85 62	91.48 118	71.71 100	91.34 62	89.37 65	89.48 107	90.26 52
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UniMVSNet_ETH3D		85.39 65	91.12 46	78.71 103	90.48 38	83.72 83	81.76 141	82.41 6	93.84 7	64.43 160	95.41 8	98.76 1	63.72 143	93.63 34	89.74 60	89.47 108	82.74 115

MSLP-MVS++		86.29 60	89.10 58	83.01 61	85.71 85	89.79 35	87.04 106	74.39 52	85.17 75	78.92 87	77.59 154	93.57 87	82.60 17	93.23 37	91.88 40	89.42 109	92.46 31

TinyColmap		83.79 79	86.12 85	81.07 80	83.42 110	81.44 101	85.42 116	68.55 91	88.71 45	89.46 8	87.60 87	92.72 97	70.34 110	89.29 86	81.94 131	89.20 110	81.12 127

Vis-MVSNet (Re-imp)		76.15 142	80.84 136	70.68 150	83.66 108	74.80 157	81.66 143	69.59 76	80.48 118	46.94 202	87.44 89	80.63 169	53.14 183	86.87 107	84.56 109	89.12 111	71.12 170

ET-MVSNet_ETH3D		74.71 152	74.19 172	75.31 124	79.22 143	75.29 151	82.70 135	64.05 131	65.45 184	70.96 133	77.15 159	57.70 212	65.89 134	84.40 132	81.65 133	89.03 112	77.67 151

USDC		81.39 108	83.07 126	79.43 99	81.48 127	78.95 122	82.62 136	66.17 109	87.45 55	90.73 4	82.40 132	93.65 86	66.57 131	83.63 136	77.97 154	89.00 113	77.45 152

Anonymous202405211			84.68 106		83.92 103	79.45 117	79.03 160	67.79 99	82.01 97		88.77 80	92.58 99	55.93 169	86.68 109	84.26 110	88.92 114	78.98 143

v1192		83.61 82	85.23 95	81.72 74	84.05 100	82.15 97	89.54 80	66.20 108	81.38 108	86.76 33	91.79 42	96.03 38	74.88 76	81.81 149	80.92 138	88.91 115	82.50 117

v144192		83.43 85	84.97 101	81.63 76	83.43 109	81.23 104	89.42 83	66.04 112	81.45 107	86.40 35	91.46 46	95.70 48	75.76 68	82.14 145	80.23 145	88.74 116	82.57 116

OpenMVS	75.38 16	78.44 129	81.39 135	74.99 129	80.46 132	79.85 113	79.99 152	58.31 174	77.34 133	73.85 114	77.19 158	82.33 165	68.60 120	84.67 130	81.95 130	88.72 117	86.40 82

v1144		83.22 88	85.01 99	81.14 79	83.76 107	81.60 100	88.95 86	65.58 118	81.89 98	85.80 37	91.68 44	95.84 43	74.04 82	82.12 146	80.56 141	88.70 118	81.41 125

v1921920		83.49 84	84.94 102	81.80 73	83.78 106	81.20 105	89.50 81	65.91 113	81.64 101	87.18 25	91.70 43	95.39 54	75.85 66	81.56 152	80.27 144	88.60 119	82.80 113

casdiffmvs		79.93 116	84.11 115	75.05 126	81.41 129	78.99 121	82.95 133	62.90 147	81.53 103	68.60 147	91.94 38	96.03 38	65.84 135	82.89 139	77.07 162	88.59 120	80.34 136

v10		83.17 90	85.22 96	80.78 84	83.26 112	82.99 89	88.66 89	66.49 106	79.24 126	83.60 49	91.46 46	95.47 52	74.12 80	82.60 144	80.66 139	88.53 121	84.11 100

v1240		83.57 83	84.94 102	81.97 71	84.05 100	81.27 103	89.46 82	66.06 110	81.31 109	87.50 21	91.88 41	95.46 53	76.25 62	81.16 154	80.51 142	88.52 122	82.98 111

QAPM		80.43 113	84.34 109	75.86 119	79.40 140	82.06 98	79.86 155	61.94 153	83.28 86	74.73 109	81.74 135	85.44 154	70.97 105	84.99 128	84.71 108	88.29 123	88.14 70

UGNet		79.62 120	85.91 89	72.28 142	73.52 177	83.91 80	86.64 108	69.51 78	79.85 122	62.57 166	85.82 108	89.63 130	53.18 182	88.39 95	87.35 81	88.28 124	86.43 81
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		77.64 132	79.64 139	75.31 124	79.87 137	76.89 139	81.55 144	63.64 137	76.21 137	72.03 125	85.59 110	82.97 162	66.63 130	79.27 165	77.78 156	88.14 125	78.76 146

FMVSNet1		78.20 131	84.83 104	70.46 153	78.62 148	79.03 120	77.90 164	67.53 102	83.02 88	55.10 182	87.19 94	93.18 93	55.65 171	85.57 117	83.39 119	87.98 126	82.40 118

FPMVS		81.56 105	84.04 117	78.66 104	82.92 115	75.96 146	86.48 110	65.66 117	84.67 79	71.47 129	77.78 152	83.22 161	77.57 51	91.24 64	90.21 54	87.84 127	85.21 91

v2v482		82.20 99	84.26 111	79.81 96	82.67 119	80.18 111	87.67 96	63.96 135	81.69 100	84.73 42	91.27 49	96.33 33	72.05 97	81.94 148	79.56 148	87.79 128	78.84 144

v8		82.20 99	84.56 108	79.45 98	82.42 120	81.65 99	87.26 100	64.27 127	79.36 125	81.70 71	91.04 52	95.75 46	73.30 89	82.82 140	79.18 151	87.74 129	82.09 120

PVSNet_BlendedMVS		76.45 140	78.12 145	74.49 132	76.76 161	78.46 124	79.65 156	63.26 143	65.42 185	73.15 118	75.05 175	88.96 137	66.51 132	82.73 142	77.66 157	87.61 130	78.60 147

PVSNet_Blended		76.45 140	78.12 145	74.49 132	76.76 161	78.46 124	79.65 156	63.26 143	65.42 185	73.15 118	75.05 175	88.96 137	66.51 132	82.73 142	77.66 157	87.61 130	78.60 147

tfpn200view9		72.01 165	75.40 167	68.06 168	77.97 154	76.44 141	77.04 169	62.67 148	66.81 175	50.82 198	67.30 204	75.67 188	52.46 189	85.06 123	82.64 127	87.41 132	73.86 163

pmmvs6		80.46 112	88.34 66	71.26 145	81.96 124	77.51 131	77.54 165	68.83 87	93.72 8	55.92 179	93.94 19	98.03 10	55.94 168	89.21 87	85.61 97	87.36 133	80.38 132

thres600view7		74.34 154	78.43 144	69.56 159	80.47 131	76.28 143	78.65 163	62.56 149	77.39 132	52.53 189	74.03 179	76.78 183	55.90 170	85.06 123	85.19 101	87.25 134	74.29 161

thres200		72.41 164	76.00 164	68.21 167	78.28 150	76.28 143	74.94 183	62.56 149	72.14 156	51.35 197	69.59 202	76.51 184	54.89 173	85.06 123	80.51 142	87.25 134	71.92 169

IB-MVS	71.28 17	75.21 149	77.00 155	73.12 140	76.76 161	77.45 132	83.05 131	58.92 171	63.01 195	64.31 161	59.99 213	87.57 146	68.64 119	86.26 114	82.34 129	87.05 136	82.36 119
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)		79.05 126	86.66 78	70.18 155	83.32 111	75.99 145	77.54 165	63.98 134	90.68 25	55.84 180	94.80 11	96.06 37	53.73 181	86.27 113	83.22 123	86.65 137	79.61 141

pm-mvs1		78.21 130	85.68 91	69.50 160	80.38 133	75.73 148	76.25 173	65.04 121	87.59 53	54.47 184	93.16 26	95.99 42	54.20 177	86.37 112	82.98 126	86.64 138	77.96 150

MVSTER		68.08 181	69.73 183	66.16 177	66.33 204	70.06 172	75.71 180	52.36 194	55.18 213	58.64 173	70.23 201	56.72 215	57.34 163	79.68 163	76.03 167	86.61 139	80.20 138

thres400		73.13 160	76.99 156	68.62 164	79.46 139	74.93 155	77.23 167	61.23 158	75.54 140	52.31 192	72.20 187	77.10 181	54.89 173	82.92 138	82.62 128	86.57 140	73.66 166

EPNet		79.36 123	79.44 140	79.27 102	89.51 47	77.20 136	88.35 91	77.35 32	68.27 172	74.29 111	76.31 163	79.22 172	59.63 155	85.02 127	85.45 99	86.49 141	84.61 93
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PatchMatch-RL		76.05 143	76.64 157	75.36 123	77.84 157	69.87 174	81.09 146	63.43 140	71.66 157	68.34 149	71.70 188	81.76 166	74.98 75	84.83 129	83.44 118	86.45 142	73.22 167

CLD-MVS		82.75 96	87.22 77	77.54 113	88.01 64	85.76 72	90.23 72	54.52 185	82.28 95	82.11 68	88.48 81	95.27 56	63.95 141	89.41 85	88.29 74	86.45 142	81.01 128
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
IterMVS-LS		79.79 117	82.56 129	76.56 118	81.83 125	77.85 129	79.90 154	69.42 81	78.93 128	71.21 130	90.47 54	85.20 156	70.86 107	80.54 159	80.57 140	86.15 144	84.36 96
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
V42		79.59 121	83.59 123	74.93 131	69.61 190	77.05 138	86.59 109	55.84 180	78.42 130	77.29 93	89.84 63	95.08 63	74.12 80	83.05 137	80.11 146	86.12 145	81.59 124

GBi-Net		73.17 158	77.64 149	67.95 169	76.76 161	77.36 133	75.77 177	64.57 124	62.99 196	51.83 194	76.05 166	77.76 178	52.73 186	85.57 117	83.39 119	86.04 146	80.37 133

test1		73.17 158	77.64 149	67.95 169	76.76 161	77.36 133	75.77 177	64.57 124	62.99 196	51.83 194	76.05 166	77.76 178	52.73 186	85.57 117	83.39 119	86.04 146	80.37 133

FMVSNet2		74.43 153	79.70 138	68.27 166	76.76 161	77.36 133	75.77 177	65.36 119	72.28 153	52.97 188	81.92 134	85.61 153	52.73 186	80.66 158	79.73 147	86.04 146	80.37 133

ambc			88.38 63		91.62 18	87.97 52	84.48 125		88.64 46	87.93 16	87.38 90	94.82 70	74.53 78	89.14 88	83.86 115	85.94 149	86.84 78

Fast-Effi-MVS+-dtu		76.92 135	77.18 153	76.62 117	79.55 138	79.17 119	84.80 122	77.40 30	64.46 189	68.75 145	70.81 196	86.57 149	63.36 148	81.74 150	81.76 132	85.86 150	75.78 156

PM-MVS		80.42 114	83.63 122	76.67 116	78.04 153	72.37 166	87.14 102	60.18 165	80.13 119	71.75 127	86.12 104	93.92 83	77.08 55	86.56 110	85.12 102	85.83 151	81.18 126

Baseline_NR-MVSNet		82.79 94	86.51 79	78.44 107	88.30 58	75.62 150	87.81 94	74.97 49	81.53 103	66.84 155	94.71 13	96.46 27	66.90 129	91.79 53	83.37 122	85.83 151	82.09 120

thres100view900		69.86 172	72.97 179	66.24 176	77.97 154	72.49 165	73.29 187	59.12 169	66.81 175	50.82 198	67.30 204	75.67 188	50.54 192	78.24 168	79.40 149	85.71 153	70.88 171

pmmvs-eth3d		79.64 119	82.06 132	76.83 115	80.05 135	72.64 164	87.47 98	66.59 105	80.83 114	73.50 116	89.32 70	93.20 92	67.78 123	80.78 157	81.64 134	85.58 154	76.01 154

MVS_Test		76.72 137	79.40 141	73.60 135	78.85 147	74.99 154	79.91 153	61.56 155	69.67 164	72.44 121	85.98 106	90.78 124	63.50 146	78.30 167	75.74 169	85.33 155	80.31 137

v148		79.33 124	82.32 130	75.84 120	80.14 134	75.74 147	81.98 140	57.06 177	81.51 105	79.36 85	89.42 67	96.42 29	71.32 101	81.54 153	75.29 171	85.20 156	76.32 153

tfpnnormal		77.16 134	84.26 111	68.88 163	81.02 130	75.02 153	76.52 172	63.30 141	87.29 56	52.40 191	91.24 50	93.97 81	54.85 175	85.46 120	81.08 136	85.18 157	75.76 157

FC-MVSNet-test		75.91 145	83.59 123	66.95 174	76.63 169	69.07 176	85.33 119	64.97 122	84.87 78	41.95 207	93.17 25	87.04 147	47.78 196	91.09 69	85.56 98	85.06 158	74.34 160

CANet_DTU		75.04 150	78.45 143	71.07 146	77.27 158	77.96 128	83.88 128	58.00 175	64.11 190	68.67 146	75.65 172	88.37 142	53.92 180	82.05 147	81.11 135	84.67 159	79.88 139

FMVSNet3		71.40 169	75.20 170	66.97 173	75.00 175	76.59 140	74.29 184	64.57 124	62.99 196	51.83 194	76.05 166	77.76 178	51.49 191	76.58 175	77.03 163	84.62 160	79.43 142

pmmvs4		75.92 144	77.48 152	74.10 134	78.21 152	70.94 168	84.06 126	64.78 123	75.13 143	68.47 148	84.12 123	83.32 159	64.74 140	75.93 179	79.14 152	84.31 161	73.77 164

baseline2		68.71 178	68.34 187	69.14 161	75.69 171	69.70 175	76.60 171	55.53 182	60.13 204	62.07 169	66.76 206	60.35 205	60.77 152	76.53 177	74.03 173	84.19 162	70.88 171

GA-MVS		75.01 151	76.39 159	73.39 137	78.37 149	75.66 149	80.03 151	58.40 173	70.51 161	75.85 100	83.24 127	76.14 185	63.75 142	77.28 171	76.62 165	83.97 163	75.30 159

CDS-MVSNet		73.07 161	77.02 154	68.46 165	81.62 126	72.89 163	79.56 158	70.78 71	69.56 165	52.52 190	77.37 157	81.12 168	42.60 201	84.20 133	83.93 112	83.65 164	70.07 175
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
RPMNet		67.02 183	63.99 198	70.56 152	71.55 185	67.63 180	75.81 175	69.44 80	59.93 205	63.24 163	64.32 208	47.51 223	59.68 154	70.37 196	69.64 187	83.64 165	68.49 180

CR-MVSNet		69.56 174	68.34 187	70.99 148	72.78 182	67.63 180	64.47 206	67.74 100	59.93 205	72.30 122	80.10 138	56.77 214	65.04 138	71.64 191	72.91 177	83.61 166	69.40 177

PMMVS		61.98 197	65.61 193	57.74 195	45.03 218	51.76 209	69.54 199	35.05 211	55.49 212	55.32 181	68.23 203	78.39 176	58.09 160	70.21 197	71.56 182	83.42 167	63.66 188

IterMVS-SCA-FT		77.23 133	79.18 142	74.96 130	76.67 168	79.85 113	75.58 182	61.34 157	73.10 147	73.79 115	86.23 102	79.61 171	79.00 36	80.28 161	75.50 170	83.41 168	79.70 140

diffmvs		76.74 136	81.61 134	71.06 147	75.64 172	74.45 159	80.68 148	57.57 176	77.48 131	67.62 153	88.95 75	93.94 82	61.98 150	79.74 162	76.18 166	82.85 169	80.50 131

EU-MVSNet		76.48 139	80.53 137	71.75 144	67.62 196	70.30 171	81.74 142	54.06 188	75.47 141	71.01 132	80.10 138	93.17 94	73.67 85	83.73 135	77.85 155	82.40 170	83.07 108

baseline1		69.62 173	73.55 176	65.02 185	78.95 146	70.39 170	71.38 193	62.03 152	70.97 160	47.95 201	78.47 150	68.19 198	47.77 197	79.65 164	76.94 164	82.05 171	70.27 173

HyFIR lowres test		73.29 157	74.14 173	72.30 141	73.08 179	78.33 126	83.12 130	62.41 151	63.81 191	62.13 168	76.67 162	78.50 175	71.09 103	74.13 183	77.47 160	81.98 172	70.10 174

CVMVSNet		75.65 147	77.62 151	73.35 139	71.95 183	69.89 173	83.04 132	60.84 161	69.12 168	68.76 144	79.92 141	78.93 174	73.64 87	81.02 155	81.01 137	81.86 173	83.43 105

pmmvs5		68.91 176	74.35 171	62.56 188	67.45 198	66.78 184	71.70 190	51.47 197	67.17 174	56.25 178	82.41 131	88.59 141	47.21 198	73.21 189	74.23 172	81.30 174	68.03 181

gg-mvs-nofinetune		72.68 163	75.21 169	69.73 157	81.48 127	69.04 177	70.48 194	76.67 36	86.92 60	67.80 152	88.06 84	64.67 200	42.12 203	77.60 169	73.65 174	79.81 175	66.57 182

IterMVS		73.62 155	76.53 158	70.23 154	71.83 184	77.18 137	80.69 147	53.22 192	72.23 154	66.62 156	85.21 113	78.96 173	69.54 114	76.28 178	71.63 181	79.45 176	74.25 162
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MS-PatchMatch		71.18 170	73.99 174	67.89 171	77.16 159	71.76 167	77.18 168	56.38 179	67.35 173	55.04 183	74.63 177	75.70 187	62.38 149	76.62 174	75.97 168	79.22 177	75.90 155

gm-plane-assit		71.56 167	69.99 182	73.39 137	84.43 97	73.21 162	90.42 71	51.36 198	84.08 82	76.00 98	91.30 48	37.09 224	59.01 157	73.65 186	70.24 185	79.09 178	60.37 199

MDA-MVSNet-bldmvs		76.51 138	82.87 128	69.09 162	50.71 217	74.72 158	84.05 127	60.27 164	81.62 102	71.16 131	88.21 83	91.58 115	69.62 113	92.78 46	77.48 159	78.75 179	73.69 165

EPNet_dtu		71.90 166	73.03 178	70.59 151	78.28 150	61.64 195	82.44 137	64.12 129	63.26 193	69.74 137	71.47 190	82.41 163	51.89 190	78.83 166	78.01 153	77.07 180	75.60 158
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CMPMVS	55.74 18	71.56 167	76.26 160	66.08 179	68.11 194	63.91 192	63.17 208	50.52 200	68.79 171	75.49 102	70.78 197	85.67 152	63.54 145	81.58 151	77.20 161	75.63 181	85.86 85
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test-mter		59.39 201	61.59 205	56.82 197	53.21 213	54.82 203	73.12 189	26.57 216	53.19 214	56.31 177	64.71 207	60.47 204	56.36 167	68.69 200	64.27 195	75.38 182	65.00 184

test-LLR		62.15 196	59.46 212	65.29 183	79.07 144	52.66 207	69.46 200	62.93 145	50.76 216	53.81 186	63.11 210	58.91 208	52.87 184	66.54 205	62.34 197	73.59 183	61.87 195

TESTMET0.1,1		57.21 204	59.46 212	54.60 203	50.95 215	52.66 207	69.46 200	26.91 215	50.76 216	53.81 186	63.11 210	58.91 208	52.87 184	66.54 205	62.34 197	73.59 183	61.87 195

pmmvs3		62.72 193	68.71 186	55.74 199	50.74 216	57.10 200	70.05 196	28.82 214	61.57 203	57.39 175	71.19 194	85.73 151	53.96 179	73.36 188	69.43 188	73.47 185	62.55 193

CostFormer		66.81 184	66.94 190	66.67 175	72.79 181	68.25 179	79.55 159	55.57 181	65.52 183	62.77 165	76.98 160	60.09 206	56.73 165	65.69 207	62.35 196	72.59 186	69.71 176

MDTV_nov1_ep13_2view		72.96 162	75.59 166	69.88 156	71.15 187	64.86 189	82.31 138	54.45 186	76.30 136	78.32 90	86.52 99	91.58 115	61.35 151	76.80 172	66.83 192	71.70 187	66.26 183

MDTV_nov1_ep13		64.96 187	64.77 195	65.18 184	67.08 199	62.46 194	75.80 176	51.10 199	62.27 200	69.74 137	74.12 178	62.65 201	55.64 172	68.19 201	62.16 200	71.70 187	61.57 197

PatchT		66.25 185	66.76 191	65.67 182	55.87 212	60.75 196	70.17 195	59.00 170	59.80 207	72.30 122	78.68 148	54.12 219	65.04 138	71.64 191	72.91 177	71.63 189	69.40 177

baseline		69.33 175	75.37 168	62.28 189	66.54 202	66.67 185	73.95 186	48.07 201	66.10 178	59.26 172	82.45 130	86.30 150	54.44 176	74.42 182	73.25 176	71.42 190	78.43 149

dps		65.14 186	64.50 196	65.89 181	71.41 186	65.81 188	71.44 192	61.59 154	58.56 208	61.43 170	75.45 173	52.70 221	58.06 161	69.57 198	64.65 194	71.39 191	64.77 185

SCA		68.54 179	67.52 189	69.73 157	67.79 195	75.04 152	76.96 170	68.94 86	66.41 177	67.86 151	74.03 179	60.96 203	65.55 136	68.99 199	65.67 193	71.30 192	61.54 198

MVS-HIRNet		59.74 199	58.74 215	60.92 191	57.74 211	45.81 215	56.02 215	58.69 172	55.69 211	65.17 159	70.86 195	71.66 194	56.75 164	61.11 212	53.74 211	71.17 193	52.28 210

MIMVSNet1		73.40 156	81.85 133	63.55 186	72.90 180	64.37 190	84.58 124	53.60 190	90.84 21	53.92 185	87.75 86	96.10 35	45.31 199	85.37 121	79.32 150	70.98 194	69.18 179

test20.03		69.91 171	76.20 162	62.58 187	84.01 102	67.34 182	75.67 181	65.88 115	79.98 121	40.28 211	82.65 129	89.31 135	39.63 206	77.41 170	73.28 175	69.98 195	63.40 190

Anonymous20231206		67.28 182	73.41 177	60.12 192	76.45 170	63.61 193	74.21 185	56.52 178	76.35 135	42.23 206	75.81 171	90.47 127	41.51 204	74.52 180	69.97 186	69.83 196	63.17 191

CHOSEN 1792x2688		68.80 177	71.09 180	66.13 178	69.11 192	68.89 178	78.98 161	54.68 183	61.63 201	56.69 176	71.56 189	78.39 176	67.69 124	72.13 190	72.01 180	69.63 197	73.02 168

testgi		68.20 180	76.05 163	59.04 193	79.99 136	67.32 183	81.16 145	51.78 196	84.91 77	39.36 212	73.42 183	95.19 58	32.79 212	76.54 176	70.40 184	69.14 198	64.55 186

TAMVS		63.02 190	69.30 184	55.70 200	70.12 188	56.89 201	69.63 198	45.13 204	70.23 162	38.00 213	77.79 151	75.15 190	42.60 201	74.48 181	72.81 179	68.70 199	57.75 206

test0.0.03 1		61.79 198	65.33 194	57.65 196	79.07 144	64.09 191	68.51 203	62.93 145	61.59 202	33.71 215	61.58 212	71.58 196	33.43 211	70.95 194	68.68 189	68.26 200	58.82 202

tpm cat1		64.79 189	62.74 203	67.17 172	74.61 176	65.91 187	76.18 174	59.32 168	64.88 188	66.41 157	71.21 193	53.56 220	59.17 156	61.53 211	58.16 205	67.33 201	63.95 187

PatchmatchNet		64.81 188	63.74 199	66.06 180	69.21 191	58.62 199	73.16 188	60.01 167	65.92 179	66.19 158	76.27 164	59.09 207	60.45 153	66.58 204	61.47 202	67.33 201	58.24 204
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MIMVSNet		63.02 190	69.02 185	56.01 198	68.20 193	59.26 198	70.01 197	53.79 189	71.56 158	41.26 210	71.38 191	82.38 164	36.38 208	71.43 193	67.32 191	66.45 203	59.83 201

FMVSNet5		56.37 207	60.14 209	51.98 208	60.83 208	59.58 197	66.85 205	42.37 207	52.68 215	41.33 209	47.09 216	54.68 218	35.28 209	73.88 184	70.77 183	65.24 204	62.26 194

CHOSEN 280x420		56.32 208	58.85 214	53.36 204	51.63 214	39.91 218	69.12 202	38.61 210	56.29 210	36.79 214	48.84 215	62.59 202	63.39 147	73.61 187	67.66 190	60.61 205	63.07 192

GG-mvs-BLEND		41.63 213	60.36 208	19.78 214	0.14 225	66.04 186	55.66 216	0.17 222	57.64 209	2.42 224	51.82 214	69.42 197	0.28 221	64.11 210	58.29 204	60.02 206	55.18 208

tpm		62.79 192	63.25 200	62.26 190	70.09 189	53.78 204	71.65 191	47.31 202	65.72 181	76.70 95	80.62 137	56.40 217	48.11 195	64.20 209	58.54 203	59.70 207	63.47 189

tpmrst		59.42 200	60.02 210	58.71 194	67.56 197	53.10 206	66.99 204	51.88 195	63.80 192	57.68 174	76.73 161	56.49 216	48.73 194	56.47 215	55.55 208	59.43 208	58.02 205

pmnet_mix02		62.60 194	70.81 181	53.02 205	66.56 201	50.44 211	62.81 209	46.84 203	79.13 127	43.76 205	87.45 88	90.75 125	39.85 205	70.48 195	57.09 206	58.27 209	60.32 200

new-patchmatchnet		62.59 195	73.79 175	49.53 209	76.98 160	53.57 205	53.46 217	54.64 184	85.43 72	28.81 216	91.94 38	96.41 30	25.28 214	76.80 172	53.66 212	57.99 210	58.69 203

EPMVS		56.62 206	59.77 211	52.94 206	62.41 207	50.55 210	60.66 211	52.83 193	65.15 187	41.80 208	77.46 156	57.28 213	42.68 200	59.81 213	54.82 209	57.23 211	53.35 209

new_pmnet		52.29 210	63.16 201	39.61 212	58.89 210	44.70 216	48.78 219	34.73 212	65.88 180	17.85 220	73.42 183	80.00 170	23.06 215	67.00 203	62.28 199	54.36 212	48.81 212

E-PMN		59.07 202	62.79 202	54.72 201	67.01 200	47.81 214	60.44 212	43.40 205	72.95 150	44.63 204	70.42 199	73.17 193	58.73 158	80.97 156	51.98 213	54.14 213	42.26 215

EMVS		58.97 203	62.63 204	54.70 202	66.26 205	48.71 212	61.74 210	42.71 206	72.80 152	46.00 203	73.01 186	71.66 194	57.91 162	80.41 160	50.68 215	53.55 214	41.11 216

ADS-MVSNet		56.89 205	61.09 206	52.00 207	59.48 209	48.10 213	58.02 213	54.37 187	72.82 151	49.19 200	75.32 174	65.97 199	37.96 207	59.34 214	54.66 210	52.99 215	51.42 211

N_pmnet		54.95 209	65.90 192	42.18 210	66.37 203	43.86 217	57.92 214	39.79 209	79.54 124	17.24 221	86.31 100	87.91 144	25.44 213	64.68 208	51.76 214	46.33 216	47.23 213

MVE	41.12 19	51.80 211	60.92 207	41.16 211	35.21 220	34.14 220	48.45 220	41.39 208	69.11 169	19.53 219	63.33 209	73.80 191	63.56 144	67.19 202	61.51 201	38.85 217	57.38 207
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		48.13 212	64.06 197	29.55 213	44.06 219	36.69 219	51.95 218	29.97 213	74.75 145	8.90 223	76.02 169	91.24 121	7.53 217	73.78 185	55.91 207	34.87 218	40.01 217

test_method		22.69 214	26.99 216	17.67 215	2.13 222	4.31 223	27.50 221	4.53 218	37.94 218	24.52 218	36.20 218	51.40 222	15.26 216	29.86 217	17.09 217	32.07 219	12.16 218

DeepMVS_CX						17.78 221	20.40 222	6.69 217	31.41 219	9.80 222	38.61 217	34.88 225	33.78 210	28.41 218		23.59 220	45.77 214

tmp_tt				13.54 216	16.73 221	6.42 222	8.49 223	2.36 219	28.69 220	27.44 217	18.40 219	13.51 226	3.70 218	33.23 216	36.26 216	22.54 221

testmvs		0.93 216	1.37 218	0.41 218	0.36 224	0.36 225	0.62 225	0.39 220	1.48 221	0.18 226	2.41 220	1.31 228	0.41 220	1.25 220	1.08 219	0.48 222	1.68 219

test123		1.06 215	1.41 217	0.64 217	0.39 223	0.48 224	0.52 226	0.25 221	1.11 222	1.37 225	2.01 221	1.98 227	0.87 219	1.43 219	1.27 218	0.46 223	1.62 220

uanet_test		0.00 217	0.00 219	0.00 219	0.00 226	0.00 226	0.00 227	0.00 223	0.00 223	0.00 227	0.00 222	0.00 229	0.00 222	0.00 221	0.00 220	0.00 224	0.00 221

sosnet-low-res		0.00 217	0.00 219	0.00 219	0.00 226	0.00 226	0.00 227	0.00 223	0.00 223	0.00 227	0.00 222	0.00 229	0.00 222	0.00 221	0.00 220	0.00 224	0.00 221

sosnet		0.00 217	0.00 219	0.00 219	0.00 226	0.00 226	0.00 227	0.00 223	0.00 223	0.00 227	0.00 222	0.00 229	0.00 222	0.00 221	0.00 220	0.00 224	0.00 221

RE-MVS-def										87.10 29

9.14												89.43 132

SR-MVS					91.82 14			80.80 7				95.53 51

our_test_3					73.27 178	70.91 169	83.26 129

MTAPA										89.37 9		94.85 68

MTMP										90.54 5		95.16 60

Patchmatch-RL test							4.13 224

mPP-MVS					93.05 4							95.77 45

NP-MVS									78.65 129

Patchmtry						56.88 202	64.47 206	67.74 100		72.30 122

High-resolution multi-view benchmark