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.

HFP-MVS		98.48 9	98.62 10	98.32 12	99.39 18	99.33 16	99.27 10	97.42 19	98.27 6	95.25 24	98.34 9	98.83 26	99.08 1	98.26 27	98.08 24	99.48 22	99.26 29

ACMMPR		98.40 12	98.49 12	98.28 14	99.41 14	99.40 9	99.36 3	97.35 22	98.30 5	95.02 26	97.79 17	98.39 37	99.04 2	98.26 27	98.10 22	99.50 21	99.22 35

SD-MVS		98.52 7	98.77 8	98.23 16	98.15 50	99.26 21	98.79 26	97.59 16	98.52 2	96.25 16	97.99 15	99.75 5	99.01 3	98.27 26	97.97 27	99.59 4	99.63 1
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
CPTT-MVS		97.78 26	97.54 33	98.05 22	98.91 35	99.05 32	99.00 20	96.96 34	97.14 40	95.92 18	95.50 42	98.78 28	98.99 4	97.20 61	96.07 82	98.54 151	99.04 63

DVP-MVS		98.86 3	98.97 2	98.75 2	99.43 13	99.63 1	99.25 12	97.81 1	98.62 1	97.69 1	97.59 20	99.90 1	98.93 5	98.99 3	98.42 11	99.37 52	99.62 3
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
MSLP-MVS++		98.04 23	97.93 32	98.18 17	99.10 28	99.09 31	98.34 36	96.99 33	97.54 30	96.60 13	94.82 49	98.45 35	98.89 6	97.46 55	98.77 4	99.17 86	99.37 16

TSAR-MVS + MP.		98.49 8	98.78 7	98.15 20	98.14 51	99.17 28	99.34 5	97.18 30	98.44 4	95.72 20	97.84 16	99.28 11	98.87 7	99.05 1	98.05 25	99.66 1	99.60 6
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
zzz-MVS		98.43 11	98.31 23	98.57 4	99.48 5	99.40 9	99.32 8	97.62 13	97.70 22	96.67 11	96.59 32	99.09 21	98.86 8	98.65 12	97.56 43	99.45 30	99.17 45

APDe-MVS		98.87 2	98.96 3	98.77 1	99.58 2	99.53 5	99.44 1	97.81 1	98.22 9	97.33 4	98.70 4	99.33 9	98.86 8	98.96 5	98.40 13	99.63 3	99.57 8

SMA-MVS		98.66 6	98.89 6	98.39 9	99.60 1	99.41 8	99.00 20	97.63 12	97.78 17	95.83 19	98.33 10	99.83 3	98.85 10	98.93 7	98.56 6	99.41 43	99.40 14
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
CNVR-MVS		98.47 10	98.46 15	98.48 7	99.40 15	99.05 32	99.02 19	97.54 17	97.73 18	96.65 12	97.20 29	99.13 19	98.85 10	98.91 8	98.10 22	99.41 43	99.08 54

PGM-MVS		97.81 25	98.11 28	97.46 30	99.55 3	99.34 15	99.32 8	94.51 46	96.21 60	93.07 37	98.05 14	97.95 42	98.82 12	98.22 30	97.89 32	99.48 22	99.09 53

CP-MVS		98.32 17	98.34 21	98.29 13	99.34 21	99.30 17	99.15 14	97.35 22	97.49 31	95.58 22	97.72 18	98.62 33	98.82 12	98.29 25	97.67 38	99.51 19	99.28 24

MCST-MVS		98.20 18	98.36 18	98.01 23	99.40 15	99.05 32	99.00 20	97.62 13	97.59 29	93.70 34	97.42 27	99.30 10	98.77 14	98.39 23	97.48 45	99.59 4	99.31 23

AdaColmap		97.53 30	96.93 45	98.24 15	99.21 24	98.77 62	98.47 34	97.34 24	96.68 51	96.52 14	95.11 47	96.12 58	98.72 15	97.19 63	96.24 78	99.17 86	98.39 111

ACMMP_NAP		98.20 18	98.49 12	97.85 26	99.50 4	99.40 9	99.26 11	97.64 11	97.47 33	92.62 46	97.59 20	99.09 21	98.71 16	98.82 11	97.86 33	99.40 46	99.19 39

DeepC-MVS_fast	96.13 1	98.13 20	98.27 25	97.97 25	99.16 27	99.03 39	99.05 18	97.24 27	98.22 9	94.17 32	95.82 38	98.07 39	98.69 17	98.83 10	98.80 2	99.52 14	99.10 51
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SED-MVS		98.90 1	99.07 1	98.69 3	99.38 19	99.61 2	99.33 7	97.80 3	98.25 7	97.60 2	98.87 3	99.89 2	98.67 18	99.02 2	98.26 17	99.36 54	99.61 5

MSP-MVS		98.73 5	98.93 4	98.50 6	99.44 12	99.57 3	99.36 3	97.65 8	98.14 11	96.51 15	98.49 6	99.65 7	98.67 18	98.60 13	98.42 11	99.40 46	99.63 1
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
HPM-MVS++		98.34 16	98.47 14	98.18 17	99.46 8	99.15 29	99.10 16	97.69 7	97.67 25	94.93 27	97.62 19	99.70 6	98.60 20	98.45 18	97.46 46	99.31 61	99.26 29

DPE-MVS		98.75 4	98.91 5	98.57 4	99.21 24	99.54 4	99.42 2	97.78 5	97.49 31	96.84 9	98.94 1	99.82 4	98.59 21	98.90 9	98.22 18	99.56 10	99.48 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
NCCC		98.10 21	98.05 30	98.17 19	99.38 19	99.05 32	99.00 20	97.53 18	98.04 13	95.12 25	94.80 50	99.18 17	98.58 22	98.49 16	97.78 36	99.39 48	98.98 71

MP-MVS		98.09 22	98.30 24	97.84 27	99.34 21	99.19 27	99.23 13	97.40 20	97.09 42	93.03 40	97.58 22	98.85 25	98.57 23	98.44 20	97.69 37	99.48 22	99.23 33
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
X-MVS		97.84 24	98.19 27	97.42 31	99.40 15	99.35 12	99.06 17	97.25 26	97.38 34	90.85 57	96.06 36	98.72 29	98.53 24	98.41 22	98.15 21	99.46 26	99.28 24

APD-MVS		98.36 15	98.32 22	98.41 8	99.47 6	99.26 21	99.12 15	97.77 6	96.73 49	96.12 17	97.27 28	98.88 24	98.46 25	98.47 17	98.39 14	99.52 14	99.22 35
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
train_agg		97.65 29	98.06 29	97.18 34	98.94 33	98.91 53	98.98 24	97.07 32	96.71 50	90.66 62	97.43 26	99.08 23	98.20 26	97.96 42	97.14 57	99.22 78	99.19 39

DeepC-MVS	94.87 4	96.76 47	96.50 52	97.05 36	98.21 49	99.28 19	98.67 27	97.38 21	97.31 35	90.36 69	89.19 100	93.58 69	98.19 27	98.31 24	98.50 7	99.51 19	99.36 17
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SteuartSystems-ACMMP		98.38 14	98.71 9	97.99 24	99.34 21	99.46 7	99.34 5	97.33 25	97.31 35	94.25 30	98.06 13	99.17 18	98.13 28	98.98 4	98.46 9	99.55 11	99.54 9
Skip Steuart: Steuart Systems R&D Blog.
xxxxxxxxxxxxxcwj		97.07 38	95.99 60	98.33 10	99.45 9	99.05 32	98.27 37	97.65 8	97.73 18	97.02 7	98.18 11	81.99 142	98.11 29	98.15 32	97.62 39	99.45 30	99.19 39

SF-MVS		98.39 13	98.45 16	98.33 10	99.45 9	99.05 32	98.27 37	97.65 8	97.73 18	97.02 7	98.18 11	99.25 14	98.11 29	98.15 32	97.62 39	99.45 30	99.19 39

CSCG		97.44 32	97.18 40	97.75 28	99.47 6	99.52 6	98.55 31	95.41 41	97.69 24	95.72 20	94.29 53	95.53 62	98.10 31	96.20 100	97.38 51	99.24 72	99.62 3

3Dnovator+	93.91 7	97.23 35	97.22 37	97.24 33	98.89 36	98.85 58	98.26 39	93.25 58	97.99 14	95.56 23	90.01 96	98.03 41	98.05 32	97.91 43	98.43 10	99.44 38	99.35 18

TSAR-MVS + GP.		97.45 31	98.36 18	96.39 43	95.56 83	98.93 50	97.74 49	93.31 55	97.61 28	94.24 31	98.44 8	99.19 16	98.03 33	97.60 51	97.41 49	99.44 38	99.33 20

PLC	94.95 3	97.37 33	96.77 49	98.07 21	98.97 32	98.21 84	97.94 46	96.85 36	97.66 26	97.58 3	93.33 58	96.84 48	98.01 34	97.13 65	96.20 80	99.09 98	98.01 123
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
3Dnovator	93.79 8	97.08 37	97.20 38	96.95 38	99.09 29	99.03 39	98.20 40	93.33 54	97.99 14	93.82 33	90.61 90	96.80 49	97.82 35	97.90 44	98.78 3	99.47 25	99.26 29

LS3D		95.46 58	95.14 73	95.84 51	97.91 55	98.90 55	98.58 30	97.79 4	97.07 43	83.65 115	88.71 103	88.64 101	97.82 35	97.49 54	97.42 48	99.26 71	97.72 135

CNLPA		96.90 42	96.28 55	97.64 29	98.56 43	98.63 74	96.85 64	96.60 37	97.73 18	97.08 6	89.78 98	96.28 56	97.80 37	96.73 77	96.63 69	98.94 116	98.14 122

ACMMP		97.37 33	97.48 35	97.25 32	98.88 37	99.28 19	98.47 34	96.86 35	97.04 44	92.15 47	97.57 23	96.05 60	97.67 38	97.27 59	95.99 87	99.46 26	99.14 50
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
canonicalmvs		95.25 64	95.45 68	95.00 65	95.27 91	98.72 66	96.89 62	89.82 103	96.51 53	90.84 60	93.72 57	86.01 115	97.66 39	95.78 112	97.94 29	99.54 13	99.50 10

QAPM		96.78 46	97.14 42	96.36 44	99.05 30	99.14 30	98.02 43	93.26 56	97.27 37	90.84 60	91.16 82	97.31 44	97.64 40	97.70 49	98.20 19	99.33 56	99.18 43

TAPA-MVS	94.18 5	96.38 48	96.49 53	96.25 45	98.26 48	98.66 69	98.00 44	94.96 44	97.17 39	89.48 81	92.91 63	96.35 53	97.53 41	96.59 82	95.90 90	99.28 65	97.82 127
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PHI-MVS		97.78 26	98.44 17	97.02 37	98.73 38	99.25 23	98.11 41	95.54 40	96.66 52	92.79 43	98.52 5	99.38 8	97.50 42	97.84 45	98.39 14	99.45 30	99.03 64

ETV-MVS		96.31 49	97.47 36	94.96 67	94.79 103	98.78 61	96.08 87	91.41 84	96.16 61	90.50 64	95.76 40	96.20 57	97.39 43	98.42 21	97.82 34	99.57 8	99.18 43

OMC-MVS		97.00 40	96.92 46	97.09 35	98.69 39	98.66 69	97.85 47	95.02 43	98.09 12	94.47 28	93.15 59	96.90 46	97.38 44	97.16 64	96.82 67	99.13 93	97.65 136

CS-MVS		96.23 52	97.15 41	95.16 61	95.01 99	98.98 44	97.13 57	90.68 92	96.00 68	91.21 54	94.03 54	96.48 51	97.35 45	98.00 41	97.43 47	99.55 11	99.15 47

MAR-MVS		95.50 55	95.60 64	95.39 59	98.67 40	98.18 87	95.89 94	89.81 104	94.55 101	91.97 49	92.99 61	90.21 88	97.30 46	96.79 74	97.49 44	98.72 137	98.99 69
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
DPM-MVS		96.86 43	96.82 48	96.91 39	98.08 52	98.20 85	98.52 33	97.20 29	97.24 38	91.42 52	91.84 75	98.45 35	97.25 47	97.07 66	97.40 50	98.95 115	97.55 139

abl_6				96.82 40	98.60 42	98.74 63	97.74 49	93.73 50	96.25 58	94.37 29	94.55 52	98.60 34	97.25 47			99.27 67	98.61 96

MVS_111021_LR		97.16 36	98.01 31	96.16 47	98.47 44	98.98 44	96.94 61	93.89 49	97.64 27	91.44 51	98.89 2	96.41 52	97.20 49	98.02 40	97.29 56	99.04 109	98.85 86

CDPH-MVS		96.84 44	97.49 34	96.09 48	98.92 34	98.85 58	98.61 28	95.09 42	96.00 68	87.29 101	95.45 44	97.42 43	97.16 50	97.83 46	97.94 29	99.44 38	98.92 77

thres400		93.56 97	92.43 121	94.87 70	95.40 85	98.91 53	96.70 71	92.38 66	92.93 123	88.19 96	86.69 116	77.35 159	97.13 51	96.75 76	95.85 92	99.42 42	98.56 98

thres200		93.62 95	92.54 114	94.88 69	95.36 86	98.93 50	96.75 69	92.31 67	92.84 124	88.28 94	86.99 113	77.81 158	97.13 51	96.82 71	95.92 88	99.45 30	98.49 104

tfpn200view9		93.64 94	92.57 113	94.89 68	95.33 87	98.94 48	96.82 65	92.31 67	92.63 127	88.29 92	87.21 111	78.01 156	97.12 53	96.82 71	95.85 92	99.45 30	98.56 98

thres600view7		93.49 99	92.37 124	94.79 73	95.42 84	98.93 50	96.58 75	92.31 67	93.04 121	87.88 97	86.62 117	76.94 162	97.09 54	96.82 71	95.63 96	99.45 30	98.63 95

EIA-MVS		95.50 55	96.19 57	94.69 75	94.83 102	98.88 57	95.93 91	91.50 83	94.47 102	89.43 82	93.14 60	92.72 74	97.05 55	97.82 48	97.13 58	99.43 41	99.15 47

ET-MVSNet_ETH3D		93.34 101	94.33 87	92.18 106	83.26 207	97.66 96	96.72 70	89.89 102	95.62 81	87.17 102	96.00 37	83.69 133	96.99 56	93.78 148	95.34 104	99.06 104	98.18 121

TSAR-MVS + COLMAP		94.79 70	94.51 82	95.11 62	96.50 70	97.54 97	97.99 45	94.54 45	97.81 16	85.88 107	96.73 31	81.28 146	96.99 56	96.29 96	95.21 109	98.76 136	96.73 162

PCF-MVS	93.95 6	95.65 54	95.14 73	96.25 45	97.73 58	98.73 65	97.59 52	97.13 31	92.50 131	89.09 90	89.85 97	96.65 50	96.90 58	94.97 132	94.89 116	99.08 99	98.38 112
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TSAR-MVS + ACMM		97.71 28	98.60 11	96.66 41	98.64 41	99.05 32	98.85 25	97.23 28	98.45 3	89.40 84	97.51 24	99.27 13	96.88 59	98.53 14	97.81 35	98.96 114	99.59 7

OpenMVS	92.33 11	95.50 55	95.22 72	95.82 52	98.98 31	98.97 46	97.67 51	93.04 64	94.64 99	89.18 88	84.44 135	94.79 64	96.79 60	97.23 60	97.61 41	99.24 72	98.88 82

thres100view900		93.55 98	92.47 120	94.81 72	95.33 87	98.74 63	96.78 68	92.30 70	92.63 127	88.29 92	87.21 111	78.01 156	96.78 61	96.38 91	95.92 88	99.38 49	98.40 110

Anonymous20231211		93.49 99	92.33 125	94.84 71	94.78 105	98.00 91	96.11 86	91.85 75	94.86 96	90.91 56	74.69 171	89.18 96	96.73 62	94.82 133	95.51 100	98.67 141	99.24 32

Effi-MVS+		92.93 105	93.86 97	91.86 107	94.07 121	98.09 90	95.59 99	85.98 147	94.27 106	79.54 135	91.12 85	81.81 143	96.71 63	96.67 80	96.06 83	99.27 67	98.98 71

MVS_111021_HR		97.04 39	98.20 26	95.69 53	98.44 46	99.29 18	96.59 74	93.20 59	97.70 22	89.94 76	98.46 7	96.89 47	96.71 63	98.11 37	97.95 28	99.27 67	99.01 67

Fast-Effi-MVS+		91.87 113	92.08 128	91.62 113	92.91 136	97.21 107	94.93 109	84.60 165	93.61 116	81.49 126	83.50 140	78.95 151	96.62 65	96.55 84	96.22 79	99.16 89	98.51 102

casdiffmvs		94.38 83	94.15 93	94.64 77	94.70 109	98.51 77	96.03 90	91.66 79	95.70 78	89.36 85	86.48 119	85.03 125	96.60 66	97.40 56	97.30 54	99.52 14	98.67 93

Anonymous202405211			92.18 126		95.04 98	98.20 85	96.14 85	91.79 78	93.93 109		74.60 172	88.38 104	96.48 67	95.17 128	95.82 94	99.00 110	99.15 47

MVS_Test		94.82 68	95.66 63	93.84 88	94.79 103	98.35 80	96.49 78	89.10 114	96.12 64	87.09 103	92.58 66	90.61 85	96.48 67	96.51 89	96.89 64	99.11 96	98.54 100

ACMM	92.75 10	94.41 82	93.84 98	95.09 63	96.41 73	96.80 115	94.88 111	93.54 52	96.41 55	90.16 70	92.31 69	83.11 136	96.32 69	96.22 99	94.65 122	99.22 78	97.35 145
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OPM-MVS		93.61 96	92.43 121	95.00 65	96.94 67	97.34 103	97.78 48	94.23 47	89.64 163	85.53 108	88.70 104	82.81 138	96.28 70	96.28 97	95.00 115	99.24 72	97.22 148

CANet		96.84 44	97.20 38	96.42 42	97.92 54	99.24 25	98.60 29	93.51 53	97.11 41	93.07 37	91.16 82	97.24 45	96.21 71	98.24 29	98.05 25	99.22 78	99.35 18

PMMVS		94.61 75	95.56 65	93.50 93	94.30 116	96.74 119	94.91 110	89.56 108	95.58 83	87.72 98	96.15 35	92.86 72	96.06 72	95.47 120	95.02 113	98.43 159	97.09 151

CLD-MVS		94.79 70	94.36 86	95.30 60	95.21 93	97.46 100	97.23 56	92.24 71	96.43 54	91.77 50	92.69 65	84.31 127	96.06 72	95.52 118	95.03 112	99.31 61	99.06 58
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchMatch-RL		94.69 74	94.41 84	95.02 64	97.63 59	98.15 88	94.50 119	91.99 73	95.32 86	91.31 53	95.47 43	83.44 134	96.02 74	96.56 83	95.23 108	98.69 140	96.67 163

diffmvs		94.31 84	94.21 88	94.42 80	94.64 110	98.28 81	96.36 81	91.56 80	96.77 48	88.89 91	88.97 101	84.23 128	96.01 75	96.05 104	96.41 73	99.05 108	98.79 90

DCV-MVSNet		94.76 73	95.12 75	94.35 81	95.10 97	95.81 149	96.46 79	89.49 109	96.33 56	90.16 70	92.55 67	90.26 87	95.83 76	95.52 118	96.03 85	99.06 104	99.33 20

MVS_0304		96.31 49	96.91 47	95.62 54	97.21 64	99.20 26	98.55 31	93.10 61	97.04 44	89.73 78	90.30 92	96.35 53	95.71 77	98.14 34	97.93 31	99.38 49	99.40 14

HyFIR lowres test		92.03 111	91.55 135	92.58 103	97.13 65	98.72 66	94.65 116	86.54 140	93.58 117	82.56 119	67.75 201	90.47 86	95.67 78	95.87 108	95.54 99	98.91 119	98.93 76

baseline1		94.59 76	94.47 83	94.72 74	95.16 94	97.97 93	96.07 88	91.94 74	94.86 96	89.98 74	91.60 79	85.87 117	95.64 79	97.07 66	96.90 63	99.52 14	97.06 155

CHOSEN 280x420		95.46 58	97.01 43	93.66 91	97.28 63	97.98 92	96.40 80	85.39 154	96.10 65	91.07 55	96.53 33	96.34 55	95.61 80	97.65 50	96.95 62	96.21 185	97.49 140

HQP-MVS		94.43 80	94.57 81	94.27 82	96.41 73	97.23 106	96.89 62	93.98 48	95.94 71	83.68 114	95.01 48	84.46 126	95.58 81	95.47 120	94.85 120	99.07 101	99.00 68

MSDG		94.82 68	93.73 100	96.09 48	98.34 47	97.43 102	97.06 58	96.05 38	95.84 75	90.56 63	86.30 124	89.10 98	95.55 82	96.13 103	95.61 97	99.00 110	95.73 171

DeepPCF-MVS	95.28 2	97.00 40	98.35 20	95.42 58	97.30 62	98.94 48	94.82 112	96.03 39	98.24 8	92.11 48	95.80 39	98.64 32	95.51 83	98.95 6	98.66 5	96.78 184	99.20 38

DI_MVS_plusplus_trai		94.01 87	93.63 102	94.44 79	94.54 111	98.26 83	97.51 53	90.63 93	95.88 73	89.34 86	80.54 153	89.36 93	95.48 84	96.33 95	96.27 77	99.17 86	98.78 91

EPP-MVSNet		95.27 63	96.18 58	94.20 83	94.88 101	98.64 72	94.97 108	90.70 91	95.34 85	89.67 80	91.66 78	93.84 67	95.42 85	97.32 58	97.00 60	99.58 6	99.47 12

RPSCF		94.05 86	94.00 94	94.12 84	96.20 75	96.41 129	96.61 73	91.54 81	95.83 76	89.73 78	96.94 30	92.80 73	95.35 86	91.63 182	90.44 185	95.27 197	93.94 188

LGP-MVS_train		94.12 85	94.62 80	93.53 92	96.44 72	97.54 97	97.40 55	91.84 76	94.66 98	81.09 128	95.70 41	83.36 135	95.10 87	96.36 94	95.71 95	99.32 58	99.03 64

DELS-MVS		96.06 53	96.04 59	96.07 50	97.77 56	99.25 23	98.10 42	93.26 56	94.42 103	92.79 43	88.52 107	93.48 70	95.06 88	98.51 15	98.83 1	99.45 30	99.28 24
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
ACMP	92.88 9	94.43 80	94.38 85	94.50 78	96.01 78	97.69 95	95.85 97	92.09 72	95.74 77	89.12 89	95.14 46	82.62 140	94.77 89	95.73 114	94.67 121	99.14 92	99.06 58
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
thisisatest0530		94.54 77	95.47 67	93.46 94	94.51 112	98.65 71	94.66 115	90.72 89	95.69 80	86.90 104	93.80 55	89.44 92	94.74 90	96.98 70	94.86 117	99.19 85	98.85 86

tttt0517		94.52 78	95.44 69	93.44 95	94.51 112	98.68 68	94.61 117	90.72 89	95.61 82	86.84 105	93.78 56	89.26 95	94.74 90	97.02 69	94.86 117	99.20 84	98.87 84

baseline		94.83 67	95.82 62	93.68 90	94.75 106	97.80 94	96.51 77	88.53 119	97.02 46	89.34 86	92.93 62	92.18 76	94.69 92	95.78 112	96.08 81	98.27 162	98.97 75

PVSNet_BlendedMVS		95.41 60	95.28 70	95.57 55	97.42 60	99.02 41	95.89 94	93.10 61	96.16 61	93.12 35	91.99 71	85.27 120	94.66 93	98.09 38	97.34 52	99.24 72	99.08 54

PVSNet_Blended		95.41 60	95.28 70	95.57 55	97.42 60	99.02 41	95.89 94	93.10 61	96.16 61	93.12 35	91.99 71	85.27 120	94.66 93	98.09 38	97.34 52	99.24 72	99.08 54

FC-MVSNet-train		93.85 90	93.91 95	93.78 89	94.94 100	96.79 118	94.29 122	91.13 86	93.84 113	88.26 95	90.40 91	85.23 122	94.65 95	96.54 85	95.31 105	99.38 49	99.28 24

CANet_DTU		93.92 89	96.57 51	90.83 121	95.63 81	98.39 79	96.99 60	87.38 131	96.26 57	71.97 174	96.31 34	93.02 71	94.53 96	97.38 57	96.83 66	98.49 154	97.79 128

FMVSNet1		91.54 120	90.93 141	92.26 105	90.35 160	95.27 168	95.22 105	87.16 134	91.37 148	87.62 99	75.45 166	83.84 131	94.43 97	96.52 86	96.30 74	98.82 126	97.74 134

IterMVS-LS		92.56 109	93.18 109	91.84 108	93.90 122	94.97 175	94.99 107	86.20 144	94.18 107	82.68 118	85.81 126	87.36 108	94.43 97	95.31 124	96.02 86	98.87 122	98.60 97
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		93.81 91	94.18 89	93.38 96	91.34 150	95.86 145	96.22 82	88.68 116	95.23 89	90.40 65	86.39 120	91.16 79	94.40 99	96.52 86	96.30 74	99.21 81	97.79 128

test1		93.81 91	94.18 89	93.38 96	91.34 150	95.86 145	96.22 82	88.68 116	95.23 89	90.40 65	86.39 120	91.16 79	94.40 99	96.52 86	96.30 74	99.21 81	97.79 128

FMVSNet2		93.30 102	93.36 108	93.22 100	91.34 150	95.86 145	96.22 82	88.24 123	95.15 93	89.92 77	81.64 147	89.36 93	94.40 99	96.77 75	96.98 61	99.21 81	97.79 128

IS_MVSNet		95.28 62	96.43 54	93.94 85	95.30 89	99.01 43	95.90 92	91.12 87	94.13 108	87.50 100	91.23 81	94.45 66	94.17 102	98.45 18	98.50 7	99.65 2	99.23 33

FMVSNet3		93.79 93	94.17 91	93.35 98	91.21 153	95.99 138	96.62 72	88.68 116	95.23 89	90.40 65	86.39 120	91.16 79	94.11 103	95.96 105	96.67 68	99.07 101	97.79 128

CHOSEN 1792x2688		92.66 108	92.49 117	92.85 102	97.13 65	98.89 56	95.90 92	88.50 120	95.32 86	83.31 116	71.99 190	88.96 99	94.10 104	96.69 78	96.49 71	98.15 164	99.10 51

UniMVSNet_ETH3D		88.47 160	86.00 190	91.35 115	91.55 147	96.29 132	92.53 147	88.81 115	85.58 193	82.33 120	67.63 202	66.87 202	94.04 105	91.49 183	95.24 107	98.84 125	98.92 77

SCA		90.92 127	93.04 111	88.45 149	93.72 127	97.33 104	92.77 142	76.08 198	96.02 67	78.26 139	91.96 73	90.86 82	93.99 106	90.98 186	90.04 188	95.88 189	94.06 187

EPMVS		90.88 128	92.12 127	89.44 140	94.71 107	97.24 105	93.55 129	76.81 193	95.89 72	81.77 123	91.49 80	86.47 111	93.87 107	90.21 189	90.07 187	95.92 188	93.49 194

COLMAP_ROB	90.49 14	93.27 103	92.71 112	93.93 86	97.75 57	97.44 101	96.07 88	93.17 60	95.40 84	83.86 113	83.76 139	88.72 100	93.87 107	94.25 144	94.11 139	98.87 122	95.28 177
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	90.88 12	91.41 122	91.13 138	91.74 110	95.11 96	96.95 110	93.13 138	89.48 110	92.42 133	79.93 132	85.13 129	78.02 155	93.82 109	93.49 155	93.88 145	98.94 116	97.99 124

ACMH	90.77 13	91.51 121	91.63 134	91.38 114	95.62 82	96.87 113	91.76 166	89.66 106	91.58 146	78.67 137	86.73 115	78.12 154	93.77 110	94.59 135	94.54 130	98.78 134	98.98 71
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CostFormer		90.69 129	90.48 146	90.93 119	94.18 118	96.08 137	94.03 124	78.20 189	93.47 118	89.96 75	90.97 87	80.30 147	93.72 111	87.66 199	88.75 192	95.51 194	96.12 167

MVSTER		94.89 66	95.07 76	94.68 76	94.71 107	96.68 121	97.00 59	90.57 94	95.18 92	93.05 39	95.21 45	86.41 112	93.72 111	97.59 52	95.88 91	99.00 110	98.50 103

test_part1		91.21 123	89.47 151	93.24 99	94.26 117	95.45 161	95.26 103	88.36 121	88.49 173	90.04 72	72.61 187	82.82 137	93.69 113	93.25 159	94.62 124	97.84 172	99.06 58

USDC		90.69 129	90.52 145	90.88 120	94.17 119	96.43 128	95.82 98	86.76 137	93.92 110	76.27 152	86.49 118	74.30 172	93.67 114	95.04 131	93.36 154	98.61 147	94.13 184

Effi-MVS+-dtu		91.78 115	93.59 104	89.68 138	92.44 142	97.11 108	94.40 120	84.94 161	92.43 132	75.48 156	91.09 86	83.75 132	93.55 115	96.61 81	95.47 101	97.24 180	98.67 93

PatchmatchNet		90.56 131	92.49 117	88.31 152	93.83 125	96.86 114	92.42 150	76.50 195	95.96 70	78.31 138	91.96 73	89.66 91	93.48 116	90.04 191	89.20 191	95.32 195	93.73 192
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TinyColmap		89.42 146	88.58 158	90.40 127	93.80 126	95.45 161	93.96 126	86.54 140	92.24 139	76.49 149	80.83 150	70.44 189	93.37 117	94.45 139	93.30 157	98.26 163	93.37 195

LTVRE_ROB	87.32 16	87.55 173	88.25 162	86.73 179	90.66 155	95.80 150	93.05 139	84.77 162	83.35 199	60.32 207	83.12 142	67.39 200	93.32 118	94.36 142	94.86 117	98.28 161	98.87 84
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
ADS-MVSNet		89.80 143	91.33 137	88.00 161	94.43 114	96.71 120	92.29 154	74.95 203	96.07 66	77.39 142	88.67 105	86.09 114	93.26 119	88.44 195	89.57 190	95.68 191	93.81 191

MDTV_nov1_ep13		91.57 119	93.18 109	89.70 136	93.39 130	96.97 109	93.53 130	80.91 184	95.70 78	81.86 122	92.40 68	89.93 89	93.25 120	91.97 180	90.80 183	95.25 198	94.46 181

UniMVSNet_NR-MVSNet		90.35 135	89.96 147	90.80 122	89.66 169	95.83 148	92.48 148	90.53 95	90.96 153	79.57 133	79.33 157	77.14 160	93.21 121	92.91 165	94.50 133	99.37 52	99.05 61

DU-MVS		89.67 145	88.84 156	90.63 125	89.26 179	95.61 154	92.48 148	89.91 100	91.22 149	79.57 133	77.72 161	71.18 186	93.21 121	92.53 169	94.57 127	99.35 55	99.05 61

pmmvs4		90.55 132	89.91 148	91.30 116	90.26 162	94.95 176	92.73 144	87.94 126	93.44 119	85.35 109	82.28 146	76.09 164	93.02 123	93.56 153	92.26 177	98.51 153	96.77 161

tpmrst		88.86 158	89.62 149	87.97 162	94.33 115	95.98 139	92.62 146	76.36 196	94.62 100	76.94 146	85.98 125	82.80 139	92.80 124	86.90 201	87.15 198	94.77 202	93.93 189

RPMNet		90.19 138	92.03 130	88.05 158	93.46 128	95.95 142	93.41 132	74.59 204	92.40 134	75.91 154	84.22 136	86.41 112	92.49 125	94.42 140	93.85 147	98.44 157	96.96 156

FMVSNet5		90.36 134	90.93 141	89.70 136	87.99 195	92.25 200	92.03 161	83.51 171	92.20 140	84.13 112	85.59 127	86.48 110	92.43 126	94.61 134	94.52 131	98.13 165	90.85 200

dps		90.11 141	89.37 154	90.98 118	93.89 123	96.21 134	93.49 131	77.61 191	91.95 142	92.74 45	88.85 102	78.77 153	92.37 127	87.71 198	87.71 196	95.80 190	94.38 182

Baseline_NR-MVSNet		89.27 150	88.01 166	90.73 124	89.26 179	93.71 195	92.71 145	89.78 105	90.73 154	81.28 127	73.53 181	72.85 178	92.30 128	92.53 169	93.84 148	99.07 101	98.88 82

CR-MVSNet		90.16 139	91.96 131	88.06 157	93.32 131	95.95 142	93.36 134	75.99 199	92.40 134	75.19 160	83.18 141	85.37 119	92.05 129	95.21 126	94.56 128	98.47 156	97.08 153

PatchT		89.13 153	91.71 132	86.11 185	92.92 135	95.59 156	83.64 201	75.09 202	91.87 143	75.19 160	82.63 144	85.06 124	92.05 129	95.21 126	94.56 128	97.76 174	97.08 153

v2v482		88.25 163	87.71 173	88.88 144	89.23 183	95.28 166	92.10 158	87.89 127	88.69 171	73.31 170	75.32 167	71.64 183	91.89 131	92.10 177	92.92 163	98.86 124	97.99 124

tfpnnormal		88.50 159	87.01 181	90.23 128	91.36 149	95.78 151	92.74 143	90.09 98	83.65 198	76.33 151	71.46 193	69.58 194	91.84 132	95.54 117	94.02 142	99.06 104	99.03 64

TranMVSNet+NR-MVSNet		89.23 151	88.48 160	90.11 134	89.07 185	95.25 169	92.91 141	90.43 96	90.31 159	77.10 145	76.62 164	71.57 184	91.83 133	92.12 175	94.59 126	99.32 58	98.92 77

EPNet		96.27 51	96.97 44	95.46 57	98.47 44	98.28 81	97.41 54	93.67 51	95.86 74	92.86 42	97.51 24	93.79 68	91.76 134	97.03 68	97.03 59	98.61 147	99.28 24
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Fast-Effi-MVS+-dtu		91.19 124	93.64 101	88.33 151	92.19 144	96.46 127	93.99 125	81.52 182	92.59 129	71.82 175	92.17 70	85.54 118	91.68 135	95.73 114	94.64 123	98.80 131	98.34 113

tpm		87.95 166	89.44 153	86.21 184	92.53 141	94.62 185	91.40 169	76.36 196	91.46 147	69.80 189	87.43 110	75.14 167	91.55 136	89.85 193	90.60 184	95.61 192	96.96 156

tpm cat1		88.90 156	87.78 172	90.22 129	93.88 124	95.39 164	93.79 127	78.11 190	92.55 130	89.43 82	81.31 148	79.84 149	91.40 137	84.95 202	86.34 201	94.68 204	94.09 185

baseline2		93.01 104	94.17 91	91.64 111	92.83 138	97.49 99	93.40 133	87.53 129	93.67 115	86.07 106	91.83 76	86.58 109	91.36 138	96.38 91	95.06 111	98.67 141	98.20 120

v10		88.00 165	87.96 167	88.05 158	89.44 174	94.68 182	92.36 151	83.35 172	89.37 165	72.96 171	73.98 178	72.79 179	91.35 139	93.59 150	92.88 164	98.81 129	98.42 108

v1192		87.51 174	87.31 175	87.74 166	89.04 186	94.87 180	92.07 159	85.03 159	88.49 173	70.32 182	72.65 186	70.35 190	91.21 140	93.59 150	92.80 166	98.78 134	98.42 108

UniMVSNet (Re)		90.03 142	89.61 150	90.51 126	89.97 166	96.12 136	92.32 152	89.26 111	90.99 152	80.95 129	78.25 160	75.08 169	91.14 141	93.78 148	93.87 146	99.41 43	99.21 37

v1921920		87.31 178	87.13 179	87.52 172	88.87 189	94.72 181	91.96 164	84.59 166	88.28 175	69.86 188	72.50 188	70.03 193	91.10 142	93.33 157	92.61 171	98.71 138	98.44 105

v1144		87.92 169	87.79 171	88.07 155	89.27 178	95.15 171	92.17 157	85.62 151	88.52 172	71.52 176	73.80 179	72.40 181	91.06 143	93.54 154	92.80 166	98.81 129	98.33 114

MIMVSNet		88.99 155	91.07 139	86.57 181	86.78 201	95.62 153	91.20 174	75.40 201	90.65 156	76.57 148	84.05 137	82.44 141	91.01 144	95.84 109	95.38 103	98.48 155	93.50 193

test-LLR		91.62 118	93.56 105	89.35 142	93.31 132	96.57 124	92.02 162	87.06 135	92.34 137	75.05 163	90.20 93	88.64 101	90.93 145	96.19 101	94.07 140	97.75 175	96.90 159

TESTMET0.1,1		91.07 125	93.56 105	88.17 153	90.43 157	96.57 124	92.02 162	82.83 176	92.34 137	75.05 163	90.20 93	88.64 101	90.93 145	96.19 101	94.07 140	97.75 175	96.90 159

SixPastTwentyTwo		88.37 161	89.47 151	87.08 176	90.01 165	95.93 144	87.41 191	85.32 155	90.26 161	70.26 183	86.34 123	71.95 182	90.93 145	92.89 166	91.72 180	98.55 150	97.22 148

test-mter		90.95 126	93.54 107	87.93 163	90.28 161	96.80 115	91.44 168	82.68 177	92.15 141	74.37 167	89.57 99	88.23 106	90.88 148	96.37 93	94.31 136	97.93 171	97.37 144

PVSNet_Blended_VisFu		94.77 72	95.54 66	93.87 87	96.48 71	98.97 46	94.33 121	91.84 76	94.93 95	90.37 68	85.04 130	94.99 63	90.87 149	98.12 36	97.30 54	99.30 63	99.45 13

CP-MVSNet		87.89 170	87.27 176	88.62 147	89.30 177	95.06 172	90.60 179	85.78 149	87.43 183	75.98 153	74.60 172	68.14 199	90.76 150	93.07 163	93.60 151	99.30 63	98.98 71

v144192		87.40 176	87.20 178	87.64 167	88.89 187	94.88 179	91.65 167	84.70 164	87.80 178	71.17 180	73.20 184	70.91 187	90.75 151	92.69 167	92.49 172	98.71 138	98.43 106

pmmvs5		87.83 171	88.09 164	87.51 173	89.59 172	95.48 159	89.75 185	84.73 163	86.07 191	71.44 177	80.57 152	70.09 192	90.74 152	94.47 138	92.87 165	98.82 126	97.10 150

v8		88.21 164	87.94 169	88.51 148	89.62 170	95.01 174	92.31 153	84.99 160	88.94 166	74.70 165	75.03 168	73.51 176	90.67 153	92.11 176	92.74 169	98.80 131	98.24 118

v1240		86.89 180	86.75 185	87.06 177	88.75 191	94.65 184	91.30 173	84.05 168	87.49 182	68.94 192	71.96 191	68.86 198	90.65 154	93.33 157	92.72 170	98.67 141	98.24 118

gm-plane-assit		83.26 195	85.29 192	80.89 196	89.52 173	89.89 206	70.26 211	78.24 188	77.11 208	58.01 211	74.16 177	66.90 201	90.63 155	97.20 61	96.05 84	98.66 144	95.68 172

MS-PatchMatch		91.82 114	92.51 115	91.02 117	95.83 80	96.88 111	95.05 106	84.55 167	93.85 112	82.01 121	82.51 145	91.71 77	90.52 156	95.07 130	93.03 161	98.13 165	94.52 179

CDS-MVSNet		92.77 106	93.60 103	91.80 109	92.63 140	96.80 115	95.24 104	89.14 113	90.30 160	84.58 111	86.76 114	90.65 84	90.42 157	95.89 107	96.49 71	98.79 133	98.32 116
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		90.54 133	90.87 143	90.16 130	91.48 148	96.61 123	93.26 136	86.08 145	87.71 179	81.66 125	83.11 143	84.04 129	90.42 157	94.54 136	94.60 125	98.04 169	95.48 175

V42		88.31 162	87.95 168	88.73 146	89.44 174	95.34 165	92.23 156	87.21 133	88.83 168	74.49 166	74.89 170	73.43 177	90.41 159	92.08 178	92.77 168	98.60 149	98.33 114

anonymousdsp		88.90 156	91.00 140	86.44 182	88.74 192	95.97 140	90.40 181	82.86 175	88.77 170	67.33 194	81.18 149	81.44 145	90.22 160	96.23 98	94.27 137	99.12 95	99.16 46

PS-CasMVS		87.33 177	86.68 186	88.10 154	89.22 184	94.93 177	90.35 182	85.70 150	86.44 188	74.01 168	73.43 182	66.59 205	90.04 161	92.92 164	93.52 152	99.28 65	98.91 80

IterMVS-SCA-FT		90.24 136	92.48 119	87.63 168	92.85 137	94.30 191	93.79 127	81.47 183	92.66 126	69.95 186	84.66 133	88.38 104	89.99 162	95.39 123	94.34 135	97.74 177	97.63 137

IterMVS		90.20 137	92.43 121	87.61 169	92.82 139	94.31 190	94.11 123	81.54 181	92.97 122	69.90 187	84.71 132	88.16 107	89.96 163	95.25 125	94.17 138	97.31 179	97.46 141
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
gg-mvs-nofinetune		86.17 185	88.57 159	83.36 193	93.44 129	98.15 88	96.58 75	72.05 207	74.12 210	49.23 214	64.81 205	90.85 83	89.90 164	97.83 46	96.84 65	98.97 113	97.41 143

GA-MVS		89.28 149	90.75 144	87.57 170	91.77 146	96.48 126	92.29 154	87.58 128	90.61 157	65.77 196	84.48 134	76.84 163	89.46 165	95.84 109	93.68 150	98.52 152	97.34 146

PEN-MVS		87.22 179	86.50 188	88.07 155	88.88 188	94.44 187	90.99 176	86.21 142	86.53 187	73.66 169	74.97 169	66.56 206	89.42 166	91.20 185	93.48 153	99.24 72	98.31 117

NR-MVSNet		89.34 148	88.66 157	90.13 133	90.40 158	95.61 154	93.04 140	89.91 100	91.22 149	78.96 136	77.72 161	68.90 197	89.16 167	94.24 145	93.95 143	99.32 58	98.99 69

pm-mvs1		89.19 152	89.02 155	89.38 141	90.40 158	95.74 152	92.05 160	88.10 125	86.13 189	77.70 140	73.72 180	79.44 150	88.97 168	95.81 111	94.51 132	99.08 99	97.78 133

MVS-HIRNet		85.36 189	86.89 182	83.57 192	90.13 163	94.51 186	83.57 202	72.61 206	88.27 176	71.22 179	68.97 197	81.81 143	88.91 169	93.08 162	91.94 178	94.97 201	89.64 203

PM-MVS		84.72 192	84.47 196	85.03 188	84.67 203	91.57 202	86.27 195	82.31 179	87.65 180	70.62 181	76.54 165	56.41 213	88.75 170	92.59 168	89.85 189	97.54 178	96.66 164

Vis-MVSNet (Re-imp)		94.46 79	96.24 56	92.40 104	95.23 92	98.64 72	95.56 100	90.99 88	94.42 103	85.02 110	90.88 88	94.65 65	88.01 171	98.17 31	98.37 16	99.57 8	98.53 101

v7n		86.43 183	86.52 187	86.33 183	87.91 196	94.93 177	90.15 183	83.05 173	86.57 186	70.21 184	71.48 192	66.78 203	87.72 172	94.19 147	92.96 162	98.92 118	98.76 92

pmmvs6		85.98 187	84.89 195	87.25 175	88.83 190	94.35 189	89.36 186	85.30 157	78.51 207	75.44 157	62.71 206	75.41 166	87.65 173	93.58 152	92.40 174	96.89 182	97.29 147

DTE-MVSNet		86.67 182	86.09 189	87.35 174	88.45 194	94.08 193	90.65 178	86.05 146	86.13 189	72.19 173	74.58 174	66.77 204	87.61 174	90.31 188	93.12 159	99.13 93	97.62 138

MDTV_nov1_ep13_2view		86.30 184	88.27 161	84.01 191	87.71 198	94.67 183	88.08 189	76.78 194	90.59 158	68.66 193	80.46 154	80.12 148	87.58 175	89.95 192	88.20 194	95.25 198	93.90 190

pmmvs-eth3d		84.33 193	82.94 198	85.96 187	84.16 204	90.94 203	86.55 194	83.79 169	84.25 196	75.85 155	70.64 195	56.43 212	87.44 176	92.20 174	90.41 186	97.97 170	95.68 172

v148		87.51 174	86.79 183	88.36 150	89.39 176	95.21 170	89.84 184	88.20 124	87.61 181	77.56 141	73.38 183	70.32 191	86.80 177	90.70 187	92.31 175	98.37 160	97.98 126

TransMVSNet (Re)		87.73 172	86.79 183	88.83 145	90.76 154	94.40 188	91.33 172	89.62 107	84.73 195	75.41 158	72.73 185	71.41 185	86.80 177	94.53 137	93.93 144	99.06 104	95.83 169

pmnet_mix02		86.12 186	87.12 180	84.96 189	89.82 167	94.12 192	84.88 199	86.63 139	91.78 144	65.60 197	80.76 151	76.98 161	86.61 179	87.29 200	84.80 204	96.21 185	94.09 185

WR-MVS_H		87.93 167	87.85 170	88.03 160	89.62 170	95.58 158	90.47 180	85.55 152	87.20 184	76.83 147	74.42 175	72.67 180	86.37 180	93.22 160	93.04 160	99.33 56	98.83 88

UGNet		94.92 65	96.63 50	92.93 101	96.03 77	98.63 74	94.53 118	91.52 82	96.23 59	90.03 73	92.87 64	96.10 59	86.28 181	96.68 79	96.60 70	99.16 89	99.32 22
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
UA-Net		93.96 88	95.95 61	91.64 111	96.06 76	98.59 76	95.29 102	90.00 99	91.06 151	82.87 117	90.64 89	98.06 40	86.06 182	98.14 34	98.20 19	99.58 6	96.96 156

test0.0.03 1		91.97 112	93.91 95	89.72 135	93.31 132	96.40 130	91.34 171	87.06 135	93.86 111	81.67 124	91.15 84	89.16 97	86.02 183	95.08 129	95.09 110	98.91 119	96.64 165

thisisatest0515		90.12 140	92.06 129	87.85 164	90.03 164	96.17 135	87.83 190	87.45 130	91.71 145	77.15 144	85.40 128	84.01 130	85.74 184	95.41 122	93.30 157	98.88 121	98.43 106

FC-MVSNet-test		91.63 117	93.82 99	89.08 143	92.02 145	96.40 130	93.26 136	87.26 132	93.72 114	77.26 143	88.61 106	89.86 90	85.50 185	95.72 116	95.02 113	99.16 89	97.44 142

CMPMVS	65.18 17	84.76 191	83.10 197	86.69 180	95.29 90	95.05 173	88.37 188	85.51 153	80.27 205	71.31 178	68.37 199	73.85 174	85.25 186	87.72 197	87.75 195	94.38 205	88.70 204
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
N_pmnet		84.80 190	85.10 194	84.45 190	89.25 182	92.86 198	84.04 200	86.21 142	88.78 169	66.73 195	72.41 189	74.87 171	85.21 187	88.32 196	86.45 199	95.30 196	92.04 197

WR-MVS		87.93 167	88.09 164	87.75 165	89.26 179	95.28 166	90.81 177	86.69 138	88.90 167	75.29 159	74.31 176	73.72 175	85.19 188	92.26 172	93.32 156	99.27 67	98.81 89

TDRefinement		89.07 154	88.15 163	90.14 132	95.16 94	96.88 111	95.55 101	90.20 97	89.68 162	76.42 150	76.67 163	74.30 172	84.85 189	93.11 161	91.91 179	98.64 146	94.47 180

CVMVSNet		89.77 144	91.66 133	87.56 171	93.21 134	95.45 161	91.94 165	89.22 112	89.62 164	69.34 191	83.99 138	85.90 116	84.81 190	94.30 143	95.28 106	96.85 183	97.09 151

pmmvs3		79.16 200	80.12 202	78.05 202	79.36 208	86.59 209	78.13 209	73.87 205	76.42 209	57.51 212	70.59 196	57.02 211	84.66 191	90.10 190	88.32 193	94.75 203	91.77 199

Vis-MVSNet		92.77 106	95.00 78	90.16 130	94.10 120	98.79 60	94.76 114	88.26 122	92.37 136	79.95 131	88.19 109	91.58 78	84.38 192	97.59 52	97.58 42	99.52 14	98.91 80
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EG-PatchMatch MVS		86.68 181	87.24 177	86.02 186	90.58 156	96.26 133	91.08 175	81.59 180	84.96 194	69.80 189	71.35 194	75.08 169	84.23 193	94.24 145	93.35 155	98.82 126	95.46 176

testgi		89.42 146	91.50 136	87.00 178	92.40 143	95.59 156	89.15 187	85.27 158	92.78 125	72.42 172	91.75 77	76.00 165	84.09 194	94.38 141	93.82 149	98.65 145	96.15 166

EPNet_dtu		92.45 110	95.02 77	89.46 139	98.02 53	95.47 160	94.79 113	92.62 65	94.97 94	70.11 185	94.76 51	92.61 75	84.07 195	95.94 106	95.56 98	97.15 181	95.82 170
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MDA-MVSNet-bldmvs		80.11 198	80.24 201	79.94 198	77.01 210	93.21 196	78.86 208	85.94 148	82.71 202	60.86 204	79.71 156	51.77 215	83.71 196	75.60 207	86.37 200	93.28 206	92.35 196

new_pmnet		81.53 197	82.68 199	80.20 197	83.47 206	89.47 207	82.21 205	78.36 187	87.86 177	60.14 209	67.90 200	69.43 195	82.03 197	89.22 194	87.47 197	94.99 200	87.39 205

DeepMVS_CX						86.86 208	79.50 207	70.43 209	90.73 154	63.66 200	80.36 155	60.83 208	79.68 198	76.23 206		89.46 209	86.53 206

EU-MVSNet		85.62 188	87.65 174	83.24 194	88.54 193	92.77 199	87.12 192	85.32 155	86.71 185	64.54 199	78.52 159	75.11 168	78.35 199	92.25 173	92.28 176	95.58 193	95.93 168

IB-MVS	89.56 15	91.71 116	92.50 116	90.79 123	95.94 79	98.44 78	87.05 193	91.38 85	93.15 120	92.98 41	84.78 131	85.14 123	78.27 200	92.47 171	94.44 134	99.10 97	99.08 54
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
MIMVSNet1		80.03 199	80.93 200	78.97 200	72.46 213	90.73 204	80.81 206	82.44 178	80.39 204	63.64 201	57.57 207	64.93 207	76.37 201	91.66 181	91.55 181	98.07 168	89.70 202

new-patchmatchnet		78.49 201	78.19 203	78.84 201	84.13 205	90.06 205	77.11 210	80.39 185	79.57 206	59.64 210	66.01 203	55.65 214	75.62 202	84.55 203	80.70 205	96.14 187	90.77 201

Anonymous20231206		83.84 194	85.19 193	82.26 195	87.38 199	92.87 197	85.49 197	83.65 170	86.07 191	63.44 203	68.42 198	69.01 196	75.45 203	93.34 156	92.44 173	98.12 167	94.20 183

ambc			73.83 205		76.23 211	85.13 210	82.27 204		84.16 197	65.58 198	52.82 209	23.31 220	73.55 204	91.41 184	85.26 203	92.97 207	94.70 178

Gipuma		68.35 203	66.71 206	70.27 204	74.16 212	68.78 214	63.93 214	71.77 208	83.34 200	54.57 213	34.37 211	31.88 217	68.69 205	83.30 204	85.53 202	88.48 210	79.78 209
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test20.03		82.92 196	85.52 191	79.90 199	87.75 197	91.84 201	82.80 203	82.99 174	82.65 203	60.32 207	78.90 158	70.50 188	67.10 206	92.05 179	90.89 182	98.44 157	91.80 198

FPMVS		75.84 202	74.59 204	77.29 203	86.92 200	83.89 211	85.01 198	80.05 186	82.91 201	60.61 206	65.25 204	60.41 209	63.86 207	75.60 207	73.60 209	87.29 211	80.47 208

EMVS		49.98 208	46.76 211	53.74 209	64.96 215	51.29 217	37.81 217	69.35 211	51.83 213	22.69 218	29.57 213	25.06 218	57.28 208	44.81 213	56.11 212	70.32 215	68.64 213

E-PMN		50.67 207	47.85 210	53.96 208	64.13 216	50.98 218	38.06 216	69.51 210	51.40 214	24.60 217	29.46 214	24.39 219	56.07 209	48.17 212	59.70 211	71.40 214	70.84 212

PMVS	63.12 18	67.27 204	66.39 207	68.30 205	77.98 209	60.24 215	59.53 215	76.82 192	66.65 211	60.74 205	54.39 208	59.82 210	51.24 210	73.92 210	70.52 210	83.48 212	79.17 210
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt				66.88 206	86.07 202	73.86 213	68.22 212	33.38 214	96.88 47	80.67 130	88.23 108	78.82 152	49.78 211	82.68 205	77.47 207	83.19 213

MVE	50.86 19	49.54 209	51.43 209	47.33 210	44.14 217	59.20 216	36.45 218	60.59 213	41.47 215	31.14 216	29.58 212	17.06 221	48.52 212	62.22 211	74.63 208	63.12 216	75.87 211
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		64.36 206	65.94 208	62.52 207	67.37 214	77.44 212	64.39 213	69.32 212	61.47 212	34.59 215	46.09 210	41.03 216	48.02 213	74.56 209	78.23 206	91.43 208	82.76 207

testmvs		12.09 210	16.94 212	6.42 212	3.15 218	6.08 219	9.51 220	3.84 215	21.46 216	5.31 219	27.49 215	6.76 222	10.89 214	17.06 214	15.01 213	5.84 217	24.75 214

test123		9.58 211	13.53 213	4.97 213	1.31 220	5.47 220	8.32 221	2.95 216	18.14 217	2.03 221	20.82 216	2.34 223	10.60 215	10.00 215	14.16 214	4.60 218	23.77 215

GG-mvs-BLEND		66.17 205	94.91 79	32.63 211	1.32 219	96.64 122	91.40 169	0.85 217	94.39 105	2.20 220	90.15 95	95.70 61	2.27 216	96.39 90	95.44 102	97.78 173	95.68 172

uanet_test		0.00 212	0.00 214	0.00 214	0.00 221	0.00 221	0.00 222	0.00 218	0.00 218	0.00 222	0.00 217	0.00 224	0.00 217	0.00 216	0.00 215	0.00 219	0.00 216

sosnet-low-res		0.00 212	0.00 214	0.00 214	0.00 221	0.00 221	0.00 222	0.00 218	0.00 218	0.00 222	0.00 217	0.00 224	0.00 217	0.00 216	0.00 215	0.00 219	0.00 216

sosnet		0.00 212	0.00 214	0.00 214	0.00 221	0.00 221	0.00 222	0.00 218	0.00 218	0.00 222	0.00 217	0.00 224	0.00 217	0.00 216	0.00 215	0.00 219	0.00 216

RE-MVS-def										63.50 202

9.14												99.28 11

SR-MVS					99.45 9			97.61 15				99.20 15

our_test_3					89.78 168	93.84 194	85.59 196

MTAPA										96.83 10		99.12 20

MTMP										97.18 5		98.83 26

Patchmatch-RL test							34.61 219

XVS					96.60 68	99.35 12	96.82 65			90.85 57		98.72 29				99.46 26

X-MVStestdata					96.60 68	99.35 12	96.82 65			90.85 57		98.72 29				99.46 26

mPP-MVS					99.21 24							98.29 38

NP-MVS									95.32 86

Patchmtry						95.96 141	93.36 134	75.99 199		75.19 160

High-resolution multi-view benchmark