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 10	98.62 11	98.32 13	99.39 19	99.33 22	99.27 11	97.42 20	98.27 7	95.25 25	98.34 10	98.83 27	99.08 1	98.26 34	98.08 25	99.48 27	99.26 33

ACMMPR		98.40 13	98.49 13	98.28 15	99.41 15	99.40 13	99.36 4	97.35 23	98.30 6	95.02 27	97.79 18	98.39 38	99.04 2	98.26 34	98.10 23	99.50 26	99.22 39

SD-MVS		98.52 8	98.77 9	98.23 17	98.15 51	99.26 27	98.79 27	97.59 17	98.52 3	96.25 17	97.99 16	99.75 6	99.01 3	98.27 33	97.97 31	99.59 6	99.63 2
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 27	97.54 36	98.05 23	98.91 36	99.05 38	99.00 21	96.96 35	97.14 43	95.92 19	95.50 45	98.78 29	98.99 4	97.20 68	96.07 88	98.54 159	99.04 67

DVP-MVS		98.86 4	98.97 3	98.75 2	99.43 14	99.63 1	99.25 13	97.81 2	98.62 2	97.69 1	97.59 21	99.90 2	98.93 5	98.99 4	98.42 11	99.37 58	99.62 4
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 24	97.93 33	98.18 18	99.10 29	99.09 37	98.34 37	96.99 34	97.54 31	96.60 14	94.82 52	98.45 36	98.89 6	97.46 62	98.77 4	99.17 93	99.37 20

TSAR-MVS + MP.		98.49 9	98.78 8	98.15 21	98.14 52	99.17 34	99.34 6	97.18 31	98.44 5	95.72 21	97.84 17	99.28 12	98.87 7	99.05 1	98.05 26	99.66 2	99.60 7
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 12	98.31 24	98.57 5	99.48 5	99.40 13	99.32 9	97.62 14	97.70 23	96.67 12	96.59 33	99.09 22	98.86 8	98.65 13	97.56 50	99.45 35	99.17 49

APDe-MVS		98.87 3	98.96 4	98.77 1	99.58 2	99.53 7	99.44 1	97.81 2	98.22 10	97.33 4	98.70 5	99.33 10	98.86 8	98.96 6	98.40 13	99.63 4	99.57 9

SMA-MVS		98.66 7	98.89 7	98.39 10	99.60 1	99.41 12	99.00 21	97.63 13	97.78 18	95.83 20	98.33 11	99.83 4	98.85 10	98.93 8	98.56 6	99.41 49	99.40 18
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 11	98.46 16	98.48 8	99.40 16	99.05 38	99.02 20	97.54 18	97.73 19	96.65 13	97.20 30	99.13 20	98.85 10	98.91 9	98.10 23	99.41 49	99.08 57

PGM-MVS		97.81 26	98.11 29	97.46 31	99.55 3	99.34 21	99.32 9	94.51 47	96.21 64	93.07 39	98.05 15	97.95 43	98.82 12	98.22 37	97.89 37	99.48 27	99.09 56

CP-MVS		98.32 18	98.34 22	98.29 14	99.34 22	99.30 23	99.15 15	97.35 23	97.49 33	95.58 23	97.72 19	98.62 34	98.82 12	98.29 29	97.67 45	99.51 24	99.28 28

MCST-MVS		98.20 19	98.36 19	98.01 24	99.40 16	99.05 38	99.00 21	97.62 14	97.59 30	93.70 36	97.42 28	99.30 11	98.77 14	98.39 27	97.48 52	99.59 6	99.31 27

AdaColmap		97.53 31	96.93 48	98.24 16	99.21 25	98.77 67	98.47 35	97.34 25	96.68 54	96.52 15	95.11 50	96.12 59	98.72 15	97.19 70	96.24 84	99.17 93	98.39 115

ACMMP_NAP		98.20 19	98.49 13	97.85 27	99.50 4	99.40 13	99.26 12	97.64 12	97.47 35	92.62 49	97.59 21	99.09 22	98.71 16	98.82 12	97.86 38	99.40 52	99.19 43

DeepC-MVS_fast	96.13 1	98.13 21	98.27 26	97.97 26	99.16 28	99.03 45	99.05 19	97.24 28	98.22 10	94.17 34	95.82 41	98.07 40	98.69 17	98.83 11	98.80 2	99.52 19	99.10 54
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DVP-MVS++		98.92 1	99.18 1	98.61 4	99.47 6	99.61 2	99.39 3	97.82 1	98.80 1	96.86 9	98.90 2	99.92 1	98.67 18	99.02 2	98.20 19	99.43 46	99.82 1

SED-MVS		98.90 2	99.07 2	98.69 3	99.38 20	99.61 2	99.33 8	97.80 4	98.25 8	97.60 2	98.87 4	99.89 3	98.67 18	99.02 2	98.26 17	99.36 60	99.61 6

MSP-MVS		98.73 6	98.93 5	98.50 7	99.44 13	99.57 4	99.36 4	97.65 9	98.14 12	96.51 16	98.49 7	99.65 8	98.67 18	98.60 15	98.42 11	99.40 52	99.63 2
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 17	98.47 15	98.18 18	99.46 9	99.15 35	99.10 17	97.69 8	97.67 26	94.93 28	97.62 20	99.70 7	98.60 21	98.45 21	97.46 53	99.31 67	99.26 33

DPE-MVS		98.75 5	98.91 6	98.57 5	99.21 25	99.54 6	99.42 2	97.78 6	97.49 33	96.84 10	98.94 1	99.82 5	98.59 22	98.90 10	98.22 18	99.56 16	99.48 14
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
NCCC		98.10 22	98.05 31	98.17 20	99.38 20	99.05 38	99.00 21	97.53 19	98.04 14	95.12 26	94.80 53	99.18 18	98.58 23	98.49 18	97.78 42	99.39 54	98.98 75

MP-MVS		98.09 23	98.30 25	97.84 28	99.34 22	99.19 33	99.23 14	97.40 21	97.09 45	93.03 42	97.58 23	98.85 26	98.57 24	98.44 23	97.69 44	99.48 27	99.23 37
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
X-MVS		97.84 25	98.19 28	97.42 32	99.40 16	99.35 18	99.06 18	97.25 27	97.38 36	90.85 64	96.06 38	98.72 30	98.53 25	98.41 25	98.15 22	99.46 31	99.28 28

APD-MVS		98.36 16	98.32 23	98.41 9	99.47 6	99.26 27	99.12 16	97.77 7	96.73 52	96.12 18	97.27 29	98.88 25	98.46 26	98.47 19	98.39 14	99.52 19	99.22 39
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DROMVSNet		96.49 51	97.63 35	95.16 67	94.75 112	98.69 73	97.39 57	88.97 120	96.34 59	92.02 54	96.04 39	96.46 52	98.21 27	98.41 25	97.96 32	99.61 5	99.55 10

train_agg		97.65 30	98.06 30	97.18 35	98.94 34	98.91 58	98.98 25	97.07 33	96.71 53	90.66 69	97.43 27	99.08 24	98.20 28	97.96 48	97.14 63	99.22 84	99.19 43

CS-MVS-test		97.00 41	97.85 34	96.00 53	97.77 57	99.56 5	96.35 87	91.95 78	97.54 31	92.20 51	96.14 37	96.00 62	98.19 29	98.46 20	97.78 42	99.57 13	99.45 16

DeepC-MVS	94.87 4	96.76 50	96.50 55	97.05 37	98.21 50	99.28 25	98.67 28	97.38 22	97.31 37	90.36 76	89.19 104	93.58 73	98.19 29	98.31 28	98.50 7	99.51 24	99.36 21
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CS-MVS		96.87 45	97.41 40	96.24 48	97.42 62	99.48 9	97.30 58	91.83 83	97.17 41	93.02 43	94.80 53	94.45 68	98.16 31	98.61 14	97.85 39	99.69 1	99.50 12

SteuartSystems-ACMMP		98.38 15	98.71 10	97.99 25	99.34 22	99.46 10	99.34 6	97.33 26	97.31 37	94.25 32	98.06 14	99.17 19	98.13 32	98.98 5	98.46 9	99.55 17	99.54 11
Skip Steuart: Steuart Systems R&D Blog.
xxxxxxxxxxxxxcwj		97.07 39	95.99 63	98.33 11	99.45 10	99.05 38	98.27 38	97.65 9	97.73 19	97.02 7	98.18 12	81.99 147	98.11 33	98.15 39	97.62 46	99.45 35	99.19 43

SF-MVS		98.39 14	98.45 17	98.33 11	99.45 10	99.05 38	98.27 38	97.65 9	97.73 19	97.02 7	98.18 12	99.25 15	98.11 33	98.15 39	97.62 46	99.45 35	99.19 43

CSCG		97.44 33	97.18 44	97.75 29	99.47 6	99.52 8	98.55 32	95.41 42	97.69 25	95.72 21	94.29 57	95.53 64	98.10 35	96.20 108	97.38 57	99.24 78	99.62 4

3Dnovator+	93.91 7	97.23 36	97.22 41	97.24 34	98.89 37	98.85 63	98.26 40	93.25 59	97.99 15	95.56 24	90.01 100	98.03 42	98.05 36	97.91 49	98.43 10	99.44 43	99.35 22

TSAR-MVS + GP.		97.45 32	98.36 19	96.39 44	95.56 89	98.93 55	97.74 50	93.31 56	97.61 29	94.24 33	98.44 9	99.19 17	98.03 37	97.60 58	97.41 55	99.44 43	99.33 24

PLC	94.95 3	97.37 34	96.77 52	98.07 22	98.97 33	98.21 91	97.94 47	96.85 37	97.66 27	97.58 3	93.33 61	96.84 49	98.01 38	97.13 72	96.20 86	99.09 105	98.01 131
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
3Dnovator	93.79 8	97.08 38	97.20 42	96.95 39	99.09 30	99.03 45	98.20 41	93.33 55	97.99 15	93.82 35	90.61 94	96.80 50	97.82 39	97.90 50	98.78 3	99.47 30	99.26 33

LS3D		95.46 61	95.14 77	95.84 55	97.91 56	98.90 60	98.58 31	97.79 5	97.07 46	83.65 123	88.71 107	88.64 105	97.82 39	97.49 61	97.42 54	99.26 77	97.72 143

CNLPA		96.90 44	96.28 58	97.64 30	98.56 44	98.63 80	96.85 68	96.60 38	97.73 19	97.08 6	89.78 102	96.28 57	97.80 41	96.73 84	96.63 75	98.94 124	98.14 127

ACMMP		97.37 34	97.48 38	97.25 33	98.88 38	99.28 25	98.47 35	96.86 36	97.04 47	92.15 52	97.57 24	96.05 61	97.67 42	97.27 66	95.99 93	99.46 31	99.14 53
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 67	95.45 71	95.00 71	95.27 97	98.72 71	96.89 66	89.82 108	96.51 56	90.84 67	93.72 60	86.01 119	97.66 43	95.78 120	97.94 34	99.54 18	99.50 12

QAPM		96.78 49	97.14 45	96.36 45	99.05 31	99.14 36	98.02 44	93.26 57	97.27 39	90.84 67	91.16 86	97.31 45	97.64 44	97.70 56	98.20 19	99.33 62	99.18 47

TAPA-MVS	94.18 5	96.38 52	96.49 56	96.25 46	98.26 49	98.66 75	98.00 45	94.96 45	97.17 41	89.48 88	92.91 66	96.35 54	97.53 45	96.59 89	95.90 96	99.28 71	97.82 135
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PHI-MVS		97.78 27	98.44 18	97.02 38	98.73 39	99.25 29	98.11 42	95.54 41	96.66 55	92.79 46	98.52 6	99.38 9	97.50 46	97.84 51	98.39 14	99.45 35	99.03 68

ETV-MVS		96.31 53	97.47 39	94.96 73	94.79 109	98.78 66	96.08 93	91.41 90	96.16 65	90.50 71	95.76 43	96.20 58	97.39 47	98.42 24	97.82 40	99.57 13	99.18 47

OMC-MVS		97.00 41	96.92 49	97.09 36	98.69 40	98.66 75	97.85 48	95.02 44	98.09 13	94.47 29	93.15 62	96.90 47	97.38 48	97.16 71	96.82 73	99.13 100	97.65 144

MAR-MVS		95.50 58	95.60 67	95.39 64	98.67 41	98.18 94	95.89 101	89.81 109	94.55 108	91.97 55	92.99 64	90.21 92	97.30 49	96.79 81	97.49 51	98.72 145	98.99 73
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 46	96.82 51	96.91 40	98.08 53	98.20 92	98.52 34	97.20 30	97.24 40	91.42 58	91.84 78	98.45 36	97.25 50	97.07 73	97.40 56	98.95 123	97.55 147

abl_6				96.82 41	98.60 43	98.74 68	97.74 50	93.73 51	96.25 62	94.37 31	94.55 56	98.60 35	97.25 50			99.27 73	98.61 100

MVS_111021_LR		97.16 37	98.01 32	96.16 49	98.47 45	98.98 50	96.94 65	93.89 50	97.64 28	91.44 57	98.89 3	96.41 53	97.20 52	98.02 47	97.29 62	99.04 116	98.85 90

CDPH-MVS		96.84 47	97.49 37	96.09 50	98.92 35	98.85 63	98.61 29	95.09 43	96.00 72	87.29 108	95.45 47	97.42 44	97.16 53	97.83 52	97.94 34	99.44 43	98.92 81

thres400		93.56 104	92.43 129	94.87 76	95.40 91	98.91 58	96.70 76	92.38 70	92.93 131	88.19 103	86.69 120	77.35 166	97.13 54	96.75 83	95.85 98	99.42 48	98.56 102

thres200		93.62 102	92.54 122	94.88 75	95.36 92	98.93 55	96.75 74	92.31 71	92.84 132	88.28 101	86.99 117	77.81 165	97.13 54	96.82 78	95.92 94	99.45 35	98.49 108

tfpn200view9		93.64 101	92.57 121	94.89 74	95.33 93	98.94 53	96.82 69	92.31 71	92.63 135	88.29 99	87.21 115	78.01 163	97.12 56	96.82 78	95.85 98	99.45 35	98.56 102

thres600view7		93.49 106	92.37 132	94.79 79	95.42 90	98.93 55	96.58 80	92.31 71	93.04 129	87.88 104	86.62 121	76.94 169	97.09 57	96.82 78	95.63 103	99.45 35	98.63 99

EIA-MVS		95.50 58	96.19 60	94.69 81	94.83 108	98.88 62	95.93 98	91.50 89	94.47 109	89.43 89	93.14 63	92.72 78	97.05 58	97.82 54	97.13 64	99.43 46	99.15 51

ET-MVSNet_ETH3D		93.34 108	94.33 91	92.18 114	83.26 215	97.66 104	96.72 75	89.89 107	95.62 84	87.17 109	96.00 40	83.69 138	96.99 59	93.78 156	95.34 111	99.06 111	98.18 126

TSAR-MVS + COLMAP		94.79 73	94.51 86	95.11 68	96.50 73	97.54 105	97.99 46	94.54 46	97.81 17	85.88 114	96.73 32	81.28 151	96.99 59	96.29 103	95.21 116	98.76 144	96.73 170

PCF-MVS	93.95 6	95.65 57	95.14 77	96.25 46	97.73 60	98.73 70	97.59 53	97.13 32	92.50 139	89.09 97	89.85 101	96.65 51	96.90 61	94.97 140	94.89 124	99.08 106	98.38 116
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TSAR-MVS + ACMM		97.71 29	98.60 12	96.66 42	98.64 42	99.05 38	98.85 26	97.23 29	98.45 4	89.40 91	97.51 25	99.27 14	96.88 62	98.53 16	97.81 41	98.96 122	99.59 8

OpenMVS	92.33 11	95.50 58	95.22 75	95.82 56	98.98 32	98.97 51	97.67 52	93.04 65	94.64 106	89.18 95	84.44 140	94.79 66	96.79 63	97.23 67	97.61 48	99.24 78	98.88 86

thres100view900		93.55 105	92.47 128	94.81 78	95.33 93	98.74 68	96.78 73	92.30 74	92.63 135	88.29 99	87.21 115	78.01 163	96.78 64	96.38 98	95.92 94	99.38 55	98.40 114

Anonymous20231211		93.49 106	92.33 133	94.84 77	94.78 111	98.00 98	96.11 92	91.85 80	94.86 103	90.91 63	74.69 179	89.18 100	96.73 65	94.82 141	95.51 107	98.67 149	99.24 36

Effi-MVS+		92.93 112	93.86 101	91.86 115	94.07 128	98.09 97	95.59 106	85.98 153	94.27 113	79.54 143	91.12 89	81.81 148	96.71 66	96.67 87	96.06 89	99.27 73	98.98 75

MVS_111021_HR		97.04 40	98.20 27	95.69 57	98.44 47	99.29 24	96.59 79	93.20 60	97.70 23	89.94 83	98.46 8	96.89 48	96.71 66	98.11 44	97.95 33	99.27 73	99.01 71

Fast-Effi-MVS+		91.87 121	92.08 136	91.62 121	92.91 144	97.21 115	94.93 117	84.60 172	93.61 123	81.49 134	83.50 145	78.95 158	96.62 68	96.55 91	96.22 85	99.16 96	98.51 106

casdiffmvs		94.38 86	94.15 97	94.64 83	94.70 116	98.51 84	96.03 96	91.66 85	95.70 81	89.36 92	86.48 124	85.03 129	96.60 69	97.40 63	97.30 60	99.52 19	98.67 97

Anonymous202405211			92.18 134		95.04 104	98.20 92	96.14 91	91.79 84	93.93 116		74.60 180	88.38 108	96.48 70	95.17 136	95.82 101	99.00 117	99.15 51

MVS_Test		94.82 71	95.66 66	93.84 94	94.79 109	98.35 87	96.49 83	89.10 119	96.12 68	87.09 110	92.58 69	90.61 89	96.48 70	96.51 96	96.89 70	99.11 103	98.54 104

ACMM	92.75 10	94.41 85	93.84 102	95.09 69	96.41 76	96.80 123	94.88 119	93.54 53	96.41 58	90.16 77	92.31 72	83.11 141	96.32 72	96.22 106	94.65 130	99.22 84	97.35 153
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OPM-MVS		93.61 103	92.43 129	95.00 71	96.94 70	97.34 111	97.78 49	94.23 48	89.64 171	85.53 115	88.70 108	82.81 143	96.28 73	96.28 104	95.00 123	99.24 78	97.22 156
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CANet		96.84 47	97.20 42	96.42 43	97.92 55	99.24 31	98.60 30	93.51 54	97.11 44	93.07 39	91.16 86	97.24 46	96.21 74	98.24 36	98.05 26	99.22 84	99.35 22

PMMVS		94.61 78	95.56 68	93.50 99	94.30 123	96.74 127	94.91 118	89.56 113	95.58 86	87.72 105	96.15 36	92.86 76	96.06 75	95.47 128	95.02 121	98.43 167	97.09 159

CLD-MVS		94.79 73	94.36 90	95.30 65	95.21 99	97.46 108	97.23 59	92.24 75	96.43 57	91.77 56	92.69 68	84.31 132	96.06 75	95.52 126	95.03 120	99.31 67	99.06 62
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 77	94.41 88	95.02 70	97.63 61	98.15 95	94.50 127	91.99 77	95.32 90	91.31 60	95.47 46	83.44 139	96.02 77	96.56 90	95.23 115	98.69 148	96.67 171

diffmvs		94.31 88	94.21 92	94.42 86	94.64 117	98.28 88	96.36 86	91.56 86	96.77 51	88.89 98	88.97 105	84.23 133	96.01 78	96.05 112	96.41 79	99.05 115	98.79 94

DCV-MVSNet		94.76 76	95.12 79	94.35 87	95.10 103	95.81 157	96.46 84	89.49 114	96.33 60	90.16 77	92.55 70	90.26 91	95.83 79	95.52 126	96.03 91	99.06 111	99.33 24

MVS_0304		96.31 53	96.91 50	95.62 58	97.21 67	99.20 32	98.55 32	93.10 62	97.04 47	89.73 85	90.30 96	96.35 54	95.71 80	98.14 41	97.93 36	99.38 55	99.40 18

HyFIR lowres test		92.03 119	91.55 143	92.58 109	97.13 68	98.72 71	94.65 124	86.54 146	93.58 124	82.56 127	67.75 209	90.47 90	95.67 81	95.87 116	95.54 106	98.91 127	98.93 80

baseline1		94.59 79	94.47 87	94.72 80	95.16 100	97.97 100	96.07 94	91.94 79	94.86 103	89.98 81	91.60 82	85.87 121	95.64 82	97.07 73	96.90 69	99.52 19	97.06 163

GeoE		92.52 117	92.64 120	92.39 112	93.96 129	97.76 102	96.01 97	85.60 158	93.23 127	83.94 120	81.56 153	84.80 130	95.63 83	96.22 106	95.83 100	99.19 91	99.07 61

CHOSEN 280x420		95.46 61	97.01 46	93.66 97	97.28 66	97.98 99	96.40 85	85.39 161	96.10 69	91.07 61	96.53 34	96.34 56	95.61 84	97.65 57	96.95 68	96.21 193	97.49 148

HQP-MVS		94.43 83	94.57 85	94.27 88	96.41 76	97.23 114	96.89 66	93.98 49	95.94 74	83.68 122	95.01 51	84.46 131	95.58 85	95.47 128	94.85 128	99.07 108	99.00 72

MSDG		94.82 71	93.73 104	96.09 50	98.34 48	97.43 110	97.06 60	96.05 39	95.84 78	90.56 70	86.30 129	89.10 102	95.55 86	96.13 111	95.61 104	99.00 117	95.73 179

DeepPCF-MVS	95.28 2	97.00 41	98.35 21	95.42 63	97.30 65	98.94 53	94.82 120	96.03 40	98.24 9	92.11 53	95.80 42	98.64 33	95.51 87	98.95 7	98.66 5	96.78 192	99.20 42

DI_MVS_plusplus_trai		94.01 92	93.63 106	94.44 85	94.54 118	98.26 90	97.51 54	90.63 98	95.88 76	89.34 93	80.54 161	89.36 97	95.48 88	96.33 102	96.27 83	99.17 93	98.78 95

FA-MVS(training)		93.94 94	95.16 76	92.53 110	94.87 107	98.57 83	95.42 109	79.49 194	95.37 88	90.98 62	86.54 122	94.26 70	95.44 89	97.80 55	95.19 117	98.97 120	98.38 116

EPP-MVSNet		95.27 66	96.18 61	94.20 89	94.88 106	98.64 78	94.97 116	90.70 97	95.34 89	89.67 87	91.66 81	93.84 71	95.42 90	97.32 65	97.00 66	99.58 10	99.47 15

RPSCF		94.05 91	94.00 98	94.12 90	96.20 78	96.41 137	96.61 78	91.54 87	95.83 79	89.73 85	96.94 31	92.80 77	95.35 91	91.63 191	90.44 193	95.27 205	93.94 196

test2506		94.32 87	93.00 116	95.87 54	96.16 79	99.39 16	96.96 63	92.80 67	95.22 96	94.47 29	91.55 83	70.45 196	95.25 92	98.29 29	97.98 29	99.59 6	98.10 129

ECVR-MVS		94.14 89	92.96 117	95.52 61	96.16 79	99.39 16	96.96 63	92.80 67	95.22 96	92.38 50	81.48 154	80.31 152	95.25 92	98.29 29	97.98 29	99.59 6	98.05 130

LGP-MVS_train		94.12 90	94.62 84	93.53 98	96.44 75	97.54 105	97.40 56	91.84 81	94.66 105	81.09 136	95.70 44	83.36 140	95.10 94	96.36 101	95.71 102	99.32 64	99.03 68

DELS-MVS		96.06 56	96.04 62	96.07 52	97.77 57	99.25 29	98.10 43	93.26 57	94.42 110	92.79 46	88.52 111	93.48 74	95.06 95	98.51 17	98.83 1	99.45 35	99.28 28
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
test1111		93.94 94	92.78 118	95.29 66	96.14 81	99.42 11	96.79 72	92.85 66	95.08 100	91.39 59	80.69 159	79.86 155	95.00 96	98.28 32	98.00 28	99.58 10	98.11 128

ACMP	92.88 9	94.43 83	94.38 89	94.50 84	96.01 84	97.69 103	95.85 104	92.09 76	95.74 80	89.12 96	95.14 49	82.62 145	94.77 97	95.73 122	94.67 129	99.14 99	99.06 62
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
thisisatest0530		94.54 80	95.47 70	93.46 100	94.51 119	98.65 77	94.66 123	90.72 95	95.69 83	86.90 111	93.80 58	89.44 96	94.74 98	96.98 77	94.86 125	99.19 91	98.85 90

tttt0517		94.52 81	95.44 72	93.44 101	94.51 119	98.68 74	94.61 125	90.72 95	95.61 85	86.84 112	93.78 59	89.26 99	94.74 98	97.02 76	94.86 125	99.20 90	98.87 88

baseline		94.83 70	95.82 65	93.68 96	94.75 112	97.80 101	96.51 82	88.53 125	97.02 49	89.34 93	92.93 65	92.18 80	94.69 100	95.78 120	96.08 87	98.27 170	98.97 79

PVSNet_BlendedMVS		95.41 63	95.28 73	95.57 59	97.42 62	99.02 47	95.89 101	93.10 62	96.16 65	93.12 37	91.99 74	85.27 124	94.66 101	98.09 45	97.34 58	99.24 78	99.08 57

PVSNet_Blended		95.41 63	95.28 73	95.57 59	97.42 62	99.02 47	95.89 101	93.10 62	96.16 65	93.12 37	91.99 74	85.27 124	94.66 101	98.09 45	97.34 58	99.24 78	99.08 57

FC-MVSNet-train		93.85 97	93.91 99	93.78 95	94.94 105	96.79 126	94.29 130	91.13 92	93.84 120	88.26 102	90.40 95	85.23 126	94.65 103	96.54 92	95.31 112	99.38 55	99.28 28

CANet_DTU		93.92 96	96.57 54	90.83 129	95.63 87	98.39 86	96.99 62	87.38 137	96.26 61	71.97 182	96.31 35	93.02 75	94.53 104	97.38 64	96.83 72	98.49 162	97.79 136

FMVSNet1		91.54 128	90.93 149	92.26 113	90.35 168	95.27 176	95.22 113	87.16 140	91.37 156	87.62 106	75.45 174	83.84 136	94.43 105	96.52 93	96.30 80	98.82 134	97.74 142

IterMVS-LS		92.56 116	93.18 113	91.84 116	93.90 130	94.97 183	94.99 115	86.20 150	94.18 114	82.68 126	85.81 131	87.36 112	94.43 105	95.31 132	96.02 92	98.87 130	98.60 101
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		93.81 98	94.18 93	93.38 102	91.34 158	95.86 153	96.22 88	88.68 122	95.23 93	90.40 72	86.39 125	91.16 83	94.40 107	96.52 93	96.30 80	99.21 87	97.79 136

test1		93.81 98	94.18 93	93.38 102	91.34 158	95.86 153	96.22 88	88.68 122	95.23 93	90.40 72	86.39 125	91.16 83	94.40 107	96.52 93	96.30 80	99.21 87	97.79 136

FMVSNet2		93.30 109	93.36 112	93.22 106	91.34 158	95.86 153	96.22 88	88.24 129	95.15 99	89.92 84	81.64 152	89.36 97	94.40 107	96.77 82	96.98 67	99.21 87	97.79 136

IS_MVSNet		95.28 65	96.43 57	93.94 91	95.30 95	99.01 49	95.90 99	91.12 93	94.13 115	87.50 107	91.23 85	94.45 68	94.17 110	98.45 21	98.50 7	99.65 3	99.23 37

FMVSNet3		93.79 100	94.17 95	93.35 104	91.21 161	95.99 146	96.62 77	88.68 122	95.23 93	90.40 72	86.39 125	91.16 83	94.11 111	95.96 113	96.67 74	99.07 108	97.79 136

CHOSEN 1792x2688		92.66 115	92.49 125	92.85 108	97.13 68	98.89 61	95.90 99	88.50 126	95.32 90	83.31 124	71.99 198	88.96 103	94.10 112	96.69 85	96.49 77	98.15 172	99.10 54

UniMVSNet_ETH3D		88.47 168	86.00 198	91.35 123	91.55 155	96.29 140	92.53 155	88.81 121	85.58 202	82.33 128	67.63 210	66.87 211	94.04 113	91.49 192	95.24 114	98.84 133	98.92 81

SCA		90.92 135	93.04 115	88.45 157	93.72 135	97.33 112	92.77 150	76.08 206	96.02 71	78.26 147	91.96 76	90.86 86	93.99 114	90.98 195	90.04 196	95.88 197	94.06 195

EPMVS		90.88 136	92.12 135	89.44 148	94.71 114	97.24 113	93.55 137	76.81 201	95.89 75	81.77 131	91.49 84	86.47 115	93.87 115	90.21 198	90.07 195	95.92 196	93.49 202

COLMAP_ROB	90.49 14	93.27 110	92.71 119	93.93 92	97.75 59	97.44 109	96.07 94	93.17 61	95.40 87	83.86 121	83.76 144	88.72 104	93.87 115	94.25 152	94.11 147	98.87 130	95.28 185
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	91.41 130	91.13 146	91.74 118	95.11 102	96.95 118	93.13 146	89.48 115	92.42 141	79.93 140	85.13 134	78.02 162	93.82 117	93.49 163	93.88 153	98.94 124	97.99 132

ACMH	90.77 13	91.51 129	91.63 142	91.38 122	95.62 88	96.87 121	91.76 174	89.66 111	91.58 154	78.67 145	86.73 119	78.12 161	93.77 118	94.59 143	94.54 138	98.78 142	98.98 75
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CostFormer		90.69 137	90.48 154	90.93 127	94.18 125	96.08 145	94.03 132	78.20 197	93.47 125	89.96 82	90.97 91	80.30 153	93.72 119	87.66 208	88.75 200	95.51 202	96.12 175

MVSTER		94.89 69	95.07 80	94.68 82	94.71 114	96.68 129	97.00 61	90.57 99	95.18 98	93.05 41	95.21 48	86.41 116	93.72 119	97.59 59	95.88 97	99.00 117	98.50 107

test_part1		91.21 131	89.47 159	93.24 105	94.26 124	95.45 169	95.26 111	88.36 127	88.49 181	90.04 79	72.61 195	82.82 142	93.69 121	93.25 167	94.62 132	97.84 180	99.06 62

USDC		90.69 137	90.52 153	90.88 128	94.17 126	96.43 136	95.82 105	86.76 143	93.92 117	76.27 160	86.49 123	74.30 179	93.67 122	95.04 139	93.36 162	98.61 155	94.13 192

Effi-MVS+-dtu		91.78 123	93.59 108	89.68 146	92.44 150	97.11 116	94.40 128	84.94 168	92.43 140	75.48 164	91.09 90	83.75 137	93.55 123	96.61 88	95.47 108	97.24 188	98.67 97

PatchmatchNet		90.56 139	92.49 125	88.31 160	93.83 133	96.86 122	92.42 158	76.50 203	95.96 73	78.31 146	91.96 76	89.66 95	93.48 124	90.04 200	89.20 199	95.32 203	93.73 200
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TinyColmap		89.42 154	88.58 166	90.40 135	93.80 134	95.45 169	93.96 134	86.54 146	92.24 147	76.49 157	80.83 157	70.44 197	93.37 125	94.45 147	93.30 165	98.26 171	93.37 203

LTVRE_ROB	87.32 16	87.55 181	88.25 170	86.73 187	90.66 163	95.80 158	93.05 147	84.77 169	83.35 208	60.32 216	83.12 147	67.39 209	93.32 126	94.36 150	94.86 125	98.28 169	98.87 88
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		89.80 151	91.33 145	88.00 169	94.43 121	96.71 128	92.29 162	74.95 211	96.07 70	77.39 150	88.67 109	86.09 118	93.26 127	88.44 204	89.57 198	95.68 199	93.81 199

MDTV_nov1_ep13		91.57 127	93.18 113	89.70 144	93.39 138	96.97 117	93.53 138	80.91 191	95.70 81	81.86 130	92.40 71	89.93 93	93.25 128	91.97 188	90.80 191	95.25 206	94.46 189

UniMVSNet_NR-MVSNet		90.35 143	89.96 155	90.80 130	89.66 177	95.83 156	92.48 156	90.53 100	90.96 161	79.57 141	79.33 165	77.14 167	93.21 129	92.91 173	94.50 141	99.37 58	99.05 65

DU-MVS		89.67 153	88.84 164	90.63 133	89.26 187	95.61 162	92.48 156	89.91 105	91.22 157	79.57 141	77.72 169	71.18 193	93.21 129	92.53 177	94.57 135	99.35 61	99.05 65

pmmvs4		90.55 140	89.91 156	91.30 124	90.26 170	94.95 184	92.73 152	87.94 132	93.44 126	85.35 116	82.28 151	76.09 171	93.02 131	93.56 161	92.26 185	98.51 161	96.77 169

tpmrst		88.86 166	89.62 157	87.97 170	94.33 122	95.98 147	92.62 154	76.36 204	94.62 107	76.94 154	85.98 130	82.80 144	92.80 132	86.90 210	87.15 206	94.77 210	93.93 197

RPMNet		90.19 146	92.03 138	88.05 166	93.46 136	95.95 150	93.41 140	74.59 212	92.40 142	75.91 162	84.22 141	86.41 116	92.49 133	94.42 148	93.85 155	98.44 165	96.96 164

FMVSNet5		90.36 142	90.93 149	89.70 144	87.99 203	92.25 208	92.03 169	83.51 178	92.20 148	84.13 119	85.59 132	86.48 114	92.43 134	94.61 142	94.52 139	98.13 173	90.85 209

dps		90.11 149	89.37 162	90.98 126	93.89 131	96.21 142	93.49 139	77.61 199	91.95 150	92.74 48	88.85 106	78.77 160	92.37 135	87.71 207	87.71 204	95.80 198	94.38 190

Baseline_NR-MVSNet		89.27 158	88.01 174	90.73 132	89.26 187	93.71 203	92.71 153	89.78 110	90.73 162	81.28 135	73.53 189	72.85 185	92.30 136	92.53 177	93.84 156	99.07 108	98.88 86

CR-MVSNet		90.16 147	91.96 139	88.06 165	93.32 139	95.95 150	93.36 142	75.99 207	92.40 142	75.19 168	83.18 146	85.37 123	92.05 137	95.21 134	94.56 136	98.47 164	97.08 161

PatchT		89.13 161	91.71 140	86.11 193	92.92 143	95.59 164	83.64 209	75.09 210	91.87 151	75.19 168	82.63 149	85.06 128	92.05 137	95.21 134	94.56 136	97.76 182	97.08 161

v2v482		88.25 171	87.71 181	88.88 152	89.23 191	95.28 174	92.10 166	87.89 133	88.69 179	73.31 178	75.32 175	71.64 190	91.89 139	92.10 185	92.92 171	98.86 132	97.99 132

tfpnnormal		88.50 167	87.01 189	90.23 136	91.36 157	95.78 159	92.74 151	90.09 103	83.65 207	76.33 159	71.46 201	69.58 202	91.84 140	95.54 125	94.02 150	99.06 111	99.03 68

TranMVSNet+NR-MVSNet		89.23 159	88.48 168	90.11 142	89.07 193	95.25 177	92.91 149	90.43 101	90.31 167	77.10 153	76.62 172	71.57 191	91.83 141	92.12 183	94.59 134	99.32 64	98.92 81

EPNet		96.27 55	96.97 47	95.46 62	98.47 45	98.28 88	97.41 55	93.67 52	95.86 77	92.86 45	97.51 25	93.79 72	91.76 142	97.03 75	97.03 65	98.61 155	99.28 28
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Fast-Effi-MVS+-dtu		91.19 132	93.64 105	88.33 159	92.19 152	96.46 135	93.99 133	81.52 189	92.59 137	71.82 183	92.17 73	85.54 122	91.68 143	95.73 122	94.64 131	98.80 139	98.34 118

tpm		87.95 174	89.44 161	86.21 192	92.53 149	94.62 193	91.40 177	76.36 204	91.46 155	69.80 197	87.43 114	75.14 174	91.55 144	89.85 202	90.60 192	95.61 200	96.96 164

tpm cat1		88.90 164	87.78 180	90.22 137	93.88 132	95.39 172	93.79 135	78.11 198	92.55 138	89.43 89	81.31 155	79.84 156	91.40 145	84.95 211	86.34 209	94.68 212	94.09 193

baseline2		93.01 111	94.17 95	91.64 119	92.83 146	97.49 107	93.40 141	87.53 135	93.67 122	86.07 113	91.83 79	86.58 113	91.36 146	96.38 98	95.06 119	98.67 149	98.20 125

v10		88.00 173	87.96 175	88.05 166	89.44 182	94.68 190	92.36 159	83.35 179	89.37 173	72.96 179	73.98 186	72.79 186	91.35 147	93.59 158	92.88 172	98.81 137	98.42 112

v1192		87.51 182	87.31 183	87.74 174	89.04 194	94.87 188	92.07 167	85.03 166	88.49 181	70.32 190	72.65 194	70.35 198	91.21 148	93.59 158	92.80 174	98.78 142	98.42 112

UniMVSNet (Re)		90.03 150	89.61 158	90.51 134	89.97 174	96.12 144	92.32 160	89.26 116	90.99 160	80.95 137	78.25 168	75.08 176	91.14 149	93.78 156	93.87 154	99.41 49	99.21 41

v1921920		87.31 186	87.13 187	87.52 180	88.87 197	94.72 189	91.96 172	84.59 173	88.28 183	69.86 196	72.50 196	70.03 201	91.10 150	93.33 165	92.61 179	98.71 146	98.44 109

v1144		87.92 177	87.79 179	88.07 163	89.27 186	95.15 179	92.17 165	85.62 157	88.52 180	71.52 184	73.80 187	72.40 188	91.06 151	93.54 162	92.80 174	98.81 137	98.33 119

MIMVSNet		88.99 163	91.07 147	86.57 189	86.78 209	95.62 161	91.20 182	75.40 209	90.65 164	76.57 156	84.05 142	82.44 146	91.01 152	95.84 117	95.38 110	98.48 163	93.50 201

test-LLR		91.62 126	93.56 109	89.35 150	93.31 140	96.57 132	92.02 170	87.06 141	92.34 145	75.05 171	90.20 97	88.64 105	90.93 153	96.19 109	94.07 148	97.75 183	96.90 167

TESTMET0.1,1		91.07 133	93.56 109	88.17 161	90.43 165	96.57 132	92.02 170	82.83 183	92.34 145	75.05 171	90.20 97	88.64 105	90.93 153	96.19 109	94.07 148	97.75 183	96.90 167

SixPastTwentyTwo		88.37 169	89.47 159	87.08 184	90.01 173	95.93 152	87.41 199	85.32 162	90.26 169	70.26 191	86.34 128	71.95 189	90.93 153	92.89 174	91.72 188	98.55 158	97.22 156

test-mter		90.95 134	93.54 111	87.93 171	90.28 169	96.80 123	91.44 176	82.68 184	92.15 149	74.37 175	89.57 103	88.23 110	90.88 156	96.37 100	94.31 144	97.93 179	97.37 152

PVSNet_Blended_VisFu		94.77 75	95.54 69	93.87 93	96.48 74	98.97 51	94.33 129	91.84 81	94.93 102	90.37 75	85.04 135	94.99 65	90.87 157	98.12 43	97.30 60	99.30 69	99.45 16

CP-MVSNet		87.89 178	87.27 184	88.62 155	89.30 185	95.06 180	90.60 187	85.78 155	87.43 192	75.98 161	74.60 180	68.14 208	90.76 158	93.07 171	93.60 159	99.30 69	98.98 75

v144192		87.40 184	87.20 186	87.64 175	88.89 195	94.88 187	91.65 175	84.70 171	87.80 187	71.17 188	73.20 192	70.91 194	90.75 159	92.69 175	92.49 180	98.71 146	98.43 110

pmmvs5		87.83 179	88.09 172	87.51 181	89.59 180	95.48 167	89.75 193	84.73 170	86.07 200	71.44 185	80.57 160	70.09 200	90.74 160	94.47 146	92.87 173	98.82 134	97.10 158

v8		88.21 172	87.94 177	88.51 156	89.62 178	95.01 182	92.31 161	84.99 167	88.94 174	74.70 173	75.03 176	73.51 183	90.67 161	92.11 184	92.74 177	98.80 139	98.24 123

v1240		86.89 188	86.75 193	87.06 185	88.75 199	94.65 192	91.30 181	84.05 175	87.49 191	68.94 200	71.96 199	68.86 206	90.65 162	93.33 165	92.72 178	98.67 149	98.24 123

gm-plane-assit		83.26 203	85.29 200	80.89 204	89.52 181	89.89 214	70.26 220	78.24 196	77.11 217	58.01 220	74.16 185	66.90 210	90.63 163	97.20 68	96.05 90	98.66 152	95.68 180

MS-PatchMatch		91.82 122	92.51 123	91.02 125	95.83 86	96.88 119	95.05 114	84.55 174	93.85 119	82.01 129	82.51 150	91.71 81	90.52 164	95.07 138	93.03 169	98.13 173	94.52 187

CDS-MVSNet		92.77 113	93.60 107	91.80 117	92.63 148	96.80 123	95.24 112	89.14 118	90.30 168	84.58 118	86.76 118	90.65 88	90.42 165	95.89 115	96.49 77	98.79 141	98.32 121
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		90.54 141	90.87 151	90.16 138	91.48 156	96.61 131	93.26 144	86.08 151	87.71 188	81.66 133	83.11 148	84.04 134	90.42 165	94.54 144	94.60 133	98.04 177	95.48 183

V42		88.31 170	87.95 176	88.73 154	89.44 182	95.34 173	92.23 164	87.21 139	88.83 176	74.49 174	74.89 178	73.43 184	90.41 167	92.08 186	92.77 176	98.60 157	98.33 119

anonymousdsp		88.90 164	91.00 148	86.44 190	88.74 200	95.97 148	90.40 189	82.86 182	88.77 178	67.33 202	81.18 156	81.44 150	90.22 168	96.23 105	94.27 145	99.12 102	99.16 50

PS-CasMVS		87.33 185	86.68 194	88.10 162	89.22 192	94.93 185	90.35 190	85.70 156	86.44 197	74.01 176	73.43 190	66.59 214	90.04 169	92.92 172	93.52 160	99.28 71	98.91 84

IterMVS-SCA-FT		90.24 144	92.48 127	87.63 176	92.85 145	94.30 199	93.79 135	81.47 190	92.66 134	69.95 194	84.66 138	88.38 108	89.99 170	95.39 131	94.34 143	97.74 185	97.63 145

IterMVS		90.20 145	92.43 129	87.61 177	92.82 147	94.31 198	94.11 131	81.54 188	92.97 130	69.90 195	84.71 137	88.16 111	89.96 171	95.25 133	94.17 146	97.31 187	97.46 149
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
gg-mvs-nofinetune		86.17 193	88.57 167	83.36 201	93.44 137	98.15 95	96.58 80	72.05 215	74.12 219	49.23 223	64.81 213	90.85 87	89.90 172	97.83 52	96.84 71	98.97 120	97.41 151

GA-MVS		89.28 157	90.75 152	87.57 178	91.77 154	96.48 134	92.29 162	87.58 134	90.61 165	65.77 204	84.48 139	76.84 170	89.46 173	95.84 117	93.68 158	98.52 160	97.34 154

PEN-MVS		87.22 187	86.50 196	88.07 163	88.88 196	94.44 195	90.99 184	86.21 148	86.53 196	73.66 177	74.97 177	66.56 215	89.42 174	91.20 194	93.48 161	99.24 78	98.31 122

NR-MVSNet		89.34 156	88.66 165	90.13 141	90.40 166	95.61 162	93.04 148	89.91 105	91.22 157	78.96 144	77.72 169	68.90 205	89.16 175	94.24 153	93.95 151	99.32 64	98.99 73

pm-mvs1		89.19 160	89.02 163	89.38 149	90.40 166	95.74 160	92.05 168	88.10 131	86.13 198	77.70 148	73.72 188	79.44 157	88.97 176	95.81 119	94.51 140	99.08 106	97.78 141

MVS-HIRNet		85.36 197	86.89 190	83.57 200	90.13 171	94.51 194	83.57 210	72.61 214	88.27 184	71.22 187	68.97 205	81.81 148	88.91 177	93.08 170	91.94 186	94.97 209	89.64 212

PM-MVS		84.72 200	84.47 204	85.03 196	84.67 211	91.57 210	86.27 203	82.31 186	87.65 189	70.62 189	76.54 173	56.41 222	88.75 178	92.59 176	89.85 197	97.54 186	96.66 172

Vis-MVSNet (Re-imp)		94.46 82	96.24 59	92.40 111	95.23 98	98.64 78	95.56 107	90.99 94	94.42 110	85.02 117	90.88 92	94.65 67	88.01 179	98.17 38	98.37 16	99.57 13	98.53 105

v7n		86.43 191	86.52 195	86.33 191	87.91 204	94.93 185	90.15 191	83.05 180	86.57 195	70.21 192	71.48 200	66.78 212	87.72 180	94.19 155	92.96 170	98.92 126	98.76 96

pmmvs6		85.98 195	84.89 203	87.25 183	88.83 198	94.35 197	89.36 194	85.30 164	78.51 216	75.44 165	62.71 215	75.41 173	87.65 181	93.58 160	92.40 182	96.89 190	97.29 155

DTE-MVSNet		86.67 190	86.09 197	87.35 182	88.45 202	94.08 201	90.65 186	86.05 152	86.13 198	72.19 181	74.58 182	66.77 213	87.61 182	90.31 197	93.12 167	99.13 100	97.62 146

MDTV_nov1_ep13_2view		86.30 192	88.27 169	84.01 199	87.71 206	94.67 191	88.08 197	76.78 202	90.59 166	68.66 201	80.46 162	80.12 154	87.58 183	89.95 201	88.20 202	95.25 206	93.90 198

pmmvs-eth3d		84.33 201	82.94 206	85.96 195	84.16 212	90.94 211	86.55 202	83.79 176	84.25 205	75.85 163	70.64 203	56.43 221	87.44 184	92.20 182	90.41 194	97.97 178	95.68 180

v148		87.51 182	86.79 191	88.36 158	89.39 184	95.21 178	89.84 192	88.20 130	87.61 190	77.56 149	73.38 191	70.32 199	86.80 185	90.70 196	92.31 183	98.37 168	97.98 134

TransMVSNet (Re)		87.73 180	86.79 191	88.83 153	90.76 162	94.40 196	91.33 180	89.62 112	84.73 204	75.41 166	72.73 193	71.41 192	86.80 185	94.53 145	93.93 152	99.06 111	95.83 177

pmnet_mix02		86.12 194	87.12 188	84.96 197	89.82 175	94.12 200	84.88 207	86.63 145	91.78 152	65.60 205	80.76 158	76.98 168	86.61 187	87.29 209	84.80 212	96.21 193	94.09 193

WR-MVS_H		87.93 175	87.85 178	88.03 168	89.62 178	95.58 166	90.47 188	85.55 159	87.20 193	76.83 155	74.42 183	72.67 187	86.37 188	93.22 168	93.04 168	99.33 62	98.83 92

UGNet		94.92 68	96.63 53	92.93 107	96.03 83	98.63 80	94.53 126	91.52 88	96.23 63	90.03 80	92.87 67	96.10 60	86.28 189	96.68 86	96.60 76	99.16 96	99.32 26
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 93	95.95 64	91.64 119	96.06 82	98.59 82	95.29 110	90.00 104	91.06 159	82.87 125	90.64 93	98.06 41	86.06 190	98.14 41	98.20 19	99.58 10	96.96 164

test0.0.03 1		91.97 120	93.91 99	89.72 143	93.31 140	96.40 138	91.34 179	87.06 141	93.86 118	81.67 132	91.15 88	89.16 101	86.02 191	95.08 137	95.09 118	98.91 127	96.64 173

thisisatest0515		90.12 148	92.06 137	87.85 172	90.03 172	96.17 143	87.83 198	87.45 136	91.71 153	77.15 152	85.40 133	84.01 135	85.74 192	95.41 130	93.30 165	98.88 129	98.43 110

FC-MVSNet-test		91.63 125	93.82 103	89.08 151	92.02 153	96.40 138	93.26 144	87.26 138	93.72 121	77.26 151	88.61 110	89.86 94	85.50 193	95.72 124	95.02 121	99.16 96	97.44 150

CMPMVS	65.18 17	84.76 199	83.10 205	86.69 188	95.29 96	95.05 181	88.37 196	85.51 160	80.27 214	71.31 186	68.37 207	73.85 181	85.25 194	87.72 206	87.75 203	94.38 213	88.70 213
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
N_pmnet		84.80 198	85.10 202	84.45 198	89.25 190	92.86 206	84.04 208	86.21 148	88.78 177	66.73 203	72.41 197	74.87 178	85.21 195	88.32 205	86.45 207	95.30 204	92.04 206

WR-MVS		87.93 175	88.09 172	87.75 173	89.26 187	95.28 174	90.81 185	86.69 144	88.90 175	75.29 167	74.31 184	73.72 182	85.19 196	92.26 180	93.32 164	99.27 73	98.81 93

TDRefinement		89.07 162	88.15 171	90.14 140	95.16 100	96.88 119	95.55 108	90.20 102	89.68 170	76.42 158	76.67 171	74.30 179	84.85 197	93.11 169	91.91 187	98.64 154	94.47 188

CVMVSNet		89.77 152	91.66 141	87.56 179	93.21 142	95.45 169	91.94 173	89.22 117	89.62 172	69.34 199	83.99 143	85.90 120	84.81 198	94.30 151	95.28 113	96.85 191	97.09 159

pmmvs3		79.16 208	80.12 210	78.05 210	79.36 216	86.59 217	78.13 217	73.87 213	76.42 218	57.51 221	70.59 204	57.02 220	84.66 199	90.10 199	88.32 201	94.75 211	91.77 208

Vis-MVSNet		92.77 113	95.00 82	90.16 138	94.10 127	98.79 65	94.76 122	88.26 128	92.37 144	79.95 139	88.19 113	91.58 82	84.38 200	97.59 59	97.58 49	99.52 19	98.91 84
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EG-PatchMatch MVS		86.68 189	87.24 185	86.02 194	90.58 164	96.26 141	91.08 183	81.59 187	84.96 203	69.80 197	71.35 202	75.08 176	84.23 201	94.24 153	93.35 163	98.82 134	95.46 184

testgi		89.42 154	91.50 144	87.00 186	92.40 151	95.59 164	89.15 195	85.27 165	92.78 133	72.42 180	91.75 80	76.00 172	84.09 202	94.38 149	93.82 157	98.65 153	96.15 174

EPNet_dtu		92.45 118	95.02 81	89.46 147	98.02 54	95.47 168	94.79 121	92.62 69	94.97 101	70.11 193	94.76 55	92.61 79	84.07 203	95.94 114	95.56 105	97.15 189	95.82 178
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MDA-MVSNet-bldmvs		80.11 206	80.24 209	79.94 206	77.01 218	93.21 204	78.86 216	85.94 154	82.71 211	60.86 213	79.71 164	51.77 224	83.71 204	75.60 216	86.37 208	93.28 214	92.35 204

new_pmnet		81.53 205	82.68 207	80.20 205	83.47 214	89.47 215	82.21 213	78.36 195	87.86 186	60.14 218	67.90 208	69.43 203	82.03 205	89.22 203	87.47 205	94.99 208	87.39 214

DeepMVS_CX						86.86 216	79.50 215	70.43 217	90.73 162	63.66 208	80.36 163	60.83 217	79.68 206	76.23 215		89.46 217	86.53 215

EU-MVSNet		85.62 196	87.65 182	83.24 202	88.54 201	92.77 207	87.12 200	85.32 162	86.71 194	64.54 207	78.52 167	75.11 175	78.35 207	92.25 181	92.28 184	95.58 201	95.93 176

IB-MVS	89.56 15	91.71 124	92.50 124	90.79 131	95.94 85	98.44 85	87.05 201	91.38 91	93.15 128	92.98 44	84.78 136	85.14 127	78.27 208	92.47 179	94.44 142	99.10 104	99.08 57
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		80.03 207	80.93 208	78.97 208	72.46 221	90.73 212	80.81 214	82.44 185	80.39 213	63.64 209	57.57 216	64.93 216	76.37 209	91.66 190	91.55 189	98.07 176	89.70 211

new-patchmatchnet		78.49 209	78.19 212	78.84 209	84.13 213	90.06 213	77.11 218	80.39 192	79.57 215	59.64 219	66.01 211	55.65 223	75.62 210	84.55 212	80.70 214	96.14 195	90.77 210

Anonymous20231206		83.84 202	85.19 201	82.26 203	87.38 207	92.87 205	85.49 205	83.65 177	86.07 200	63.44 211	68.42 206	69.01 204	75.45 211	93.34 164	92.44 181	98.12 175	94.20 191

ambc			73.83 214		76.23 219	85.13 218	82.27 212		84.16 206	65.58 206	52.82 218	23.31 229	73.55 212	91.41 193	85.26 211	92.97 215	94.70 186

test_method		72.96 211	78.68 211	66.28 215	50.17 225	64.90 223	75.45 219	50.90 222	87.89 185	62.54 212	62.98 214	68.34 207	70.45 213	91.90 189	82.41 213	88.19 219	92.35 204

Gipuma		68.35 212	66.71 215	70.27 212	74.16 220	68.78 222	63.93 223	71.77 216	83.34 209	54.57 222	34.37 220	31.88 226	68.69 214	83.30 213	85.53 210	88.48 218	79.78 218
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test20.03		82.92 204	85.52 199	79.90 207	87.75 205	91.84 209	82.80 211	82.99 181	82.65 212	60.32 216	78.90 166	70.50 195	67.10 215	92.05 187	90.89 190	98.44 165	91.80 207

FPMVS		75.84 210	74.59 213	77.29 211	86.92 208	83.89 219	85.01 206	80.05 193	82.91 210	60.61 215	65.25 212	60.41 218	63.86 216	75.60 216	73.60 218	87.29 220	80.47 217

EMVS		49.98 217	46.76 220	53.74 218	64.96 223	51.29 226	37.81 226	69.35 219	51.83 222	22.69 227	29.57 222	25.06 227	57.28 217	44.81 222	56.11 221	70.32 224	68.64 222

E-PMN		50.67 216	47.85 219	53.96 217	64.13 224	50.98 227	38.06 225	69.51 218	51.40 223	24.60 226	29.46 223	24.39 228	56.07 218	48.17 221	59.70 220	71.40 223	70.84 221

PMVS	63.12 18	67.27 213	66.39 216	68.30 213	77.98 217	60.24 224	59.53 224	76.82 200	66.65 220	60.74 214	54.39 217	59.82 219	51.24 219	73.92 219	70.52 219	83.48 221	79.17 219
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt				66.88 214	86.07 210	73.86 221	68.22 221	33.38 223	96.88 50	80.67 138	88.23 112	78.82 159	49.78 220	82.68 214	77.47 216	83.19 222

MVE	50.86 19	49.54 218	51.43 218	47.33 219	44.14 226	59.20 225	36.45 227	60.59 221	41.47 224	31.14 225	29.58 221	17.06 230	48.52 221	62.22 220	74.63 217	63.12 225	75.87 220
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		64.36 215	65.94 217	62.52 216	67.37 222	77.44 220	64.39 222	69.32 220	61.47 221	34.59 224	46.09 219	41.03 225	48.02 222	74.56 218	78.23 215	91.43 216	82.76 216

testmvs		12.09 219	16.94 221	6.42 221	3.15 227	6.08 228	9.51 229	3.84 224	21.46 225	5.31 228	27.49 224	6.76 231	10.89 223	17.06 223	15.01 222	5.84 226	24.75 223

test123		9.58 220	13.53 222	4.97 222	1.31 229	5.47 229	8.32 230	2.95 225	18.14 226	2.03 230	20.82 225	2.34 232	10.60 224	10.00 224	14.16 223	4.60 227	23.77 224

GG-mvs-BLEND		66.17 214	94.91 83	32.63 220	1.32 228	96.64 130	91.40 177	0.85 226	94.39 112	2.20 229	90.15 99	95.70 63	2.27 225	96.39 97	95.44 109	97.78 181	95.68 180

uanet_test		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet-low-res		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

RE-MVS-def										63.50 210

9.14												99.28 12

SR-MVS					99.45 10			97.61 16				99.20 16

our_test_3					89.78 176	93.84 202	85.59 204

MTAPA										96.83 11		99.12 21

MTMP										97.18 5		98.83 27

Patchmatch-RL test							34.61 228

XVS					96.60 71	99.35 18	96.82 69			90.85 64		98.72 30				99.46 31

X-MVStestdata					96.60 71	99.35 18	96.82 69			90.85 64		98.72 30				99.46 31

mPP-MVS					99.21 25							98.29 39

NP-MVS									95.32 90

Patchmtry						95.96 149	93.36 142	75.99 207		75.19 168

High-resolution multi-view benchmark