High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

LTVRE_ROB	97.71 1	99.33 1	99.47 1	99.16 7	99.16 41	99.11 14	99.39 12	99.16 11	99.26 2	99.22 5	99.51 18	99.75 4	98.54 15	99.71 1	99.47 3	99.52 12	99.46 1
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
SixPastTwentyTwo		99.25 2	99.20 3	99.32 1	99.53 14	99.32 8	99.64 2	99.19 10	98.05 11	99.19 6	99.74 4	98.96 50	99.03 2	99.69 2	99.58 1	99.32 25	99.06 6

WR-MVS		99.22 3	99.15 5	99.30 2	99.54 10	99.62 1	99.63 4	99.45 1	97.75 15	98.47 22	99.71 5	99.05 40	98.88 4	99.54 5	99.49 2	99.81 1	98.87 11

PS-CasMVS		99.08 4	98.90 11	99.28 3	99.65 3	99.56 4	99.59 6	99.39 3	96.36 36	98.83 14	99.46 21	99.09 33	98.62 10	99.51 7	99.36 8	99.63 3	98.97 7

PEN-MVS		99.08 4	98.95 8	99.23 5	99.65 3	99.59 2	99.64 2	99.34 6	96.68 28	98.65 17	99.43 23	99.33 16	98.47 17	99.50 8	99.32 9	99.60 5	98.79 13

v7n		99.03 6	99.03 7	99.02 9	99.09 52	99.11 14	99.57 9	98.82 19	98.21 9	99.25 3	99.84 2	99.59 6	98.76 6	99.23 19	98.83 32	98.63 73	98.40 35

DTE-MVSNet		99.03 6	98.88 12	99.21 6	99.66 2	99.59 2	99.62 5	99.34 6	96.92 24	98.52 19	99.36 29	98.98 46	98.57 13	99.49 9	99.23 12	99.56 9	98.55 27

TDRefinement		99.00 8	99.13 6	98.86 10	98.99 62	99.05 19	99.58 7	98.29 49	98.96 4	97.96 37	99.40 26	98.67 76	98.87 5	99.60 3	99.46 4	99.46 18	98.74 16

WR-MVS_H		98.97 9	98.82 14	99.14 8	99.56 8	99.56 4	99.54 11	99.42 2	96.07 41	98.37 24	99.34 31	99.09 33	98.43 18	99.45 10	99.41 5	99.53 10	98.86 12

UniMVSNet_ETH3D		98.93 10	99.20 3	98.63 22	99.54 10	99.33 7	98.73 63	99.37 4	98.87 5	97.86 39	99.27 35	99.78 2	96.59 85	99.52 6	99.40 6	99.67 2	98.21 43

CP-MVSNet		98.91 11	98.61 19	99.25 4	99.63 5	99.50 6	99.55 10	99.36 5	95.53 69	98.77 16	99.11 42	98.64 79	98.57 13	99.42 11	99.28 11	99.61 4	98.78 14

anonymousdsp		98.85 12	98.88 12	98.83 11	98.69 82	98.20 81	99.68 1	97.35 125	97.09 23	98.98 10	99.86 1	99.43 10	98.94 3	99.28 14	99.19 13	99.33 23	99.08 5

pmmvs6		98.77 13	99.35 2	98.09 43	98.32 102	98.92 25	98.57 70	99.03 12	99.36 1	96.86 83	99.77 3	99.86 1	96.20 101	99.56 4	99.39 7	99.59 6	98.61 24

ACMH	95.26 7	98.75 14	98.93 9	98.54 25	98.86 67	99.01 21	99.58 7	98.10 68	98.67 6	97.30 61	99.18 39	99.42 11	98.40 19	99.19 21	98.86 30	98.99 48	98.19 44
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
COLMAP_ROB	96.84 2	98.75 14	98.82 14	98.66 20	99.14 45	98.79 39	99.30 17	97.67 97	98.33 8	97.82 41	99.20 38	99.18 31	98.76 6	99.27 17	98.96 22	99.29 27	98.03 48
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UA-Net		98.66 16	98.60 22	98.73 15	99.83 1	99.28 9	98.56 72	99.24 8	96.04 42	97.12 70	98.44 79	98.95 51	98.17 28	99.15 24	99.00 21	99.48 17	99.33 3

DeepC-MVS	96.08 5	98.58 17	98.49 24	98.68 18	99.37 26	98.52 66	99.01 35	98.17 63	97.17 22	98.25 27	99.56 15	99.62 5	98.29 22	98.40 63	98.09 70	98.97 50	98.08 47
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TranMVSNet+NR-MVSNet		98.45 18	98.22 31	98.72 17	99.32 31	99.06 17	98.99 36	98.89 14	95.52 70	97.53 50	99.42 25	98.83 63	98.01 34	98.55 55	98.34 57	99.57 8	97.80 59

CSCG		98.45 18	98.61 19	98.26 37	99.11 49	99.06 17	98.17 92	97.49 110	97.93 13	97.37 58	98.88 56	99.29 19	98.10 29	98.40 63	97.51 91	99.32 25	99.16 4

DVP-MVS++		98.44 20	98.92 10	97.88 63	99.17 39	99.00 22	98.89 46	98.26 51	97.54 18	96.05 117	99.35 30	99.76 3	96.34 96	98.79 37	98.65 41	98.56 79	99.35 2

Gipuma		98.43 21	98.15 34	98.76 14	99.00 61	98.29 78	97.91 107	98.06 70	99.02 3	99.50 1	96.33 129	98.67 76	99.22 1	99.02 27	98.02 76	98.88 63	97.66 67
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ACMH+	94.90 8	98.40 22	98.71 17	98.04 53	98.93 64	98.84 32	99.30 17	97.86 89	97.78 14	94.19 175	98.77 66	99.39 13	98.61 11	99.33 13	99.07 14	99.33 23	97.81 58

ACMMPR		98.31 23	98.07 39	98.60 23	99.58 6	98.83 33	99.09 27	98.48 31	96.25 38	97.03 74	96.81 117	99.09 33	98.39 20	98.55 55	98.45 49	99.01 45	98.53 30

APDe-MVS		98.29 24	98.42 26	98.14 40	99.45 21	98.90 26	99.18 23	98.30 47	95.96 48	95.13 148	98.79 63	99.25 26	97.92 38	98.80 35	98.71 36	98.85 66	98.54 28
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS		98.27 25	98.61 19	97.87 64	99.17 39	99.03 20	99.07 29	98.17 63	96.75 27	94.35 170	98.92 52	99.58 7	97.86 41	98.67 46	98.70 37	98.63 73	98.63 22
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
TransMVSNet (Re)		98.23 26	98.72 16	97.66 77	98.22 112	98.73 50	98.66 66	98.03 75	98.60 7	96.40 102	99.60 12	98.24 100	95.26 123	99.19 21	99.05 17	99.36 20	97.64 68

DU-MVS		98.23 26	97.74 55	98.81 12	99.23 33	98.77 41	98.76 57	98.88 15	94.10 117	98.50 20	98.87 58	98.32 97	97.99 35	98.40 63	98.08 73	99.49 16	97.64 68

UniMVSNet (Re)		98.23 26	97.85 48	98.67 19	99.15 42	98.87 28	98.74 60	98.84 17	94.27 115	97.94 38	99.01 45	98.39 93	97.82 42	98.35 68	98.29 62	99.51 15	97.78 60

MIMVSNet1		98.22 29	98.51 23	97.87 64	99.40 25	98.82 37	99.31 16	98.53 28	97.39 19	96.59 93	99.31 33	99.23 28	94.76 134	98.93 32	98.67 39	98.63 73	97.25 92

HFP-MVS		98.17 30	98.02 40	98.35 35	99.36 27	98.62 58	98.79 56	98.46 34	96.24 39	96.53 95	97.13 113	98.98 46	98.02 33	98.20 71	98.42 51	98.95 54	98.54 28

Baseline_NR-MVSNet		98.17 30	97.90 45	98.48 29	99.23 33	98.59 59	98.83 53	98.73 24	93.97 122	96.95 77	99.66 7	98.23 102	97.90 39	98.40 63	99.06 16	99.25 29	97.42 84

TSAR-MVS + MP.		98.15 32	98.23 30	98.06 51	98.47 92	98.16 87	99.23 20	96.87 141	95.58 64	96.72 86	98.41 80	99.06 37	98.05 32	98.99 29	98.90 26	99.00 46	98.51 31
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
pm-mvs1		98.14 33	98.66 18	97.53 86	97.93 134	98.49 68	98.14 94	98.19 59	97.95 12	96.17 113	99.63 10	98.85 59	95.41 121	98.91 33	98.89 27	99.34 22	97.86 57

SMA-MVS		98.13 34	98.22 31	98.02 56	99.44 23	98.73 50	98.24 89	97.87 88	95.22 77	96.76 85	98.66 72	99.35 15	97.03 70	98.53 58	98.39 53	98.80 68	98.69 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
ACMMP_NAP		98.12 35	98.08 38	98.18 39	99.34 28	98.74 49	98.97 38	98.00 77	95.13 81	96.90 78	97.54 102	99.27 23	97.18 64	98.72 42	98.45 49	98.68 72	98.69 18

UniMVSNet_NR-MVSNet		98.12 35	97.56 63	98.78 13	99.13 47	98.89 27	98.76 57	98.78 20	93.81 125	98.50 20	98.81 62	97.64 123	97.99 35	98.18 74	97.92 79	99.53 10	97.64 68

ACMM	94.29 11	98.12 35	97.71 56	98.59 24	99.51 16	98.58 61	99.24 19	98.25 52	96.22 40	96.90 78	95.01 153	98.89 56	98.52 16	98.66 48	98.32 60	99.13 36	98.28 41
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SteuartSystems-ACMMP		98.06 38	97.78 53	98.39 33	99.54 10	98.79 39	98.94 42	98.42 36	93.98 121	95.85 124	96.66 123	99.25 26	98.61 11	98.71 44	98.38 54	98.97 50	98.67 21
Skip Steuart: Steuart Systems R&D Blog.
SED-MVS		98.05 39	98.46 25	97.57 82	99.01 58	98.99 23	98.82 55	98.24 53	95.76 57	94.70 160	98.96 47	99.49 9	96.19 102	98.74 38	98.65 41	98.46 87	98.63 22

OPM-MVS		98.01 40	98.01 41	98.00 58	99.11 49	98.12 90	98.68 64	97.72 95	96.65 30	96.68 90	98.40 81	99.28 22	97.44 55	98.20 71	97.82 86	98.40 93	97.58 73
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet		98.01 40	98.42 26	97.54 85	96.89 183	98.82 37	99.14 24	97.59 100	96.30 37	97.04 73	99.26 36	98.83 63	96.01 107	98.73 40	98.21 64	98.58 78	98.75 15
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS		98.00 42	97.38 68	98.73 15	98.72 77	99.15 11	99.12 26	98.76 21	91.58 155	98.15 31	96.70 121	98.72 75	98.20 24	98.64 51	98.92 24	99.43 19	97.97 51

NR-MVSNet		98.00 42	97.88 46	98.13 41	98.33 100	98.77 41	98.83 53	98.88 15	94.10 117	97.46 55	98.87 58	98.58 84	95.78 110	99.13 25	98.16 68	99.52 12	97.53 76

CP-MVS		98.00 42	97.57 62	98.50 26	99.47 20	98.56 63	98.91 44	98.38 42	94.71 96	97.01 75	95.20 149	99.06 37	98.20 24	98.61 52	98.46 46	99.02 43	98.40 35

DPE-MVS		97.99 45	98.12 35	97.84 67	98.65 86	98.86 29	98.86 50	98.05 73	94.18 116	95.49 141	98.90 54	99.33 16	97.11 66	98.53 58	98.65 41	98.86 65	98.39 37
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ACMMP		97.99 45	97.60 61	98.45 31	99.53 14	98.83 33	99.13 25	98.30 47	94.57 102	96.39 106	95.32 147	98.95 51	98.37 21	98.61 52	98.47 45	99.00 46	98.45 32
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
MP-MVS		97.98 47	97.53 64	98.50 26	99.56 8	98.58 61	98.97 38	98.39 41	93.49 128	97.14 67	96.08 136	99.23 28	98.06 31	98.50 60	98.38 54	98.90 58	98.44 33
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
EG-PatchMatch MVS		97.98 47	97.92 43	98.04 53	98.84 70	98.04 98	97.90 108	96.83 144	95.07 83	98.79 15	99.07 43	99.37 14	97.88 40	98.74 38	98.16 68	98.01 115	96.96 100

ACMP	94.03 12	97.97 49	97.61 60	98.39 33	99.43 24	98.51 67	98.97 38	98.06 70	94.63 100	96.10 115	96.12 135	99.20 30	98.63 9	98.68 45	98.20 67	99.14 33	97.93 54
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CS-MVS-test		97.96 50	97.38 68	98.64 21	98.57 88	99.13 12	99.36 13	98.66 25	91.67 154	98.17 30	96.91 116	98.84 61	97.99 35	98.80 35	98.88 28	99.08 41	97.43 83

LGP-MVS_train		97.96 50	97.53 64	98.45 31	99.45 21	98.64 56	99.09 27	98.27 50	92.99 140	96.04 118	96.57 124	99.29 19	98.66 8	98.73 40	98.42 51	99.19 31	98.09 46

LS3D		97.93 52	97.80 50	98.08 47	99.20 36	98.77 41	98.89 46	97.92 83	96.59 31	96.99 76	96.71 120	97.14 135	96.39 95	99.04 26	98.96 22	99.10 40	97.39 85

SD-MVS		97.84 53	97.78 53	97.90 61	98.33 100	98.06 95	97.95 104	97.80 94	96.03 46	96.72 86	97.57 100	99.18 31	97.50 53	97.88 77	97.08 104	99.11 38	98.68 20
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
RPSCF		97.83 54	98.27 28	97.31 98	98.23 110	98.06 95	97.44 134	95.79 174	96.90 25	95.81 126	98.76 67	98.61 83	97.70 47	98.90 34	98.36 56	98.90 58	98.29 38

thisisatest0515		97.82 55	97.67 57	97.99 59	98.49 91	98.07 94	98.48 77	98.06 70	95.35 75	97.74 43	98.83 61	97.61 124	96.74 77	97.53 97	98.30 61	98.43 92	98.01 50

PGM-MVS		97.82 55	97.25 74	98.48 29	99.54 10	98.75 48	99.02 31	98.35 45	92.41 144	96.84 84	95.39 146	98.99 45	98.24 23	98.43 62	98.34 57	98.90 58	98.41 34

PMVS	90.51 17	97.77 57	97.98 42	97.53 86	98.68 83	98.14 89	97.67 118	97.03 136	96.43 32	98.38 23	98.72 69	97.03 137	94.44 139	99.37 12	99.30 10	98.98 49	96.86 107
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MSP-MVS		97.67 58	97.88 46	97.43 92	99.34 28	98.99 23	98.87 49	98.12 66	95.63 60	94.16 176	97.45 103	99.50 8	96.44 94	96.35 135	98.70 37	97.65 131	98.57 26
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
tfpnnormal		97.66 59	97.79 51	97.52 88	98.32 102	98.53 65	98.45 80	97.69 96	97.59 17	96.12 114	97.79 95	96.70 142	95.69 114	98.35 68	98.34 57	98.85 66	97.22 95

FC-MVSNet-train		97.65 60	98.16 33	97.05 110	98.85 68	98.85 30	99.34 14	98.08 69	94.50 107	94.41 167	99.21 37	98.80 67	92.66 166	98.98 30	98.85 31	98.96 52	97.94 53

v10		97.64 61	97.26 73	98.08 47	98.07 123	98.56 63	98.86 50	98.18 61	94.48 108	98.24 28	99.56 15	98.98 46	97.72 46	96.05 145	96.26 132	97.42 140	96.93 101

EC-MVSNet		97.63 62	96.88 97	98.50 26	98.74 76	99.16 10	99.33 15	98.83 18	88.77 184	96.62 92	96.48 126	97.75 116	98.19 26	99.00 28	98.76 34	99.29 27	98.27 42

X-MVS		97.60 63	97.00 91	98.29 36	99.50 17	98.76 44	98.90 45	98.37 43	94.67 99	96.40 102	91.47 200	98.78 69	97.60 52	98.55 55	98.50 44	98.96 52	98.29 38

3Dnovator+	96.20 4	97.58 64	97.14 82	98.10 42	98.98 63	97.85 110	98.60 69	98.33 46	96.41 34	97.23 65	94.66 162	97.26 132	96.91 74	97.91 76	97.87 82	98.53 82	98.03 48

DCV-MVSNet		97.56 65	97.63 59	97.47 90	98.41 96	99.12 13	98.63 67	98.57 26	95.71 59	95.60 138	93.79 179	98.01 111	94.25 141	99.16 23	98.88 28	99.35 21	98.74 16

HPM-MVS++		97.56 65	97.11 86	98.09 43	99.18 38	97.95 105	98.57 70	98.20 57	94.08 119	97.25 64	95.96 140	98.81 66	97.13 65	97.51 98	97.30 101	98.21 103	98.15 45

FC-MVSNet-test		97.54 67	98.26 29	96.70 127	98.87 66	97.79 117	98.49 76	98.56 27	96.04 42	90.39 206	99.65 8	98.67 76	95.15 125	99.23 19	99.07 14	98.73 71	97.39 85

TSAR-MVS + ACMM		97.54 67	97.79 51	97.26 99	98.23 110	98.10 93	97.71 116	97.88 87	95.97 47	95.57 140	98.71 70	98.57 85	97.36 58	97.74 86	96.81 113	96.83 166	98.59 25

DeepC-MVS_fast	95.38 6	97.53 69	97.30 72	97.79 72	98.83 71	97.64 120	98.18 90	97.14 132	95.57 65	97.83 40	97.10 114	98.80 67	96.53 91	97.41 101	97.32 99	98.24 102	97.26 91
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
v1192		97.52 70	97.03 90	98.09 43	98.31 105	98.01 100	98.96 41	97.25 128	95.22 77	98.89 12	99.64 9	98.83 63	97.68 48	95.63 152	95.91 142	97.47 136	95.97 137

v1144		97.51 71	97.05 89	98.04 53	98.26 108	97.98 102	98.88 48	97.42 118	95.38 74	98.56 18	99.59 14	99.01 44	97.65 49	95.77 149	96.06 139	97.47 136	95.56 149

v8		97.51 71	97.16 80	97.91 60	97.99 130	98.48 69	98.76 57	98.17 63	94.54 106	97.69 45	99.48 20	98.76 72	97.63 51	96.10 144	96.14 134	97.20 150	96.64 115

v1921920		97.50 73	97.00 91	98.07 49	98.20 114	97.94 108	99.03 30	97.06 134	95.29 76	99.01 9	99.62 11	98.73 74	97.74 45	95.52 155	95.78 147	97.39 142	96.12 133

Anonymous20231211		97.49 74	97.91 44	97.00 113	98.31 105	98.72 52	98.27 87	97.84 91	94.76 95	94.77 159	98.14 88	98.38 95	93.60 151	98.96 31	98.66 40	99.22 30	97.77 62

v144192		97.49 74	96.99 93	98.07 49	98.11 122	97.95 105	99.02 31	97.21 129	94.90 91	98.88 13	99.53 17	98.89 56	97.75 44	95.59 153	95.90 143	97.43 139	96.16 131

test1111		97.48 76	97.20 77	97.81 71	98.78 74	98.85 30	98.68 64	98.40 37	96.68 28	94.84 157	99.13 41	90.32 192	97.01 71	99.27 17	99.05 17	99.19 31	97.10 97

GeoE		97.48 76	96.84 102	98.22 38	99.01 58	98.39 72	98.85 52	98.76 21	92.37 145	97.53 50	97.58 99	98.23 102	97.11 66	97.57 96	96.98 107	98.10 111	96.78 110

APD-MVS		97.47 78	97.16 80	97.84 67	99.32 31	98.39 72	98.47 79	98.21 56	92.08 150	95.23 145	96.68 122	98.90 54	96.99 72	98.20 71	98.21 64	98.80 68	97.67 66
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PVSNet_Blended_VisFu		97.44 79	97.14 82	97.79 72	99.15 42	98.44 70	98.32 85	97.66 98	93.74 127	97.73 44	98.79 63	96.93 140	95.64 119	97.69 88	96.91 110	98.25 101	97.50 79

PHI-MVS		97.44 79	97.17 79	97.74 75	98.14 119	98.41 71	98.03 100	97.50 108	92.07 151	98.01 36	97.33 108	98.62 82	96.02 106	98.34 70	98.21 64	98.76 70	97.24 94

v1240		97.43 81	96.87 101	98.09 43	98.25 109	97.92 109	99.02 31	97.06 134	94.77 94	99.09 8	99.68 6	98.51 88	97.78 43	95.25 160	95.81 145	97.32 146	96.13 132

ECVR-MVS		97.40 82	97.11 86	97.73 76	98.66 84	98.83 33	98.50 74	98.40 37	96.04 42	95.00 155	98.95 49	91.07 189	96.70 79	99.28 14	99.04 19	99.14 33	96.58 117

FMVSNet1		97.40 82	98.09 36	96.60 132	97.80 148	98.76 44	98.26 88	98.50 30	96.79 26	93.13 193	99.28 34	98.64 79	92.90 163	97.67 90	97.86 83	99.02 43	97.64 68

casdiffmvs_mvg		97.34 84	97.65 58	96.97 114	97.74 151	98.33 76	98.45 80	97.18 130	95.81 53	93.92 180	99.04 44	99.05 40	95.48 120	97.00 118	97.71 89	99.07 42	96.63 116
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
v2v482		97.33 85	96.84 102	97.90 61	98.19 115	97.83 111	98.74 60	97.44 116	95.42 73	98.23 29	99.46 21	98.84 61	97.46 54	95.51 156	96.10 137	97.36 144	94.72 159

EPP-MVSNet		97.29 86	96.88 97	97.76 74	98.70 79	99.10 16	98.92 43	98.36 44	95.12 82	93.36 191	97.39 105	91.00 190	97.65 49	98.72 42	98.91 25	99.58 7	97.92 55

MVS_111021_HR		97.27 87	97.11 86	97.46 91	98.46 93	97.82 114	97.50 130	96.86 142	94.97 87	97.13 69	96.99 115	98.39 93	96.82 76	97.65 93	97.38 94	98.02 114	96.56 120

SF-MVS		97.26 88	97.43 66	97.05 110	98.80 73	97.83 111	96.02 184	97.44 116	94.98 86	95.74 130	97.16 111	98.45 92	95.72 112	97.85 78	97.97 78	98.60 76	97.78 60

TSAR-MVS + GP.		97.26 88	97.33 71	97.18 104	98.21 113	98.06 95	96.38 175	97.66 98	93.92 124	95.23 145	98.48 77	98.33 96	97.41 56	97.63 94	97.35 95	98.18 105	97.57 74

OMC-MVS		97.23 90	97.21 76	97.25 102	97.85 139	97.52 129	97.92 106	95.77 175	95.83 52	97.09 72	97.86 93	98.52 87	96.62 83	97.51 98	96.65 119	98.26 99	96.57 118

3Dnovator	96.31 3	97.22 91	97.19 78	97.25 102	98.14 119	97.95 105	98.03 100	96.77 147	96.42 33	97.14 67	95.11 150	97.59 125	95.14 127	97.79 83	97.72 87	98.26 99	97.76 64

MVS_0304		97.18 92	96.84 102	97.58 81	99.15 42	98.19 82	98.11 95	97.81 93	92.36 146	98.06 34	97.43 104	99.06 37	94.24 142	96.80 123	96.54 123	98.12 109	97.52 77

sasdasda		97.11 93	96.88 97	97.38 93	98.34 98	98.72 52	97.52 128	97.94 80	95.60 61	95.01 153	94.58 164	94.50 167	96.59 85	97.84 79	98.03 74	98.90 58	98.91 9

canonicalmvs		97.11 93	96.88 97	97.38 93	98.34 98	98.72 52	97.52 128	97.94 80	95.60 61	95.01 153	94.58 164	94.50 167	96.59 85	97.84 79	98.03 74	98.90 58	98.91 9

V42		97.10 95	96.97 94	97.26 99	97.64 155	97.60 122	98.45 80	95.99 163	94.44 109	97.35 59	99.40 26	98.63 81	97.34 60	96.33 138	96.38 129	96.82 168	96.00 135

CPTT-MVS		97.08 96	96.25 116	98.05 52	99.21 35	98.30 77	98.54 73	97.98 78	94.28 113	95.89 123	89.57 209	98.54 86	98.18 27	97.82 82	97.32 99	98.54 80	97.91 56

DeepPCF-MVS	94.55 10	97.05 97	97.13 85	96.95 116	96.06 198	97.12 146	98.01 102	95.44 181	95.18 79	97.50 52	97.86 93	98.08 107	97.31 62	97.23 106	97.00 106	97.36 144	97.45 81

QAPM		97.04 98	97.14 82	96.93 118	97.78 150	98.02 99	97.36 140	96.72 148	94.68 98	96.23 108	97.21 110	97.68 121	95.70 113	97.37 102	97.24 103	97.78 124	97.77 62

CNVR-MVS		97.03 99	96.77 107	97.34 95	98.89 65	97.67 119	97.64 121	97.17 131	94.40 111	95.70 134	94.02 174	98.76 72	96.49 93	97.78 84	97.29 102	98.12 109	97.47 80

casdiffmvs		97.00 100	97.36 70	96.59 133	97.65 154	97.98 102	98.06 97	96.81 145	95.78 55	92.77 199	99.40 26	99.26 25	95.65 118	96.70 127	96.39 128	98.59 77	95.99 136
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
v148		96.99 101	96.70 109	97.34 95	97.89 137	97.23 138	98.33 84	96.96 137	95.57 65	97.12 70	98.99 46	99.40 12	97.23 63	96.22 141	95.45 152	96.50 174	94.02 171

DELS-MVS		96.90 102	97.24 75	96.50 138	97.85 139	98.18 83	97.88 111	95.92 167	93.48 129	95.34 143	98.86 60	98.94 53	94.03 145	97.33 104	97.04 105	98.00 116	96.85 108
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
MVS_111021_LR		96.86 103	96.72 108	97.03 112	97.80 148	97.06 149	97.04 154	95.51 180	94.55 103	97.47 53	97.35 107	97.68 121	96.66 81	97.11 111	96.73 115	97.69 128	96.57 118

PM-MVS		96.85 104	96.62 111	97.11 106	97.13 178	96.51 162	98.29 86	94.65 198	94.84 92	98.12 32	98.59 73	97.20 133	97.41 56	96.24 140	96.41 127	97.09 155	96.56 120

pmmvs-eth3d		96.84 105	96.22 118	97.56 83	97.63 157	96.38 169	98.74 60	96.91 140	94.63 100	98.26 26	99.43 23	98.28 98	96.58 88	94.52 170	95.54 150	97.24 148	94.75 158

CANet		96.81 106	96.50 112	97.17 105	99.10 51	97.96 104	97.86 112	97.51 106	91.30 158	97.75 42	97.64 97	97.89 114	93.39 155	96.98 119	96.73 115	97.40 141	96.99 99

Fast-Effi-MVS+		96.80 107	95.92 129	97.84 67	98.57 88	97.46 132	98.06 97	98.24 53	89.64 179	97.57 49	96.45 127	97.35 130	96.73 78	97.22 107	96.64 120	97.86 121	96.65 114

MCST-MVS		96.79 108	96.08 122	97.62 79	98.78 74	97.52 129	98.01 102	97.32 126	93.20 132	95.84 125	93.97 176	98.12 105	97.34 60	96.34 136	95.88 144	98.45 88	97.51 78

UGNet		96.79 108	97.82 49	95.58 162	97.57 160	98.39 72	98.48 77	97.84 91	95.85 51	94.68 161	97.91 92	99.07 36	87.12 206	97.71 87	97.51 91	97.80 122	98.29 38
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
TAPA-MVS	93.96 13	96.79 108	96.70 109	96.90 120	97.64 155	97.58 123	97.54 127	94.50 200	95.14 80	96.64 91	96.76 119	97.90 113	96.63 82	95.98 146	96.14 134	98.45 88	97.39 85
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CLD-MVS		96.73 111	96.92 95	96.51 137	98.70 79	97.57 125	97.64 121	92.07 207	93.10 138	96.31 107	98.29 83	99.02 43	95.99 108	97.20 108	96.47 125	98.37 95	96.81 109
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MGCFI-Net		96.69 112	96.89 96	96.44 140	98.30 107	98.63 57	97.39 137	97.90 84	95.72 58	91.16 204	94.65 163	94.55 165	95.04 128	97.78 84	98.00 77	98.87 64	98.93 8

train_agg		96.68 113	95.93 128	97.56 83	99.08 53	97.16 142	98.44 83	97.37 122	91.12 162	95.18 147	95.43 145	98.48 90	97.36 58	96.48 132	95.52 151	97.95 119	97.34 89

CDPH-MVS		96.68 113	95.99 125	97.48 89	99.13 47	97.64 120	98.08 96	97.46 112	90.56 168	95.13 148	94.87 158	98.27 99	96.56 89	97.09 112	96.45 126	98.54 80	97.08 98

MSLP-MVS++		96.66 115	96.46 115	96.89 121	98.02 125	97.71 118	95.57 191	96.96 137	94.36 112	96.19 112	91.37 201	98.24 100	97.07 68	97.69 88	97.89 80	97.52 134	97.95 52

TinyColmap		96.64 116	96.07 123	97.32 97	97.84 144	96.40 166	97.63 123	96.25 158	95.86 50	98.98 10	97.94 91	96.34 149	96.17 103	97.30 105	95.38 155	97.04 157	93.24 178

IS_MVSNet		96.62 117	96.48 114	96.78 125	98.46 93	98.68 55	98.61 68	98.24 53	92.23 147	89.63 211	95.90 141	94.40 169	96.23 98	98.65 49	98.77 33	99.52 12	96.76 111

NCCC		96.56 118	95.68 131	97.59 80	99.04 57	97.54 128	97.67 118	97.56 104	94.84 92	96.10 115	87.91 212	98.09 106	96.98 73	97.20 108	96.80 114	98.21 103	97.38 88

WB-MVS		96.54 119	98.09 36	94.73 179	96.68 190	98.34 75	94.77 210	97.39 119	98.12 10	89.72 210	98.95 49	99.32 18	93.33 156	98.67 46	97.88 81	96.47 176	95.38 152

ETV-MVS		96.54 119	95.27 139	98.02 56	99.07 55	97.48 131	98.16 93	98.19 59	87.33 199	97.58 48	92.67 188	95.93 155	96.22 99	98.49 61	98.46 46	98.91 57	96.50 123

Effi-MVS+		96.46 121	95.28 138	97.85 66	98.64 87	97.16 142	97.15 152	98.75 23	90.27 172	98.03 35	93.93 177	96.21 150	96.55 90	96.34 136	96.69 118	97.97 118	96.33 126

IterMVS-LS		96.35 122	95.85 130	96.93 118	97.53 161	98.00 101	97.37 138	97.97 79	95.49 72	96.71 89	98.94 51	93.23 176	94.82 133	93.15 189	95.05 158	97.17 152	97.12 96
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
USDC		96.30 123	95.64 133	97.07 108	97.62 158	96.35 171	97.17 151	95.71 176	95.52 70	99.17 7	98.11 89	97.46 127	95.67 115	95.44 158	93.60 178	97.09 155	92.99 182

Vis-MVSNet (Re-imp)		96.29 124	96.50 112	96.05 147	97.96 133	97.83 111	97.30 143	97.86 89	93.14 134	88.90 214	96.80 118	95.28 159	95.15 125	98.37 67	98.25 63	99.12 37	95.84 139

MSDG		96.27 125	96.17 121	96.38 143	97.85 139	96.27 173	96.55 172	94.41 201	94.55 103	95.62 137	97.56 101	97.80 115	96.22 99	97.17 110	96.27 131	97.67 130	93.60 175

CNLPA		96.24 126	95.97 126	96.57 135	97.48 167	97.10 148	96.75 165	94.95 192	94.92 90	96.20 111	94.81 159	96.61 144	96.25 97	96.94 120	95.64 148	97.79 123	95.74 145

EIA-MVS		96.23 127	94.85 151	97.84 67	99.08 53	98.21 80	97.69 117	98.03 75	85.68 209	98.09 33	91.75 199	97.07 136	95.66 117	97.58 95	97.72 87	98.47 86	95.91 138

PLC	92.55 15	96.10 128	95.36 135	96.96 115	98.13 121	96.88 153	96.49 173	96.67 152	94.07 120	95.71 133	91.14 202	96.09 152	96.84 75	96.70 127	96.58 122	97.92 120	96.03 134
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test20.03		96.08 129	96.80 105	95.25 171	99.19 37	97.58 123	97.24 148	97.56 104	94.95 89	91.91 200	98.58 74	98.03 109	87.88 202	97.43 100	96.94 109	97.69 128	94.05 170

FA-MVS(training)		96.07 130	95.59 134	96.63 130	98.00 129	97.44 133	97.36 140	98.53 28	92.21 148	95.97 120	96.18 133	94.22 172	92.98 160	96.79 124	96.70 117	96.95 162	95.56 149

TSAR-MVS + COLMAP		96.05 131	95.94 127	96.18 146	97.46 168	96.41 165	97.26 147	95.83 171	94.69 97	95.30 144	98.31 82	96.52 145	94.71 135	95.48 157	94.87 160	96.54 173	95.33 153

EU-MVSNet		96.03 132	96.23 117	95.80 156	95.48 211	94.18 192	98.99 36	91.51 209	97.22 21	97.66 46	99.15 40	98.51 88	98.08 30	95.92 147	92.88 185	93.09 198	95.72 146

PCF-MVS	92.69 14	95.98 133	95.05 146	97.06 109	98.43 95	97.56 126	97.76 114	96.65 153	89.95 177	95.70 134	96.18 133	98.48 90	95.74 111	93.64 181	93.35 182	98.09 113	96.18 130
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HQP-MVS		95.97 134	95.01 148	97.08 107	98.72 77	97.19 140	97.07 153	96.69 151	91.49 156	95.77 129	92.19 194	97.93 112	96.15 104	94.66 167	94.16 169	98.10 111	97.45 81

Effi-MVS+-dtu		95.94 135	95.08 145	96.94 117	98.54 90	97.38 134	96.66 169	97.89 86	88.68 185	95.92 121	92.90 187	97.28 131	94.18 144	96.68 129	96.13 136	98.45 88	96.51 122

diffmvs		95.86 136	96.21 119	95.44 165	97.25 176	96.85 156	96.99 157	95.23 186	94.96 88	92.82 198	98.89 55	98.85 59	93.52 153	94.21 176	94.25 168	96.84 165	95.49 151
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
AdaColmap		95.85 137	94.65 154	97.26 99	98.70 79	97.20 139	97.33 142	97.30 127	91.28 160	95.90 122	88.16 211	96.17 151	96.60 84	97.34 103	96.82 112	97.71 125	95.60 148

FMVSNet2		95.77 138	96.20 120	95.27 169	96.77 186	98.18 83	97.28 144	97.90 84	93.12 135	91.37 202	98.25 85	96.05 153	90.04 186	94.96 165	95.94 141	98.28 96	96.90 102

OpenMVS	94.63 9	95.75 139	95.04 147	96.58 134	97.85 139	97.55 127	96.71 167	96.07 160	90.15 175	96.47 97	90.77 207	95.95 154	94.41 140	97.01 117	96.95 108	98.00 116	96.90 102

pmmvs5		95.70 140	95.22 140	96.26 144	96.55 193	97.24 137	97.50 130	94.99 191	90.95 164	96.87 80	98.47 78	97.40 128	94.45 138	92.86 190	94.98 159	97.23 149	94.64 161

Anonymous20231206		95.69 141	95.68 131	95.70 158	98.32 102	96.95 151	97.37 138	96.65 153	93.33 130	93.61 185	98.70 71	98.03 109	91.04 175	95.07 163	94.59 167	97.20 150	93.09 181

MAR-MVS		95.51 142	94.49 158	96.71 126	97.92 135	96.40 166	96.72 166	98.04 74	86.74 203	96.72 86	92.52 191	95.14 161	94.02 146	96.81 122	96.54 123	96.85 163	97.25 92
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
DI_MVS_plusplus_trai		95.48 143	94.51 156	96.61 131	97.13 178	97.30 136	98.05 99	96.79 146	93.75 126	95.08 151	96.38 128	89.76 194	94.95 129	93.97 180	94.82 164	97.64 132	95.63 147

MDA-MVSNet-bldmvs		95.45 144	95.20 141	95.74 157	94.24 216	96.38 169	97.93 105	94.80 193	95.56 68	96.87 80	98.29 83	95.24 160	96.50 92	98.65 49	90.38 197	94.09 192	91.93 186

PVSNet_BlendedMVS		95.44 145	95.09 143	95.86 154	97.31 173	97.13 144	96.31 178	95.01 189	88.55 188	96.23 108	94.55 168	97.75 116	92.56 168	96.42 133	95.44 153	97.71 125	95.81 140

PVSNet_Blended		95.44 145	95.09 143	95.86 154	97.31 173	97.13 144	96.31 178	95.01 189	88.55 188	96.23 108	94.55 168	97.75 116	92.56 168	96.42 133	95.44 153	97.71 125	95.81 140

pmmvs4		95.37 147	94.25 159	96.67 129	97.01 181	95.28 186	97.60 124	96.07 160	93.11 136	97.29 62	98.09 90	94.23 171	95.21 124	91.56 201	93.91 175	96.82 168	93.59 176

MVS_Test		95.34 148	94.88 150	95.89 153	96.93 182	96.84 157	96.66 169	97.08 133	90.06 176	94.02 177	97.61 98	96.64 143	93.59 152	92.73 193	94.02 173	97.03 158	96.24 127

GBi-Net		95.21 149	95.35 136	95.04 174	96.77 186	98.18 83	97.28 144	97.58 101	88.43 190	90.28 207	96.01 137	92.43 180	90.04 186	97.67 90	97.86 83	98.28 96	96.90 102

test1		95.21 149	95.35 136	95.04 174	96.77 186	98.18 83	97.28 144	97.58 101	88.43 190	90.28 207	96.01 137	92.43 180	90.04 186	97.67 90	97.86 83	98.28 96	96.90 102

IterMVS-SCA-FT		95.16 151	93.95 163	96.56 136	97.89 137	96.69 159	96.94 159	96.05 162	93.06 139	97.35 59	98.79 63	91.45 185	95.93 109	92.78 191	91.00 195	95.22 188	93.91 173

HyFIR lowres test		95.05 152	93.54 168	96.81 124	97.81 147	96.88 153	98.18 90	97.46 112	94.28 113	94.98 156	96.57 124	92.89 179	96.15 104	90.90 206	91.87 191	96.28 180	91.35 187

CHOSEN 1792x2688		94.98 153	94.69 153	95.31 167	97.27 175	95.58 182	97.90 108	95.56 179	95.03 84	93.77 184	95.65 143	99.29 19	95.30 122	91.51 202	91.28 194	92.05 206	94.50 163

CANet_DTU		94.96 154	94.62 155	95.35 166	98.03 124	96.11 175	96.92 161	95.60 178	88.59 187	97.27 63	95.27 148	96.50 146	88.77 198	95.53 154	95.59 149	95.54 186	94.78 157

CDS-MVSNet		94.91 155	95.17 142	94.60 183	97.85 139	96.21 174	96.90 163	96.39 156	90.81 165	93.40 189	97.24 109	94.54 166	85.78 212	96.25 139	96.15 133	97.26 147	95.01 156
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
DPM-MVS		94.86 156	93.90 165	95.99 149	98.19 115	96.52 161	96.29 180	95.95 164	93.11 136	94.61 163	88.17 210	96.44 147	93.77 150	93.33 184	93.54 180	97.11 154	96.22 128

MS-PatchMatch		94.84 157	94.76 152	94.94 177	96.38 194	94.69 191	95.90 186	94.03 203	92.49 143	93.81 182	95.79 142	96.38 148	94.54 136	94.70 166	94.85 161	94.97 190	94.43 165

thisisatest0530		94.81 158	93.06 174	96.85 123	98.01 126	97.18 141	96.93 160	97.36 123	89.73 178	95.80 127	94.98 154	77.88 215	94.89 130	96.73 126	97.35 95	98.13 108	97.54 75

tttt0517		94.81 158	93.04 175	96.88 122	98.15 118	97.37 135	96.99 157	97.36 123	89.51 180	95.74 130	94.89 156	77.53 217	94.89 130	96.94 120	97.35 95	98.17 106	97.70 65

testgi		94.81 158	96.05 124	93.35 194	99.06 56	96.87 155	97.57 126	96.70 150	95.77 56	88.60 216	93.19 185	98.87 58	81.21 220	97.03 116	96.64 120	96.97 161	93.99 172

PatchMatch-RL		94.79 161	93.75 167	96.00 148	96.80 185	95.00 188	95.47 196	95.25 185	90.68 167	95.80 127	92.97 186	93.64 174	95.67 115	96.13 143	95.81 145	96.99 160	92.01 185

FPMVS		94.70 162	94.99 149	94.37 185	95.84 204	93.20 197	96.00 185	91.93 208	95.03 84	94.64 162	94.68 160	93.29 175	90.95 176	98.07 75	97.34 98	96.85 163	93.29 177

new-patchmatchnet		94.48 163	94.02 161	95.02 176	97.51 165	95.00 188	95.68 190	94.26 202	97.32 20	95.73 132	99.60 12	98.22 104	91.30 171	94.13 177	84.41 207	95.65 185	89.45 198

IterMVS		94.48 163	93.46 170	95.66 159	97.52 162	96.43 163	97.20 149	94.73 196	92.91 142	96.44 98	98.75 68	91.10 187	94.53 137	92.10 197	90.10 199	93.51 195	92.84 184
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MDTV_nov1_ep13_2view		94.39 165	93.34 171	95.63 160	97.23 177	95.33 185	97.76 114	96.84 143	94.55 103	97.47 53	98.96 47	97.70 119	93.88 147	92.27 195	86.81 205	90.56 208	87.73 206

Fast-Effi-MVS+-dtu		94.34 166	93.26 173	95.62 161	97.82 145	95.97 178	95.86 187	99.01 13	86.88 201	93.39 190	90.83 205	95.46 158	90.61 180	94.46 172	94.68 165	97.01 159	94.51 162

thres600view7		94.34 166	92.31 184	96.70 127	98.19 115	98.12 90	97.85 113	97.45 114	91.49 156	93.98 179	84.27 215	82.02 206	94.24 142	97.04 113	98.76 34	98.49 84	94.47 164

EPNet		94.33 168	93.52 169	95.27 169	98.81 72	94.71 190	96.77 164	98.20 57	88.12 193	96.53 95	92.53 190	91.19 186	85.25 216	95.22 161	95.26 156	96.09 183	97.63 72
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test2506		94.29 169	91.43 192	97.64 78	98.66 84	98.83 33	98.50 74	98.40 37	96.04 42	94.45 166	94.88 157	55.05 231	96.70 79	99.28 14	99.04 19	99.14 33	96.87 106

GA-MVS		94.18 170	92.98 176	95.58 162	97.36 170	96.42 164	96.21 181	95.86 168	90.29 171	95.08 151	96.19 132	85.37 198	92.82 164	94.01 179	94.14 170	96.16 182	94.41 166

gg-mvs-nofinetune		94.13 171	93.93 164	94.37 185	97.99 130	95.86 179	95.45 199	99.22 9	97.61 16	95.10 150	99.50 19	84.50 199	81.73 219	95.31 159	94.12 171	96.71 171	90.59 191

baseline		94.07 172	94.50 157	93.57 192	96.34 195	93.40 196	95.56 194	92.39 206	92.07 151	94.00 178	98.24 86	97.51 126	89.19 192	91.75 199	92.72 186	93.96 194	95.79 142

FMVSNet3		94.06 173	93.85 166	94.31 188	95.46 212	97.80 116	96.34 176	97.58 101	88.43 190	90.28 207	96.01 137	92.43 180	88.67 199	91.82 198	93.96 174	97.53 133	96.50 123

thres400		94.04 174	91.94 187	96.50 138	97.98 132	97.82 114	97.66 120	96.96 137	90.96 163	94.20 173	83.24 217	82.82 204	93.80 148	96.50 131	98.09 70	98.38 94	94.15 168

dmvs_re		94.02 175	92.39 182	95.91 152	97.71 152	95.43 184	97.00 156	95.94 165	82.49 218	94.61 163	83.69 216	93.01 178	92.71 165	97.83 81	97.56 90	97.50 135	96.73 112

CVMVSNet		94.01 176	94.25 159	93.73 191	94.36 215	92.44 200	97.45 133	88.56 212	95.59 63	93.06 196	98.88 56	90.03 193	94.84 132	94.08 178	93.45 181	94.09 192	95.31 154

thres200		93.98 177	91.90 188	96.40 142	97.66 153	98.12 90	97.20 149	97.45 114	90.16 174	93.82 181	83.08 218	83.74 202	93.80 148	97.04 113	97.48 93	98.49 84	93.70 174

baseline1		93.89 178	92.82 178	95.14 173	97.62 158	96.97 150	96.12 182	96.36 157	91.30 158	91.53 201	94.68 160	80.72 208	90.80 178	95.71 150	96.29 130	98.44 91	94.09 169

tfpn200view9		93.80 179	91.75 189	96.20 145	97.52 162	98.15 88	97.48 132	97.47 111	87.65 195	93.56 187	83.03 219	84.12 200	92.62 167	97.04 113	98.09 70	98.52 83	94.17 167

MIMVSNet		93.68 180	93.96 162	93.35 194	97.82 145	96.08 176	96.34 176	98.46 34	91.28 160	86.67 221	94.95 155	94.87 163	84.39 217	94.53 168	94.65 166	96.45 177	91.34 188

pmnet_mix02		93.59 181	92.65 179	94.69 181	96.76 189	94.16 193	97.03 155	93.00 205	95.79 54	96.03 119	98.91 53	97.69 120	92.99 159	90.03 209	84.10 209	92.35 204	87.89 205

EPNet_dtu		93.45 182	92.51 181	94.55 184	98.39 97	91.67 209	95.46 197	97.50 108	86.56 204	97.38 57	93.52 180	94.20 173	85.82 211	93.31 186	92.53 187	92.72 200	95.76 144
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IB-MVS	92.44 16	93.33 183	92.15 186	94.70 180	97.42 169	96.39 168	95.57 191	94.67 197	86.40 207	93.59 186	78.28 223	95.76 157	89.59 191	95.88 148	95.98 140	97.39 142	96.34 125
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
ET-MVSNet_ETH3D		93.18 184	90.80 195	95.95 150	96.05 199	96.07 177	96.92 161	96.51 155	89.34 181	95.63 136	94.08 173	72.31 226	93.13 157	94.33 174	94.83 162	97.44 138	94.65 160

thres100view900		92.93 185	90.89 194	95.31 167	97.52 162	96.82 158	96.41 174	95.08 187	87.65 195	93.56 187	83.03 219	84.12 200	91.12 174	94.53 168	96.91 110	98.17 106	93.21 179

N_pmnet		92.46 186	92.38 183	92.55 200	97.91 136	93.47 195	97.42 135	94.01 204	96.40 35	88.48 217	98.50 76	98.07 108	88.14 201	91.04 205	84.30 208	89.35 213	84.85 212

TAMVS		92.46 186	93.34 171	91.44 208	97.03 180	93.84 194	94.68 211	90.60 210	90.44 170	85.31 222	97.14 112	93.03 177	85.78 212	94.34 173	93.67 177	95.22 188	90.93 190

CMPMVS	71.81 19	92.34 188	92.85 177	91.75 206	92.70 220	90.43 214	88.84 223	88.56 212	85.87 208	94.35 170	90.98 203	95.89 156	91.14 173	96.14 142	94.83 162	94.93 191	95.78 143
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
baseline2		92.06 189	89.82 198	94.68 182	97.32 171	95.72 180	94.97 207	95.08 187	84.75 212	94.34 172	90.68 208	77.75 216	90.13 185	93.38 182	93.58 179	96.25 181	92.90 183

MVSTER		91.97 190	90.31 196	93.91 189	96.81 184	96.91 152	94.22 212	95.64 177	84.98 210	92.98 197	93.42 181	72.56 224	86.64 210	95.11 162	93.89 176	97.16 153	95.31 154

CR-MVSNet		91.94 191	88.50 201	95.94 151	96.14 197	92.08 204	95.23 202	98.47 32	84.30 214	96.44 98	94.58 164	75.57 218	92.92 161	90.22 207	92.22 188	96.43 178	90.56 192

gm-plane-assit		91.85 192	87.91 203	96.44 140	99.14 45	98.25 79	99.02 31	97.38 121	95.57 65	98.31 25	99.34 31	51.00 232	88.93 195	93.16 188	91.57 192	95.85 184	86.50 209

PMMVS		91.67 193	91.47 191	91.91 205	89.43 225	88.61 220	94.99 206	85.67 217	87.50 197	93.80 183	94.42 171	94.88 162	90.71 179	92.26 196	92.96 184	96.83 166	89.65 196

CHOSEN 280x420		91.55 194	90.27 197	93.05 197	94.61 214	88.01 221	96.56 171	94.62 199	88.04 194	94.20 173	92.66 189	86.60 196	90.82 177	95.06 164	91.89 190	87.49 218	89.61 197

PatchT		91.40 195	88.54 200	94.74 178	91.48 224	92.18 203	97.42 135	97.51 106	84.96 211	96.44 98	94.16 172	75.47 219	92.92 161	90.22 207	92.22 188	92.66 203	90.56 192

pmmvs3		91.20 196	91.40 193	90.96 210	91.71 223	91.08 210	95.41 200	81.34 221	87.36 198	94.57 165	95.02 152	94.30 170	90.42 181	94.28 175	89.26 201	92.30 205	88.49 203

test0.0.03 1		91.17 197	91.50 190	90.80 211	98.01 126	95.46 183	94.22 212	95.80 172	86.55 205	81.75 224	90.83 205	87.93 195	78.48 221	94.51 171	94.11 172	96.50 174	91.08 189

SCA		91.15 198	87.65 205	95.23 172	96.15 196	95.68 181	96.68 168	98.18 61	90.46 169	97.21 66	92.44 192	80.17 210	93.51 154	86.04 216	83.58 212	89.68 212	85.21 211

new_pmnet		90.85 199	92.26 185	89.21 214	93.68 219	89.05 219	93.20 220	84.16 220	92.99 140	84.25 223	97.72 96	94.60 164	86.80 209	93.20 187	91.30 193	93.21 196	86.94 208

RPMNet		90.52 200	86.27 214	95.48 164	95.95 202	92.08 204	95.55 195	98.12 66	84.30 214	95.60 138	87.49 213	72.78 223	91.24 172	87.93 211	89.34 200	96.41 179	89.98 195

MDTV_nov1_ep13		90.30 201	87.32 209	93.78 190	96.00 201	92.97 198	95.46 197	95.39 182	88.61 186	95.41 142	94.45 170	80.39 209	89.87 189	86.58 214	83.54 213	90.56 208	84.71 213

PatchmatchNet		89.98 202	86.23 215	94.36 187	96.56 192	91.90 208	96.07 183	96.72 148	90.18 173	96.87 80	93.36 184	78.06 214	91.46 170	84.71 220	81.40 217	88.45 215	83.97 217
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ADS-MVSNet		89.89 203	87.70 204	92.43 202	95.52 209	90.91 212	95.57 191	95.33 183	93.19 133	91.21 203	93.41 182	82.12 205	89.05 193	86.21 215	83.77 211	87.92 216	84.31 214

tpm		89.84 204	86.81 211	93.36 193	96.60 191	91.92 207	95.02 205	97.39 119	86.79 202	96.54 94	95.03 151	69.70 227	87.66 203	88.79 210	86.19 206	86.95 220	89.27 199

test-LLR		89.77 205	87.47 207	92.45 201	98.01 126	89.77 216	93.25 218	95.80 172	81.56 220	89.19 212	92.08 195	79.59 211	85.77 214	91.47 203	89.04 203	92.69 201	88.75 200

FMVSNet5		89.65 206	87.60 206	92.04 204	95.63 208	96.61 160	94.82 209	94.75 194	80.11 224	87.72 219	77.73 224	73.81 222	83.81 218	95.64 151	96.08 138	95.49 187	93.21 179

EPMVS		89.28 207	86.28 213	92.79 199	96.01 200	92.00 206	95.83 188	95.85 170	90.78 166	91.00 205	94.58 164	74.65 220	88.93 195	85.00 218	82.88 215	89.09 214	84.09 216

test-mter		89.16 208	88.14 202	90.37 212	94.79 213	91.05 211	93.60 217	85.26 218	81.65 219	88.32 218	92.22 193	79.35 213	87.03 207	92.28 194	90.12 198	93.19 197	90.29 194

CostFormer		89.06 209	85.65 216	93.03 198	95.88 203	92.40 201	95.30 201	95.86 168	86.49 206	93.12 195	93.40 183	74.18 221	88.25 200	82.99 221	81.46 216	89.77 211	88.66 202

MVS-HIRNet		88.72 210	86.49 212	91.33 209	91.81 222	85.66 222	87.02 225	96.25 158	81.48 222	94.82 158	96.31 131	92.14 183	90.32 183	87.60 212	83.82 210	87.74 217	78.42 221

TESTMET0.1,1		88.60 211	87.47 207	89.93 213	94.23 217	89.77 216	93.25 218	84.47 219	81.56 220	89.19 212	92.08 195	79.59 211	85.77 214	91.47 203	89.04 203	92.69 201	88.75 200

dps		88.36 212	84.32 219	93.07 196	93.86 218	92.29 202	94.89 208	95.93 166	83.50 216	93.13 193	91.87 197	67.79 229	90.32 183	85.99 217	83.22 214	90.28 210	85.56 210

tpmrst		87.60 213	84.13 220	91.66 207	95.65 207	89.73 218	93.77 215	94.74 195	88.85 183	93.35 192	95.60 144	72.37 225	87.40 204	81.24 222	78.19 219	85.02 223	82.90 220

tpm cat1		87.19 214	82.78 221	92.33 203	95.66 206	90.61 213	94.19 214	95.27 184	86.97 200	94.38 168	90.91 204	69.40 228	87.21 205	79.57 224	77.82 220	87.25 219	84.18 215

E-PMN		86.94 215	85.10 217	89.09 216	95.77 205	83.54 225	89.89 222	86.55 214	92.18 149	87.34 220	94.02 174	83.42 203	89.63 190	93.32 185	77.11 221	85.33 221	72.09 222

EMVS		86.63 216	84.48 218	89.15 215	95.51 210	83.66 224	90.19 221	86.14 216	91.78 153	88.68 215	93.83 178	81.97 207	89.05 193	92.76 192	76.09 222	85.31 222	71.28 223

PMMVS2		86.47 217	92.62 180	79.29 218	92.01 221	85.63 223	93.74 216	86.37 215	93.95 123	54.18 229	98.19 87	97.39 129	58.46 222	96.57 130	93.07 183	90.99 207	83.55 219

MVE	72.99 18	85.37 218	89.43 199	80.63 217	74.43 226	71.94 227	88.25 224	89.81 211	93.27 131	67.32 227	96.32 130	91.83 184	90.40 182	93.36 183	90.79 196	73.55 226	88.49 203
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		61.30 219	70.45 222	50.62 219	22.69 228	30.92 229	68.31 228	25.76 223	80.56 223	68.71 225	82.80 221	91.08 188	44.64 223	80.50 223	56.70 223	73.64 225	70.58 224

GG-mvs-BLEND		61.03 220	87.02 210	30.71 221	0.74 231	90.01 215	78.90 227	0.74 227	84.56 213	9.46 230	79.17 222	90.69 191	1.37 227	91.74 200	89.13 202	93.04 199	83.83 218

testmvs		4.99 221	6.88 223	2.78 223	1.73 229	2.04 231	3.10 231	1.71 225	7.27 226	3.92 232	12.18 226	6.71 233	3.31 226	6.94 225	5.51 225	2.94 228	7.51 225

test123		4.41 222	5.71 224	2.88 222	1.28 230	2.21 230	3.09 232	1.65 226	6.35 227	4.98 231	8.53 227	3.88 234	3.46 225	5.79 226	5.71 224	2.85 229	7.50 226

uanet_test		0.00 223	0.00 225	0.00 224	0.00 232	0.00 232	0.00 233	0.00 228	0.00 228	0.00 233	0.00 228	0.00 235	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

sosnet-low-res		0.00 223	0.00 225	0.00 224	0.00 232	0.00 232	0.00 233	0.00 228	0.00 228	0.00 233	0.00 228	0.00 235	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

sosnet		0.00 223	0.00 225	0.00 224	0.00 232	0.00 232	0.00 233	0.00 228	0.00 228	0.00 233	0.00 228	0.00 235	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

TPM-MVS					97.49 166	96.32 172	95.05 204			94.36 169	91.82 198	96.92 141	88.89 197			96.67 172	96.22 128
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										99.38 2

9.14												96.98 139

SR-MVS					99.33 30			98.40 37				98.90 54

Anonymous202405211			97.39 67		98.85 68	98.59 59	97.89 110	97.93 82	94.41 110		97.37 106	96.99 138	93.09 158	98.61 52	98.46 46	99.11 38	97.27 90

our_test_3					97.32 171	95.13 187	97.59 125

ambc			96.78 106		99.01 58	97.11 147	95.73 189		95.91 49	99.25 3	98.56 75	97.17 134	97.04 69	96.76 125	95.22 157	96.72 170	96.73 112

MTAPA										97.43 56		99.27 23

MTMP										97.63 47		99.03 42

Patchmatch-RL test							17.42 230

tmp_tt				45.72 220	60.00 227	38.74 228	45.50 229	12.18 224	79.58 225	68.42 226	67.62 225	65.04 230	22.12 224	84.83 219	78.72 218	66.08 227

XVS					99.48 18	98.76 44	99.22 21			96.40 102		98.78 69				98.94 55

X-MVStestdata					99.48 18	98.76 44	99.22 21			96.40 102		98.78 69				98.94 55

mPP-MVS					99.58 6							98.98 46

NP-MVS									89.27 182

Patchmtry						92.70 199	95.23 202	98.47 32		96.44 98

DeepMVS_CX						72.99 226	80.14 226	37.34 222	83.46 217	60.13 228	84.40 214	85.48 197	86.93 208	87.22 213		79.61 224	87.32 207

High-resolution multi-view benchmark