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 10	99.19 6	99.74 4	98.96 49	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 14	98.47 22	99.71 5	99.05 39	98.88 4	99.54 5	99.49 2	99.81 1	98.87 9

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 35	98.83 14	99.46 21	99.09 32	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 27	98.65 17	99.43 23	99.33 16	98.47 17	99.50 8	99.32 9	99.60 5	98.79 11

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 71	98.40 33

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 23	98.52 19	99.36 29	98.98 45	98.57 13	99.49 9	99.23 12	99.56 9	98.55 25

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 75	98.87 5	99.60 3	99.46 4	99.46 18	98.74 14

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 40	98.37 24	99.34 31	99.09 32	98.43 18	99.45 10	99.41 5	99.53 10	98.86 10

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 41

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 66	98.77 16	99.11 42	98.64 78	98.57 13	99.42 11	99.28 11	99.61 4	98.78 12

anonymousdsp		98.85 12	98.88 12	98.83 11	98.69 82	98.20 78	99.68 1	97.35 122	97.09 22	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	98.32 101	98.92 25	98.57 70	99.03 12	99.36 1	96.86 83	99.77 3	99.86 1	96.20 100	99.56 4	99.39 7	99.59 6	98.61 22

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 42
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 95	98.33 8	97.82 41	99.20 38	99.18 30	98.76 6	99.27 17	98.96 22	99.29 27	98.03 46
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 41	97.12 70	98.44 78	98.95 50	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 64	99.01 35	98.17 63	97.17 21	98.25 27	99.56 15	99.62 5	98.29 22	98.40 62	98.09 70	98.97 50	98.08 45
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 67	97.53 50	99.42 25	98.83 62	98.01 34	98.55 54	98.34 57	99.57 8	97.80 57

CSCG		98.45 18	98.61 19	98.26 37	99.11 49	99.06 17	98.17 92	97.49 108	97.93 12	97.37 58	98.88 55	99.29 18	98.10 29	98.40 62	97.51 88	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 17	96.05 117	99.35 30	99.76 3	96.34 95	98.79 37	98.65 41	98.56 77	99.35 2

Gipuma		98.43 21	98.15 34	98.76 14	99.00 61	98.29 75	97.91 107	98.06 70	99.02 3	99.50 1	96.33 128	98.67 75	99.22 1	99.02 27	98.02 75	98.88 62	97.66 65
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 87	97.78 13	94.19 174	98.77 65	99.39 13	98.61 11	99.33 13	99.07 14	99.33 23	97.81 56

ACMMPR		98.31 23	98.07 38	98.60 23	99.58 6	98.83 33	99.09 27	98.48 31	96.25 37	97.03 74	96.81 116	99.09 32	98.39 20	98.55 54	98.45 49	99.01 45	98.53 28

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 47	95.13 148	98.79 62	99.25 25	97.92 38	98.80 35	98.71 36	98.85 64	98.54 26

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 26	94.35 169	98.92 51	99.58 7	97.86 41	98.67 46	98.70 37	98.63 71	98.63 20
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	98.22 110	98.73 50	98.66 66	98.03 75	98.60 7	96.40 102	99.60 12	98.24 99	95.26 122	99.19 21	99.05 17	99.36 20	97.64 66

DU-MVS		98.23 26	97.74 54	98.81 12	99.23 33	98.77 41	98.76 57	98.88 15	94.10 114	98.50 20	98.87 57	98.32 96	97.99 35	98.40 62	98.08 73	99.49 16	97.64 66

UniMVSNet (Re)		98.23 26	97.85 47	98.67 19	99.15 42	98.87 28	98.74 60	98.84 17	94.27 112	97.94 38	99.01 45	98.39 92	97.82 42	98.35 67	98.29 62	99.51 15	97.78 58

MIMVSNet1		98.22 29	98.51 23	97.87 64	99.40 25	98.82 37	99.31 16	98.53 28	97.39 18	96.59 93	99.31 33	99.23 27	94.76 132	98.93 32	98.67 39	98.63 71	97.25 90

HFP-MVS		98.17 30	98.02 39	98.35 35	99.36 27	98.62 56	98.79 56	98.46 34	96.24 38	96.53 95	97.13 112	98.98 45	98.02 33	98.20 70	98.42 51	98.95 54	98.54 26

Baseline_NR-MVSNet		98.17 30	97.90 44	98.48 29	99.23 33	98.59 57	98.83 53	98.73 24	93.97 119	96.95 77	99.66 7	98.23 101	97.90 39	98.40 62	99.06 16	99.25 29	97.42 82

TSAR-MVS + MP.		98.15 32	98.23 30	98.06 51	98.47 92	98.16 84	99.23 20	96.87 138	95.58 61	96.72 86	98.41 79	99.06 36	98.05 32	98.99 29	98.90 26	99.00 46	98.51 29
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	97.93 132	98.49 66	98.14 94	98.19 59	97.95 11	96.17 113	99.63 10	98.85 58	95.41 120	98.91 33	98.89 27	99.34 22	97.86 55

SMA-MVS		98.13 34	98.22 31	98.02 56	99.44 23	98.73 50	98.24 89	97.87 86	95.22 74	96.76 85	98.66 71	99.35 15	97.03 70	98.53 57	98.39 53	98.80 66	98.69 16
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 37	98.18 39	99.34 28	98.74 49	98.97 38	98.00 77	95.13 78	96.90 78	97.54 101	99.27 22	97.18 64	98.72 42	98.45 49	98.68 70	98.69 16

UniMVSNet_NR-MVSNet		98.12 35	97.56 62	98.78 13	99.13 47	98.89 27	98.76 57	98.78 20	93.81 122	98.50 20	98.81 61	97.64 122	97.99 35	98.18 73	97.92 77	99.53 10	97.64 66

ACMM	94.29 11	98.12 35	97.71 55	98.59 24	99.51 16	98.58 59	99.24 19	98.25 52	96.22 39	96.90 78	95.01 152	98.89 55	98.52 16	98.66 47	98.32 60	99.13 36	98.28 39
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SteuartSystems-ACMMP		98.06 38	97.78 52	98.39 33	99.54 10	98.79 39	98.94 42	98.42 36	93.98 118	95.85 124	96.66 122	99.25 25	98.61 11	98.71 44	98.38 54	98.97 50	98.67 19
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 56	94.70 159	98.96 47	99.49 9	96.19 101	98.74 38	98.65 41	98.46 85	98.63 20

OPM-MVS		98.01 40	98.01 40	98.00 58	99.11 49	98.12 87	98.68 64	97.72 93	96.65 29	96.68 90	98.40 80	99.28 21	97.44 55	98.20 70	97.82 83	98.40 91	97.58 71
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	96.89 181	98.82 37	99.14 24	97.59 98	96.30 36	97.04 73	99.26 36	98.83 62	96.01 106	98.73 40	98.21 64	98.58 76	98.75 13
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS		98.00 42	97.38 67	98.73 15	98.72 77	99.15 11	99.12 26	98.76 21	91.58 152	98.15 31	96.70 120	98.72 74	98.20 24	98.64 50	98.92 24	99.43 19	97.97 49

NR-MVSNet		98.00 42	97.88 45	98.13 41	98.33 99	98.77 41	98.83 53	98.88 15	94.10 114	97.46 55	98.87 57	98.58 83	95.78 109	99.13 25	98.16 68	99.52 12	97.53 74

CP-MVS		98.00 42	97.57 61	98.50 26	99.47 20	98.56 61	98.91 44	98.38 42	94.71 93	97.01 75	95.20 148	99.06 36	98.20 24	98.61 51	98.46 46	99.02 43	98.40 33

DPE-MVS		97.99 45	98.12 35	97.84 67	98.65 86	98.86 29	98.86 50	98.05 73	94.18 113	95.49 141	98.90 53	99.33 16	97.11 66	98.53 57	98.65 41	98.86 63	98.39 35
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 60	98.45 31	99.53 14	98.83 33	99.13 25	98.30 47	94.57 99	96.39 106	95.32 146	98.95 50	98.37 21	98.61 51	98.47 45	99.00 46	98.45 30
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 63	98.50 26	99.56 8	98.58 59	98.97 38	98.39 41	93.49 125	97.14 67	96.08 135	99.23 27	98.06 31	98.50 59	98.38 54	98.90 58	98.44 31
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 42	98.04 53	98.84 70	98.04 95	97.90 108	96.83 141	95.07 80	98.79 15	99.07 43	99.37 14	97.88 40	98.74 38	98.16 68	98.01 113	96.96 98

ACMP	94.03 12	97.97 49	97.61 59	98.39 33	99.43 24	98.51 65	98.97 38	98.06 70	94.63 97	96.10 115	96.12 134	99.20 29	98.63 9	98.68 45	98.20 67	99.14 33	97.93 52
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CS-MVS-test		97.96 50	97.38 67	98.64 21	98.57 88	99.13 12	99.36 13	98.66 25	91.67 151	98.17 30	96.91 115	98.84 60	97.99 35	98.80 35	98.88 28	99.08 41	97.43 81

LGP-MVS_train		97.96 50	97.53 63	98.45 31	99.45 21	98.64 55	99.09 27	98.27 50	92.99 137	96.04 118	96.57 123	99.29 18	98.66 8	98.73 40	98.42 51	99.19 31	98.09 44

LS3D		97.93 52	97.80 49	98.08 47	99.20 36	98.77 41	98.89 46	97.92 82	96.59 30	96.99 76	96.71 119	97.14 134	96.39 94	99.04 26	98.96 22	99.10 40	97.39 83

SD-MVS		97.84 53	97.78 52	97.90 61	98.33 99	98.06 92	97.95 104	97.80 92	96.03 45	96.72 86	97.57 99	99.18 30	97.50 53	97.88 76	97.08 101	99.11 38	98.68 18
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 97	98.23 108	98.06 92	97.44 133	95.79 171	96.90 24	95.81 126	98.76 66	98.61 82	97.70 47	98.90 34	98.36 56	98.90 58	98.29 36

thisisatest0515		97.82 55	97.67 56	97.99 59	98.49 91	98.07 91	98.48 77	98.06 70	95.35 72	97.74 43	98.83 60	97.61 123	96.74 77	97.53 94	98.30 61	98.43 90	98.01 48

PGM-MVS		97.82 55	97.25 73	98.48 29	99.54 10	98.75 48	99.02 31	98.35 45	92.41 141	96.84 84	95.39 145	98.99 44	98.24 23	98.43 61	98.34 57	98.90 58	98.41 32

PMVS	90.51 17	97.77 57	97.98 41	97.53 86	98.68 83	98.14 86	97.67 118	97.03 133	96.43 31	98.38 23	98.72 68	97.03 136	94.44 137	99.37 12	99.30 10	98.98 49	96.86 105
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MSP-MVS		97.67 58	97.88 45	97.43 92	99.34 28	98.99 23	98.87 49	98.12 66	95.63 58	94.16 175	97.45 102	99.50 8	96.44 93	96.35 132	98.70 37	97.65 129	98.57 24
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 50	97.52 88	98.32 101	98.53 63	98.45 80	97.69 94	97.59 16	96.12 114	97.79 94	96.70 141	95.69 113	98.35 67	98.34 57	98.85 64	97.22 93

FC-MVSNet-train		97.65 60	98.16 33	97.05 109	98.85 68	98.85 30	99.34 14	98.08 69	94.50 104	94.41 166	99.21 37	98.80 66	92.66 163	98.98 30	98.85 31	98.96 52	97.94 51

v10		97.64 61	97.26 72	98.08 47	98.07 121	98.56 61	98.86 50	98.18 61	94.48 105	98.24 28	99.56 15	98.98 45	97.72 46	96.05 142	96.26 129	97.42 138	96.93 99

EC-MVSNet		97.63 62	96.88 95	98.50 26	98.74 76	99.16 10	99.33 15	98.83 18	88.77 181	96.62 92	96.48 125	97.75 115	98.19 26	99.00 28	98.76 34	99.29 27	98.27 40

X-MVS		97.60 63	97.00 90	98.29 36	99.50 17	98.76 44	98.90 45	98.37 43	94.67 96	96.40 102	91.47 197	98.78 68	97.60 52	98.55 54	98.50 44	98.96 52	98.29 36

3Dnovator+	96.20 4	97.58 64	97.14 81	98.10 42	98.98 63	97.85 107	98.60 69	98.33 46	96.41 33	97.23 65	94.66 161	97.26 131	96.91 74	97.91 75	97.87 79	98.53 80	98.03 46

DCV-MVSNet		97.56 65	97.63 58	97.47 90	98.41 96	99.12 13	98.63 67	98.57 26	95.71 57	95.60 138	93.79 176	98.01 110	94.25 139	99.16 23	98.88 28	99.35 21	98.74 14

HPM-MVS++		97.56 65	97.11 85	98.09 43	99.18 38	97.95 102	98.57 70	98.20 57	94.08 116	97.25 64	95.96 139	98.81 65	97.13 65	97.51 95	97.30 98	98.21 101	98.15 43

FC-MVSNet-test		97.54 67	98.26 29	96.70 126	98.87 66	97.79 114	98.49 76	98.56 27	96.04 41	90.39 204	99.65 8	98.67 75	95.15 124	99.23 19	99.07 14	98.73 69	97.39 83

TSAR-MVS + ACMM		97.54 67	97.79 50	97.26 98	98.23 108	98.10 90	97.71 116	97.88 85	95.97 46	95.57 140	98.71 69	98.57 84	97.36 58	97.74 83	96.81 110	96.83 164	98.59 23

DeepC-MVS_fast	95.38 6	97.53 69	97.30 71	97.79 72	98.83 71	97.64 117	98.18 90	97.14 129	95.57 62	97.83 40	97.10 113	98.80 66	96.53 90	97.41 98	97.32 96	98.24 100	97.26 89
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 89	98.09 43	98.31 104	98.01 97	98.96 41	97.25 125	95.22 74	98.89 12	99.64 9	98.83 62	97.68 48	95.63 149	95.91 139	97.47 134	95.97 135

v1144		97.51 71	97.05 88	98.04 53	98.26 106	97.98 99	98.88 48	97.42 116	95.38 71	98.56 18	99.59 14	99.01 43	97.65 49	95.77 146	96.06 136	97.47 134	95.56 147

v8		97.51 71	97.16 79	97.91 60	97.99 128	98.48 67	98.76 57	98.17 63	94.54 103	97.69 45	99.48 20	98.76 71	97.63 51	96.10 141	96.14 131	97.20 148	96.64 113

v1921920		97.50 73	97.00 90	98.07 49	98.20 112	97.94 105	99.03 30	97.06 131	95.29 73	99.01 9	99.62 11	98.73 73	97.74 45	95.52 152	95.78 144	97.39 140	96.12 131

Anonymous20231211		97.49 74	97.91 43	97.00 112	98.31 104	98.72 52	98.27 87	97.84 89	94.76 92	94.77 158	98.14 87	98.38 94	93.60 149	98.96 31	98.66 40	99.22 30	97.77 60

v144192		97.49 74	96.99 92	98.07 49	98.11 120	97.95 102	99.02 31	97.21 126	94.90 88	98.88 13	99.53 17	98.89 55	97.75 44	95.59 150	95.90 140	97.43 137	96.16 129

test1111		97.48 76	97.20 76	97.81 71	98.78 74	98.85 30	98.68 64	98.40 37	96.68 27	94.84 156	99.13 41	90.32 189	97.01 71	99.27 17	99.05 17	99.19 31	97.10 95

GeoE		97.48 76	96.84 99	98.22 38	99.01 58	98.39 70	98.85 52	98.76 21	92.37 142	97.53 50	97.58 98	98.23 101	97.11 66	97.57 93	96.98 104	98.10 109	96.78 108

APD-MVS		97.47 78	97.16 79	97.84 67	99.32 31	98.39 70	98.47 79	98.21 56	92.08 147	95.23 145	96.68 121	98.90 53	96.99 72	98.20 70	98.21 64	98.80 66	97.67 64
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PVSNet_Blended_VisFu		97.44 79	97.14 81	97.79 72	99.15 42	98.44 68	98.32 85	97.66 96	93.74 124	97.73 44	98.79 62	96.93 139	95.64 118	97.69 85	96.91 107	98.25 99	97.50 77

PHI-MVS		97.44 79	97.17 78	97.74 75	98.14 117	98.41 69	98.03 100	97.50 106	92.07 148	98.01 36	97.33 107	98.62 81	96.02 105	98.34 69	98.21 64	98.76 68	97.24 92

v1240		97.43 81	96.87 98	98.09 43	98.25 107	97.92 106	99.02 31	97.06 131	94.77 91	99.09 8	99.68 6	98.51 87	97.78 43	95.25 157	95.81 142	97.32 144	96.13 130

ECVR-MVS		97.40 82	97.11 85	97.73 76	98.66 84	98.83 33	98.50 74	98.40 37	96.04 41	95.00 154	98.95 49	91.07 186	96.70 79	99.28 14	99.04 19	99.14 33	96.58 115

FMVSNet1		97.40 82	98.09 36	96.60 131	97.80 146	98.76 44	98.26 88	98.50 30	96.79 25	93.13 192	99.28 34	98.64 78	92.90 160	97.67 87	97.86 80	99.02 43	97.64 66

casdiffmvs_mvg		97.34 84	97.65 57	96.97 113	97.74 149	98.33 73	98.45 80	97.18 127	95.81 52	93.92 179	99.04 44	99.05 39	95.48 119	97.00 115	97.71 86	99.07 42	96.63 114
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 99	97.90 61	98.19 113	97.83 108	98.74 60	97.44 114	95.42 70	98.23 29	99.46 21	98.84 60	97.46 54	95.51 153	96.10 134	97.36 142	94.72 156

EPP-MVSNet		97.29 86	96.88 95	97.76 74	98.70 79	99.10 16	98.92 43	98.36 44	95.12 79	93.36 190	97.39 104	91.00 187	97.65 49	98.72 42	98.91 25	99.58 7	97.92 53

MVS_111021_HR		97.27 87	97.11 85	97.46 91	98.46 93	97.82 111	97.50 129	96.86 139	94.97 84	97.13 69	96.99 114	98.39 92	96.82 76	97.65 90	97.38 91	98.02 112	96.56 118

SF-MVS		97.26 88	97.43 65	97.05 109	98.80 73	97.83 108	96.02 182	97.44 114	94.98 83	95.74 130	97.16 110	98.45 91	95.72 111	97.85 77	97.97 76	98.60 74	97.78 58

TSAR-MVS + GP.		97.26 88	97.33 70	97.18 103	98.21 111	98.06 92	96.38 173	97.66 96	93.92 121	95.23 145	98.48 76	98.33 95	97.41 56	97.63 91	97.35 92	98.18 103	97.57 72

OMC-MVS		97.23 90	97.21 75	97.25 101	97.85 137	97.52 126	97.92 106	95.77 172	95.83 51	97.09 72	97.86 92	98.52 86	96.62 83	97.51 95	96.65 116	98.26 97	96.57 116

3Dnovator	96.31 3	97.22 91	97.19 77	97.25 101	98.14 117	97.95 102	98.03 100	96.77 144	96.42 32	97.14 67	95.11 149	97.59 124	95.14 126	97.79 81	97.72 84	98.26 97	97.76 62

MVS_0304		97.18 92	96.84 99	97.58 81	99.15 42	98.19 79	98.11 95	97.81 91	92.36 143	98.06 34	97.43 103	99.06 36	94.24 140	96.80 120	96.54 120	98.12 107	97.52 75

canonicalmvs		97.11 93	96.88 95	97.38 93	98.34 98	98.72 52	97.52 128	97.94 80	95.60 59	95.01 153	94.58 162	94.50 165	96.59 85	97.84 78	98.03 74	98.90 58	98.91 8

V42		97.10 94	96.97 93	97.26 98	97.64 153	97.60 119	98.45 80	95.99 160	94.44 106	97.35 59	99.40 26	98.63 80	97.34 60	96.33 135	96.38 126	96.82 166	96.00 133

CPTT-MVS		97.08 95	96.25 113	98.05 52	99.21 35	98.30 74	98.54 73	97.98 78	94.28 110	95.89 123	89.57 206	98.54 85	98.18 27	97.82 80	97.32 96	98.54 78	97.91 54

DeepPCF-MVS	94.55 10	97.05 96	97.13 84	96.95 115	96.06 195	97.12 143	98.01 102	95.44 178	95.18 76	97.50 52	97.86 92	98.08 106	97.31 62	97.23 103	97.00 103	97.36 142	97.45 79

QAPM		97.04 97	97.14 81	96.93 117	97.78 148	98.02 96	97.36 138	96.72 145	94.68 95	96.23 108	97.21 109	97.68 120	95.70 112	97.37 99	97.24 100	97.78 122	97.77 60

CNVR-MVS		97.03 98	96.77 104	97.34 94	98.89 65	97.67 116	97.64 121	97.17 128	94.40 108	95.70 134	94.02 171	98.76 71	96.49 92	97.78 82	97.29 99	98.12 107	97.47 78

casdiffmvs		97.00 99	97.36 69	96.59 132	97.65 152	97.98 99	98.06 97	96.81 142	95.78 54	92.77 198	99.40 26	99.26 24	95.65 117	96.70 124	96.39 125	98.59 75	95.99 134
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		96.99 100	96.70 106	97.34 94	97.89 135	97.23 135	98.33 84	96.96 134	95.57 62	97.12 70	98.99 46	99.40 12	97.23 63	96.22 138	95.45 149	96.50 172	94.02 168

DELS-MVS		96.90 101	97.24 74	96.50 137	97.85 137	98.18 80	97.88 111	95.92 164	93.48 126	95.34 143	98.86 59	98.94 52	94.03 143	97.33 101	97.04 102	98.00 114	96.85 106
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		96.86 102	96.72 105	97.03 111	97.80 146	97.06 146	97.04 152	95.51 177	94.55 100	97.47 53	97.35 106	97.68 120	96.66 81	97.11 108	96.73 112	97.69 126	96.57 116

PM-MVS		96.85 103	96.62 108	97.11 105	97.13 176	96.51 159	98.29 86	94.65 195	94.84 89	98.12 32	98.59 72	97.20 132	97.41 56	96.24 137	96.41 124	97.09 153	96.56 118

pmmvs-eth3d		96.84 104	96.22 115	97.56 83	97.63 155	96.38 166	98.74 60	96.91 137	94.63 97	98.26 26	99.43 23	98.28 97	96.58 87	94.52 167	95.54 147	97.24 146	94.75 155

CANet		96.81 105	96.50 109	97.17 104	99.10 51	97.96 101	97.86 112	97.51 104	91.30 155	97.75 42	97.64 96	97.89 113	93.39 153	96.98 116	96.73 112	97.40 139	96.99 97

Fast-Effi-MVS+		96.80 106	95.92 126	97.84 67	98.57 88	97.46 129	98.06 97	98.24 53	89.64 176	97.57 49	96.45 126	97.35 129	96.73 78	97.22 104	96.64 117	97.86 119	96.65 112

MCST-MVS		96.79 107	96.08 119	97.62 79	98.78 74	97.52 126	98.01 102	97.32 123	93.20 129	95.84 125	93.97 173	98.12 104	97.34 60	96.34 133	95.88 141	98.45 86	97.51 76

UGNet		96.79 107	97.82 48	95.58 160	97.57 158	98.39 70	98.48 77	97.84 89	95.85 50	94.68 160	97.91 91	99.07 35	87.12 203	97.71 84	97.51 88	97.80 120	98.29 36
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	96.79 107	96.70 106	96.90 119	97.64 153	97.58 120	97.54 127	94.50 197	95.14 77	96.64 91	96.76 118	97.90 112	96.63 82	95.98 143	96.14 131	98.45 86	97.39 83
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CLD-MVS		96.73 110	96.92 94	96.51 136	98.70 79	97.57 122	97.64 121	92.07 204	93.10 135	96.31 107	98.29 82	99.02 42	95.99 107	97.20 105	96.47 122	98.37 93	96.81 107
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
train_agg		96.68 111	95.93 125	97.56 83	99.08 53	97.16 139	98.44 83	97.37 119	91.12 159	95.18 147	95.43 144	98.48 89	97.36 58	96.48 129	95.52 148	97.95 117	97.34 87

CDPH-MVS		96.68 111	95.99 122	97.48 89	99.13 47	97.64 117	98.08 96	97.46 110	90.56 165	95.13 148	94.87 157	98.27 98	96.56 88	97.09 109	96.45 123	98.54 78	97.08 96

MSLP-MVS++		96.66 113	96.46 112	96.89 120	98.02 123	97.71 115	95.57 189	96.96 134	94.36 109	96.19 112	91.37 198	98.24 99	97.07 68	97.69 85	97.89 78	97.52 132	97.95 50

TinyColmap		96.64 114	96.07 120	97.32 96	97.84 142	96.40 163	97.63 123	96.25 155	95.86 49	98.98 10	97.94 90	96.34 148	96.17 102	97.30 102	95.38 152	97.04 155	93.24 175

IS_MVSNet		96.62 115	96.48 111	96.78 124	98.46 93	98.68 54	98.61 68	98.24 53	92.23 144	89.63 208	95.90 140	94.40 166	96.23 97	98.65 48	98.77 33	99.52 12	96.76 109

NCCC		96.56 116	95.68 128	97.59 80	99.04 57	97.54 125	97.67 118	97.56 102	94.84 89	96.10 115	87.91 209	98.09 105	96.98 73	97.20 105	96.80 111	98.21 101	97.38 86

ETV-MVS		96.54 117	95.27 136	98.02 56	99.07 55	97.48 128	98.16 93	98.19 59	87.33 196	97.58 48	92.67 185	95.93 154	96.22 98	98.49 60	98.46 46	98.91 57	96.50 121

Effi-MVS+		96.46 118	95.28 135	97.85 66	98.64 87	97.16 139	97.15 150	98.75 23	90.27 169	98.03 35	93.93 174	96.21 149	96.55 89	96.34 133	96.69 115	97.97 116	96.33 124

IterMVS-LS		96.35 119	95.85 127	96.93 117	97.53 159	98.00 98	97.37 136	97.97 79	95.49 69	96.71 89	98.94 50	93.23 173	94.82 131	93.15 186	95.05 155	97.17 150	97.12 94
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
USDC		96.30 120	95.64 130	97.07 107	97.62 156	96.35 168	97.17 149	95.71 173	95.52 67	99.17 7	98.11 88	97.46 126	95.67 114	95.44 155	93.60 175	97.09 153	92.99 179

Vis-MVSNet (Re-imp)		96.29 121	96.50 109	96.05 145	97.96 131	97.83 108	97.30 141	97.86 87	93.14 131	88.90 211	96.80 117	95.28 158	95.15 124	98.37 66	98.25 63	99.12 37	95.84 137

MSDG		96.27 122	96.17 118	96.38 141	97.85 137	96.27 170	96.55 170	94.41 198	94.55 100	95.62 137	97.56 100	97.80 114	96.22 98	97.17 107	96.27 128	97.67 128	93.60 172

CNLPA		96.24 123	95.97 123	96.57 134	97.48 165	97.10 145	96.75 163	94.95 189	94.92 87	96.20 111	94.81 158	96.61 143	96.25 96	96.94 117	95.64 145	97.79 121	95.74 143

EIA-MVS		96.23 124	94.85 148	97.84 67	99.08 53	98.21 77	97.69 117	98.03 75	85.68 206	98.09 33	91.75 196	97.07 135	95.66 116	97.58 92	97.72 84	98.47 84	95.91 136

PLC	92.55 15	96.10 125	95.36 132	96.96 114	98.13 119	96.88 150	96.49 171	96.67 149	94.07 117	95.71 133	91.14 199	96.09 151	96.84 75	96.70 124	96.58 119	97.92 118	96.03 132
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test20.03		96.08 126	96.80 102	95.25 169	99.19 37	97.58 120	97.24 146	97.56 102	94.95 86	91.91 199	98.58 73	98.03 108	87.88 199	97.43 97	96.94 106	97.69 126	94.05 167

FA-MVS(training)		96.07 127	95.59 131	96.63 129	98.00 127	97.44 130	97.36 138	98.53 28	92.21 145	95.97 120	96.18 132	94.22 169	92.98 157	96.79 121	96.70 114	96.95 160	95.56 147

TSAR-MVS + COLMAP		96.05 128	95.94 124	96.18 144	97.46 166	96.41 162	97.26 145	95.83 168	94.69 94	95.30 144	98.31 81	96.52 144	94.71 133	95.48 154	94.87 157	96.54 171	95.33 150

EU-MVSNet		96.03 129	96.23 114	95.80 154	95.48 208	94.18 189	98.99 36	91.51 206	97.22 20	97.66 46	99.15 40	98.51 87	98.08 30	95.92 144	92.88 182	93.09 195	95.72 144

PCF-MVS	92.69 14	95.98 130	95.05 143	97.06 108	98.43 95	97.56 123	97.76 114	96.65 150	89.95 174	95.70 134	96.18 132	98.48 89	95.74 110	93.64 178	93.35 179	98.09 111	96.18 128
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HQP-MVS		95.97 131	95.01 145	97.08 106	98.72 77	97.19 137	97.07 151	96.69 148	91.49 153	95.77 129	92.19 191	97.93 111	96.15 103	94.66 164	94.16 166	98.10 109	97.45 79

Effi-MVS+-dtu		95.94 132	95.08 142	96.94 116	98.54 90	97.38 131	96.66 167	97.89 84	88.68 182	95.92 121	92.90 184	97.28 130	94.18 142	96.68 126	96.13 133	98.45 86	96.51 120

diffmvs		95.86 133	96.21 116	95.44 163	97.25 174	96.85 153	96.99 155	95.23 183	94.96 85	92.82 197	98.89 54	98.85 58	93.52 151	94.21 173	94.25 165	96.84 163	95.49 149
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		95.85 134	94.65 151	97.26 98	98.70 79	97.20 136	97.33 140	97.30 124	91.28 157	95.90 122	88.16 208	96.17 150	96.60 84	97.34 100	96.82 109	97.71 123	95.60 146

FMVSNet2		95.77 135	96.20 117	95.27 167	96.77 184	98.18 80	97.28 142	97.90 83	93.12 132	91.37 201	98.25 84	96.05 152	90.04 183	94.96 162	95.94 138	98.28 94	96.90 100

OpenMVS	94.63 9	95.75 136	95.04 144	96.58 133	97.85 137	97.55 124	96.71 165	96.07 157	90.15 172	96.47 97	90.77 204	95.95 153	94.41 138	97.01 114	96.95 105	98.00 114	96.90 100

pmmvs5		95.70 137	95.22 137	96.26 142	96.55 190	97.24 134	97.50 129	94.99 188	90.95 161	96.87 80	98.47 77	97.40 127	94.45 136	92.86 187	94.98 156	97.23 147	94.64 158

Anonymous20231206		95.69 138	95.68 128	95.70 156	98.32 101	96.95 148	97.37 136	96.65 150	93.33 127	93.61 184	98.70 70	98.03 108	91.04 172	95.07 160	94.59 164	97.20 148	93.09 178

MAR-MVS		95.51 139	94.49 155	96.71 125	97.92 133	96.40 163	96.72 164	98.04 74	86.74 200	96.72 86	92.52 188	95.14 160	94.02 144	96.81 119	96.54 120	96.85 161	97.25 90
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		95.48 140	94.51 153	96.61 130	97.13 176	97.30 133	98.05 99	96.79 143	93.75 123	95.08 151	96.38 127	89.76 191	94.95 127	93.97 177	94.82 161	97.64 130	95.63 145

MDA-MVSNet-bldmvs		95.45 141	95.20 138	95.74 155	94.24 213	96.38 166	97.93 105	94.80 190	95.56 65	96.87 80	98.29 82	95.24 159	96.50 91	98.65 48	90.38 194	94.09 189	91.93 183

PVSNet_BlendedMVS		95.44 142	95.09 140	95.86 152	97.31 171	97.13 141	96.31 176	95.01 186	88.55 185	96.23 108	94.55 165	97.75 115	92.56 165	96.42 130	95.44 150	97.71 123	95.81 138

PVSNet_Blended		95.44 142	95.09 140	95.86 152	97.31 171	97.13 141	96.31 176	95.01 186	88.55 185	96.23 108	94.55 165	97.75 115	92.56 165	96.42 130	95.44 150	97.71 123	95.81 138

pmmvs4		95.37 144	94.25 156	96.67 128	97.01 179	95.28 183	97.60 124	96.07 157	93.11 133	97.29 62	98.09 89	94.23 168	95.21 123	91.56 198	93.91 172	96.82 166	93.59 173

MVS_Test		95.34 145	94.88 147	95.89 151	96.93 180	96.84 154	96.66 167	97.08 130	90.06 173	94.02 176	97.61 97	96.64 142	93.59 150	92.73 190	94.02 170	97.03 156	96.24 125

GBi-Net		95.21 146	95.35 133	95.04 172	96.77 184	98.18 80	97.28 142	97.58 99	88.43 187	90.28 205	96.01 136	92.43 177	90.04 183	97.67 87	97.86 80	98.28 94	96.90 100

test1		95.21 146	95.35 133	95.04 172	96.77 184	98.18 80	97.28 142	97.58 99	88.43 187	90.28 205	96.01 136	92.43 177	90.04 183	97.67 87	97.86 80	98.28 94	96.90 100

IterMVS-SCA-FT		95.16 148	93.95 160	96.56 135	97.89 135	96.69 156	96.94 157	96.05 159	93.06 136	97.35 59	98.79 62	91.45 182	95.93 108	92.78 188	91.00 192	95.22 185	93.91 170

HyFIR lowres test		95.05 149	93.54 165	96.81 123	97.81 145	96.88 150	98.18 90	97.46 110	94.28 110	94.98 155	96.57 123	92.89 176	96.15 103	90.90 203	91.87 188	96.28 177	91.35 184

CHOSEN 1792x2688		94.98 150	94.69 150	95.31 165	97.27 173	95.58 179	97.90 108	95.56 176	95.03 81	93.77 183	95.65 142	99.29 18	95.30 121	91.51 199	91.28 191	92.05 203	94.50 160

CANet_DTU		94.96 151	94.62 152	95.35 164	98.03 122	96.11 172	96.92 159	95.60 175	88.59 184	97.27 63	95.27 147	96.50 145	88.77 195	95.53 151	95.59 146	95.54 183	94.78 154

CDS-MVSNet		94.91 152	95.17 139	94.60 180	97.85 137	96.21 171	96.90 161	96.39 153	90.81 162	93.40 188	97.24 108	94.54 164	85.78 209	96.25 136	96.15 130	97.26 145	95.01 153
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
DPM-MVS		94.86 153	93.90 162	95.99 147	98.19 113	96.52 158	96.29 178	95.95 161	93.11 133	94.61 162	88.17 207	96.44 146	93.77 148	93.33 181	93.54 177	97.11 152	96.22 126

MS-PatchMatch		94.84 154	94.76 149	94.94 175	96.38 191	94.69 188	95.90 184	94.03 200	92.49 140	93.81 181	95.79 141	96.38 147	94.54 134	94.70 163	94.85 158	94.97 187	94.43 162

thisisatest0530		94.81 155	93.06 171	96.85 122	98.01 124	97.18 138	96.93 158	97.36 120	89.73 175	95.80 127	94.98 153	77.88 212	94.89 128	96.73 123	97.35 92	98.13 106	97.54 73

tttt0517		94.81 155	93.04 172	96.88 121	98.15 116	97.37 132	96.99 155	97.36 120	89.51 177	95.74 130	94.89 155	77.53 214	94.89 128	96.94 117	97.35 92	98.17 104	97.70 63

testgi		94.81 155	96.05 121	93.35 191	99.06 56	96.87 152	97.57 126	96.70 147	95.77 55	88.60 213	93.19 182	98.87 57	81.21 217	97.03 113	96.64 117	96.97 159	93.99 169

PatchMatch-RL		94.79 158	93.75 164	96.00 146	96.80 183	95.00 185	95.47 194	95.25 182	90.68 164	95.80 127	92.97 183	93.64 171	95.67 114	96.13 140	95.81 142	96.99 158	92.01 182

FPMVS		94.70 159	94.99 146	94.37 182	95.84 201	93.20 194	96.00 183	91.93 205	95.03 81	94.64 161	94.68 159	93.29 172	90.95 173	98.07 74	97.34 95	96.85 161	93.29 174

new-patchmatchnet		94.48 160	94.02 158	95.02 174	97.51 163	95.00 185	95.68 188	94.26 199	97.32 19	95.73 132	99.60 12	98.22 103	91.30 168	94.13 174	84.41 204	95.65 182	89.45 195

IterMVS		94.48 160	93.46 167	95.66 157	97.52 160	96.43 160	97.20 147	94.73 193	92.91 139	96.44 98	98.75 67	91.10 184	94.53 135	92.10 194	90.10 196	93.51 192	92.84 181
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MDTV_nov1_ep13_2view		94.39 162	93.34 168	95.63 158	97.23 175	95.33 182	97.76 114	96.84 140	94.55 100	97.47 53	98.96 47	97.70 118	93.88 145	92.27 192	86.81 202	90.56 205	87.73 203

Fast-Effi-MVS+-dtu		94.34 163	93.26 170	95.62 159	97.82 143	95.97 175	95.86 185	99.01 13	86.88 198	93.39 189	90.83 202	95.46 157	90.61 177	94.46 169	94.68 162	97.01 157	94.51 159

thres600view7		94.34 163	92.31 181	96.70 126	98.19 113	98.12 87	97.85 113	97.45 112	91.49 153	93.98 178	84.27 212	82.02 203	94.24 140	97.04 110	98.76 34	98.49 82	94.47 161

EPNet		94.33 165	93.52 166	95.27 167	98.81 72	94.71 187	96.77 162	98.20 57	88.12 190	96.53 95	92.53 187	91.19 183	85.25 213	95.22 158	95.26 153	96.09 180	97.63 70
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test2506		94.29 166	91.43 189	97.64 78	98.66 84	98.83 33	98.50 74	98.40 37	96.04 41	94.45 165	94.88 156	55.05 228	96.70 79	99.28 14	99.04 19	99.14 33	96.87 104

GA-MVS		94.18 167	92.98 173	95.58 160	97.36 168	96.42 161	96.21 179	95.86 165	90.29 168	95.08 151	96.19 131	85.37 195	92.82 161	94.01 176	94.14 167	96.16 179	94.41 163

gg-mvs-nofinetune		94.13 168	93.93 161	94.37 182	97.99 128	95.86 176	95.45 197	99.22 9	97.61 15	95.10 150	99.50 19	84.50 196	81.73 216	95.31 156	94.12 168	96.71 169	90.59 188

baseline		94.07 169	94.50 154	93.57 189	96.34 192	93.40 193	95.56 192	92.39 203	92.07 148	94.00 177	98.24 85	97.51 125	89.19 189	91.75 196	92.72 183	93.96 191	95.79 140

FMVSNet3		94.06 170	93.85 163	94.31 185	95.46 209	97.80 113	96.34 174	97.58 99	88.43 187	90.28 205	96.01 136	92.43 177	88.67 196	91.82 195	93.96 171	97.53 131	96.50 121

thres400		94.04 171	91.94 184	96.50 137	97.98 130	97.82 111	97.66 120	96.96 134	90.96 160	94.20 172	83.24 214	82.82 201	93.80 146	96.50 128	98.09 70	98.38 92	94.15 165

dmvs_re		94.02 172	92.39 179	95.91 150	97.71 150	95.43 181	97.00 154	95.94 162	82.49 215	94.61 162	83.69 213	93.01 175	92.71 162	97.83 79	97.56 87	97.50 133	96.73 110

CVMVSNet		94.01 173	94.25 156	93.73 188	94.36 212	92.44 197	97.45 132	88.56 209	95.59 60	93.06 195	98.88 55	90.03 190	94.84 130	94.08 175	93.45 178	94.09 189	95.31 151

thres200		93.98 174	91.90 185	96.40 140	97.66 151	98.12 87	97.20 147	97.45 112	90.16 171	93.82 180	83.08 215	83.74 199	93.80 146	97.04 110	97.48 90	98.49 82	93.70 171

baseline1		93.89 175	92.82 175	95.14 171	97.62 156	96.97 147	96.12 180	96.36 154	91.30 155	91.53 200	94.68 159	80.72 205	90.80 175	95.71 147	96.29 127	98.44 89	94.09 166

tfpn200view9		93.80 176	91.75 186	96.20 143	97.52 160	98.15 85	97.48 131	97.47 109	87.65 192	93.56 186	83.03 216	84.12 197	92.62 164	97.04 110	98.09 70	98.52 81	94.17 164

MIMVSNet		93.68 177	93.96 159	93.35 191	97.82 143	96.08 173	96.34 174	98.46 34	91.28 157	86.67 218	94.95 154	94.87 162	84.39 214	94.53 165	94.65 163	96.45 174	91.34 185

pmnet_mix02		93.59 178	92.65 176	94.69 178	96.76 187	94.16 190	97.03 153	93.00 202	95.79 53	96.03 119	98.91 52	97.69 119	92.99 156	90.03 206	84.10 206	92.35 201	87.89 202

EPNet_dtu		93.45 179	92.51 178	94.55 181	98.39 97	91.67 206	95.46 195	97.50 106	86.56 201	97.38 57	93.52 177	94.20 170	85.82 208	93.31 183	92.53 184	92.72 197	95.76 142
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IB-MVS	92.44 16	93.33 180	92.15 183	94.70 177	97.42 167	96.39 165	95.57 189	94.67 194	86.40 204	93.59 185	78.28 220	95.76 156	89.59 188	95.88 145	95.98 137	97.39 140	96.34 123
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		93.18 181	90.80 192	95.95 148	96.05 196	96.07 174	96.92 159	96.51 152	89.34 178	95.63 136	94.08 170	72.31 223	93.13 154	94.33 171	94.83 159	97.44 136	94.65 157

thres100view900		92.93 182	90.89 191	95.31 165	97.52 160	96.82 155	96.41 172	95.08 184	87.65 192	93.56 186	83.03 216	84.12 197	91.12 171	94.53 165	96.91 107	98.17 104	93.21 176

N_pmnet		92.46 183	92.38 180	92.55 197	97.91 134	93.47 192	97.42 134	94.01 201	96.40 34	88.48 214	98.50 75	98.07 107	88.14 198	91.04 202	84.30 205	89.35 210	84.85 209

TAMVS		92.46 183	93.34 168	91.44 205	97.03 178	93.84 191	94.68 208	90.60 207	90.44 167	85.31 219	97.14 111	93.03 174	85.78 209	94.34 170	93.67 174	95.22 185	90.93 187

CMPMVS	71.81 19	92.34 185	92.85 174	91.75 203	92.70 217	90.43 211	88.84 220	88.56 209	85.87 205	94.35 169	90.98 200	95.89 155	91.14 170	96.14 139	94.83 159	94.93 188	95.78 141
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
baseline2		92.06 186	89.82 195	94.68 179	97.32 169	95.72 177	94.97 205	95.08 184	84.75 209	94.34 171	90.68 205	77.75 213	90.13 182	93.38 179	93.58 176	96.25 178	92.90 180

MVSTER		91.97 187	90.31 193	93.91 186	96.81 182	96.91 149	94.22 209	95.64 174	84.98 207	92.98 196	93.42 178	72.56 221	86.64 207	95.11 159	93.89 173	97.16 151	95.31 151

CR-MVSNet		91.94 188	88.50 198	95.94 149	96.14 194	92.08 201	95.23 200	98.47 32	84.30 211	96.44 98	94.58 162	75.57 215	92.92 158	90.22 204	92.22 185	96.43 175	90.56 189

gm-plane-assit		91.85 189	87.91 200	96.44 139	99.14 45	98.25 76	99.02 31	97.38 118	95.57 62	98.31 25	99.34 31	51.00 229	88.93 192	93.16 185	91.57 189	95.85 181	86.50 206

PMMVS		91.67 190	91.47 188	91.91 202	89.43 222	88.61 217	94.99 204	85.67 214	87.50 194	93.80 182	94.42 168	94.88 161	90.71 176	92.26 193	92.96 181	96.83 164	89.65 193

CHOSEN 280x420		91.55 191	90.27 194	93.05 194	94.61 211	88.01 218	96.56 169	94.62 196	88.04 191	94.20 172	92.66 186	86.60 193	90.82 174	95.06 161	91.89 187	87.49 215	89.61 194

PatchT		91.40 192	88.54 197	94.74 176	91.48 221	92.18 200	97.42 134	97.51 104	84.96 208	96.44 98	94.16 169	75.47 216	92.92 158	90.22 204	92.22 185	92.66 200	90.56 189

pmmvs3		91.20 193	91.40 190	90.96 207	91.71 220	91.08 207	95.41 198	81.34 218	87.36 195	94.57 164	95.02 151	94.30 167	90.42 178	94.28 172	89.26 198	92.30 202	88.49 200

test0.0.03 1		91.17 194	91.50 187	90.80 208	98.01 124	95.46 180	94.22 209	95.80 169	86.55 202	81.75 221	90.83 202	87.93 192	78.48 218	94.51 168	94.11 169	96.50 172	91.08 186

SCA		91.15 195	87.65 202	95.23 170	96.15 193	95.68 178	96.68 166	98.18 61	90.46 166	97.21 66	92.44 189	80.17 207	93.51 152	86.04 213	83.58 209	89.68 209	85.21 208

new_pmnet		90.85 196	92.26 182	89.21 211	93.68 216	89.05 216	93.20 217	84.16 217	92.99 137	84.25 220	97.72 95	94.60 163	86.80 206	93.20 184	91.30 190	93.21 193	86.94 205

RPMNet		90.52 197	86.27 211	95.48 162	95.95 199	92.08 201	95.55 193	98.12 66	84.30 211	95.60 138	87.49 210	72.78 220	91.24 169	87.93 208	89.34 197	96.41 176	89.98 192

MDTV_nov1_ep13		90.30 198	87.32 206	93.78 187	96.00 198	92.97 195	95.46 195	95.39 179	88.61 183	95.41 142	94.45 167	80.39 206	89.87 186	86.58 211	83.54 210	90.56 205	84.71 210

PatchmatchNet		89.98 199	86.23 212	94.36 184	96.56 189	91.90 205	96.07 181	96.72 145	90.18 170	96.87 80	93.36 181	78.06 211	91.46 167	84.71 217	81.40 214	88.45 212	83.97 214
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ADS-MVSNet		89.89 200	87.70 201	92.43 199	95.52 206	90.91 209	95.57 189	95.33 180	93.19 130	91.21 202	93.41 179	82.12 202	89.05 190	86.21 212	83.77 208	87.92 213	84.31 211

tpm		89.84 201	86.81 208	93.36 190	96.60 188	91.92 204	95.02 203	97.39 117	86.79 199	96.54 94	95.03 150	69.70 224	87.66 200	88.79 207	86.19 203	86.95 217	89.27 196

test-LLR		89.77 202	87.47 204	92.45 198	98.01 124	89.77 213	93.25 215	95.80 169	81.56 217	89.19 209	92.08 192	79.59 208	85.77 211	91.47 200	89.04 200	92.69 198	88.75 197

FMVSNet5		89.65 203	87.60 203	92.04 201	95.63 205	96.61 157	94.82 207	94.75 191	80.11 221	87.72 216	77.73 221	73.81 219	83.81 215	95.64 148	96.08 135	95.49 184	93.21 176

EPMVS		89.28 204	86.28 210	92.79 196	96.01 197	92.00 203	95.83 186	95.85 167	90.78 163	91.00 203	94.58 162	74.65 217	88.93 192	85.00 215	82.88 212	89.09 211	84.09 213

test-mter		89.16 205	88.14 199	90.37 209	94.79 210	91.05 208	93.60 214	85.26 215	81.65 216	88.32 215	92.22 190	79.35 210	87.03 204	92.28 191	90.12 195	93.19 194	90.29 191

CostFormer		89.06 206	85.65 213	93.03 195	95.88 200	92.40 198	95.30 199	95.86 165	86.49 203	93.12 194	93.40 180	74.18 218	88.25 197	82.99 218	81.46 213	89.77 208	88.66 199

MVS-HIRNet		88.72 207	86.49 209	91.33 206	91.81 219	85.66 219	87.02 222	96.25 155	81.48 219	94.82 157	96.31 130	92.14 180	90.32 180	87.60 209	83.82 207	87.74 214	78.42 218

TESTMET0.1,1		88.60 208	87.47 204	89.93 210	94.23 214	89.77 213	93.25 215	84.47 216	81.56 217	89.19 209	92.08 192	79.59 208	85.77 211	91.47 200	89.04 200	92.69 198	88.75 197

dps		88.36 209	84.32 216	93.07 193	93.86 215	92.29 199	94.89 206	95.93 163	83.50 213	93.13 192	91.87 194	67.79 226	90.32 180	85.99 214	83.22 211	90.28 207	85.56 207

tpmrst		87.60 210	84.13 217	91.66 204	95.65 204	89.73 215	93.77 212	94.74 192	88.85 180	93.35 191	95.60 143	72.37 222	87.40 201	81.24 219	78.19 216	85.02 220	82.90 217

tpm cat1		87.19 211	82.78 218	92.33 200	95.66 203	90.61 210	94.19 211	95.27 181	86.97 197	94.38 167	90.91 201	69.40 225	87.21 202	79.57 221	77.82 217	87.25 216	84.18 212

E-PMN		86.94 212	85.10 214	89.09 213	95.77 202	83.54 222	89.89 219	86.55 211	92.18 146	87.34 217	94.02 171	83.42 200	89.63 187	93.32 182	77.11 218	85.33 218	72.09 219

EMVS		86.63 213	84.48 215	89.15 212	95.51 207	83.66 221	90.19 218	86.14 213	91.78 150	88.68 212	93.83 175	81.97 204	89.05 190	92.76 189	76.09 219	85.31 219	71.28 220

PMMVS2		86.47 214	92.62 177	79.29 215	92.01 218	85.63 220	93.74 213	86.37 212	93.95 120	54.18 226	98.19 86	97.39 128	58.46 219	96.57 127	93.07 180	90.99 204	83.55 216

MVE	72.99 18	85.37 215	89.43 196	80.63 214	74.43 223	71.94 224	88.25 221	89.81 208	93.27 128	67.32 224	96.32 129	91.83 181	90.40 179	93.36 180	90.79 193	73.55 223	88.49 200
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		61.30 216	70.45 219	50.62 216	22.69 225	30.92 226	68.31 225	25.76 220	80.56 220	68.71 222	82.80 218	91.08 185	44.64 220	80.50 220	56.70 220	73.64 222	70.58 221

GG-mvs-BLEND		61.03 217	87.02 207	30.71 218	0.74 228	90.01 212	78.90 224	0.74 224	84.56 210	9.46 227	79.17 219	90.69 188	1.37 224	91.74 197	89.13 199	93.04 196	83.83 215

testmvs		4.99 218	6.88 220	2.78 220	1.73 226	2.04 228	3.10 228	1.71 222	7.27 223	3.92 229	12.18 223	6.71 230	3.31 223	6.94 222	5.51 222	2.94 225	7.51 222

test123		4.41 219	5.71 221	2.88 219	1.28 227	2.21 227	3.09 229	1.65 223	6.35 224	4.98 228	8.53 224	3.88 231	3.46 222	5.79 223	5.71 221	2.85 226	7.50 223

uanet_test		0.00 220	0.00 222	0.00 221	0.00 229	0.00 229	0.00 230	0.00 225	0.00 225	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet-low-res		0.00 220	0.00 222	0.00 221	0.00 229	0.00 229	0.00 230	0.00 225	0.00 225	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet		0.00 220	0.00 222	0.00 221	0.00 229	0.00 229	0.00 230	0.00 225	0.00 225	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

TPM-MVS					97.49 164	96.32 169	95.05 202			94.36 168	91.82 195	96.92 140	88.89 194			96.67 170	96.22 126

RE-MVS-def										99.38 2

9.14												96.98 138

SR-MVS					99.33 30			98.40 37				98.90 53

Anonymous202405211			97.39 66		98.85 68	98.59 57	97.89 110	97.93 81	94.41 107		97.37 105	96.99 137	93.09 155	98.61 51	98.46 46	99.11 38	97.27 88

our_test_3					97.32 169	95.13 184	97.59 125

ambc			96.78 103		99.01 58	97.11 144	95.73 187		95.91 48	99.25 3	98.56 74	97.17 133	97.04 69	96.76 122	95.22 154	96.72 168	96.73 110

MTAPA										97.43 56		99.27 22

MTMP										97.63 47		99.03 41

Patchmatch-RL test							17.42 227

tmp_tt				45.72 217	60.00 224	38.74 225	45.50 226	12.18 221	79.58 222	68.42 223	67.62 222	65.04 227	22.12 221	84.83 216	78.72 215	66.08 224

XVS					99.48 18	98.76 44	99.22 21			96.40 102		98.78 68				98.94 55

X-MVStestdata					99.48 18	98.76 44	99.22 21			96.40 102		98.78 68				98.94 55

mPP-MVS					99.58 6							98.98 45

NP-MVS									89.27 179

Patchmtry						92.70 196	95.23 200	98.47 32		96.44 98

DeepMVS_CX						72.99 223	80.14 223	37.34 219	83.46 214	60.13 225	84.40 211	85.48 194	86.93 205	87.22 210		79.61 221	87.32 204

High-resolution multi-view benchmark