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 44	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 71	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 16	98.47 22	99.71 5	99.05 60	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 52	98.83 14	99.46 21	99.09 52	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 44	98.65 17	99.43 25	99.33 26	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 55	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 75	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 35	98.52 19	99.36 34	98.98 67	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 65	99.05 19	99.58 7	98.29 49	98.96 4	97.96 36	99.40 31	98.67 103	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 59	98.37 24	99.34 37	99.09 52	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 67	99.37 4	98.87 5	97.86 38	99.27 43	99.78 2	96.59 87	99.52 6	99.40 6	99.67 2	98.21 44

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 93	98.77 16	99.11 58	98.64 107	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 85	98.20 91	99.68 1	97.35 133	97.09 32	98.98 10	99.86 1	99.43 19	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	98.32 107	98.92 25	98.57 75	99.03 12	99.36 1	96.86 85	99.77 3	99.86 1	96.20 104	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 70	99.01 21	99.58 7	98.10 68	98.67 6	97.30 61	99.18 50	99.42 20	98.40 19	99.19 21	98.86 30	98.99 48	98.19 45
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 48	98.79 41	99.30 17	97.67 99	98.33 8	97.82 40	99.20 48	99.18 47	98.76 6	99.27 17	98.96 22	99.29 27	98.03 50
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 77	99.24 8	96.04 60	97.12 70	98.44 107	98.95 72	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 69	99.01 36	98.17 63	97.17 31	98.25 27	99.56 15	99.62 5	98.29 22	98.40 64	98.09 72	98.97 50	98.08 48
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 33	98.72 17	99.32 31	99.06 17	98.99 37	98.89 14	95.52 94	97.53 49	99.42 30	98.83 88	98.01 34	98.55 55	98.34 58	99.57 8	97.80 63

CSCG		98.45 18	98.61 19	98.26 37	99.11 52	99.06 17	98.17 107	97.49 112	97.93 13	97.37 58	98.88 77	99.29 30	98.10 29	98.40 64	97.51 97	99.32 25	99.16 4

DVP-MVS++		98.44 20	98.92 10	97.88 63	99.17 41	99.00 22	98.89 49	98.26 51	97.54 19	96.05 124	99.35 35	99.76 3	96.34 99	98.79 37	98.65 41	98.56 81	99.35 2

Gipuma		98.43 21	98.15 36	98.76 14	99.00 64	98.29 84	97.91 127	98.06 70	99.02 3	99.50 1	96.33 165	98.67 103	99.22 1	99.02 27	98.02 78	98.88 63	97.66 71
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 67	98.84 34	99.30 17	97.86 90	97.78 15	94.19 203	98.77 89	99.39 22	98.61 11	99.33 13	99.07 14	99.33 23	97.81 62

ACMMPR		98.31 23	98.07 41	98.60 23	99.58 6	98.83 35	99.09 27	98.48 31	96.25 55	97.03 74	96.81 153	99.09 52	98.39 20	98.55 55	98.45 49	99.01 45	98.53 30

APDe-MVS		98.29 24	98.42 27	98.14 40	99.45 21	98.90 26	99.18 23	98.30 47	95.96 67	95.13 168	98.79 86	99.25 39	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 41	99.03 20	99.07 30	98.17 63	96.75 41	94.35 197	98.92 72	99.58 7	97.86 41	98.67 46	98.70 37	98.63 75	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 79	98.22 122	98.73 53	98.66 70	98.03 75	98.60 7	96.40 108	99.60 12	98.24 129	95.26 148	99.19 21	99.05 17	99.36 20	97.64 72

DU-MVS		98.23 26	97.74 62	98.81 12	99.23 34	98.77 44	98.76 61	98.88 15	94.10 146	98.50 20	98.87 79	98.32 126	97.99 35	98.40 64	98.08 75	99.49 16	97.64 72

UniMVSNet (Re)		98.23 26	97.85 51	98.67 19	99.15 45	98.87 28	98.74 64	98.84 17	94.27 144	97.94 37	99.01 64	98.39 122	97.82 42	98.35 69	98.29 63	99.51 15	97.78 64

MIMVSNet1		98.22 29	98.51 23	97.87 64	99.40 25	98.82 39	99.31 16	98.53 28	97.39 22	96.59 99	99.31 39	99.23 41	94.76 167	98.93 32	98.67 39	98.63 75	97.25 96

HFP-MVS		98.17 30	98.02 42	98.35 35	99.36 27	98.62 61	98.79 60	98.46 34	96.24 56	96.53 101	97.13 148	98.98 67	98.02 33	98.20 72	98.42 51	98.95 54	98.54 28

Baseline_NR-MVSNet		98.17 30	97.90 48	98.48 29	99.23 34	98.59 62	98.83 57	98.73 24	93.97 153	96.95 77	99.66 7	98.23 131	97.90 39	98.40 64	99.06 16	99.25 29	97.42 87

MED-MVS		98.16 32	98.49 24	97.77 74	99.17 41	98.85 30	98.51 79	97.93 82	97.26 26	95.03 174	99.43 25	99.08 55	97.16 66	98.47 62	98.42 51	98.85 66	97.91 58

TSAR-MVS + MP.		98.15 33	98.23 31	98.06 51	98.47 97	98.16 96	99.23 20	96.87 160	95.58 88	96.72 91	98.41 108	99.06 57	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 34	98.66 18	97.53 88	97.93 154	98.49 72	98.14 110	98.19 59	97.95 12	96.17 119	99.63 10	98.85 84	95.41 137	98.91 33	98.89 27	99.34 22	97.86 61

SMA-MVS		98.13 35	98.22 33	98.02 56	99.44 23	98.73 53	98.24 102	97.87 89	95.22 102	96.76 90	98.66 97	99.35 24	97.03 72	98.53 58	98.39 54	98.80 69	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 36	98.08 40	98.18 39	99.34 28	98.74 52	98.97 39	98.00 77	95.13 106	96.90 79	97.54 136	99.27 34	97.18 65	98.72 42	98.45 49	98.68 74	98.69 18

UniMVSNet_NR-MVSNet		98.12 36	97.56 72	98.78 13	99.13 50	98.89 27	98.76 61	98.78 20	93.81 156	98.50 20	98.81 84	97.64 155	97.99 35	98.18 75	97.92 81	99.53 10	97.64 72

ACMM	94.29 11	98.12 36	97.71 63	98.59 24	99.51 16	98.58 64	99.24 19	98.25 52	96.22 57	96.90 79	95.01 194	98.89 78	98.52 16	98.66 48	98.32 61	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 39	97.78 57	98.39 33	99.54 10	98.79 41	98.94 43	98.42 36	93.98 151	95.85 134	96.66 159	99.25 39	98.61 11	98.71 44	98.38 55	98.97 50	98.67 21
Skip Steuart: Steuart Systems R&D Blog.
SED-MVS		98.05 40	98.46 26	97.57 84	99.01 61	98.99 23	98.82 59	98.24 53	95.76 77	94.70 187	98.96 67	99.49 15	96.19 105	98.74 38	98.65 41	98.46 90	98.63 22

OPM-MVS		98.01 41	98.01 43	98.00 58	99.11 52	98.12 101	98.68 68	97.72 97	96.65 46	96.68 95	98.40 110	99.28 33	97.44 55	98.20 72	97.82 89	98.40 97	97.58 77
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet		98.01 41	98.42 27	97.54 87	96.89 218	98.82 39	99.14 24	97.59 102	96.30 54	97.04 73	99.26 46	98.83 88	96.01 114	98.73 40	98.21 65	98.58 80	98.75 15
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS		98.00 43	97.38 80	98.73 15	98.72 80	99.15 11	99.12 26	98.76 21	91.58 195	98.15 31	96.70 157	98.72 101	98.20 24	98.64 51	98.92 24	99.43 19	97.97 53

NR-MVSNet		98.00 43	97.88 49	98.13 41	98.33 105	98.77 44	98.83 57	98.88 15	94.10 146	97.46 55	98.87 79	98.58 112	95.78 119	99.13 25	98.16 69	99.52 12	97.53 80

CP-MVS		98.00 43	97.57 71	98.50 26	99.47 20	98.56 66	98.91 47	98.38 42	94.71 123	97.01 75	95.20 190	99.06 57	98.20 24	98.61 52	98.46 46	99.02 43	98.40 35

DPE-MVS		97.99 46	98.12 37	97.84 67	98.65 90	98.86 29	98.86 53	98.05 73	94.18 145	95.49 157	98.90 75	99.33 26	97.11 68	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 46	97.60 70	98.45 31	99.53 14	98.83 35	99.13 25	98.30 47	94.57 130	96.39 112	95.32 188	98.95 72	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 48	97.53 73	98.50 26	99.56 8	98.58 64	98.97 39	98.39 41	93.49 160	97.14 67	96.08 172	99.23 41	98.06 31	98.50 60	98.38 55	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 48	97.92 46	98.04 53	98.84 73	98.04 111	97.90 128	96.83 164	95.07 108	98.79 15	99.07 60	99.37 23	97.88 40	98.74 38	98.16 69	98.01 123	96.96 104

ACMP	94.03 12	97.97 50	97.61 69	98.39 33	99.43 24	98.51 71	98.97 39	98.06 70	94.63 128	96.10 121	96.12 171	99.20 45	98.63 9	98.68 45	98.20 68	99.14 33	97.93 56
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SPE-MVS-test		97.96 51	97.38 80	98.64 21	98.57 92	99.13 12	99.36 13	98.66 25	91.67 194	98.17 30	96.91 152	98.84 86	97.99 35	98.80 35	98.88 28	99.08 41	97.43 86

LGP-MVS_train		97.96 51	97.53 73	98.45 31	99.45 21	98.64 59	99.09 27	98.27 50	92.99 174	96.04 125	96.57 160	99.29 30	98.66 8	98.73 40	98.42 51	99.19 31	98.09 47

aaEdge-Enhanced		97.94 53	98.23 31	97.60 82	99.15 45	98.85 30	98.92 44	97.17 143	96.03 64	94.88 181	99.43 25	99.18 47	97.31 62	98.07 77	98.14 71	98.14 114	97.91 58

LS3D		97.93 54	97.80 53	98.08 47	99.20 38	98.77 44	98.89 49	97.92 84	96.59 47	96.99 76	96.71 156	97.14 169	96.39 98	99.04 26	98.96 22	99.10 40	97.39 88

SD-MVS		97.84 55	97.78 57	97.90 61	98.33 105	98.06 106	97.95 122	97.80 94	96.03 64	96.72 91	97.57 134	99.18 47	97.50 53	97.88 80	97.08 111	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 56	98.27 29	97.31 104	98.23 120	98.06 106	97.44 165	95.79 199	96.90 36	95.81 138	98.76 90	98.61 111	97.70 47	98.90 34	98.36 57	98.90 58	98.29 38

thisisatest0515		97.82 57	97.67 64	97.99 59	98.49 96	98.07 105	98.48 87	98.06 70	95.35 99	97.74 42	98.83 82	97.61 156	96.74 79	97.53 102	98.30 62	98.43 96	98.01 52

PGM-MVS		97.82 57	97.25 90	98.48 29	99.54 10	98.75 51	99.02 32	98.35 45	92.41 179	96.84 86	95.39 187	98.99 66	98.24 23	98.43 63	98.34 58	98.90 58	98.41 34

PMVS	90.51 17	97.77 59	97.98 44	97.53 88	98.68 86	98.14 100	97.67 147	97.03 154	96.43 48	98.38 23	98.72 93	97.03 172	94.44 173	99.37 12	99.30 10	98.98 49	96.86 112
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FE-MVSNET2		97.75 60	97.79 54	97.70 78	97.41 196	98.37 79	99.09 27	97.73 96	96.88 37	97.47 52	99.43 25	99.35 24	96.00 115	96.66 142	97.74 91	98.48 88	96.10 145

MSP-MVS		97.67 61	97.88 49	97.43 95	99.34 28	98.99 23	98.87 52	98.12 66	95.63 83	94.16 206	97.45 137	99.50 14	96.44 97	96.35 148	98.70 37	97.65 155	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 62	97.79 54	97.52 90	98.32 107	98.53 68	98.45 90	97.69 98	97.59 18	96.12 120	97.79 127	96.70 177	95.69 124	98.35 69	98.34 58	98.85 66	97.22 99

FC-MVSNet-train		97.65 63	98.16 35	97.05 122	98.85 71	98.85 30	99.34 14	98.08 69	94.50 135	94.41 194	99.21 47	98.80 93	92.66 206	98.98 30	98.85 31	98.96 52	97.94 55

v10		97.64 64	97.26 88	98.08 47	98.07 141	98.56 66	98.86 53	98.18 61	94.48 136	98.24 28	99.56 15	98.98 67	97.72 46	96.05 162	96.26 143	97.42 167	96.93 105

EC-MVSNet		97.63 65	96.88 119	98.50 26	98.74 79	99.16 10	99.33 15	98.83 18	88.77 227	96.62 98	96.48 162	97.75 148	98.19 26	99.00 28	98.76 34	99.29 27	98.27 42

X-MVS		97.60 66	97.00 111	98.29 36	99.50 17	98.76 47	98.90 48	98.37 43	94.67 127	96.40 108	91.47 242	98.78 95	97.60 52	98.55 55	98.50 44	98.96 52	98.29 38

Casviewmamba		97.58 67	97.98 44	97.11 117	98.13 136	98.52 69	98.51 79	97.40 124	96.76 40	93.79 216	99.18 50	99.19 46	96.13 109	97.73 90	97.56 95	98.69 73	96.92 106

E6new		97.58 67	97.78 57	97.34 99	98.30 112	98.16 96	98.50 81	97.36 129	97.45 20	95.96 128	99.46 21	99.57 8	96.03 111	96.88 132	96.67 128	97.88 135	96.30 134

E6		97.58 67	97.78 57	97.34 99	98.30 112	98.16 96	98.50 81	97.36 129	97.45 20	95.96 128	99.46 21	99.57 8	96.03 111	96.88 132	96.67 128	97.88 135	96.30 134

3Dnovator+	96.20 4	97.58 67	97.14 102	98.10 42	98.98 66	97.85 129	98.60 74	98.33 46	96.41 50	97.23 65	94.66 203	97.26 165	96.91 76	97.91 79	97.87 84	98.53 84	98.03 50

DCV-MVSNet		97.56 71	97.63 68	97.47 93	98.41 101	99.12 13	98.63 71	98.57 26	95.71 80	95.60 153	93.79 220	98.01 142	94.25 175	99.16 23	98.88 28	99.35 21	98.74 16

HPM-MVS++		97.56 71	97.11 106	98.09 43	99.18 40	97.95 120	98.57 75	98.20 57	94.08 149	97.25 64	95.96 178	98.81 92	97.13 67	97.51 103	97.30 107	98.21 109	98.15 46

FC-MVSNet-test		97.54 73	98.26 30	96.70 148	98.87 69	97.79 138	98.49 85	98.56 27	96.04 60	90.39 253	99.65 8	98.67 103	95.15 153	99.23 19	99.07 14	98.73 72	97.39 88

TSAR-MVS + ACMM		97.54 73	97.79 54	97.26 105	98.23 120	98.10 104	97.71 141	97.88 88	95.97 66	95.57 155	98.71 94	98.57 113	97.36 58	97.74 89	96.81 121	96.83 198	98.59 25

casdiffseed414692147		97.53 75	97.64 67	97.41 96	98.18 131	98.22 89	98.63 71	97.45 117	95.90 69	95.35 160	99.20 48	99.51 12	96.45 96	97.32 113	96.81 121	98.39 98	96.53 127

DeepC-MVS_fast	95.38 6	97.53 75	97.30 87	97.79 72	98.83 74	97.64 142	98.18 105	97.14 147	95.57 89	97.83 39	97.10 149	98.80 93	96.53 93	97.41 106	97.32 105	98.24 108	97.26 95
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 77	97.03 110	98.09 43	98.31 110	98.01 115	98.96 42	97.25 138	95.22 102	98.89 12	99.64 9	98.83 88	97.68 48	95.63 176	95.91 159	97.47 163	95.97 154

v1144		97.51 78	97.05 109	98.04 53	98.26 118	97.98 117	98.88 51	97.42 123	95.38 98	98.56 18	99.59 14	99.01 64	97.65 49	95.77 172	96.06 153	97.47 163	95.56 174

v8		97.51 78	97.16 100	97.91 60	97.99 150	98.48 73	98.76 61	98.17 63	94.54 134	97.69 44	99.48 20	98.76 98	97.63 51	96.10 159	96.14 147	97.20 180	96.64 120

v1921920		97.50 80	97.00 111	98.07 49	98.20 126	97.94 125	99.03 31	97.06 152	95.29 101	99.01 9	99.62 11	98.73 100	97.74 45	95.52 182	95.78 168	97.39 169	96.12 143

Anonymous20231211		97.49 81	97.91 47	97.00 128	98.31 110	98.72 55	98.27 99	97.84 92	94.76 122	94.77 186	98.14 119	98.38 124	93.60 190	98.96 31	98.66 40	99.22 30	97.77 66

v144192		97.49 81	96.99 113	98.07 49	98.11 138	97.95 120	99.02 32	97.21 141	94.90 117	98.88 13	99.53 17	98.89 78	97.75 44	95.59 179	95.90 160	97.43 166	96.16 141

test1111		97.48 83	97.20 95	97.81 71	98.78 77	98.85 30	98.68 68	98.40 37	96.68 44	94.84 182	99.13 54	90.32 234	97.01 73	99.27 17	99.05 17	99.19 31	97.10 101

GeoE		97.48 83	96.84 124	98.22 38	99.01 61	98.39 76	98.85 56	98.76 21	92.37 180	97.53 49	97.58 133	98.23 131	97.11 68	97.57 101	96.98 115	98.10 118	96.78 115

APD-MVS		97.47 85	97.16 100	97.84 67	99.32 31	98.39 76	98.47 89	98.21 56	92.08 186	95.23 164	96.68 158	98.90 76	96.99 74	98.20 72	98.21 65	98.80 69	97.67 70
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PVSNet_Blended_VisFu		97.44 86	97.14 102	97.79 72	99.15 45	98.44 74	98.32 96	97.66 100	93.74 159	97.73 43	98.79 86	96.93 175	95.64 129	97.69 92	96.91 118	98.25 107	97.50 82

PHI-MVS		97.44 86	97.17 99	97.74 76	98.14 133	98.41 75	98.03 118	97.50 110	92.07 187	98.01 35	97.33 141	98.62 110	96.02 113	98.34 71	98.21 65	98.76 71	97.24 98

v1240		97.43 88	96.87 123	98.09 43	98.25 119	97.92 126	99.02 32	97.06 152	94.77 121	99.09 8	99.68 6	98.51 117	97.78 43	95.25 189	95.81 166	97.32 175	96.13 142

viewmacassd2359aftdt		97.42 89	97.67 64	97.13 114	98.20 126	98.06 106	98.16 108	97.16 146	97.27 25	95.23 164	99.29 40	99.48 16	96.05 110	96.73 137	96.66 130	98.00 124	96.17 140

ECVR-MVS		97.40 90	97.11 106	97.73 77	98.66 87	98.83 35	98.50 81	98.40 37	96.04 60	95.00 177	98.95 69	91.07 231	96.70 81	99.28 14	99.04 19	99.14 33	96.58 122

FMVSNet1		97.40 90	98.09 38	96.60 154	97.80 169	98.76 47	98.26 101	98.50 30	96.79 39	93.13 228	99.28 42	98.64 107	92.90 203	97.67 94	97.86 86	99.02 43	97.64 72

MGCNet		97.38 92	97.26 88	97.51 91	99.28 33	98.79 41	98.86 53	97.79 95	94.68 125	96.79 87	97.69 129	95.75 194	93.91 183	98.10 76	97.76 90	98.45 91	98.08 48

E4		97.37 93	97.52 75	97.20 110	98.29 115	98.05 110	98.27 99	97.33 134	97.28 24	95.81 138	99.29 40	99.51 12	95.64 129	96.20 155	96.24 145	97.89 134	96.07 146

casdiffmvs_mvg		97.34 94	97.65 66	96.97 129	97.74 172	98.33 81	98.45 90	97.18 142	95.81 73	93.92 212	99.04 62	99.05 60	95.48 135	97.00 128	97.71 94	99.07 42	96.63 121
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 95	96.84 124	97.90 61	98.19 128	97.83 130	98.74 64	97.44 120	95.42 97	98.23 29	99.46 21	98.84 86	97.46 54	95.51 183	96.10 150	97.36 172	94.72 191

EPP-MVSNet		97.29 96	96.88 119	97.76 75	98.70 82	99.10 16	98.92 44	98.36 44	95.12 107	93.36 226	97.39 138	91.00 232	97.65 49	98.72 42	98.91 25	99.58 7	97.92 57

hybridcas		97.27 97	97.75 61	96.71 146	97.88 159	98.23 88	98.29 97	97.11 150	96.86 38	92.95 236	99.18 50	99.12 51	95.74 120	97.22 116	97.27 109	98.30 101	96.36 131

MVS_111021_HR		97.27 97	97.11 106	97.46 94	98.46 98	97.82 134	97.50 161	96.86 161	94.97 112	97.13 69	96.99 150	98.39 122	96.82 78	97.65 98	97.38 100	98.02 122	96.56 125

E5new		97.26 99	97.38 80	97.13 114	98.29 115	98.02 112	98.19 103	97.24 139	97.21 28	95.82 136	99.13 54	99.44 17	95.39 141	95.81 169	95.99 154	97.83 139	96.05 147

E5		97.26 99	97.38 80	97.13 114	98.29 115	98.02 112	98.19 103	97.24 139	97.21 28	95.82 136	99.13 54	99.44 17	95.39 141	95.81 169	95.99 154	97.83 139	96.05 147

SF-MVS		97.26 99	97.43 78	97.05 122	98.80 76	97.83 130	96.02 226	97.44 120	94.98 111	95.74 143	97.16 146	98.45 121	95.72 122	97.85 81	97.97 80	98.60 78	97.78 64

TSAR-MVS + GP.		97.26 99	97.33 86	97.18 111	98.21 123	98.06 106	96.38 217	97.66 100	93.92 155	95.23 164	98.48 104	98.33 125	97.41 56	97.63 99	97.35 101	98.18 111	97.57 78

OMC-MVS		97.23 103	97.21 94	97.25 108	97.85 160	97.52 152	97.92 126	95.77 200	95.83 72	97.09 72	97.86 125	98.52 116	96.62 85	97.51 103	96.65 131	98.26 105	96.57 123

3Dnovator	96.31 3	97.22 104	97.19 97	97.25 108	98.14 133	97.95 120	98.03 118	96.77 169	96.42 49	97.14 67	95.11 191	97.59 157	95.14 155	97.79 86	97.72 92	98.26 105	97.76 68

usedtu_dtu_shiyan2		97.20 105	97.35 85	97.03 124	99.23 34	98.25 85	98.34 94	97.49 112	97.86 14	95.90 131	98.27 115	99.30 29	93.22 196	97.41 106	96.26 143	97.99 127	94.14 202

E3new		97.13 106	97.22 92	97.03 124	98.21 123	97.95 120	98.09 111	97.13 148	96.71 42	95.63 150	99.01 64	99.27 34	95.38 143	95.82 168	95.86 164	97.73 147	95.90 156

E3		97.13 106	97.22 92	97.03 124	98.21 123	97.95 120	98.09 111	97.13 148	96.70 43	95.64 149	99.02 63	99.27 34	95.38 143	95.81 169	95.86 164	97.73 147	95.90 156

sasdasda		97.11 108	96.88 119	97.38 97	98.34 103	98.72 55	97.52 159	97.94 80	95.60 85	95.01 175	94.58 205	94.50 204	96.59 87	97.84 82	98.03 76	98.90 58	98.91 9

canonicalmvs		97.11 108	96.88 119	97.38 97	98.34 103	98.72 55	97.52 159	97.94 80	95.60 85	95.01 175	94.58 205	94.50 204	96.59 87	97.84 82	98.03 76	98.90 58	98.91 9

V42		97.10 110	96.97 114	97.26 105	97.64 176	97.60 144	98.45 90	95.99 188	94.44 137	97.35 59	99.40 31	98.63 109	97.34 60	96.33 151	96.38 140	96.82 200	96.00 151

CPTT-MVS		97.08 111	96.25 144	98.05 52	99.21 37	98.30 83	98.54 78	97.98 78	94.28 142	95.89 133	89.57 251	98.54 114	98.18 27	97.82 85	97.32 105	98.54 82	97.91 58

DeepPCF-MVS	94.55 10	97.05 112	97.13 105	96.95 131	96.06 236	97.12 171	98.01 120	95.44 211	95.18 104	97.50 51	97.86 125	98.08 137	97.31 62	97.23 115	97.00 114	97.36 172	97.45 84

QAPM		97.04 113	97.14 102	96.93 133	97.78 171	98.02 112	97.36 175	96.72 171	94.68 125	96.23 114	97.21 143	97.68 153	95.70 123	97.37 108	97.24 110	97.78 145	97.77 66

CNVR-MVS		97.03 114	96.77 130	97.34 99	98.89 68	97.67 141	97.64 150	97.17 143	94.40 140	95.70 147	94.02 215	98.76 98	96.49 95	97.78 87	97.29 108	98.12 117	97.47 83

viewmanbaseed2359cas		97.01 115	97.20 95	96.79 143	98.06 142	97.90 127	97.80 134	96.78 168	96.34 53	94.82 183	98.80 85	99.15 50	95.50 134	96.14 156	96.07 152	97.79 143	96.00 151

casdiffmvs		97.00 116	97.36 84	96.59 155	97.65 175	97.98 117	98.06 114	96.81 165	95.78 75	92.77 239	99.40 31	99.26 38	95.65 128	96.70 139	96.39 139	98.59 79	95.99 153
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		96.99 117	96.70 134	97.34 99	97.89 157	97.23 163	98.33 95	96.96 156	95.57 89	97.12 70	98.99 66	99.40 21	97.23 64	96.22 154	95.45 175	96.50 208	94.02 205

viewdifsd2359ckpt09		96.95 118	96.77 130	97.15 113	98.55 94	98.24 87	97.80 134	97.30 136	94.93 115	95.25 163	98.13 120	98.53 115	95.97 117	95.57 180	95.96 157	98.03 121	96.05 147

viewcassd2359sk11		96.93 119	96.96 115	96.90 135	98.14 133	97.88 128	97.95 122	96.98 155	96.18 58	95.53 156	98.75 91	99.06 57	95.17 151	95.49 184	95.54 171	97.62 157	95.81 160

viewdifsd2359ckpt11		96.92 120	97.45 76	96.31 167	97.53 183	97.42 157	97.70 143	95.37 213	96.93 33	94.17 205	99.27 43	99.52 10	95.11 156	97.33 110	95.90 160	97.98 128	95.79 163

viewmsd2359difaftdt		96.92 120	97.45 76	96.31 167	97.53 183	97.42 157	97.70 143	95.37 213	96.93 33	94.18 204	99.27 43	99.52 10	95.11 156	97.33 110	95.90 160	97.98 128	95.79 163

DELS-MVS		96.90 122	97.24 91	96.50 160	97.85 160	98.18 92	97.88 131	95.92 192	93.48 161	95.34 161	98.86 81	98.94 74	94.03 178	97.33 110	97.04 113	98.00 124	96.85 113
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		96.86 123	96.72 133	97.03 124	97.80 169	97.06 176	97.04 193	95.51 210	94.55 131	97.47 52	97.35 140	97.68 153	96.66 83	97.11 121	96.73 124	97.69 152	96.57 123

PM-MVS		96.85 124	96.62 137	97.11 117	97.13 210	96.51 196	98.29 97	94.65 232	94.84 118	98.12 32	98.59 99	97.20 167	97.41 56	96.24 153	96.41 138	97.09 185	96.56 125

FE-MVSNET		96.84 125	96.84 124	96.84 140	96.93 216	97.58 145	98.49 85	97.43 122	95.70 82	95.08 171	98.40 110	98.08 137	95.17 151	95.92 165	97.05 112	97.96 131	95.14 184

pmmvs-eth3d		96.84 125	96.22 147	97.56 85	97.63 178	96.38 204	98.74 64	96.91 159	94.63 128	98.26 26	99.43 25	98.28 127	96.58 90	94.52 202	95.54 171	97.24 178	94.75 190

MVSMamba_PlusPlus		96.81 127	96.92 116	96.69 150	98.66 87	98.33 81	96.65 212	96.73 170	92.78 177	94.79 185	96.01 173	97.55 158	95.44 136	97.67 94	97.87 84	97.85 138	98.24 43

CANet		96.81 127	96.50 139	97.17 112	99.10 54	97.96 119	97.86 132	97.51 108	91.30 199	97.75 41	97.64 130	97.89 146	93.39 194	96.98 129	96.73 124	97.40 168	96.99 103

Fast-Effi-MVS+		96.80 129	95.92 160	97.84 67	98.57 92	97.46 155	98.06 114	98.24 53	89.64 221	97.57 48	96.45 163	97.35 163	96.73 80	97.22 116	96.64 132	97.86 137	96.65 119

viewdifsd2359ckpt13		96.79 130	96.77 130	96.81 141	98.08 140	97.83 130	97.74 139	96.79 166	95.30 100	94.89 180	98.41 108	98.88 80	95.57 132	95.61 177	95.49 174	97.81 141	95.87 158

MCST-MVS		96.79 130	96.08 152	97.62 81	98.78 77	97.52 152	98.01 120	97.32 135	93.20 166	95.84 135	93.97 217	98.12 135	97.34 60	96.34 149	95.88 163	98.45 91	97.51 81

UGNet		96.79 130	97.82 52	95.58 196	97.57 181	98.39 76	98.48 87	97.84 92	95.85 71	94.68 188	97.91 124	99.07 56	87.12 254	97.71 91	97.51 97	97.80 142	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	96.79 130	96.70 134	96.90 135	97.64 176	97.58 145	97.54 158	94.50 234	95.14 105	96.64 97	96.76 155	97.90 145	96.63 84	95.98 163	96.14 147	98.45 91	97.39 88
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
E2		96.74 134	96.70 134	96.78 144	98.09 139	97.82 134	97.80 134	96.86 161	95.62 84	95.42 158	98.47 105	98.83 88	94.96 161	95.19 191	95.24 181	97.53 158	95.75 168

CLD-MVS		96.73 135	96.92 116	96.51 159	98.70 82	97.57 148	97.64 150	92.07 249	93.10 172	96.31 113	98.29 113	99.02 63	95.99 116	97.20 118	96.47 136	98.37 100	96.81 114
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
viewdifsd2359ckpt07		96.69 136	97.19 97	96.10 172	98.01 145	97.73 139	97.69 145	96.10 184	97.21 28	94.10 208	99.10 59	99.21 43	95.06 158	96.10 159	94.90 185	95.62 228	96.11 144

MGCFI-Net		96.69 136	96.89 118	96.44 163	98.30 112	98.63 60	97.39 172	97.90 85	95.72 79	91.16 251	94.65 204	94.55 202	95.04 160	97.78 87	98.00 79	98.87 64	98.93 8

train_agg		96.68 138	95.93 159	97.56 85	99.08 56	97.16 167	98.44 93	97.37 128	91.12 203	95.18 167	95.43 186	98.48 119	97.36 58	96.48 145	95.52 173	97.95 132	97.34 92

CDPH-MVS		96.68 138	95.99 156	97.48 92	99.13 50	97.64 142	98.08 113	97.46 115	90.56 210	95.13 168	94.87 199	98.27 128	96.56 91	97.09 122	96.45 137	98.54 82	97.08 102

MSLP-MVS++		96.66 140	96.46 142	96.89 137	98.02 144	97.71 140	95.57 234	96.96 156	94.36 141	96.19 118	91.37 243	98.24 129	97.07 70	97.69 92	97.89 82	97.52 160	97.95 54

TinyColmap		96.64 141	96.07 153	97.32 103	97.84 165	96.40 201	97.63 152	96.25 182	95.86 70	98.98 10	97.94 123	96.34 184	96.17 106	97.30 114	95.38 178	97.04 188	93.24 218

IS_MVSNet		96.62 142	96.48 141	96.78 144	98.46 98	98.68 58	98.61 73	98.24 53	92.23 183	89.63 258	95.90 180	94.40 206	96.23 101	98.65 49	98.77 33	99.52 12	96.76 116

NCCC		96.56 143	95.68 163	97.59 83	99.04 60	97.54 151	97.67 147	97.56 106	94.84 118	96.10 121	87.91 254	98.09 136	96.98 75	97.20 118	96.80 123	98.21 109	97.38 91

WB-MVS		96.54 144	98.09 38	94.73 218	96.68 225	98.34 80	94.77 254	97.39 125	98.12 10	89.72 257	98.95 69	99.32 28	93.33 195	98.67 46	97.88 83	96.47 210	95.38 178

ETV-MVS		96.54 144	95.27 172	98.02 56	99.07 58	97.48 154	98.16 108	98.19 59	87.33 242	97.58 47	92.67 230	95.93 190	96.22 102	98.49 61	98.46 46	98.91 57	96.50 129

Effi-MVS+		96.46 146	95.28 171	97.85 66	98.64 91	97.16 167	97.15 189	98.75 23	90.27 214	98.03 34	93.93 218	96.21 185	96.55 92	96.34 149	96.69 127	97.97 130	96.33 133

IterMVS-LS		96.35 147	95.85 162	96.93 133	97.53 183	98.00 116	97.37 173	97.97 79	95.49 96	96.71 94	98.94 71	93.23 214	94.82 166	93.15 223	95.05 183	97.17 182	97.12 100
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs_AUTHOR		96.30 148	96.79 128	95.73 190	97.43 194	97.06 176	97.24 183	95.65 205	95.76 77	92.97 235	99.35 35	99.21 43	93.99 181	95.61 177	94.85 187	97.09 185	95.65 171

USDC		96.30 148	95.64 165	97.07 120	97.62 179	96.35 206	97.17 188	95.71 203	95.52 94	99.17 7	98.11 121	97.46 160	95.67 125	95.44 186	93.60 210	97.09 185	92.99 222

Vis-MVSNet (Re-imp)		96.29 150	96.50 139	96.05 173	97.96 153	97.83 130	97.30 178	97.86 90	93.14 168	88.90 261	96.80 154	95.28 196	95.15 153	98.37 68	98.25 64	99.12 37	95.84 159

viewmamba		96.27 151	96.61 138	95.87 181	97.38 198	97.07 175	97.40 171	95.73 202	95.71 80	93.65 218	99.12 57	99.00 65	93.81 185	95.94 164	94.27 196	97.27 176	95.13 185

MSDG		96.27 151	96.17 150	96.38 166	97.85 160	96.27 208	96.55 214	94.41 235	94.55 131	95.62 152	97.56 135	97.80 147	96.22 102	97.17 120	96.27 142	97.67 154	93.60 213

CNLPA		96.24 153	95.97 157	96.57 157	97.48 192	97.10 174	96.75 206	94.95 226	94.92 116	96.20 117	94.81 200	96.61 179	96.25 100	96.94 130	95.64 169	97.79 143	95.74 169

EIA-MVS		96.23 154	94.85 184	97.84 67	99.08 56	98.21 90	97.69 145	98.03 75	85.68 252	98.09 33	91.75 241	97.07 171	95.66 127	97.58 100	97.72 92	98.47 89	95.91 155

onestephybrid01		96.10 155	96.33 143	95.84 184	97.29 205	97.01 178	97.61 153	95.69 204	93.41 162	93.45 223	98.92 72	98.92 75	93.62 189	96.06 161	94.68 192	97.35 174	95.34 179

PLC	92.55 15	96.10 155	95.36 168	96.96 130	98.13 136	96.88 182	96.49 215	96.67 175	94.07 150	95.71 146	91.14 244	96.09 187	96.84 77	96.70 139	96.58 134	97.92 133	96.03 150
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test20.03		96.08 157	96.80 127	95.25 208	99.19 39	97.58 145	97.24 183	97.56 106	94.95 114	91.91 247	98.58 100	98.03 140	87.88 250	97.43 105	96.94 117	97.69 152	94.05 204

FA-MVS(training)		96.07 158	95.59 166	96.63 152	98.00 149	97.44 156	97.36 175	98.53 28	92.21 184	95.97 127	96.18 169	94.22 209	92.98 200	96.79 135	96.70 126	96.95 194	95.56 174

TSAR-MVS + COLMAP		96.05 159	95.94 158	96.18 171	97.46 193	96.41 200	97.26 182	95.83 196	94.69 124	95.30 162	98.31 112	96.52 180	94.71 168	95.48 185	94.87 186	96.54 207	95.33 181

EU-MVSNet		96.03 160	96.23 146	95.80 187	95.48 255	94.18 235	98.99 37	91.51 251	97.22 27	97.66 45	99.15 53	98.51 117	98.08 30	95.92 165	92.88 218	93.09 243	95.72 170

dtuplus		95.99 161	96.16 151	95.80 187	97.37 199	96.47 197	97.23 185	95.76 201	94.81 120	93.04 233	98.67 96	98.88 80	93.93 182	95.14 192	93.69 208	97.49 162	95.44 177

PCF-MVS	92.69 14	95.98 162	95.05 179	97.06 121	98.43 100	97.56 149	97.76 137	96.65 176	89.95 219	95.70 147	96.18 169	98.48 119	95.74 120	93.64 213	93.35 215	98.09 120	96.18 139
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HQP-MVS		95.97 163	95.01 181	97.08 119	98.72 80	97.19 165	97.07 192	96.69 174	91.49 197	95.77 142	92.19 236	97.93 144	96.15 107	94.66 199	94.16 199	98.10 118	97.45 84

Effi-MVS+-dtu		95.94 164	95.08 178	96.94 132	98.54 95	97.38 159	96.66 210	97.89 87	88.68 228	95.92 130	92.90 229	97.28 164	94.18 177	96.68 141	96.13 149	98.45 91	96.51 128

usedtu_dtu_shiyan1		95.91 165	95.40 167	96.50 160	96.40 230	97.12 171	97.95 122	96.35 181	93.25 165	96.07 123	97.21 143	97.22 166	94.48 171	93.47 215	95.28 179	97.74 146	94.28 199

diffmvs		95.86 166	96.21 148	95.44 201	97.25 207	96.85 185	96.99 196	95.23 219	94.96 113	92.82 238	98.89 76	98.85 84	93.52 192	94.21 208	94.25 197	96.84 197	95.49 176
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		95.85 167	94.65 188	97.26 105	98.70 82	97.20 164	97.33 177	97.30 136	91.28 201	95.90 131	88.16 253	96.17 186	96.60 86	97.34 109	96.82 120	97.71 149	95.60 173

viewmambaseed2359dif		95.80 168	95.87 161	95.73 190	97.17 209	96.55 193	97.15 189	95.60 207	93.77 157	93.06 231	98.63 98	98.66 106	94.03 178	94.76 197	93.36 214	97.37 171	95.34 179

hybridnocas07		95.78 169	96.24 145	95.26 207	97.02 214	96.76 189	96.93 199	95.26 217	93.98 151	92.77 239	99.05 61	98.86 83	92.56 208	95.70 174	94.18 198	97.00 191	95.13 185

FMVSNet2		95.77 170	96.20 149	95.27 205	96.77 221	98.18 92	97.28 179	97.90 85	93.12 169	91.37 249	98.25 116	96.05 188	90.04 229	94.96 196	95.94 158	98.28 102	96.90 107

OpenMVS	94.63 9	95.75 171	95.04 180	96.58 156	97.85 160	97.55 150	96.71 208	96.07 185	90.15 217	96.47 103	90.77 249	95.95 189	94.41 174	97.01 127	96.95 116	98.00 124	96.90 107

pmmvs5		95.70 172	95.22 173	96.26 169	96.55 229	97.24 162	97.50 161	94.99 225	90.95 206	96.87 82	98.47 105	97.40 161	94.45 172	92.86 224	94.98 184	97.23 179	94.64 193

Anonymous20231206		95.69 173	95.68 163	95.70 192	98.32 107	96.95 180	97.37 173	96.65 176	93.33 163	93.61 219	98.70 95	98.03 140	91.04 217	95.07 194	94.59 195	97.20 180	93.09 221

hybrid		95.66 174	96.07 153	95.19 210	97.03 212	96.68 191	96.90 203	95.12 220	94.10 146	92.85 237	98.82 83	98.71 102	92.52 211	95.42 187	93.82 207	96.72 202	94.93 188

MAR-MVS		95.51 175	94.49 192	96.71 146	97.92 155	96.40 201	96.72 207	98.04 74	86.74 246	96.72 91	92.52 233	95.14 198	94.02 180	96.81 134	96.54 135	96.85 195	97.25 96
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_pp		95.48 176	94.51 190	96.61 153	97.13 210	97.30 161	98.05 116	96.79 166	93.75 158	95.08 171	96.38 164	89.76 236	94.95 162	93.97 212	94.82 191	97.64 156	95.63 172

MDA-MVSNet-bldmvs		95.45 177	95.20 174	95.74 189	94.24 260	96.38 204	97.93 125	94.80 227	95.56 92	96.87 82	98.29 113	95.24 197	96.50 94	98.65 49	90.38 231	94.09 235	91.93 229

PVSNet_BlendedMVS		95.44 178	95.09 176	95.86 182	97.31 203	97.13 169	96.31 220	95.01 223	88.55 231	96.23 114	94.55 209	97.75 148	92.56 208	96.42 146	95.44 176	97.71 149	95.81 160

PVSNet_Blended		95.44 178	95.09 176	95.86 182	97.31 203	97.13 169	96.31 220	95.01 223	88.55 231	96.23 114	94.55 209	97.75 148	92.56 208	96.42 146	95.44 176	97.71 149	95.81 160

pmmvs4		95.37 180	94.25 193	96.67 151	97.01 215	95.28 228	97.60 154	96.07 185	93.11 170	97.29 62	98.09 122	94.23 208	95.21 149	91.56 235	93.91 205	96.82 200	93.59 214

MVS_Test		95.34 181	94.88 183	95.89 180	96.93 216	96.84 186	96.66 210	97.08 151	90.06 218	94.02 209	97.61 131	96.64 178	93.59 191	92.73 227	94.02 203	97.03 189	96.24 136

GBi-Net		95.21 182	95.35 169	95.04 212	96.77 221	98.18 92	97.28 179	97.58 103	88.43 233	90.28 254	96.01 173	92.43 222	90.04 229	97.67 94	97.86 86	98.28 102	96.90 107

test1		95.21 182	95.35 169	95.04 212	96.77 221	98.18 92	97.28 179	97.58 103	88.43 233	90.28 254	96.01 173	92.43 222	90.04 229	97.67 94	97.86 86	98.28 102	96.90 107

IterMVS-SCA-FT		95.16 184	93.95 197	96.56 158	97.89 157	96.69 190	96.94 198	96.05 187	93.06 173	97.35 59	98.79 86	91.45 227	95.93 118	92.78 225	91.00 228	95.22 231	93.91 207

HyFIR lowres test		95.05 185	93.54 202	96.81 141	97.81 168	96.88 182	98.18 105	97.46 115	94.28 142	94.98 178	96.57 160	92.89 220	96.15 107	90.90 240	91.87 224	96.28 214	91.35 230

CHOSEN 1792x2688		94.98 186	94.69 187	95.31 203	97.27 206	95.58 220	97.90 128	95.56 209	95.03 109	93.77 217	95.65 184	99.29 30	95.30 145	91.51 236	91.28 227	92.05 253	94.50 195

CANet_DTU		94.96 187	94.62 189	95.35 202	98.03 143	96.11 210	96.92 201	95.60 207	88.59 230	97.27 63	95.27 189	96.50 181	88.77 245	95.53 181	95.59 170	95.54 229	94.78 189

CDS-MVSNet		94.91 188	95.17 175	94.60 222	97.85 160	96.21 209	96.90 203	96.39 179	90.81 207	93.40 224	97.24 142	94.54 203	85.78 260	96.25 152	96.15 146	97.26 177	95.01 187
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
DPM-MVS		94.86 189	93.90 199	95.99 175	98.19 128	96.52 195	96.29 222	95.95 189	93.11 170	94.61 190	88.17 252	96.44 182	93.77 188	93.33 218	93.54 212	97.11 184	96.22 137

MS-PatchMatch		94.84 190	94.76 186	94.94 215	96.38 231	94.69 234	95.90 228	94.03 237	92.49 178	93.81 214	95.79 181	96.38 183	94.54 169	94.70 198	94.85 187	94.97 233	94.43 197

thisisatest0530		94.81 191	93.06 208	96.85 139	98.01 145	97.18 166	96.93 199	97.36 129	89.73 220	95.80 140	94.98 195	77.88 257	94.89 163	96.73 137	97.35 101	98.13 116	97.54 79

tttt0517		94.81 191	93.04 209	96.88 138	98.15 132	97.37 160	96.99 196	97.36 129	89.51 223	95.74 143	94.89 197	77.53 259	94.89 163	96.94 130	97.35 101	98.17 112	97.70 69

testgi		94.81 191	96.05 155	93.35 234	99.06 59	96.87 184	97.57 156	96.70 173	95.77 76	88.60 264	93.19 227	98.87 82	81.21 268	97.03 126	96.64 132	96.97 193	93.99 206

PatchMatch-RL		94.79 194	93.75 201	96.00 174	96.80 220	95.00 231	95.47 239	95.25 218	90.68 209	95.80 140	92.97 228	93.64 211	95.67 125	96.13 158	95.81 166	96.99 192	92.01 228

FPMVS		94.70 195	94.99 182	94.37 224	95.84 244	93.20 240	96.00 227	91.93 250	95.03 109	94.64 189	94.68 201	93.29 213	90.95 218	98.07 77	97.34 104	96.85 195	93.29 217

new-patchmatchnet		94.48 196	94.02 195	95.02 214	97.51 190	95.00 231	95.68 233	94.26 236	97.32 23	95.73 145	99.60 12	98.22 133	91.30 213	94.13 209	84.41 250	95.65 227	89.45 242

IterMVS		94.48 196	93.46 204	95.66 193	97.52 186	96.43 198	97.20 186	94.73 230	92.91 176	96.44 104	98.75 91	91.10 229	94.53 170	92.10 231	90.10 233	93.51 239	92.84 226
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MDTV_nov1_ep13_2view		94.39 198	93.34 205	95.63 194	97.23 208	95.33 227	97.76 137	96.84 163	94.55 131	97.47 52	98.96 67	97.70 151	93.88 184	92.27 229	86.81 240	90.56 255	87.73 252

Fast-Effi-MVS+-dtu		94.34 199	93.26 207	95.62 195	97.82 166	95.97 213	95.86 230	99.01 13	86.88 244	93.39 225	90.83 247	95.46 195	90.61 222	94.46 204	94.68 192	97.01 190	94.51 194

thres600view7		94.34 199	92.31 218	96.70 148	98.19 128	98.12 101	97.85 133	97.45 117	91.49 197	93.98 211	84.27 257	82.02 248	94.24 176	97.04 123	98.76 34	98.49 86	94.47 196

EPNet		94.33 201	93.52 203	95.27 205	98.81 75	94.71 233	96.77 205	98.20 57	88.12 236	96.53 101	92.53 232	91.19 228	85.25 264	95.22 190	95.26 180	96.09 219	97.63 76
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test2506		94.29 202	91.43 232	97.64 80	98.66 87	98.83 35	98.50 81	98.40 37	96.04 60	94.45 193	94.88 198	55.05 281	96.70 81	99.28 14	99.04 19	99.14 33	96.87 111

GA-MVS		94.18 203	92.98 210	95.58 196	97.36 200	96.42 199	96.21 223	95.86 193	90.29 213	95.08 171	96.19 168	85.37 240	92.82 204	94.01 211	94.14 200	96.16 218	94.41 198

gg-mvs-nofinetune		94.13 204	93.93 198	94.37 224	97.99 150	95.86 214	95.45 242	99.22 9	97.61 17	95.10 170	99.50 19	84.50 241	81.73 267	95.31 188	94.12 201	96.71 204	90.59 234

baseline		94.07 205	94.50 191	93.57 232	96.34 232	93.40 239	95.56 237	92.39 244	92.07 187	94.00 210	98.24 117	97.51 159	89.19 237	91.75 233	92.72 219	93.96 237	95.79 163

FMVSNet3		94.06 206	93.85 200	94.31 227	95.46 256	97.80 137	96.34 218	97.58 103	88.43 233	90.28 254	96.01 173	92.43 222	88.67 246	91.82 232	93.96 204	97.53 158	96.50 129

thres400		94.04 207	91.94 224	96.50 160	97.98 152	97.82 134	97.66 149	96.96 156	90.96 205	94.20 201	83.24 259	82.82 246	93.80 186	96.50 144	98.09 72	98.38 99	94.15 201

dmvs_re		94.02 208	92.39 216	95.91 179	97.71 173	95.43 222	97.00 195	95.94 190	82.49 261	94.61 190	83.69 258	93.01 219	92.71 205	97.83 84	97.56 95	97.50 161	96.73 117

CVMVSNet		94.01 209	94.25 193	93.73 231	94.36 259	92.44 243	97.45 164	88.56 256	95.59 87	93.06 231	98.88 77	90.03 235	94.84 165	94.08 210	93.45 213	94.09 235	95.31 182

thres200		93.98 210	91.90 225	96.40 165	97.66 174	98.12 101	97.20 186	97.45 117	90.16 216	93.82 213	83.08 260	83.74 244	93.80 186	97.04 123	97.48 99	98.49 86	93.70 210

gbinet_0.2-2-1-0.02		93.92 211	92.20 222	95.93 178	96.24 233	95.75 215	98.05 116	93.85 239	91.55 196	96.68 95	96.95 151	92.86 221	95.06 158	88.67 247	85.96 244	95.71 226	93.65 212

blended_shiyan8		93.92 211	92.28 220	95.83 185	95.93 242	95.67 218	97.71 141	92.63 242	92.35 181	96.92 78	95.99 177	93.23 214	95.60 131	88.33 248	86.73 241	96.18 216	93.70 210

blended_shiyan6		93.92 211	92.29 219	95.82 186	95.95 240	95.66 219	97.72 140	92.62 243	92.31 182	96.89 81	95.96 178	93.33 212	95.55 133	88.31 249	86.73 241	96.17 217	93.73 208

baseline1		93.89 214	92.82 212	95.14 211	97.62 179	96.97 179	96.12 224	96.36 180	91.30 199	91.53 248	94.68 201	80.72 250	90.80 220	95.71 173	96.29 141	98.44 95	94.09 203

tfpn200view9		93.80 215	91.75 228	96.20 170	97.52 186	98.15 99	97.48 163	97.47 114	87.65 238	93.56 221	83.03 261	84.12 242	92.62 207	97.04 123	98.09 72	98.52 85	94.17 200

dtuonlycased		93.74 216	94.84 185	92.45 242	97.52 186	96.82 187	97.55 157	92.73 241	94.41 138	78.03 273	97.60 132	98.13 134	95.20 150	93.57 214	90.51 230	93.69 238	92.83 227

MIMVSNet		93.68 217	93.96 196	93.35 234	97.82 166	96.08 211	96.34 218	98.46 34	91.28 201	86.67 269	94.95 196	94.87 200	84.39 265	94.53 200	94.65 194	96.45 211	91.34 231

pmnet_mix02		93.59 218	92.65 213	94.69 220	96.76 224	94.16 236	97.03 194	93.00 240	95.79 74	96.03 126	98.91 74	97.69 152	92.99 199	90.03 245	84.10 253	92.35 251	87.89 251

wanda-best-256-512		93.50 219	91.78 226	95.51 198	95.64 248	95.41 223	97.43 166	92.21 245	91.80 189	96.77 88	95.73 182	93.11 216	95.28 146	87.72 251	85.73 245	95.75 222	92.99 222

FE-blended-shiyan7		93.50 219	91.78 226	95.51 198	95.64 248	95.41 223	97.43 166	92.21 245	91.80 189	96.77 88	95.73 182	93.11 216	95.28 146	87.72 251	85.73 245	95.75 222	92.99 222

EPNet_dtu		93.45 221	92.51 215	94.55 223	98.39 102	91.67 254	95.46 240	97.50 110	86.56 247	97.38 57	93.52 221	94.20 210	85.82 259	93.31 220	92.53 220	92.72 246	95.76 167
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IB-MVS	92.44 16	93.33 222	92.15 223	94.70 219	97.42 195	96.39 203	95.57 234	94.67 231	86.40 250	93.59 220	78.28 268	95.76 193	89.59 235	95.88 167	95.98 156	97.39 169	96.34 132
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		93.18 223	90.80 235	95.95 176	96.05 237	96.07 212	96.92 201	96.51 178	89.34 224	95.63 150	94.08 214	72.31 274	93.13 197	94.33 206	94.83 189	97.44 165	94.65 192

thres100view900		92.93 224	90.89 234	95.31 203	97.52 186	96.82 187	96.41 216	95.08 221	87.65 238	93.56 221	83.03 261	84.12 242	91.12 216	94.53 200	96.91 118	98.17 112	93.21 219

N_pmnet		92.46 225	92.38 217	92.55 240	97.91 156	93.47 238	97.42 169	94.01 238	96.40 51	88.48 265	98.50 102	98.07 139	88.14 249	91.04 239	84.30 251	89.35 261	84.85 259

TAMVS		92.46 225	93.34 205	91.44 251	97.03 212	93.84 237	94.68 255	90.60 253	90.44 212	85.31 270	97.14 147	93.03 218	85.78 260	94.34 205	93.67 209	95.22 231	90.93 233

CMPMVS	71.81 19	92.34 227	92.85 211	91.75 248	92.70 264	90.43 262	88.84 272	88.56 256	85.87 251	94.35 197	90.98 245	95.89 192	91.14 215	96.14 156	94.83 189	94.93 234	95.78 166
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
baseline2		92.06 228	89.82 238	94.68 221	97.32 201	95.72 216	94.97 251	95.08 221	84.75 255	94.34 199	90.68 250	77.75 258	90.13 228	93.38 216	93.58 211	96.25 215	92.90 225

dtuonly		91.97 229	91.47 230	92.55 240	96.68 225	91.24 256	95.21 247	91.44 252	91.11 204	94.12 207	97.19 145	95.93 190	89.16 238	90.89 241	87.43 239	88.71 263	86.52 255

MVSTER		91.97 229	90.31 236	93.91 229	96.81 219	96.91 181	94.22 256	95.64 206	84.98 253	92.98 234	93.42 222	72.56 272	86.64 258	95.11 193	93.89 206	97.16 183	95.31 182

CR-MVSNet		91.94 231	88.50 241	95.94 177	96.14 235	92.08 249	95.23 245	98.47 32	84.30 257	96.44 104	94.58 205	75.57 260	92.92 201	90.22 243	92.22 221	96.43 212	90.56 235

gm-plane-assit		91.85 232	87.91 243	96.44 163	99.14 48	98.25 85	99.02 32	97.38 127	95.57 89	98.31 25	99.34 37	51.00 282	88.93 242	93.16 222	91.57 225	95.85 220	86.50 256

PMMVS		91.67 233	91.47 230	91.91 247	89.43 269	88.61 268	94.99 250	85.67 261	87.50 240	93.80 215	94.42 212	94.88 199	90.71 221	92.26 230	92.96 217	96.83 198	89.65 240

CHOSEN 280x420		91.55 234	90.27 237	93.05 237	94.61 258	88.01 269	96.56 213	94.62 233	88.04 237	94.20 201	92.66 231	86.60 238	90.82 219	95.06 195	91.89 223	87.49 267	89.61 241

PatchT		91.40 235	88.54 240	94.74 217	91.48 268	92.18 246	97.42 169	97.51 108	84.96 254	96.44 104	94.16 213	75.47 261	92.92 201	90.22 243	92.22 221	92.66 249	90.56 235

pmmvs3		91.20 236	91.40 233	90.96 253	91.71 267	91.08 257	95.41 243	81.34 268	87.36 241	94.57 192	95.02 193	94.30 207	90.42 223	94.28 207	89.26 235	92.30 252	88.49 248

test0.0.03 1		91.17 237	91.50 229	90.80 254	98.01 145	95.46 221	94.22 256	95.80 197	86.55 248	81.75 272	90.83 247	87.93 237	78.48 269	94.51 203	94.11 202	96.50 208	91.08 232

SCA		91.15 238	87.65 245	95.23 209	96.15 234	95.68 217	96.68 209	98.18 61	90.46 211	97.21 66	92.44 234	80.17 252	93.51 193	86.04 259	83.58 256	89.68 259	85.21 258

new_pmnet		90.85 239	92.26 221	89.21 260	93.68 263	89.05 267	93.20 265	84.16 265	92.99 174	84.25 271	97.72 128	94.60 201	86.80 257	93.20 221	91.30 226	93.21 241	86.94 254

RPMNet		90.52 240	86.27 256	95.48 200	95.95 240	92.08 249	95.55 238	98.12 66	84.30 257	95.60 153	87.49 255	72.78 271	91.24 214	87.93 250	89.34 234	96.41 213	89.98 238

MDTV_nov1_ep13		90.30 241	87.32 249	93.78 230	96.00 239	92.97 241	95.46 240	95.39 212	88.61 229	95.41 159	94.45 211	80.39 251	89.87 232	86.58 257	83.54 257	90.56 255	84.71 261

FE-MVSNET3		90.29 242	86.44 253	94.78 216	95.64 248	95.41 223	97.43 166	92.21 245	91.80 189	92.27 242	77.48 270	73.25 267	95.41 137	87.72 251	85.73 245	95.75 222	93.73 208

PatchmatchNet		89.98 243	86.23 257	94.36 226	96.56 228	91.90 253	96.07 225	96.72 171	90.18 215	96.87 82	93.36 225	78.06 256	91.46 212	84.71 264	81.40 261	88.45 264	83.97 265
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
usedtu_blend_shiyan5		89.91 244	86.39 254	94.01 228	95.64 248	95.41 223	92.79 268	92.21 245	91.80 189	92.27 242	77.47 271	73.25 267	95.41 137	87.72 251	85.73 245	95.75 222	93.36 215

ADS-MVSNet		89.89 245	87.70 244	92.43 244	95.52 253	90.91 260	95.57 234	95.33 215	93.19 167	91.21 250	93.41 223	82.12 247	89.05 239	86.21 258	83.77 255	87.92 265	84.31 262

tpm		89.84 246	86.81 251	93.36 233	96.60 227	91.92 252	95.02 249	97.39 125	86.79 245	96.54 100	95.03 192	69.70 275	87.66 251	88.79 246	86.19 243	86.95 269	89.27 243

test-LLR		89.77 247	87.47 247	92.45 242	98.01 145	89.77 264	93.25 263	95.80 197	81.56 263	89.19 259	92.08 237	79.59 253	85.77 262	91.47 237	89.04 237	92.69 247	88.75 244

FMVSNet5		89.65 248	87.60 246	92.04 246	95.63 252	96.61 192	94.82 253	94.75 228	80.11 267	87.72 267	77.73 269	73.81 264	83.81 266	95.64 175	96.08 151	95.49 230	93.21 219

EPMVS		89.28 249	86.28 255	92.79 239	96.01 238	92.00 251	95.83 231	95.85 195	90.78 208	91.00 252	94.58 205	74.65 262	88.93 242	85.00 262	82.88 259	89.09 262	84.09 264

test-mter		89.16 250	88.14 242	90.37 256	94.79 257	91.05 258	93.60 262	85.26 262	81.65 262	88.32 266	92.22 235	79.35 255	87.03 255	92.28 228	90.12 232	93.19 242	90.29 237

CostFormer		89.06 251	85.65 258	93.03 238	95.88 243	92.40 244	95.30 244	95.86 193	86.49 249	93.12 230	93.40 224	74.18 263	88.25 247	82.99 265	81.46 260	89.77 258	88.66 246

MVS-HIRNet		88.72 252	86.49 252	91.33 252	91.81 266	85.66 270	87.02 274	96.25 182	81.48 265	94.82 183	96.31 167	92.14 225	90.32 225	87.60 255	83.82 254	87.74 266	78.42 269

TESTMET0.1,1		88.60 253	87.47 247	89.93 258	94.23 261	89.77 264	93.25 263	84.47 264	81.56 263	89.19 259	92.08 237	79.59 253	85.77 262	91.47 237	89.04 237	92.69 247	88.75 244

dps		88.36 254	84.32 261	93.07 236	93.86 262	92.29 245	94.89 252	95.93 191	83.50 259	93.13 228	91.87 239	67.79 278	90.32 225	85.99 260	83.22 258	90.28 257	85.56 257

tpmrst		87.60 255	84.13 262	91.66 250	95.65 247	89.73 266	93.77 259	94.74 229	88.85 226	93.35 227	95.60 185	72.37 273	87.40 252	81.24 266	78.19 266	85.02 272	82.90 268

blend_shiyan4		87.32 256	83.58 263	91.68 249	85.86 273	95.01 230	90.28 269	90.47 254	74.69 272	92.27 242	77.47 271	73.25 267	95.41 137	85.88 261	85.38 249	95.81 221	93.36 215

tpm cat1		87.19 257	82.78 264	92.33 245	95.66 246	90.61 261	94.19 258	95.27 216	86.97 243	94.38 195	90.91 246	69.40 276	87.21 253	79.57 269	77.82 267	87.25 268	84.18 263

E-PMN		86.94 258	85.10 259	89.09 262	95.77 245	83.54 273	89.89 271	86.55 258	92.18 185	87.34 268	94.02 215	83.42 245	89.63 234	93.32 219	77.11 268	85.33 270	72.09 271

EMVS		86.63 259	84.48 260	89.15 261	95.51 254	83.66 272	90.19 270	86.14 260	91.78 193	88.68 262	93.83 219	81.97 249	89.05 239	92.76 226	76.09 269	85.31 271	71.28 272

PMMVS2		86.47 260	92.62 214	79.29 264	92.01 265	85.63 271	93.74 260	86.37 259	93.95 154	54.18 278	98.19 118	97.39 162	58.46 270	96.57 143	93.07 216	90.99 254	83.55 267

0.4-1-1-0.1		86.09 261	82.27 265	90.55 255	88.91 270	92.09 248	93.74 260	84.65 263	77.28 269	92.48 241	81.76 264	73.62 265	90.27 227	80.00 268	81.27 262	93.27 240	89.84 239

MVE	72.99 18	85.37 262	89.43 239	80.63 263	74.43 274	71.94 275	88.25 273	89.81 255	93.27 164	67.32 276	96.32 166	91.83 226	90.40 224	93.36 217	90.79 229	73.55 275	88.49 248
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
0.3-1-1-0.015		85.22 263	81.12 267	90.00 257	88.32 271	91.29 255	93.16 266	83.68 266	76.11 270	92.27 242	79.38 266	73.25 267	89.78 233	78.77 271	80.48 263	92.78 245	88.53 247

0.4-1-1-0.2		85.13 264	81.17 266	89.76 259	88.18 272	90.98 259	92.83 267	83.39 267	75.70 271	92.15 246	80.54 265	73.62 265	89.49 236	78.89 270	80.15 264	92.48 250	88.30 250

test_method		61.30 265	70.45 268	50.62 265	22.69 278	30.92 279	68.31 277	25.76 271	80.56 266	68.71 274	82.80 263	91.08 230	44.64 271	80.50 267	56.70 271	73.64 274	70.58 273

GG-mvs-BLEND		61.03 266	87.02 250	30.71 268	0.74 283	90.01 263	78.90 276	0.74 277	84.56 256	9.46 280	79.17 267	90.69 233	1.37 279	91.74 234	89.13 236	93.04 244	83.83 266

VLMVS_CLIP		47.10 267	56.61 270	36.00 267	68.27 275	53.74 276	23.32 279	41.33 269	49.20 274	16.41 279	60.43 275	65.92 279	41.60 273	57.24 273	51.06 272	25.09 277	58.65 274

MVS_clip		41.82 268	60.29 269	20.28 269	37.55 277	34.42 278	13.98 281	10.87 273	57.10 273	3.35 284	69.38 273	68.28 277	42.17 272	61.55 272	58.12 270	13.76 278	73.17 270

VLMVS		14.77 269	20.38 272	8.23 270	16.10 279	13.23 280	4.49 282	4.94 274	21.12 276	3.97 282	19.38 277	25.63 284	14.96 276	16.63 274	16.14 273	4.91 279	30.50 276

MVS_baseline		13.50 270	21.89 271	3.71 271	5.00 280	2.85 281	0.84 285	0.00 278	22.97 275	0.00 285	24.73 276	30.02 283	16.36 275	12.07 275	11.97 274	0.08 282	48.63 275

testmvs		4.99 271	6.88 273	2.78 273	1.73 281	2.04 283	3.10 283	1.71 275	7.27 277	3.92 283	12.18 278	6.71 285	3.31 278	6.94 276	5.51 276	2.94 280	7.51 277

test123		4.41 272	5.71 274	2.88 272	1.28 282	2.21 282	3.09 284	1.65 276	6.35 278	4.98 281	8.53 279	3.88 286	3.46 277	5.79 277	5.71 275	2.85 281	7.50 278

uanet_test		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet-low-res		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

ACM-MVS					97.41 196	96.54 194	95.87 229		89.59 222	94.92 179	93.23 226	97.08 170	88.95 241			96.58 206	97.28 93

PatchmatchNet2					97.56 182	92.12 247	97.08 191
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												98.01 142	88.25 247	90.84 242	84.30 251	89.36 260	84.73 260
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										88.62 263	98.50 102
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							98.92 44	97.17 143		94.34 199						98.14 114

TPM-MVS					97.49 191	96.32 207	95.05 248			94.36 196	91.82 240	96.92 176	88.89 244			96.67 205	96.22 137
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												96.98 174

SR-MVS					99.33 30			98.40 37				98.90 76

Anonymous202405211			97.39 79		98.85 71	98.59 62	97.89 130	97.93 82	94.41 138		97.37 139	96.99 173	93.09 198	98.61 52	98.46 46	99.11 38	97.27 94

our_test_3					97.32 201	95.13 229	97.59 155

ambc			96.78 129		99.01 61	97.11 173	95.73 232		95.91 68	99.25 3	98.56 101	97.17 168	97.04 71	96.76 136	95.22 182	96.72 202	96.73 117

MTAPA										97.43 56		99.27 34

MTMP										97.63 46		99.03 62

Patchmatch-RL test							17.42 280

tmp_tt				45.72 266	60.00 276	38.74 277	45.50 278	12.18 272	79.58 268	68.42 275	67.62 274	65.04 280	22.12 274	84.83 263	78.72 265	66.08 276

XVS					99.48 18	98.76 47	99.22 21			96.40 108		98.78 95				98.94 55

X-MVStestdata					99.48 18	98.76 47	99.22 21			96.40 108		98.78 95				98.94 55

mPP-MVS					99.58 6							98.98 67

NP-MVS									89.27 225

Patchmtry						92.70 242	95.23 245	98.47 32		96.44 104

DeepMVS_CX						72.99 274	80.14 275	37.34 270	83.46 260	60.13 277	84.40 256	85.48 239	86.93 256	87.22 256		79.61 273	87.32 253

High-resolution multi-view benchmark