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 43	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 67	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 57	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 49	98.83 14	99.46 21	99.09 50	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 41	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 54	99.11 14	99.57 9	98.82 19	98.21 9	99.25 3	99.84 2	99.59 6	98.76 6	99.23 19	98.83 32	98.63 73	98.40 35

DTE-MVSNet		99.03 6	98.88 12	99.21 6	99.66 2	99.59 2	99.62 5	99.34 6	96.92 34	98.52 19	99.36 33	98.98 63	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 64	99.05 19	99.58 7	98.29 49	98.96 4	97.96 36	99.40 30	98.67 95	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 56	98.37 24	99.34 36	99.09 50	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 42	99.78 2	96.59 86	99.52 6	99.40 6	99.67 2	98.21 43

CP-MVSNet		98.91 11	98.61 19	99.25 4	99.63 5	99.50 6	99.55 10	99.36 5	95.53 89	98.77 16	99.11 54	98.64 99	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 84	98.20 87	99.68 1	97.35 131	97.09 31	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	98.32 105	98.92 25	98.57 75	99.03 12	99.36 1	96.86 85	99.77 3	99.86 1	96.20 103	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 69	99.01 21	99.58 7	98.10 68	98.67 6	97.30 61	99.18 49	99.42 20	98.40 19	99.19 21	98.86 30	98.99 48	98.19 44
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
COLMAP_ROB	96.84 2	98.75 14	98.82 14	98.66 20	99.14 47	98.79 40	99.30 17	97.67 98	98.33 8	97.82 40	99.20 47	99.18 46	98.76 6	99.27 17	98.96 22	99.29 27	98.03 49
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 57	97.12 70	98.44 98	98.95 68	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 68	99.01 36	98.17 63	97.17 30	98.25 27	99.56 15	99.62 5	98.29 22	98.40 63	98.09 71	98.97 50	98.08 47
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TranMVSNet+NR-MVSNet		98.45 18	98.22 32	98.72 17	99.32 31	99.06 17	98.99 37	98.89 14	95.52 90	97.53 49	99.42 29	98.83 81	98.01 34	98.55 55	98.34 57	99.57 8	97.80 61

CSCG		98.45 18	98.61 19	98.26 37	99.11 51	99.06 17	98.17 104	97.49 111	97.93 13	97.37 58	98.88 71	99.29 30	98.10 29	98.40 63	97.51 94	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 34	99.76 3	96.34 98	98.79 37	98.65 41	98.56 79	99.35 2

Gipuma		98.43 21	98.15 35	98.76 14	99.00 63	98.29 81	97.91 124	98.06 70	99.02 3	99.50 1	96.33 154	98.67 95	99.22 1	99.02 27	98.02 77	98.88 63	97.66 69
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 66	98.84 33	99.30 17	97.86 89	97.78 15	94.19 200	98.77 82	99.39 22	98.61 11	99.33 13	99.07 14	99.33 23	97.81 60

ACMMPR		98.31 23	98.07 40	98.60 23	99.58 6	98.83 34	99.09 27	98.48 31	96.25 52	97.03 74	96.81 142	99.09 50	98.39 20	98.55 55	98.45 49	99.01 45	98.53 30

APDe-MVS		98.29 24	98.42 26	98.14 40	99.45 21	98.90 26	99.18 23	98.30 47	95.96 64	95.13 168	98.79 79	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 38	94.35 194	98.92 67	99.58 7	97.86 41	98.67 46	98.70 37	98.63 73	98.63 22
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
TransMVSNet (Re)		98.23 26	98.72 16	97.66 78	98.22 120	98.73 52	98.66 70	98.03 75	98.60 7	96.40 108	99.60 12	98.24 121	95.26 144	99.19 21	99.05 17	99.36 20	97.64 70

DU-MVS		98.23 26	97.74 59	98.81 12	99.23 34	98.77 43	98.76 61	98.88 15	94.10 140	98.50 20	98.87 73	98.32 118	97.99 35	98.40 63	98.08 74	99.49 16	97.64 70

UniMVSNet (Re)		98.23 26	97.85 49	98.67 19	99.15 44	98.87 28	98.74 64	98.84 17	94.27 138	97.94 37	99.01 59	98.39 114	97.82 42	98.35 68	98.29 62	99.51 15	97.78 62

MIMVSNet1		98.22 29	98.51 23	97.87 64	99.40 25	98.82 38	99.31 16	98.53 28	97.39 22	96.59 99	99.31 38	99.23 41	94.76 162	98.93 32	98.67 39	98.63 73	97.25 93

HFP-MVS		98.17 30	98.02 41	98.35 35	99.36 27	98.62 60	98.79 60	98.46 34	96.24 53	96.53 101	97.13 137	98.98 63	98.02 33	98.20 71	98.42 51	98.95 54	98.54 28

Baseline_NR-MVSNet		98.17 30	97.90 46	98.48 29	99.23 34	98.59 61	98.83 57	98.73 24	93.97 145	96.95 77	99.66 7	98.23 123	97.90 39	98.40 63	99.06 16	99.25 29	97.42 85

TSAR-MVS + MP.		98.15 32	98.23 30	98.06 51	98.47 95	98.16 92	99.23 20	96.87 157	95.58 84	96.72 91	98.41 99	99.06 54	98.05 32	98.99 29	98.90 26	99.00 46	98.51 31
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
pm-mvs1		98.14 33	98.66 18	97.53 87	97.93 151	98.49 70	98.14 107	98.19 59	97.95 12	96.17 119	99.63 10	98.85 77	95.41 133	98.91 33	98.89 27	99.34 22	97.86 59

SMA-MVS		98.13 34	98.22 32	98.02 56	99.44 23	98.73 52	98.24 99	97.87 88	95.22 98	96.76 90	98.66 89	99.35 24	97.03 71	98.53 58	98.39 53	98.80 68	98.69 18
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
ACMMP_NAP		98.12 35	98.08 39	98.18 39	99.34 28	98.74 51	98.97 39	98.00 77	95.13 102	96.90 79	97.54 126	99.27 34	97.18 65	98.72 42	98.45 49	98.68 72	98.69 18

UniMVSNet_NR-MVSNet		98.12 35	97.56 69	98.78 13	99.13 49	98.89 27	98.76 61	98.78 20	93.81 148	98.50 20	98.81 77	97.64 145	97.99 35	98.18 74	97.92 80	99.53 10	97.64 70

ACMM	94.29 11	98.12 35	97.71 60	98.59 24	99.51 16	98.58 63	99.24 19	98.25 52	96.22 54	96.90 79	95.01 182	98.89 73	98.52 16	98.66 48	98.32 60	99.13 36	98.28 41
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SteuartSystems-ACMMP		98.06 38	97.78 55	98.39 33	99.54 10	98.79 40	98.94 43	98.42 36	93.98 144	95.85 134	96.66 148	99.25 39	98.61 11	98.71 44	98.38 54	98.97 50	98.67 21
Skip Steuart: Steuart Systems R&D Blog.
SED-MVS		98.05 39	98.46 25	97.57 83	99.01 60	98.99 23	98.82 59	98.24 53	95.76 74	94.70 184	98.96 62	99.49 15	96.19 104	98.74 38	98.65 41	98.46 88	98.63 22

OPM-MVS		98.01 40	98.01 42	98.00 58	99.11 51	98.12 97	98.68 68	97.72 96	96.65 43	96.68 95	98.40 101	99.28 33	97.44 55	98.20 71	97.82 87	98.40 95	97.58 75
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 86	96.89 206	98.82 38	99.14 24	97.59 101	96.30 51	97.04 73	99.26 45	98.83 81	96.01 112	98.73 40	98.21 64	98.58 78	98.75 15
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS		98.00 42	97.38 77	98.73 15	98.72 79	99.15 11	99.12 26	98.76 21	91.58 185	98.15 31	96.70 146	98.72 94	98.20 24	98.64 51	98.92 24	99.43 19	97.97 52

NR-MVSNet		98.00 42	97.88 47	98.13 41	98.33 103	98.77 43	98.83 57	98.88 15	94.10 140	97.46 55	98.87 73	98.58 104	95.78 117	99.13 25	98.16 68	99.52 12	97.53 78

CP-MVS		98.00 42	97.57 68	98.50 26	99.47 20	98.56 65	98.91 47	98.38 42	94.71 118	97.01 75	95.20 178	99.06 54	98.20 24	98.61 52	98.46 46	99.02 43	98.40 35

DPE-MVS		97.99 45	98.12 36	97.84 67	98.65 88	98.86 29	98.86 53	98.05 73	94.18 139	95.49 157	98.90 69	99.33 26	97.11 67	98.53 58	98.65 41	98.86 65	98.39 37
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ACMMP		97.99 45	97.60 67	98.45 31	99.53 14	98.83 34	99.13 25	98.30 47	94.57 125	96.39 112	95.32 176	98.95 68	98.37 21	98.61 52	98.47 45	99.00 46	98.45 32
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MP-MVS		97.98 47	97.53 70	98.50 26	99.56 8	98.58 63	98.97 39	98.39 41	93.49 152	97.14 67	96.08 161	99.23 41	98.06 31	98.50 60	98.38 54	98.90 58	98.44 33
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
EG-PatchMatch MVS		97.98 47	97.92 44	98.04 53	98.84 72	98.04 107	97.90 125	96.83 161	95.07 104	98.79 15	99.07 56	99.37 23	97.88 40	98.74 38	98.16 68	98.01 120	96.96 101

ACMP	94.03 12	97.97 49	97.61 66	98.39 33	99.43 24	98.51 69	98.97 39	98.06 70	94.63 123	96.10 121	96.12 160	99.20 45	98.63 9	98.68 45	98.20 67	99.14 33	97.93 55
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SPE-MVS-test		97.96 50	97.38 77	98.64 21	98.57 90	99.13 12	99.36 13	98.66 25	91.67 184	98.17 30	96.91 141	98.84 79	97.99 35	98.80 35	98.88 28	99.08 41	97.43 84

LGP-MVS_train		97.96 50	97.53 70	98.45 31	99.45 21	98.64 58	99.09 27	98.27 50	92.99 165	96.04 125	96.57 149	99.29 30	98.66 8	98.73 40	98.42 51	99.19 31	98.09 46

ME-MVS		97.94 52	98.23 30	97.60 81	99.15 44	98.85 30	98.92 44	97.17 141	96.03 61	94.88 179	99.43 25	99.18 46	97.31 62	98.07 76	98.14 70	98.14 111	97.91 57

LS3D		97.93 53	97.80 51	98.08 47	99.20 38	98.77 43	98.89 49	97.92 83	96.59 44	96.99 76	96.71 145	97.14 158	96.39 97	99.04 26	98.96 22	99.10 40	97.39 86

SD-MVS		97.84 54	97.78 55	97.90 61	98.33 103	98.06 102	97.95 119	97.80 93	96.03 61	96.72 91	97.57 124	99.18 46	97.50 53	97.88 79	97.08 107	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 55	98.27 28	97.31 103	98.23 118	98.06 102	97.44 160	95.79 195	96.90 35	95.81 138	98.76 83	98.61 103	97.70 47	98.90 34	98.36 56	98.90 58	98.29 38

thisisatest0515		97.82 56	97.67 61	97.99 59	98.49 94	98.07 101	98.48 85	98.06 70	95.35 95	97.74 42	98.83 76	97.61 146	96.74 78	97.53 99	98.30 61	98.43 94	98.01 51

PGM-MVS		97.82 56	97.25 87	98.48 29	99.54 10	98.75 50	99.02 32	98.35 45	92.41 169	96.84 86	95.39 175	98.99 62	98.24 23	98.43 62	98.34 57	98.90 58	98.41 34

PMVS	90.51 17	97.77 58	97.98 43	97.53 87	98.68 85	98.14 96	97.67 144	97.03 151	96.43 45	98.38 23	98.72 86	97.03 160	94.44 168	99.37 12	99.30 10	98.98 49	96.86 108
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FE-MVSNET2		97.75 59	97.79 52	97.70 77	97.41 190	98.37 77	99.09 27	97.73 95	96.88 36	97.47 52	99.43 25	99.35 24	96.00 113	96.66 138	97.74 89	98.48 86	96.10 140

MSP-MVS		97.67 60	97.88 47	97.43 94	99.34 28	98.99 23	98.87 52	98.12 66	95.63 79	94.16 203	97.45 127	99.50 14	96.44 96	96.35 144	98.70 37	97.65 151	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 61	97.79 52	97.52 89	98.32 105	98.53 67	98.45 88	97.69 97	97.59 18	96.12 120	97.79 118	96.70 165	95.69 121	98.35 68	98.34 57	98.85 66	97.22 96

FC-MVSNet-train		97.65 62	98.16 34	97.05 120	98.85 70	98.85 30	99.34 14	98.08 69	94.50 130	94.41 191	99.21 46	98.80 86	92.66 198	98.98 30	98.85 31	98.96 52	97.94 54

v10		97.64 63	97.26 85	98.08 47	98.07 138	98.56 65	98.86 53	98.18 61	94.48 131	98.24 28	99.56 15	98.98 63	97.72 46	96.05 157	96.26 139	97.42 162	96.93 102

EC-MVSNet		97.63 64	96.88 115	98.50 26	98.74 78	99.16 10	99.33 15	98.83 18	88.77 215	96.62 98	96.48 151	97.75 138	98.19 26	99.00 28	98.76 34	99.29 27	98.27 42

X-MVS		97.60 65	97.00 108	98.29 36	99.50 17	98.76 46	98.90 48	98.37 43	94.67 122	96.40 108	91.47 229	98.78 88	97.60 52	98.55 55	98.50 44	98.96 52	98.29 38

E6new		97.58 66	97.78 55	97.34 98	98.30 110	98.16 92	98.50 79	97.36 127	97.45 20	95.96 128	99.46 21	99.57 8	96.03 109	96.88 128	96.67 124	97.88 132	96.30 129

E6		97.58 66	97.78 55	97.34 98	98.30 110	98.16 92	98.50 79	97.36 127	97.45 20	95.96 128	99.46 21	99.57 8	96.03 109	96.88 128	96.67 124	97.88 132	96.30 129

3Dnovator+	96.20 4	97.58 66	97.14 99	98.10 42	98.98 65	97.85 125	98.60 74	98.33 46	96.41 47	97.23 65	94.66 191	97.26 154	96.91 75	97.91 78	97.87 83	98.53 82	98.03 49

DCV-MVSNet		97.56 69	97.63 65	97.47 92	98.41 99	99.12 13	98.63 71	98.57 26	95.71 77	95.60 153	93.79 208	98.01 133	94.25 170	99.16 23	98.88 28	99.35 21	98.74 16

HPM-MVS++		97.56 69	97.11 103	98.09 43	99.18 40	97.95 116	98.57 75	98.20 57	94.08 142	97.25 64	95.96 166	98.81 85	97.13 66	97.51 100	97.30 104	98.21 106	98.15 45

FC-MVSNet-test		97.54 71	98.26 29	96.70 145	98.87 68	97.79 134	98.49 83	98.56 27	96.04 57	90.39 242	99.65 8	98.67 95	95.15 148	99.23 19	99.07 14	98.73 71	97.39 86

TSAR-MVS + ACMM		97.54 71	97.79 52	97.26 104	98.23 118	98.10 100	97.71 138	97.88 87	95.97 63	95.57 155	98.71 87	98.57 105	97.36 58	97.74 88	96.81 117	96.83 190	98.59 25

casdiffseed414692147		97.53 73	97.64 64	97.41 95	98.18 129	98.22 85	98.63 71	97.45 116	95.90 66	95.35 160	99.20 47	99.51 12	96.45 95	97.32 110	96.81 117	98.39 96	96.53 123

DeepC-MVS_fast	95.38 6	97.53 73	97.30 84	97.79 72	98.83 73	97.64 138	98.18 102	97.14 145	95.57 85	97.83 39	97.10 138	98.80 86	96.53 92	97.41 103	97.32 102	98.24 105	97.26 92
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 75	97.03 107	98.09 43	98.31 108	98.01 111	98.96 42	97.25 136	95.22 98	98.89 12	99.64 9	98.83 81	97.68 48	95.63 169	95.91 155	97.47 158	95.97 149

v1144		97.51 76	97.05 106	98.04 53	98.26 116	97.98 113	98.88 51	97.42 122	95.38 94	98.56 18	99.59 14	99.01 61	97.65 49	95.77 166	96.06 149	97.47 158	95.56 169

v8		97.51 76	97.16 97	97.91 60	97.99 147	98.48 71	98.76 61	98.17 63	94.54 129	97.69 44	99.48 20	98.76 91	97.63 51	96.10 155	96.14 143	97.20 173	96.64 116

v1921920		97.50 78	97.00 108	98.07 49	98.20 124	97.94 121	99.03 31	97.06 149	95.29 97	99.01 9	99.62 11	98.73 93	97.74 45	95.52 175	95.78 164	97.39 164	96.12 138

Anonymous20231211		97.49 79	97.91 45	97.00 126	98.31 108	98.72 54	98.27 96	97.84 91	94.76 117	94.77 183	98.14 110	98.38 116	93.60 182	98.96 31	98.66 40	99.22 30	97.77 64

v144192		97.49 79	96.99 110	98.07 49	98.11 135	97.95 116	99.02 32	97.21 139	94.90 113	98.88 13	99.53 17	98.89 73	97.75 44	95.59 172	95.90 156	97.43 161	96.16 136

test1111		97.48 81	97.20 92	97.81 71	98.78 76	98.85 30	98.68 68	98.40 37	96.68 41	94.84 180	99.13 51	90.32 221	97.01 72	99.27 17	99.05 17	99.19 31	97.10 98

GeoE		97.48 81	96.84 120	98.22 38	99.01 60	98.39 74	98.85 56	98.76 21	92.37 170	97.53 49	97.58 123	98.23 123	97.11 67	97.57 98	96.98 111	98.10 115	96.78 111

APD-MVS		97.47 83	97.16 97	97.84 67	99.32 31	98.39 74	98.47 87	98.21 56	92.08 176	95.23 164	96.68 147	98.90 71	96.99 73	98.20 71	98.21 64	98.80 68	97.67 68
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PVSNet_Blended_VisFu		97.44 84	97.14 99	97.79 72	99.15 44	98.44 72	98.32 94	97.66 99	93.74 151	97.73 43	98.79 79	96.93 163	95.64 126	97.69 90	96.91 114	98.25 104	97.50 80

PHI-MVS		97.44 84	97.17 96	97.74 75	98.14 131	98.41 73	98.03 115	97.50 109	92.07 177	98.01 35	97.33 131	98.62 102	96.02 111	98.34 70	98.21 64	98.76 70	97.24 95

v1240		97.43 86	96.87 119	98.09 43	98.25 117	97.92 122	99.02 32	97.06 149	94.77 116	99.09 8	99.68 6	98.51 109	97.78 43	95.25 181	95.81 162	97.32 169	96.13 137

viewmacassd2359aftdt		97.42 87	97.67 61	97.13 113	98.20 124	98.06 102	98.16 105	97.16 144	97.27 25	95.23 164	99.29 39	99.48 16	96.05 108	96.73 133	96.66 126	98.00 121	96.17 135

ECVR-MVS		97.40 88	97.11 103	97.73 76	98.66 86	98.83 34	98.50 79	98.40 37	96.04 57	95.00 176	98.95 64	91.07 218	96.70 80	99.28 14	99.04 19	99.14 33	96.58 118

FMVSNet1		97.40 88	98.09 37	96.60 150	97.80 165	98.76 46	98.26 98	98.50 30	96.79 37	93.13 221	99.28 41	98.64 99	92.90 195	97.67 92	97.86 84	99.02 43	97.64 70

MGCNet		97.38 90	97.26 85	97.51 90	99.28 33	98.79 40	98.86 53	97.79 94	94.68 120	96.79 87	97.69 120	95.75 181	93.91 177	98.10 75	97.76 88	98.45 89	98.08 47

E4		97.37 91	97.52 72	97.20 109	98.29 113	98.05 106	98.27 96	97.33 132	97.28 24	95.81 138	99.29 39	99.51 12	95.64 126	96.20 151	96.24 141	97.89 131	96.07 141

casdiffmvs_mvg		97.34 92	97.65 63	96.97 127	97.74 168	98.33 79	98.45 88	97.18 140	95.81 70	93.92 208	99.04 57	99.05 57	95.48 132	97.00 124	97.71 92	99.07 42	96.63 117
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 93	96.84 120	97.90 61	98.19 126	97.83 126	98.74 64	97.44 119	95.42 93	98.23 29	99.46 21	98.84 79	97.46 54	95.51 176	96.10 146	97.36 167	94.72 181

EPP-MVSNet		97.29 94	96.88 115	97.76 74	98.70 81	99.10 16	98.92 44	98.36 44	95.12 103	93.36 219	97.39 128	91.00 219	97.65 49	98.72 42	98.91 25	99.58 7	97.92 56

MVS_111021_HR		97.27 95	97.11 103	97.46 93	98.46 96	97.82 130	97.50 156	96.86 158	94.97 108	97.13 69	96.99 139	98.39 114	96.82 77	97.65 95	97.38 97	98.02 119	96.56 121

E5new		97.26 96	97.38 77	97.13 113	98.29 113	98.02 108	98.19 100	97.24 137	97.21 27	95.82 136	99.13 51	99.44 17	95.39 137	95.81 163	95.99 150	97.83 135	96.05 142

E5		97.26 96	97.38 77	97.13 113	98.29 113	98.02 108	98.19 100	97.24 137	97.21 27	95.82 136	99.13 51	99.44 17	95.39 137	95.81 163	95.99 150	97.83 135	96.05 142

SF-MVS		97.26 96	97.43 75	97.05 120	98.80 75	97.83 126	96.02 215	97.44 119	94.98 107	95.74 143	97.16 135	98.45 113	95.72 119	97.85 80	97.97 79	98.60 76	97.78 62

TSAR-MVS + GP.		97.26 96	97.33 83	97.18 110	98.21 121	98.06 102	96.38 206	97.66 99	93.92 147	95.23 164	98.48 95	98.33 117	97.41 56	97.63 96	97.35 98	98.18 108	97.57 76

OMC-MVS		97.23 100	97.21 91	97.25 107	97.85 156	97.52 148	97.92 123	95.77 196	95.83 69	97.09 72	97.86 116	98.52 108	96.62 84	97.51 100	96.65 127	98.26 102	96.57 119

3Dnovator	96.31 3	97.22 101	97.19 94	97.25 107	98.14 131	97.95 116	98.03 115	96.77 166	96.42 46	97.14 67	95.11 179	97.59 147	95.14 150	97.79 85	97.72 90	98.26 102	97.76 66

usedtu_dtu_shiyan2		97.20 102	97.35 82	97.03 122	99.23 34	98.25 82	98.34 92	97.49 111	97.86 14	95.90 131	98.27 106	99.30 29	93.22 188	97.41 103	96.26 139	97.99 124	94.14 192

E3new		97.13 103	97.22 89	97.03 122	98.21 121	97.95 116	98.09 108	97.13 146	96.71 39	95.63 150	99.01 59	99.27 34	95.38 139	95.82 162	95.86 160	97.73 143	95.90 151

E3		97.13 103	97.22 89	97.03 122	98.21 121	97.95 116	98.09 108	97.13 146	96.70 40	95.64 149	99.02 58	99.27 34	95.38 139	95.81 163	95.86 160	97.73 143	95.90 151

sasdasda		97.11 105	96.88 115	97.38 96	98.34 101	98.72 54	97.52 154	97.94 80	95.60 81	95.01 174	94.58 193	94.50 191	96.59 86	97.84 81	98.03 75	98.90 58	98.91 9

canonicalmvs		97.11 105	96.88 115	97.38 96	98.34 101	98.72 54	97.52 154	97.94 80	95.60 81	95.01 174	94.58 193	94.50 191	96.59 86	97.84 81	98.03 75	98.90 58	98.91 9

V42		97.10 107	96.97 111	97.26 104	97.64 172	97.60 140	98.45 88	95.99 184	94.44 132	97.35 59	99.40 30	98.63 101	97.34 60	96.33 147	96.38 136	96.82 192	96.00 146

CPTT-MVS		97.08 108	96.25 138	98.05 52	99.21 37	98.30 80	98.54 78	97.98 78	94.28 136	95.89 133	89.57 238	98.54 106	98.18 27	97.82 84	97.32 102	98.54 80	97.91 57

DeepPCF-MVS	94.55 10	97.05 109	97.13 102	96.95 129	96.06 223	97.12 167	98.01 117	95.44 204	95.18 100	97.50 51	97.86 116	98.08 128	97.31 62	97.23 112	97.00 110	97.36 167	97.45 82

QAPM		97.04 110	97.14 99	96.93 131	97.78 167	98.02 108	97.36 169	96.72 167	94.68 120	96.23 114	97.21 133	97.68 143	95.70 120	97.37 105	97.24 106	97.78 141	97.77 64

CNVR-MVS		97.03 111	96.77 126	97.34 98	98.89 67	97.67 137	97.64 147	97.17 141	94.40 134	95.70 147	94.02 203	98.76 91	96.49 94	97.78 86	97.29 105	98.12 114	97.47 81

viewmanbaseed2359cas		97.01 112	97.20 92	96.79 141	98.06 139	97.90 123	97.80 131	96.78 165	96.34 50	94.82 181	98.80 78	99.15 49	95.50 131	96.14 152	96.07 148	97.79 139	96.00 146

casdiffmvs		97.00 113	97.36 81	96.59 151	97.65 171	97.98 113	98.06 111	96.81 162	95.78 72	92.77 229	99.40 30	99.26 38	95.65 125	96.70 135	96.39 135	98.59 77	95.99 148
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		96.99 114	96.70 130	97.34 98	97.89 154	97.23 159	98.33 93	96.96 153	95.57 85	97.12 70	98.99 61	99.40 21	97.23 64	96.22 150	95.45 171	96.50 198	94.02 195

viewdifsd2359ckpt09		96.95 115	96.77 126	97.15 112	98.55 92	98.24 84	97.80 131	97.30 134	94.93 111	95.25 163	98.13 111	98.53 107	95.97 115	95.57 173	95.96 153	98.03 118	96.05 142

viewcassd2359sk11		96.93 116	96.96 112	96.90 133	98.14 131	97.88 124	97.95 119	96.98 152	96.18 55	95.53 156	98.75 84	99.06 54	95.17 146	95.49 177	95.54 167	97.62 153	95.81 155

viewdifsd2359ckpt11		96.92 117	97.45 73	96.31 163	97.53 178	97.42 153	97.70 140	95.37 206	96.93 32	94.17 202	99.27 42	99.52 10	95.11 151	97.33 107	95.90 156	97.98 125	95.79 158

viewmsd2359difaftdt		96.92 117	97.45 73	96.31 163	97.53 178	97.42 153	97.70 140	95.37 206	96.93 32	94.18 201	99.27 42	99.52 10	95.11 151	97.33 107	95.90 156	97.98 125	95.79 158

DELS-MVS		96.90 119	97.24 88	96.50 156	97.85 156	98.18 88	97.88 128	95.92 188	93.48 153	95.34 161	98.86 75	98.94 70	94.03 173	97.33 107	97.04 109	98.00 121	96.85 109
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		96.86 120	96.72 129	97.03 122	97.80 165	97.06 171	97.04 185	95.51 203	94.55 126	97.47 52	97.35 130	97.68 143	96.66 82	97.11 117	96.73 120	97.69 148	96.57 119

PM-MVS		96.85 121	96.62 133	97.11 116	97.13 200	96.51 186	98.29 95	94.65 223	94.84 114	98.12 32	98.59 91	97.20 156	97.41 56	96.24 149	96.41 134	97.09 178	96.56 121

FE-MVSNET		96.84 122	96.84 120	96.84 138	96.93 204	97.58 141	98.49 83	97.43 121	95.70 78	95.08 171	98.40 101	98.08 128	95.17 146	95.92 159	97.05 108	97.96 128	95.14 177

pmmvs-eth3d		96.84 122	96.22 140	97.56 84	97.63 174	96.38 193	98.74 64	96.91 156	94.63 123	98.26 26	99.43 25	98.28 119	96.58 89	94.52 193	95.54 167	97.24 171	94.75 180

CANet		96.81 124	96.50 134	97.17 111	99.10 53	97.96 115	97.86 129	97.51 107	91.30 189	97.75 41	97.64 121	97.89 136	93.39 186	96.98 125	96.73 120	97.40 163	96.99 100

Fast-Effi-MVS+		96.80 125	95.92 151	97.84 67	98.57 90	97.46 151	98.06 111	98.24 53	89.64 210	97.57 48	96.45 152	97.35 152	96.73 79	97.22 113	96.64 128	97.86 134	96.65 115

viewdifsd2359ckpt13		96.79 126	96.77 126	96.81 139	98.08 137	97.83 126	97.74 136	96.79 163	95.30 96	94.89 178	98.41 99	98.88 75	95.57 129	95.61 170	95.49 170	97.81 137	95.87 153

MCST-MVS		96.79 126	96.08 144	97.62 80	98.78 76	97.52 148	98.01 117	97.32 133	93.20 157	95.84 135	93.97 205	98.12 126	97.34 60	96.34 145	95.88 159	98.45 89	97.51 79

UGNet		96.79 126	97.82 50	95.58 189	97.57 177	98.39 74	98.48 85	97.84 91	95.85 68	94.68 185	97.91 115	99.07 53	87.12 241	97.71 89	97.51 94	97.80 138	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	96.79 126	96.70 130	96.90 133	97.64 172	97.58 141	97.54 153	94.50 225	95.14 101	96.64 97	96.76 144	97.90 135	96.63 83	95.98 158	96.14 143	98.45 89	97.39 86
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
E2		96.74 130	96.70 130	96.78 142	98.09 136	97.82 130	97.80 131	96.86 158	95.62 80	95.42 158	98.47 96	98.83 81	94.96 156	95.19 183	95.24 177	97.53 154	95.75 163

CLD-MVS		96.73 131	96.92 113	96.51 155	98.70 81	97.57 144	97.64 147	92.07 239	93.10 163	96.31 113	98.29 104	99.02 60	95.99 114	97.20 114	96.47 132	98.37 98	96.81 110
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
viewdifsd2359ckpt07		96.69 132	97.19 94	96.10 168	98.01 142	97.73 135	97.69 142	96.10 180	97.21 27	94.10 204	99.10 55	99.21 43	95.06 153	96.10 155	94.90 181	95.62 218	96.11 139

MGCFI-Net		96.69 132	96.89 114	96.44 159	98.30 110	98.63 59	97.39 166	97.90 84	95.72 76	91.16 240	94.65 192	94.55 189	95.04 155	97.78 86	98.00 78	98.87 64	98.93 8

train_agg		96.68 134	95.93 150	97.56 84	99.08 55	97.16 163	98.44 91	97.37 126	91.12 193	95.18 167	95.43 174	98.48 111	97.36 58	96.48 141	95.52 169	97.95 129	97.34 90

CDPH-MVS		96.68 134	95.99 147	97.48 91	99.13 49	97.64 138	98.08 110	97.46 114	90.56 199	95.13 168	94.87 187	98.27 120	96.56 90	97.09 118	96.45 133	98.54 80	97.08 99

MSLP-MVS++		96.66 136	96.46 137	96.89 135	98.02 141	97.71 136	95.57 222	96.96 153	94.36 135	96.19 118	91.37 230	98.24 121	97.07 69	97.69 90	97.89 81	97.52 156	97.95 53

TinyColmap		96.64 137	96.07 145	97.32 102	97.84 161	96.40 190	97.63 149	96.25 178	95.86 67	98.98 10	97.94 114	96.34 172	96.17 105	97.30 111	95.38 174	97.04 181	93.24 208

IS_MVSNet		96.62 138	96.48 136	96.78 142	98.46 96	98.68 57	98.61 73	98.24 53	92.23 173	89.63 247	95.90 168	94.40 193	96.23 100	98.65 49	98.77 33	99.52 12	96.76 112

NCCC		96.56 139	95.68 154	97.59 82	99.04 59	97.54 147	97.67 144	97.56 105	94.84 114	96.10 121	87.91 241	98.09 127	96.98 74	97.20 114	96.80 119	98.21 106	97.38 89

WB-MVS		96.54 140	98.09 37	94.73 209	96.68 213	98.34 78	94.77 241	97.39 123	98.12 10	89.72 246	98.95 64	99.32 28	93.33 187	98.67 46	97.88 82	96.47 200	95.38 172

ETV-MVS		96.54 140	95.27 163	98.02 56	99.07 57	97.48 150	98.16 105	98.19 59	87.33 230	97.58 47	92.67 217	95.93 178	96.22 101	98.49 61	98.46 46	98.91 57	96.50 125

Effi-MVS+		96.46 142	95.28 162	97.85 66	98.64 89	97.16 163	97.15 182	98.75 23	90.27 203	98.03 34	93.93 206	96.21 173	96.55 91	96.34 145	96.69 123	97.97 127	96.33 128

IterMVS-LS		96.35 143	95.85 153	96.93 131	97.53 178	98.00 112	97.37 167	97.97 79	95.49 92	96.71 94	98.94 66	93.23 201	94.82 161	93.15 213	95.05 179	97.17 175	97.12 97
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs_AUTHOR		96.30 144	96.79 124	95.73 183	97.43 188	97.06 171	97.24 177	95.65 198	95.76 74	92.97 227	99.35 34	99.21 43	93.99 176	95.61 170	94.85 183	97.09 178	95.65 166

USDC		96.30 144	95.64 156	97.07 118	97.62 175	96.35 195	97.17 181	95.71 197	95.52 90	99.17 7	98.11 112	97.46 149	95.67 122	95.44 179	93.60 201	97.09 178	92.99 212

Vis-MVSNet (Re-imp)		96.29 146	96.50 134	96.05 169	97.96 150	97.83 126	97.30 172	97.86 89	93.14 159	88.90 250	96.80 143	95.28 183	95.15 148	98.37 67	98.25 63	99.12 37	95.84 154

MSDG		96.27 147	96.17 143	96.38 162	97.85 156	96.27 197	96.55 203	94.41 226	94.55 126	95.62 152	97.56 125	97.80 137	96.22 101	97.17 116	96.27 138	97.67 150	93.60 203

CNLPA		96.24 148	95.97 148	96.57 153	97.48 186	97.10 170	96.75 196	94.95 217	94.92 112	96.20 117	94.81 188	96.61 167	96.25 99	96.94 126	95.64 165	97.79 139	95.74 164

EIA-MVS		96.23 149	94.85 175	97.84 67	99.08 55	98.21 86	97.69 142	98.03 75	85.68 240	98.09 33	91.75 228	97.07 159	95.66 124	97.58 97	97.72 90	98.47 87	95.91 150

PLC	92.55 15	96.10 150	95.36 159	96.96 128	98.13 134	96.88 176	96.49 204	96.67 171	94.07 143	95.71 146	91.14 231	96.09 175	96.84 76	96.70 135	96.58 130	97.92 130	96.03 145
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test20.03		96.08 151	96.80 123	95.25 200	99.19 39	97.58 141	97.24 177	97.56 105	94.95 110	91.91 236	98.58 92	98.03 131	87.88 237	97.43 102	96.94 113	97.69 148	94.05 194

FA-MVS(training)		96.07 152	95.59 157	96.63 148	98.00 146	97.44 152	97.36 169	98.53 28	92.21 174	95.97 127	96.18 158	94.22 196	92.98 192	96.79 131	96.70 122	96.95 186	95.56 169

TSAR-MVS + COLMAP		96.05 153	95.94 149	96.18 167	97.46 187	96.41 189	97.26 176	95.83 192	94.69 119	95.30 162	98.31 103	96.52 168	94.71 163	95.48 178	94.87 182	96.54 197	95.33 174

EU-MVSNet		96.03 154	96.23 139	95.80 181	95.48 242	94.18 224	98.99 37	91.51 241	97.22 26	97.66 45	99.15 50	98.51 109	98.08 30	95.92 159	92.88 209	93.09 232	95.72 165

PCF-MVS	92.69 14	95.98 155	95.05 170	97.06 119	98.43 98	97.56 145	97.76 134	96.65 172	89.95 208	95.70 147	96.18 158	98.48 111	95.74 118	93.64 204	93.35 206	98.09 117	96.18 134
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HQP-MVS		95.97 156	95.01 172	97.08 117	98.72 79	97.19 161	97.07 184	96.69 170	91.49 187	95.77 142	92.19 223	97.93 134	96.15 106	94.66 190	94.16 192	98.10 115	97.45 82

Effi-MVS+-dtu		95.94 157	95.08 169	96.94 130	98.54 93	97.38 155	96.66 200	97.89 86	88.68 216	95.92 130	92.90 216	97.28 153	94.18 172	96.68 137	96.13 145	98.45 89	96.51 124

usedtu_dtu_shiyan1		95.91 158	95.40 158	96.50 156	96.40 217	97.12 167	97.95 119	96.35 177	93.25 156	96.07 123	97.21 133	97.22 155	94.48 166	93.47 205	95.28 175	97.74 142	94.28 189

diffmvs		95.86 159	96.21 141	95.44 194	97.25 197	96.85 179	96.99 188	95.23 211	94.96 109	92.82 228	98.89 70	98.85 77	93.52 184	94.21 199	94.25 191	96.84 189	95.49 171
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		95.85 160	94.65 178	97.26 104	98.70 81	97.20 160	97.33 171	97.30 134	91.28 191	95.90 131	88.16 240	96.17 174	96.60 85	97.34 106	96.82 116	97.71 145	95.60 168

viewmambaseed2359dif		95.80 161	95.87 152	95.73 183	97.17 199	96.55 184	97.15 182	95.60 200	93.77 149	93.06 224	98.63 90	98.66 98	94.03 173	94.76 188	93.36 205	97.37 166	95.34 173

FMVSNet2		95.77 162	96.20 142	95.27 198	96.77 209	98.18 88	97.28 173	97.90 84	93.12 160	91.37 238	98.25 107	96.05 176	90.04 219	94.96 187	95.94 154	98.28 99	96.90 103

OpenMVS	94.63 9	95.75 163	95.04 171	96.58 152	97.85 156	97.55 146	96.71 198	96.07 181	90.15 206	96.47 103	90.77 236	95.95 177	94.41 169	97.01 123	96.95 112	98.00 121	96.90 103

pmmvs5		95.70 164	95.22 164	96.26 165	96.55 216	97.24 158	97.50 156	94.99 216	90.95 195	96.87 82	98.47 96	97.40 150	94.45 167	92.86 214	94.98 180	97.23 172	94.64 183

Anonymous20231206		95.69 165	95.68 154	95.70 185	98.32 105	96.95 174	97.37 167	96.65 172	93.33 154	93.61 213	98.70 88	98.03 131	91.04 207	95.07 185	94.59 190	97.20 173	93.09 211

MAR-MVS		95.51 166	94.49 182	96.71 144	97.92 152	96.40 190	96.72 197	98.04 74	86.74 234	96.72 91	92.52 220	95.14 185	94.02 175	96.81 130	96.54 131	96.85 187	97.25 93
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		95.48 167	94.51 180	96.61 149	97.13 200	97.30 157	98.05 113	96.79 163	93.75 150	95.08 171	96.38 153	89.76 223	94.95 157	93.97 203	94.82 187	97.64 152	95.63 167

MDA-MVSNet-bldmvs		95.45 168	95.20 165	95.74 182	94.24 247	96.38 193	97.93 122	94.80 218	95.56 88	96.87 82	98.29 104	95.24 184	96.50 93	98.65 49	90.38 221	94.09 225	91.93 218

PVSNet_BlendedMVS		95.44 169	95.09 167	95.86 177	97.31 194	97.13 165	96.31 209	95.01 214	88.55 219	96.23 114	94.55 197	97.75 138	92.56 200	96.42 142	95.44 172	97.71 145	95.81 155

PVSNet_Blended		95.44 169	95.09 167	95.86 177	97.31 194	97.13 165	96.31 209	95.01 214	88.55 219	96.23 114	94.55 197	97.75 138	92.56 200	96.42 142	95.44 172	97.71 145	95.81 155

pmmvs4		95.37 171	94.25 183	96.67 147	97.01 203	95.28 217	97.60 150	96.07 181	93.11 161	97.29 62	98.09 113	94.23 195	95.21 145	91.56 225	93.91 198	96.82 192	93.59 204

MVS_Test		95.34 172	94.88 174	95.89 176	96.93 204	96.84 180	96.66 200	97.08 148	90.06 207	94.02 205	97.61 122	96.64 166	93.59 183	92.73 217	94.02 196	97.03 182	96.24 131

GBi-Net		95.21 173	95.35 160	95.04 203	96.77 209	98.18 88	97.28 173	97.58 102	88.43 221	90.28 243	96.01 162	92.43 209	90.04 219	97.67 92	97.86 84	98.28 99	96.90 103

test1		95.21 173	95.35 160	95.04 203	96.77 209	98.18 88	97.28 173	97.58 102	88.43 221	90.28 243	96.01 162	92.43 209	90.04 219	97.67 92	97.86 84	98.28 99	96.90 103

IterMVS-SCA-FT		95.16 175	93.95 187	96.56 154	97.89 154	96.69 182	96.94 190	96.05 183	93.06 164	97.35 59	98.79 79	91.45 214	95.93 116	92.78 215	91.00 219	95.22 221	93.91 197

HyFIR lowres test		95.05 176	93.54 192	96.81 139	97.81 164	96.88 176	98.18 102	97.46 114	94.28 136	94.98 177	96.57 149	92.89 207	96.15 106	90.90 230	91.87 215	96.28 204	91.35 219

CHOSEN 1792x2688		94.98 177	94.69 177	95.31 196	97.27 196	95.58 209	97.90 125	95.56 202	95.03 105	93.77 212	95.65 172	99.29 30	95.30 141	91.51 226	91.28 218	92.05 242	94.50 185

CANet_DTU		94.96 178	94.62 179	95.35 195	98.03 140	96.11 199	96.92 192	95.60 200	88.59 218	97.27 63	95.27 177	96.50 169	88.77 233	95.53 174	95.59 166	95.54 219	94.78 179

CDS-MVSNet		94.91 179	95.17 166	94.60 213	97.85 156	96.21 198	96.90 194	96.39 175	90.81 196	93.40 217	97.24 132	94.54 190	85.78 247	96.25 148	96.15 142	97.26 170	95.01 178
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
DPM-MVS		94.86 180	93.90 189	95.99 171	98.19 126	96.52 185	96.29 211	95.95 185	93.11 161	94.61 187	88.17 239	96.44 170	93.77 181	93.33 208	93.54 203	97.11 177	96.22 132

MS-PatchMatch		94.84 181	94.76 176	94.94 206	96.38 218	94.69 223	95.90 217	94.03 228	92.49 168	93.81 210	95.79 169	96.38 171	94.54 164	94.70 189	94.85 183	94.97 223	94.43 187

thisisatest0530		94.81 182	93.06 198	96.85 137	98.01 142	97.18 162	96.93 191	97.36 127	89.73 209	95.80 140	94.98 183	77.88 244	94.89 158	96.73 133	97.35 98	98.13 113	97.54 77

tttt0517		94.81 182	93.04 199	96.88 136	98.15 130	97.37 156	96.99 188	97.36 127	89.51 211	95.74 143	94.89 185	77.53 246	94.89 158	96.94 126	97.35 98	98.17 109	97.70 67

testgi		94.81 182	96.05 146	93.35 225	99.06 58	96.87 178	97.57 152	96.70 169	95.77 73	88.60 252	93.19 214	98.87 76	81.21 255	97.03 122	96.64 128	96.97 185	93.99 196

PatchMatch-RL		94.79 185	93.75 191	96.00 170	96.80 208	95.00 220	95.47 227	95.25 210	90.68 198	95.80 140	92.97 215	93.64 198	95.67 122	96.13 154	95.81 162	96.99 184	92.01 217

FPMVS		94.70 186	94.99 173	94.37 215	95.84 231	93.20 229	96.00 216	91.93 240	95.03 105	94.64 186	94.68 189	93.29 200	90.95 208	98.07 76	97.34 101	96.85 187	93.29 207

new-patchmatchnet		94.48 187	94.02 185	95.02 205	97.51 184	95.00 220	95.68 221	94.26 227	97.32 23	95.73 145	99.60 12	98.22 125	91.30 203	94.13 200	84.41 239	95.65 217	89.45 231

IterMVS		94.48 187	93.46 194	95.66 186	97.52 181	96.43 187	97.20 179	94.73 221	92.91 167	96.44 104	98.75 84	91.10 216	94.53 165	92.10 221	90.10 223	93.51 228	92.84 216
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MDTV_nov1_ep13_2view		94.39 189	93.34 195	95.63 187	97.23 198	95.33 216	97.76 134	96.84 160	94.55 126	97.47 52	98.96 62	97.70 141	93.88 178	92.27 219	86.81 229	90.56 244	87.73 241

Fast-Effi-MVS+-dtu		94.34 190	93.26 197	95.62 188	97.82 162	95.97 202	95.86 218	99.01 13	86.88 232	93.39 218	90.83 234	95.46 182	90.61 212	94.46 195	94.68 188	97.01 183	94.51 184

thres600view7		94.34 190	92.31 208	96.70 145	98.19 126	98.12 97	97.85 130	97.45 116	91.49 187	93.98 207	84.27 244	82.02 235	94.24 171	97.04 119	98.76 34	98.49 84	94.47 186

EPNet		94.33 192	93.52 193	95.27 198	98.81 74	94.71 222	96.77 195	98.20 57	88.12 224	96.53 101	92.53 219	91.19 215	85.25 251	95.22 182	95.26 176	96.09 209	97.63 74
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test2506		94.29 193	91.43 221	97.64 79	98.66 86	98.83 34	98.50 79	98.40 37	96.04 57	94.45 190	94.88 186	55.05 266	96.70 80	99.28 14	99.04 19	99.14 33	96.87 107

GA-MVS		94.18 194	92.98 200	95.58 189	97.36 191	96.42 188	96.21 212	95.86 189	90.29 202	95.08 171	96.19 157	85.37 227	92.82 196	94.01 202	94.14 193	96.16 208	94.41 188

gg-mvs-nofinetune		94.13 195	93.93 188	94.37 215	97.99 147	95.86 203	95.45 230	99.22 9	97.61 17	95.10 170	99.50 19	84.50 228	81.73 254	95.31 180	94.12 194	96.71 195	90.59 223

baseline		94.07 196	94.50 181	93.57 223	96.34 219	93.40 228	95.56 225	92.39 234	92.07 177	94.00 206	98.24 108	97.51 148	89.19 227	91.75 223	92.72 210	93.96 227	95.79 158

FMVSNet3		94.06 197	93.85 190	94.31 218	95.46 243	97.80 133	96.34 207	97.58 102	88.43 221	90.28 243	96.01 162	92.43 209	88.67 234	91.82 222	93.96 197	97.53 154	96.50 125

thres400		94.04 198	91.94 214	96.50 156	97.98 149	97.82 130	97.66 146	96.96 153	90.96 194	94.20 198	83.24 246	82.82 233	93.80 179	96.50 140	98.09 71	98.38 97	94.15 191

dmvs_re		94.02 199	92.39 206	95.91 175	97.71 169	95.43 211	97.00 187	95.94 186	82.49 249	94.61 187	83.69 245	93.01 206	92.71 197	97.83 83	97.56 93	97.50 157	96.73 113

CVMVSNet		94.01 200	94.25 183	93.73 222	94.36 246	92.44 232	97.45 159	88.56 245	95.59 83	93.06 224	98.88 71	90.03 222	94.84 160	94.08 201	93.45 204	94.09 225	95.31 175

thres200		93.98 201	91.90 215	96.40 161	97.66 170	98.12 97	97.20 179	97.45 116	90.16 205	93.82 209	83.08 247	83.74 231	93.80 179	97.04 119	97.48 96	98.49 84	93.70 200

gbinet_0.2-2-1-0.02		93.92 202	92.20 212	95.93 174	96.24 220	95.75 204	98.05 113	93.85 230	91.55 186	96.68 95	96.95 140	92.86 208	95.06 153	88.67 235	85.96 233	95.71 216	93.65 202

blended_shiyan8		93.92 202	92.28 210	95.83 179	95.93 229	95.67 207	97.71 138	92.63 232	92.35 171	96.92 78	95.99 165	93.23 201	95.60 128	88.33 236	86.73 230	96.18 206	93.70 200

blended_shiyan6		93.92 202	92.29 209	95.82 180	95.95 227	95.66 208	97.72 137	92.62 233	92.31 172	96.89 81	95.96 166	93.33 199	95.55 130	88.31 237	86.73 230	96.17 207	93.73 198

baseline1		93.89 205	92.82 202	95.14 202	97.62 175	96.97 173	96.12 213	96.36 176	91.30 189	91.53 237	94.68 189	80.72 237	90.80 210	95.71 167	96.29 137	98.44 93	94.09 193

tfpn200view9		93.80 206	91.75 218	96.20 166	97.52 181	98.15 95	97.48 158	97.47 113	87.65 226	93.56 215	83.03 248	84.12 229	92.62 199	97.04 119	98.09 71	98.52 83	94.17 190

MIMVSNet		93.68 207	93.96 186	93.35 225	97.82 162	96.08 200	96.34 207	98.46 34	91.28 191	86.67 257	94.95 184	94.87 187	84.39 252	94.53 191	94.65 189	96.45 201	91.34 220

pmnet_mix02		93.59 208	92.65 203	94.69 211	96.76 212	94.16 225	97.03 186	93.00 231	95.79 71	96.03 126	98.91 68	97.69 142	92.99 191	90.03 233	84.10 241	92.35 240	87.89 240

wanda-best-256-512		93.50 209	91.78 216	95.51 191	95.64 235	95.41 212	97.43 161	92.21 235	91.80 179	96.77 88	95.73 170	93.11 203	95.28 142	87.72 239	85.73 234	95.75 212	92.99 212

FE-blended-shiyan7		93.50 209	91.78 216	95.51 191	95.64 235	95.41 212	97.43 161	92.21 235	91.80 179	96.77 88	95.73 170	93.11 203	95.28 142	87.72 239	85.73 234	95.75 212	92.99 212

EPNet_dtu		93.45 211	92.51 205	94.55 214	98.39 100	91.67 242	95.46 228	97.50 109	86.56 235	97.38 57	93.52 209	94.20 197	85.82 246	93.31 210	92.53 211	92.72 235	95.76 162
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IB-MVS	92.44 16	93.33 212	92.15 213	94.70 210	97.42 189	96.39 192	95.57 222	94.67 222	86.40 238	93.59 214	78.28 255	95.76 180	89.59 225	95.88 161	95.98 152	97.39 164	96.34 127
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		93.18 213	90.80 224	95.95 172	96.05 224	96.07 201	96.92 192	96.51 174	89.34 212	95.63 150	94.08 202	72.31 261	93.13 189	94.33 197	94.83 185	97.44 160	94.65 182

thres100view900		92.93 214	90.89 223	95.31 196	97.52 181	96.82 181	96.41 205	95.08 212	87.65 226	93.56 215	83.03 248	84.12 229	91.12 206	94.53 191	96.91 114	98.17 109	93.21 209

N_pmnet		92.46 215	92.38 207	92.55 231	97.91 153	93.47 227	97.42 164	94.01 229	96.40 48	88.48 253	98.50 94	98.07 130	88.14 236	91.04 229	84.30 240	89.35 249	84.85 247

TAMVS		92.46 215	93.34 195	91.44 240	97.03 202	93.84 226	94.68 242	90.60 242	90.44 201	85.31 258	97.14 136	93.03 205	85.78 247	94.34 196	93.67 200	95.22 221	90.93 222

CMPMVS	71.81 19	92.34 217	92.85 201	91.75 237	92.70 251	90.43 249	88.84 259	88.56 245	85.87 239	94.35 194	90.98 232	95.89 179	91.14 205	96.14 152	94.83 185	94.93 224	95.78 161
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
baseline2		92.06 218	89.82 227	94.68 212	97.32 192	95.72 205	94.97 238	95.08 212	84.75 243	94.34 196	90.68 237	77.75 245	90.13 218	93.38 206	93.58 202	96.25 205	92.90 215

MVSTER		91.97 219	90.31 225	93.91 220	96.81 207	96.91 175	94.22 243	95.64 199	84.98 241	92.98 226	93.42 210	72.56 259	86.64 245	95.11 184	93.89 199	97.16 176	95.31 175

CR-MVSNet		91.94 220	88.50 230	95.94 173	96.14 222	92.08 237	95.23 233	98.47 32	84.30 245	96.44 104	94.58 193	75.57 247	92.92 193	90.22 231	92.22 212	96.43 202	90.56 224

gm-plane-assit		91.85 221	87.91 232	96.44 159	99.14 47	98.25 82	99.02 32	97.38 125	95.57 85	98.31 25	99.34 36	51.00 267	88.93 230	93.16 212	91.57 216	95.85 210	86.50 244

PMMVS		91.67 222	91.47 220	91.91 236	89.43 256	88.61 255	94.99 237	85.67 250	87.50 228	93.80 211	94.42 200	94.88 186	90.71 211	92.26 220	92.96 208	96.83 190	89.65 229

CHOSEN 280x420		91.55 223	90.27 226	93.05 228	94.61 245	88.01 256	96.56 202	94.62 224	88.04 225	94.20 198	92.66 218	86.60 225	90.82 209	95.06 186	91.89 214	87.49 254	89.61 230

PatchT		91.40 224	88.54 229	94.74 208	91.48 255	92.18 235	97.42 164	97.51 107	84.96 242	96.44 104	94.16 201	75.47 248	92.92 193	90.22 231	92.22 212	92.66 238	90.56 224

pmmvs3		91.20 225	91.40 222	90.96 242	91.71 254	91.08 244	95.41 231	81.34 257	87.36 229	94.57 189	95.02 181	94.30 194	90.42 213	94.28 198	89.26 225	92.30 241	88.49 237

test0.0.03 1		91.17 226	91.50 219	90.80 243	98.01 142	95.46 210	94.22 243	95.80 193	86.55 236	81.75 260	90.83 234	87.93 224	78.48 256	94.51 194	94.11 195	96.50 198	91.08 221

SCA		91.15 227	87.65 234	95.23 201	96.15 221	95.68 206	96.68 199	98.18 61	90.46 200	97.21 66	92.44 221	80.17 239	93.51 185	86.04 247	83.58 244	89.68 248	85.21 246

new_pmnet		90.85 228	92.26 211	89.21 249	93.68 250	89.05 254	93.20 252	84.16 254	92.99 165	84.25 259	97.72 119	94.60 188	86.80 244	93.20 211	91.30 217	93.21 230	86.94 243

RPMNet		90.52 229	86.27 245	95.48 193	95.95 227	92.08 237	95.55 226	98.12 66	84.30 245	95.60 153	87.49 242	72.78 258	91.24 204	87.93 238	89.34 224	96.41 203	89.98 227

MDTV_nov1_ep13		90.30 230	87.32 238	93.78 221	96.00 226	92.97 230	95.46 228	95.39 205	88.61 217	95.41 159	94.45 199	80.39 238	89.87 222	86.58 245	83.54 245	90.56 244	84.71 248

FE-MVSNET3		90.29 231	86.44 242	94.78 207	95.64 235	95.41 212	97.43 161	92.21 235	91.80 179	92.27 231	77.48 257	73.25 254	95.41 133	87.72 239	85.73 234	95.75 212	93.73 198

PatchmatchNet		89.98 232	86.23 246	94.36 217	96.56 215	91.90 241	96.07 214	96.72 167	90.18 204	96.87 82	93.36 213	78.06 243	91.46 202	84.71 252	81.40 249	88.45 251	83.97 252
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
usedtu_blend_shiyan5		89.91 233	86.39 243	94.01 219	95.64 235	95.41 212	92.79 255	92.21 235	91.80 179	92.27 231	77.47 258	73.25 254	95.41 133	87.72 239	85.73 234	95.75 212	93.36 205

ADS-MVSNet		89.89 234	87.70 233	92.43 233	95.52 240	90.91 247	95.57 222	95.33 208	93.19 158	91.21 239	93.41 211	82.12 234	89.05 228	86.21 246	83.77 243	87.92 252	84.31 249

tpm		89.84 235	86.81 240	93.36 224	96.60 214	91.92 240	95.02 236	97.39 123	86.79 233	96.54 100	95.03 180	69.70 262	87.66 238	88.79 234	86.19 232	86.95 256	89.27 232

test-LLR		89.77 236	87.47 236	92.45 232	98.01 142	89.77 251	93.25 250	95.80 193	81.56 251	89.19 248	92.08 224	79.59 240	85.77 249	91.47 227	89.04 227	92.69 236	88.75 233

FMVSNet5		89.65 237	87.60 235	92.04 235	95.63 239	96.61 183	94.82 240	94.75 219	80.11 255	87.72 255	77.73 256	73.81 251	83.81 253	95.64 168	96.08 147	95.49 220	93.21 209

EPMVS		89.28 238	86.28 244	92.79 230	96.01 225	92.00 239	95.83 219	95.85 191	90.78 197	91.00 241	94.58 193	74.65 249	88.93 230	85.00 250	82.88 247	89.09 250	84.09 251

test-mter		89.16 239	88.14 231	90.37 245	94.79 244	91.05 245	93.60 249	85.26 251	81.65 250	88.32 254	92.22 222	79.35 242	87.03 242	92.28 218	90.12 222	93.19 231	90.29 226

CostFormer		89.06 240	85.65 247	93.03 229	95.88 230	92.40 233	95.30 232	95.86 189	86.49 237	93.12 223	93.40 212	74.18 250	88.25 235	82.99 253	81.46 248	89.77 247	88.66 235

MVS-HIRNet		88.72 241	86.49 241	91.33 241	91.81 253	85.66 257	87.02 261	96.25 178	81.48 253	94.82 181	96.31 156	92.14 212	90.32 215	87.60 243	83.82 242	87.74 253	78.42 256

TESTMET0.1,1		88.60 242	87.47 236	89.93 247	94.23 248	89.77 251	93.25 250	84.47 253	81.56 251	89.19 248	92.08 224	79.59 240	85.77 249	91.47 227	89.04 227	92.69 236	88.75 233

dps		88.36 243	84.32 250	93.07 227	93.86 249	92.29 234	94.89 239	95.93 187	83.50 247	93.13 221	91.87 226	67.79 264	90.32 215	85.99 248	83.22 246	90.28 246	85.56 245

tpmrst		87.60 244	84.13 251	91.66 239	95.65 234	89.73 253	93.77 246	94.74 220	88.85 214	93.35 220	95.60 173	72.37 260	87.40 239	81.24 254	78.19 254	85.02 259	82.90 255

blend_shiyan4		87.32 245	83.58 252	91.68 238	85.86 260	95.01 219	90.28 256	90.47 243	74.69 260	92.27 231	77.47 258	73.25 254	95.41 133	85.88 249	85.38 238	95.81 211	93.36 205

tpm cat1		87.19 246	82.78 253	92.33 234	95.66 233	90.61 248	94.19 245	95.27 209	86.97 231	94.38 192	90.91 233	69.40 263	87.21 240	79.57 257	77.82 255	87.25 255	84.18 250

E-PMN		86.94 247	85.10 248	89.09 251	95.77 232	83.54 260	89.89 258	86.55 247	92.18 175	87.34 256	94.02 203	83.42 232	89.63 224	93.32 209	77.11 256	85.33 257	72.09 257

EMVS		86.63 248	84.48 249	89.15 250	95.51 241	83.66 259	90.19 257	86.14 249	91.78 183	88.68 251	93.83 207	81.97 236	89.05 228	92.76 216	76.09 257	85.31 258	71.28 258

PMMVS2		86.47 249	92.62 204	79.29 253	92.01 252	85.63 258	93.74 247	86.37 248	93.95 146	54.18 265	98.19 109	97.39 151	58.46 257	96.57 139	93.07 207	90.99 243	83.55 254

0.4-1-1-0.1		86.09 250	82.27 254	90.55 244	88.91 257	92.09 236	93.74 247	84.65 252	77.28 257	92.48 230	81.76 251	73.62 252	90.27 217	80.00 256	81.27 250	93.27 229	89.84 228

MVE	72.99 18	85.37 251	89.43 228	80.63 252	74.43 261	71.94 262	88.25 260	89.81 244	93.27 155	67.32 263	96.32 155	91.83 213	90.40 214	93.36 207	90.79 220	73.55 262	88.49 237
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		85.22 252	81.12 256	90.00 246	88.32 258	91.29 243	93.16 253	83.68 255	76.11 258	92.27 231	79.38 253	73.25 254	89.78 223	78.77 259	80.48 251	92.78 234	88.53 236

0.4-1-1-0.2		85.13 253	81.17 255	89.76 248	88.18 259	90.98 246	92.83 254	83.39 256	75.70 259	92.15 235	80.54 252	73.62 252	89.49 226	78.89 258	80.15 252	92.48 239	88.30 239

test_method		61.30 254	70.45 257	50.62 254	22.69 263	30.92 264	68.31 264	25.76 259	80.56 254	68.71 261	82.80 250	91.08 217	44.64 258	80.50 255	56.70 258	73.64 261	70.58 259

GG-mvs-BLEND		61.03 255	87.02 239	30.71 256	0.74 266	90.01 250	78.90 263	0.74 263	84.56 244	9.46 266	79.17 254	90.69 220	1.37 262	91.74 224	89.13 226	93.04 233	83.83 253

testmvs		4.99 256	6.88 258	2.78 258	1.73 264	2.04 266	3.10 267	1.71 261	7.27 261	3.92 268	12.18 261	6.71 268	3.31 261	6.94 260	5.51 260	2.94 264	7.51 260

test123		4.41 257	5.71 259	2.88 257	1.28 265	2.21 265	3.09 268	1.65 262	6.35 262	4.98 267	8.53 262	3.88 269	3.46 260	5.79 261	5.71 259	2.85 265	7.50 261

uanet_test		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet-low-res		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

TestfortrainingZip							98.92 44	97.17 141		94.34 196						98.14 111

TPM-MVS					97.49 185	96.32 196	95.05 235			94.36 193	91.82 227	96.92 164	88.89 232			96.67 196	96.22 132
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												96.98 162

SR-MVS					99.33 30			98.40 37				98.90 71

Anonymous202405211			97.39 76		98.85 70	98.59 61	97.89 127	97.93 82	94.41 133		97.37 129	96.99 161	93.09 190	98.61 52	98.46 46	99.11 38	97.27 91

our_test_3					97.32 192	95.13 218	97.59 151

ambc			96.78 125		99.01 60	97.11 169	95.73 220		95.91 65	99.25 3	98.56 93	97.17 157	97.04 70	96.76 132	95.22 178	96.72 194	96.73 113

MTAPA										97.43 56		99.27 34

MTMP										97.63 46		99.03 59

Patchmatch-RL test							17.42 266

tmp_tt				45.72 255	60.00 262	38.74 263	45.50 265	12.18 260	79.58 256	68.42 262	67.62 260	65.04 265	22.12 259	84.83 251	78.72 253	66.08 263

XVS					99.48 18	98.76 46	99.22 21			96.40 108		98.78 88				98.94 55

X-MVStestdata					99.48 18	98.76 46	99.22 21			96.40 108		98.78 88				98.94 55

mPP-MVS					99.58 6							98.98 63

NP-MVS									89.27 213

Patchmtry						92.70 231	95.23 233	98.47 32		96.44 104

DeepMVS_CX						72.99 261	80.14 262	37.34 258	83.46 248	60.13 264	84.40 243	85.48 226	86.93 243	87.22 244		79.61 260	87.32 242

High-resolution multi-view benchmark