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 45	99.11 15	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 15	99.32 8	99.64 2	99.19 10	98.05 11	99.19 6	99.74 4	98.96 72	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 11	99.62 1	99.63 4	99.45 1	97.75 17	98.47 22	99.71 5	99.05 61	98.88 4	99.54 5	99.49 2	99.81 1	98.87 11

PS-CasMVS		99.08 4	98.90 12	99.28 3	99.65 3	99.56 4	99.59 6	99.39 3	96.36 53	98.83 14	99.46 21	99.09 53	98.62 10	99.51 7	99.36 8	99.63 3	98.97 7

PEN-MVS		99.08 4	98.95 9	99.23 5	99.65 3	99.59 2	99.64 2	99.34 6	96.68 45	98.65 17	99.43 25	99.33 27	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 56	99.11 15	99.57 9	98.82 19	98.21 9	99.25 3	99.84 2	99.59 7	98.76 6	99.23 19	98.83 33	98.63 76	98.40 36

DTE-MVSNet		99.03 6	98.88 13	99.21 6	99.66 2	99.59 2	99.62 5	99.34 6	96.92 36	98.52 19	99.36 34	98.98 68	98.57 13	99.49 9	99.23 12	99.56 9	98.55 28

TDRefinement		99.00 8	99.13 6	98.86 10	98.99 66	99.05 20	99.58 7	98.29 49	98.96 4	97.96 36	99.40 31	98.67 104	98.87 5	99.60 3	99.46 4	99.46 18	98.74 17

WR-MVS_H		98.97 9	98.82 15	99.14 8	99.56 9	99.56 4	99.54 11	99.42 2	96.07 60	98.37 24	99.34 37	99.09 53	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 11	99.33 7	98.73 67	99.37 4	98.87 5	97.86 38	99.27 43	99.78 2	96.59 88	99.52 6	99.40 6	99.67 2	98.21 45

CP-MVSNet		98.91 11	98.61 20	99.25 4	99.63 5	99.50 6	99.55 10	99.36 5	95.53 94	98.77 16	99.11 59	98.64 108	98.57 13	99.42 11	99.28 11	99.61 4	98.78 14

anonymousdsp		98.85 12	98.88 13	98.83 11	98.69 86	98.20 92	99.68 1	97.35 134	97.09 33	98.98 10	99.86 1	99.43 20	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	98.32 108	98.92 26	98.57 75	99.03 12	99.36 1	96.86 85	99.77 3	99.86 1	96.20 105	99.56 4	99.39 7	99.59 6	98.61 25

ACMH	95.26 7	98.75 14	98.93 10	98.54 25	98.86 71	99.01 22	99.58 7	98.10 69	98.67 6	97.30 61	99.18 51	99.42 21	98.40 19	99.19 21	98.86 31	98.99 48	98.19 46
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 15	98.66 20	99.14 49	98.79 42	99.30 17	97.67 100	98.33 8	97.82 40	99.20 49	99.18 48	98.76 6	99.27 17	98.96 23	99.29 27	98.03 51
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 23	98.73 15	99.83 1	99.28 9	98.56 77	99.24 8	96.04 61	97.12 70	98.44 108	98.95 73	98.17 28	99.15 24	99.00 22	99.48 17	99.33 3

DeepC-MVS	96.08 5	98.58 17	98.49 25	98.68 18	99.37 27	98.52 70	99.01 36	98.17 63	97.17 32	98.25 27	99.56 15	99.62 6	98.29 22	98.40 65	98.09 73	98.97 50	98.08 49
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
RA-MVS		98.57 18	98.98 8	98.08 47	99.63 5	99.20 10	97.99 122	98.14 66	97.80 15	96.65 97	99.24 47	99.73 5	97.31 62	98.99 29	99.17 14	98.79 71	98.76 15

TranMVSNet+NR-MVSNet		98.45 19	98.22 34	98.72 17	99.32 32	99.06 18	98.99 37	98.89 14	95.52 95	97.53 49	99.42 30	98.83 89	98.01 34	98.55 56	98.34 59	99.57 8	97.80 64

CSCG		98.45 19	98.61 20	98.26 37	99.11 53	99.06 18	98.17 107	97.49 113	97.93 13	97.37 58	98.88 78	99.29 31	98.10 29	98.40 65	97.51 98	99.32 25	99.16 4

DVP-MVS++		98.44 21	98.92 11	97.88 64	99.17 42	99.00 23	98.89 49	98.26 51	97.54 20	96.05 125	99.35 35	99.76 3	96.34 100	98.79 38	98.65 42	98.56 82	99.35 2

Gipuma		98.43 22	98.15 37	98.76 14	99.00 65	98.29 85	97.91 128	98.06 71	99.02 3	99.50 1	96.33 166	98.67 104	99.22 1	99.02 27	98.02 79	98.88 63	97.66 72
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ACMH+	94.90 8	98.40 23	98.71 18	98.04 54	98.93 68	98.84 35	99.30 17	97.86 91	97.78 16	94.19 204	98.77 90	99.39 23	98.61 11	99.33 13	99.07 15	99.33 23	97.81 63

ACMMPR		98.31 24	98.07 42	98.60 23	99.58 7	98.83 36	99.09 27	98.48 31	96.25 56	97.03 74	96.81 154	99.09 53	98.39 20	98.55 56	98.45 50	99.01 45	98.53 31

APDe-MVS		98.29 25	98.42 28	98.14 40	99.45 22	98.90 27	99.18 23	98.30 47	95.96 68	95.13 169	98.79 87	99.25 40	97.92 38	98.80 36	98.71 37	98.85 66	98.54 29
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS		98.27 26	98.61 20	97.87 65	99.17 42	99.03 21	99.07 30	98.17 63	96.75 42	94.35 198	98.92 73	99.58 8	97.86 41	98.67 47	98.70 38	98.63 76	98.63 23
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 27	98.72 17	97.66 80	98.22 123	98.73 54	98.66 70	98.03 76	98.60 7	96.40 109	99.60 12	98.24 130	95.26 149	99.19 21	99.05 18	99.36 20	97.64 73

DU-MVS		98.23 27	97.74 63	98.81 12	99.23 35	98.77 45	98.76 61	98.88 15	94.10 147	98.50 20	98.87 80	98.32 127	97.99 35	98.40 65	98.08 76	99.49 16	97.64 73

UniMVSNet (Re)		98.23 27	97.85 52	98.67 19	99.15 46	98.87 29	98.74 64	98.84 17	94.27 145	97.94 37	99.01 65	98.39 123	97.82 42	98.35 70	98.29 64	99.51 15	97.78 65

MIMVSNet1		98.22 30	98.51 24	97.87 65	99.40 26	98.82 40	99.31 16	98.53 28	97.39 23	96.59 100	99.31 39	99.23 42	94.76 168	98.93 33	98.67 40	98.63 76	97.25 97

HFP-MVS		98.17 31	98.02 43	98.35 35	99.36 28	98.62 62	98.79 60	98.46 34	96.24 57	96.53 102	97.13 149	98.98 68	98.02 33	98.20 73	98.42 52	98.95 54	98.54 29

Baseline_NR-MVSNet		98.17 31	97.90 49	98.48 29	99.23 35	98.59 63	98.83 57	98.73 24	93.97 154	96.95 77	99.66 7	98.23 132	97.90 39	98.40 65	99.06 17	99.25 29	97.42 88

MED-MVS		98.16 33	98.49 25	97.77 75	99.17 42	98.85 31	98.51 79	97.93 83	97.26 27	95.03 175	99.43 25	99.08 56	97.16 67	98.47 63	98.42 52	98.85 66	97.91 59

TSAR-MVS + MP.		98.15 34	98.23 32	98.06 52	98.47 98	98.16 97	99.23 20	96.87 161	95.58 89	96.72 91	98.41 109	99.06 58	98.05 32	98.99 29	98.90 27	99.00 46	98.51 32
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 35	98.66 19	97.53 89	97.93 155	98.49 73	98.14 110	98.19 59	97.95 12	96.17 120	99.63 10	98.85 85	95.41 138	98.91 34	98.89 28	99.34 22	97.86 62

SMA-MVS		98.13 36	98.22 34	98.02 57	99.44 24	98.73 54	98.24 102	97.87 90	95.22 103	96.76 90	98.66 98	99.35 25	97.03 73	98.53 59	98.39 55	98.80 69	98.69 19
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 37	98.08 41	98.18 39	99.34 29	98.74 53	98.97 39	98.00 78	95.13 107	96.90 79	97.54 137	99.27 35	97.18 66	98.72 43	98.45 50	98.68 75	98.69 19

UniMVSNet_NR-MVSNet		98.12 37	97.56 73	98.78 13	99.13 50	98.89 28	98.76 61	98.78 20	93.81 157	98.50 20	98.81 85	97.64 156	97.99 35	98.18 76	97.92 82	99.53 10	97.64 73

ACMM	94.29 11	98.12 37	97.71 64	98.59 24	99.51 17	98.58 65	99.24 19	98.25 52	96.22 58	96.90 79	95.01 195	98.89 79	98.52 16	98.66 49	98.32 62	99.13 36	98.28 42
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SteuartSystems-ACMMP		98.06 40	97.78 58	98.39 33	99.54 11	98.79 42	98.94 43	98.42 36	93.98 152	95.85 135	96.66 160	99.25 40	98.61 11	98.71 45	98.38 56	98.97 50	98.67 22
Skip Steuart: Steuart Systems R&D Blog.
SED-MVS		98.05 41	98.46 27	97.57 85	99.01 62	98.99 24	98.82 59	98.24 53	95.76 78	94.70 188	98.96 68	99.49 16	96.19 106	98.74 39	98.65 42	98.46 91	98.63 23

OPM-MVS		98.01 42	98.01 44	98.00 59	99.11 53	98.12 102	98.68 68	97.72 98	96.65 47	96.68 95	98.40 111	99.28 34	97.44 55	98.20 73	97.82 90	98.40 98	97.58 78
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet		98.01 42	98.42 28	97.54 88	96.89 219	98.82 40	99.14 24	97.59 103	96.30 55	97.04 73	99.26 46	98.83 89	96.01 115	98.73 41	98.21 66	98.58 81	98.75 16
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS		98.00 44	97.38 81	98.73 15	98.72 81	99.15 12	99.12 26	98.76 21	91.58 196	98.15 31	96.70 158	98.72 102	98.20 24	98.64 52	98.92 25	99.43 19	97.97 54

NR-MVSNet		98.00 44	97.88 50	98.13 41	98.33 106	98.77 45	98.83 57	98.88 15	94.10 147	97.46 55	98.87 80	98.58 113	95.78 120	99.13 25	98.16 70	99.52 12	97.53 81

CP-MVS		98.00 44	97.57 72	98.50 26	99.47 21	98.56 67	98.91 47	98.38 42	94.71 124	97.01 75	95.20 191	99.06 58	98.20 24	98.61 53	98.46 47	99.02 43	98.40 36

DPE-MVS		97.99 47	98.12 38	97.84 68	98.65 91	98.86 30	98.86 53	98.05 74	94.18 146	95.49 158	98.90 76	99.33 27	97.11 69	98.53 59	98.65 42	98.86 65	98.39 38
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ACMMP		97.99 47	97.60 71	98.45 31	99.53 15	98.83 36	99.13 25	98.30 47	94.57 131	96.39 113	95.32 189	98.95 73	98.37 21	98.61 53	98.47 46	99.00 46	98.45 33
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 49	97.53 74	98.50 26	99.56 9	98.58 65	98.97 39	98.39 41	93.49 161	97.14 67	96.08 173	99.23 42	98.06 31	98.50 61	98.38 56	98.90 58	98.44 34
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
EG-PatchMatch MVS		97.98 49	97.92 47	98.04 54	98.84 74	98.04 112	97.90 129	96.83 165	95.07 109	98.79 15	99.07 61	99.37 24	97.88 40	98.74 39	98.16 70	98.01 124	96.96 105

ACMP	94.03 12	97.97 51	97.61 70	98.39 33	99.43 25	98.51 72	98.97 39	98.06 71	94.63 129	96.10 122	96.12 172	99.20 46	98.63 9	98.68 46	98.20 69	99.14 33	97.93 57
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SPE-MVS-test		97.96 52	97.38 81	98.64 21	98.57 93	99.13 13	99.36 13	98.66 25	91.66 195	98.17 30	96.91 153	98.84 87	97.99 35	98.80 36	98.88 29	99.08 41	97.43 87

LGP-MVS_train		97.96 52	97.53 74	98.45 31	99.45 22	98.64 60	99.09 27	98.27 50	92.99 175	96.04 126	96.57 161	99.29 31	98.66 8	98.73 41	98.42 52	99.19 31	98.09 48

aaEdge-Enhanced		97.94 54	98.23 32	97.60 83	99.15 46	98.85 31	98.92 44	97.17 144	96.03 65	94.88 182	99.43 25	99.18 48	97.31 62	98.07 78	98.14 72	98.14 115	97.91 59

LS3D		97.93 55	97.80 54	98.08 47	99.20 39	98.77 45	98.89 49	97.92 85	96.59 48	96.99 76	96.71 157	97.14 170	96.39 99	99.04 26	98.96 23	99.10 40	97.39 89

SD-MVS		97.84 56	97.78 58	97.90 62	98.33 106	98.06 107	97.95 123	97.80 95	96.03 65	96.72 91	97.57 135	99.18 48	97.50 53	97.88 81	97.08 112	99.11 38	98.68 21
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 57	98.27 30	97.31 105	98.23 121	98.06 107	97.44 166	95.79 200	96.90 37	95.81 139	98.76 91	98.61 112	97.70 47	98.90 35	98.36 58	98.90 58	98.29 39

thisisatest0515		97.82 58	97.67 65	97.99 60	98.49 97	98.07 106	98.48 87	98.06 71	95.35 100	97.74 42	98.83 83	97.61 157	96.74 80	97.53 103	98.30 63	98.43 97	98.01 53

PGM-MVS		97.82 58	97.25 91	98.48 29	99.54 11	98.75 52	99.02 32	98.35 45	92.41 180	96.84 86	95.39 188	98.99 67	98.24 23	98.43 64	98.34 59	98.90 58	98.41 35

PMVS	90.51 17	97.77 60	97.98 45	97.53 89	98.68 87	98.14 101	97.67 148	97.03 155	96.43 49	98.38 23	98.72 94	97.03 173	94.44 174	99.37 12	99.30 10	98.98 49	96.86 113
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FE-MVSNET2		97.75 61	97.79 55	97.70 79	97.41 197	98.37 80	99.09 27	97.73 97	96.88 38	97.47 52	99.43 25	99.35 25	96.00 116	96.66 143	97.74 92	98.48 89	96.10 146

MSP-MVS		97.67 62	97.88 50	97.43 96	99.34 29	98.99 24	98.87 52	98.12 67	95.63 84	94.16 207	97.45 138	99.50 15	96.44 98	96.35 149	98.70 38	97.65 156	98.57 27
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 63	97.79 55	97.52 91	98.32 108	98.53 69	98.45 90	97.69 99	97.59 19	96.12 121	97.79 128	96.70 178	95.69 125	98.35 70	98.34 59	98.85 66	97.22 100

FC-MVSNet-train		97.65 64	98.16 36	97.05 123	98.85 72	98.85 31	99.34 14	98.08 70	94.50 136	94.41 195	99.21 48	98.80 94	92.66 207	98.98 31	98.85 32	98.96 52	97.94 56

v10		97.64 65	97.26 89	98.08 47	98.07 142	98.56 67	98.86 53	98.18 61	94.48 137	98.24 28	99.56 15	98.98 68	97.72 46	96.05 163	96.26 144	97.42 168	96.93 106

EC-MVSNet		97.63 66	96.88 120	98.50 26	98.74 80	99.16 11	99.33 15	98.83 18	88.77 228	96.62 99	96.48 163	97.75 149	98.19 26	99.00 28	98.76 35	99.29 27	98.27 43

X-MVS		97.60 67	97.00 112	98.29 36	99.50 18	98.76 48	98.90 48	98.37 43	94.67 128	96.40 109	91.47 243	98.78 96	97.60 52	98.55 56	98.50 45	98.96 52	98.29 39

Casviewmamba		97.58 68	97.98 45	97.11 118	98.13 137	98.52 70	98.51 79	97.40 125	96.76 41	93.79 217	99.18 51	99.19 47	96.13 110	97.73 91	97.56 96	98.69 74	96.92 107

E6new		97.58 68	97.78 58	97.34 100	98.30 113	98.16 97	98.50 81	97.36 130	97.45 21	95.96 129	99.46 21	99.57 9	96.03 112	96.88 133	96.67 129	97.88 136	96.30 135

E6		97.58 68	97.78 58	97.34 100	98.30 113	98.16 97	98.50 81	97.36 130	97.45 21	95.96 129	99.46 21	99.57 9	96.03 112	96.88 133	96.67 129	97.88 136	96.30 135

3Dnovator+	96.20 4	97.58 68	97.14 103	98.10 42	98.98 67	97.85 130	98.60 74	98.33 46	96.41 51	97.23 65	94.66 204	97.26 166	96.91 77	97.91 80	97.87 85	98.53 85	98.03 51

DCV-MVSNet		97.56 72	97.63 69	97.47 94	98.41 102	99.12 14	98.63 71	98.57 26	95.71 81	95.60 154	93.79 221	98.01 143	94.25 176	99.16 23	98.88 29	99.35 21	98.74 17

HPM-MVS++		97.56 72	97.11 107	98.09 43	99.18 41	97.95 121	98.57 75	98.20 57	94.08 150	97.25 64	95.96 179	98.81 93	97.13 68	97.51 104	97.30 108	98.21 110	98.15 47

FC-MVSNet-test		97.54 74	98.26 31	96.70 149	98.87 70	97.79 139	98.49 85	98.56 27	96.04 61	90.39 254	99.65 8	98.67 104	95.15 154	99.23 19	99.07 15	98.73 73	97.39 89

TSAR-MVS + ACMM		97.54 74	97.79 55	97.26 106	98.23 121	98.10 105	97.71 142	97.88 89	95.97 67	95.57 156	98.71 95	98.57 114	97.36 58	97.74 90	96.81 122	96.83 199	98.59 26

casdiffseed414692147		97.53 76	97.64 68	97.41 97	98.18 132	98.22 90	98.63 71	97.45 118	95.90 70	95.35 161	99.20 49	99.51 13	96.45 97	97.32 114	96.81 122	98.39 99	96.53 128

DeepC-MVS_fast	95.38 6	97.53 76	97.30 88	97.79 73	98.83 75	97.64 143	98.18 105	97.14 148	95.57 90	97.83 39	97.10 150	98.80 94	96.53 94	97.41 107	97.32 106	98.24 109	97.26 96
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 78	97.03 111	98.09 43	98.31 111	98.01 116	98.96 42	97.25 139	95.22 103	98.89 12	99.64 9	98.83 89	97.68 48	95.63 177	95.91 160	97.47 164	95.97 155

v1144		97.51 79	97.05 110	98.04 54	98.26 119	97.98 118	98.88 51	97.42 124	95.38 99	98.56 18	99.59 14	99.01 65	97.65 49	95.77 173	96.06 154	97.47 164	95.56 175

v8		97.51 79	97.16 101	97.91 61	97.99 151	98.48 74	98.76 61	98.17 63	94.54 135	97.69 44	99.48 20	98.76 99	97.63 51	96.10 160	96.14 148	97.20 181	96.64 121

v1921920		97.50 81	97.00 112	98.07 50	98.20 127	97.94 126	99.03 31	97.06 153	95.29 102	99.01 9	99.62 11	98.73 101	97.74 45	95.52 183	95.78 169	97.39 170	96.12 144

Anonymous20231211		97.49 82	97.91 48	97.00 129	98.31 111	98.72 56	98.27 99	97.84 93	94.76 123	94.77 187	98.14 120	98.38 125	93.60 191	98.96 32	98.66 41	99.22 30	97.77 67

v144192		97.49 82	96.99 114	98.07 50	98.11 139	97.95 121	99.02 32	97.21 142	94.90 118	98.88 13	99.53 17	98.89 79	97.75 44	95.59 180	95.90 161	97.43 167	96.16 142

test1111		97.48 84	97.20 96	97.81 72	98.78 78	98.85 31	98.68 68	98.40 37	96.68 45	94.84 183	99.13 55	90.32 235	97.01 74	99.27 17	99.05 18	99.19 31	97.10 102

GeoE		97.48 84	96.84 125	98.22 38	99.01 62	98.39 77	98.85 56	98.76 21	92.37 181	97.53 49	97.58 134	98.23 132	97.11 69	97.57 102	96.98 116	98.10 119	96.78 116

APD-MVS		97.47 86	97.16 101	97.84 68	99.32 32	98.39 77	98.47 89	98.21 56	92.08 187	95.23 165	96.68 159	98.90 77	96.99 75	98.20 73	98.21 66	98.80 69	97.67 71
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PVSNet_Blended_VisFu		97.44 87	97.14 103	97.79 73	99.15 46	98.44 75	98.32 96	97.66 101	93.74 160	97.73 43	98.79 87	96.93 176	95.64 130	97.69 93	96.91 119	98.25 108	97.50 83

PHI-MVS		97.44 87	97.17 100	97.74 77	98.14 134	98.41 76	98.03 118	97.50 111	92.07 188	98.01 35	97.33 142	98.62 111	96.02 114	98.34 72	98.21 66	98.76 72	97.24 99

v1240		97.43 89	96.87 124	98.09 43	98.25 120	97.92 127	99.02 32	97.06 153	94.77 122	99.09 8	99.68 6	98.51 118	97.78 43	95.25 190	95.81 167	97.32 176	96.13 143

viewmacassd2359aftdt		97.42 90	97.67 65	97.13 115	98.20 127	98.06 107	98.16 108	97.16 147	97.27 26	95.23 165	99.29 40	99.48 17	96.05 111	96.73 138	96.66 131	98.00 125	96.17 141

ECVR-MVS		97.40 91	97.11 107	97.73 78	98.66 88	98.83 36	98.50 81	98.40 37	96.04 61	95.00 178	98.95 70	91.07 232	96.70 82	99.28 14	99.04 20	99.14 33	96.58 123

FMVSNet1		97.40 91	98.09 39	96.60 155	97.80 170	98.76 48	98.26 101	98.50 30	96.79 40	93.13 229	99.28 42	98.64 108	92.90 204	97.67 95	97.86 87	99.02 43	97.64 73

MGCNet		97.38 93	97.26 89	97.51 92	99.28 34	98.79 42	98.86 53	97.79 96	94.68 126	96.79 87	97.69 130	95.75 195	93.91 184	98.10 77	97.76 91	98.45 92	98.08 49

E4		97.37 94	97.52 76	97.20 111	98.29 116	98.05 111	98.27 99	97.33 135	97.28 25	95.81 139	99.29 40	99.51 13	95.64 130	96.20 156	96.24 146	97.89 135	96.07 147

casdiffmvs_mvg		97.34 95	97.65 67	96.97 130	97.74 173	98.33 82	98.45 90	97.18 143	95.81 74	93.92 213	99.04 63	99.05 61	95.48 136	97.00 129	97.71 95	99.07 42	96.63 122
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 96	96.84 125	97.90 62	98.19 129	97.83 131	98.74 64	97.44 121	95.42 98	98.23 29	99.46 21	98.84 87	97.46 54	95.51 184	96.10 151	97.36 173	94.72 192

EPP-MVSNet		97.29 97	96.88 120	97.76 76	98.70 83	99.10 17	98.92 44	98.36 44	95.12 108	93.36 227	97.39 139	91.00 233	97.65 49	98.72 43	98.91 26	99.58 7	97.92 58

hybridcas		97.27 98	97.75 62	96.71 147	97.88 160	98.23 89	98.29 97	97.11 151	96.86 39	92.95 237	99.18 51	99.12 52	95.74 121	97.22 117	97.27 110	98.30 102	96.36 132

MVS_111021_HR		97.27 98	97.11 107	97.46 95	98.46 99	97.82 135	97.50 162	96.86 162	94.97 113	97.13 69	96.99 151	98.39 123	96.82 79	97.65 99	97.38 101	98.02 123	96.56 126

E5new		97.26 100	97.38 81	97.13 115	98.29 116	98.02 113	98.19 103	97.24 140	97.21 29	95.82 137	99.13 55	99.44 18	95.39 142	95.81 170	95.99 155	97.83 140	96.05 148

E5		97.26 100	97.38 81	97.13 115	98.29 116	98.02 113	98.19 103	97.24 140	97.21 29	95.82 137	99.13 55	99.44 18	95.39 142	95.81 170	95.99 155	97.83 140	96.05 148

SF-MVS		97.26 100	97.43 79	97.05 123	98.80 77	97.83 131	96.02 227	97.44 121	94.98 112	95.74 144	97.16 147	98.45 122	95.71 123	97.85 82	97.97 81	98.60 79	97.78 65

TSAR-MVS + GP.		97.26 100	97.33 87	97.18 112	98.21 124	98.06 107	96.38 218	97.66 101	93.92 156	95.23 165	98.48 105	98.33 126	97.41 56	97.63 100	97.35 102	98.18 112	97.57 79

OMC-MVS		97.23 104	97.21 95	97.25 109	97.85 161	97.52 153	97.92 127	95.77 201	95.83 73	97.09 72	97.86 126	98.52 117	96.62 86	97.51 104	96.65 132	98.26 106	96.57 124

3Dnovator	96.31 3	97.22 105	97.19 98	97.25 109	98.14 134	97.95 121	98.03 118	96.77 170	96.42 50	97.14 67	95.11 192	97.59 158	95.14 156	97.79 87	97.72 93	98.26 106	97.76 69

usedtu_dtu_shiyan2		97.20 106	97.35 86	97.03 125	99.23 35	98.25 86	98.34 94	97.49 113	97.86 14	95.90 132	98.27 116	99.30 30	93.22 197	97.41 107	96.26 144	97.99 128	94.14 203

E3new		97.13 107	97.22 93	97.03 125	98.21 124	97.95 121	98.09 111	97.13 149	96.71 43	95.63 151	99.01 65	99.27 35	95.38 144	95.82 169	95.86 165	97.73 148	95.90 157

E3		97.13 107	97.22 93	97.03 125	98.21 124	97.95 121	98.09 111	97.13 149	96.70 44	95.64 150	99.02 64	99.27 35	95.38 144	95.81 170	95.86 165	97.73 148	95.90 157

sasdasda		97.11 109	96.88 120	97.38 98	98.34 104	98.72 56	97.52 160	97.94 81	95.60 86	95.01 176	94.58 206	94.50 205	96.59 88	97.84 83	98.03 77	98.90 58	98.91 9

canonicalmvs		97.11 109	96.88 120	97.38 98	98.34 104	98.72 56	97.52 160	97.94 81	95.60 86	95.01 176	94.58 206	94.50 205	96.59 88	97.84 83	98.03 77	98.90 58	98.91 9

V42		97.10 111	96.97 115	97.26 106	97.64 177	97.60 145	98.45 90	95.99 189	94.44 138	97.35 59	99.40 31	98.63 110	97.34 60	96.33 152	96.38 141	96.82 201	96.00 152

CPTT-MVS		97.08 112	96.25 145	98.05 53	99.21 38	98.30 84	98.54 78	97.98 79	94.28 143	95.89 134	89.57 252	98.54 115	98.18 27	97.82 86	97.32 106	98.54 83	97.91 59

DeepPCF-MVS	94.55 10	97.05 113	97.13 106	96.95 132	96.06 237	97.12 172	98.01 120	95.44 212	95.18 105	97.50 51	97.86 126	98.08 138	97.31 62	97.23 116	97.00 115	97.36 173	97.45 85

QAPM		97.04 114	97.14 103	96.93 134	97.78 172	98.02 113	97.36 176	96.72 172	94.68 126	96.23 115	97.21 144	97.68 154	95.70 124	97.37 109	97.24 111	97.78 146	97.77 67

CNVR-MVS		97.03 115	96.77 131	97.34 100	98.89 69	97.67 142	97.64 151	97.17 144	94.40 141	95.70 148	94.02 216	98.76 99	96.49 96	97.78 88	97.29 109	98.12 118	97.47 84

viewmanbaseed2359cas		97.01 116	97.20 96	96.79 144	98.06 143	97.90 128	97.80 135	96.78 169	96.34 54	94.82 184	98.80 86	99.15 51	95.50 135	96.14 157	96.07 153	97.79 144	96.00 152

casdiffmvs		97.00 117	97.36 85	96.59 156	97.65 176	97.98 118	98.06 114	96.81 166	95.78 76	92.77 240	99.40 31	99.26 39	95.65 129	96.70 140	96.39 140	98.59 80	95.99 154
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		96.99 118	96.70 135	97.34 100	97.89 158	97.23 164	98.33 95	96.96 157	95.57 90	97.12 70	98.99 67	99.40 22	97.23 65	96.22 155	95.45 176	96.50 209	94.02 206

viewdifsd2359ckpt09		96.95 119	96.77 131	97.15 114	98.55 95	98.24 88	97.80 135	97.30 137	94.93 116	95.25 164	98.13 121	98.53 116	95.97 118	95.57 181	95.96 158	98.03 122	96.05 148

viewcassd2359sk11		96.93 120	96.96 116	96.90 136	98.14 134	97.88 129	97.95 123	96.98 156	96.18 59	95.53 157	98.75 92	99.06 58	95.17 152	95.49 185	95.54 172	97.62 158	95.81 161

viewdifsd2359ckpt11		96.92 121	97.45 77	96.31 168	97.53 184	97.42 158	97.70 144	95.37 214	96.93 34	94.17 206	99.27 43	99.52 11	95.11 157	97.33 111	95.90 161	97.98 129	95.79 164

viewmsd2359difaftdt		96.92 121	97.45 77	96.31 168	97.53 184	97.42 158	97.70 144	95.37 214	96.93 34	94.18 205	99.27 43	99.52 11	95.11 157	97.33 111	95.90 161	97.98 129	95.79 164

DELS-MVS		96.90 123	97.24 92	96.50 161	97.85 161	98.18 93	97.88 132	95.92 193	93.48 162	95.34 162	98.86 82	98.94 75	94.03 179	97.33 111	97.04 114	98.00 125	96.85 114
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		96.86 124	96.72 134	97.03 125	97.80 170	97.06 177	97.04 194	95.51 211	94.55 132	97.47 52	97.35 141	97.68 154	96.66 84	97.11 122	96.73 125	97.69 153	96.57 124

PM-MVS		96.85 125	96.62 138	97.11 118	97.13 211	96.51 197	98.29 97	94.65 233	94.84 119	98.12 32	98.59 100	97.20 168	97.41 56	96.24 154	96.41 139	97.09 186	96.56 126

FE-MVSNET		96.84 126	96.84 125	96.84 141	96.93 217	97.58 146	98.49 85	97.43 123	95.70 83	95.08 172	98.40 111	98.08 138	95.17 152	95.92 166	97.05 113	97.96 132	95.14 185

pmmvs-eth3d		96.84 126	96.22 148	97.56 86	97.63 179	96.38 205	98.74 64	96.91 160	94.63 129	98.26 26	99.43 25	98.28 128	96.58 91	94.52 203	95.54 172	97.24 179	94.75 191

MVSMamba_PlusPlus		96.81 128	96.92 117	96.69 151	98.66 88	98.33 82	96.65 213	96.73 171	92.78 178	94.79 186	96.01 174	97.55 159	95.44 137	97.67 95	97.87 85	97.85 139	98.24 44

CANet		96.81 128	96.50 140	97.17 113	99.10 55	97.96 120	97.86 133	97.51 109	91.30 200	97.75 41	97.64 131	97.89 147	93.39 195	96.98 130	96.73 125	97.40 169	96.99 104

Fast-Effi-MVS+		96.80 130	95.92 161	97.84 68	98.57 93	97.46 156	98.06 114	98.24 53	89.64 222	97.57 48	96.45 164	97.35 164	96.73 81	97.22 117	96.64 133	97.86 138	96.65 120

viewdifsd2359ckpt13		96.79 131	96.77 131	96.81 142	98.08 141	97.83 131	97.74 140	96.79 167	95.30 101	94.89 181	98.41 109	98.88 81	95.57 133	95.61 178	95.49 175	97.81 142	95.87 159

MCST-MVS		96.79 131	96.08 153	97.62 82	98.78 78	97.52 153	98.01 120	97.32 136	93.20 167	95.84 136	93.97 218	98.12 136	97.34 60	96.34 150	95.88 164	98.45 92	97.51 82

UGNet		96.79 131	97.82 53	95.58 197	97.57 182	98.39 77	98.48 87	97.84 93	95.85 72	94.68 189	97.91 125	99.07 57	87.12 255	97.71 92	97.51 98	97.80 143	98.29 39
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	96.79 131	96.70 135	96.90 136	97.64 177	97.58 146	97.54 159	94.50 235	95.14 106	96.64 98	96.76 156	97.90 146	96.63 85	95.98 164	96.14 148	98.45 92	97.39 89
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
E2		96.74 135	96.70 135	96.78 145	98.09 140	97.82 135	97.80 135	96.86 162	95.62 85	95.42 159	98.47 106	98.83 89	94.96 162	95.19 192	95.24 182	97.53 159	95.75 169

CLD-MVS		96.73 136	96.92 117	96.51 160	98.70 83	97.57 149	97.64 151	92.07 250	93.10 173	96.31 114	98.29 114	99.02 64	95.99 117	97.20 119	96.47 137	98.37 101	96.81 115
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
viewdifsd2359ckpt07		96.69 137	97.19 98	96.10 173	98.01 146	97.73 140	97.69 146	96.10 185	97.21 29	94.10 209	99.10 60	99.21 44	95.06 159	96.10 160	94.90 186	95.62 229	96.11 145

MGCFI-Net		96.69 137	96.89 119	96.44 164	98.30 113	98.63 61	97.39 173	97.90 86	95.72 80	91.16 252	94.65 205	94.55 203	95.04 161	97.78 88	98.00 80	98.87 64	98.93 8

train_agg		96.68 139	95.93 160	97.56 86	99.08 57	97.16 168	98.44 93	97.37 129	91.12 204	95.18 168	95.43 187	98.48 120	97.36 58	96.48 146	95.52 174	97.95 133	97.34 93

CDPH-MVS		96.68 139	95.99 157	97.48 93	99.13 50	97.64 143	98.08 113	97.46 116	90.56 211	95.13 169	94.87 200	98.27 129	96.56 92	97.09 123	96.45 138	98.54 83	97.08 103

MSLP-MVS++		96.66 141	96.46 143	96.89 138	98.02 145	97.71 141	95.57 235	96.96 157	94.36 142	96.19 119	91.37 244	98.24 130	97.07 71	97.69 93	97.89 83	97.52 161	97.95 55

TinyColmap		96.64 142	96.07 154	97.32 104	97.84 166	96.40 202	97.63 153	96.25 183	95.86 71	98.98 10	97.94 124	96.34 185	96.17 107	97.30 115	95.38 179	97.04 189	93.24 219

IS_MVSNet		96.62 143	96.48 142	96.78 145	98.46 99	98.68 59	98.61 73	98.24 53	92.23 184	89.63 259	95.90 181	94.40 207	96.23 102	98.65 50	98.77 34	99.52 12	96.76 117

NCCC		96.56 144	95.68 164	97.59 84	99.04 61	97.54 152	97.67 148	97.56 107	94.84 119	96.10 122	87.91 255	98.09 137	96.98 76	97.20 119	96.80 124	98.21 110	97.38 92

WB-MVS		96.54 145	98.09 39	94.73 219	96.68 226	98.34 81	94.77 255	97.39 126	98.12 10	89.72 258	98.95 70	99.32 29	93.33 196	98.67 47	97.88 84	96.47 211	95.38 179

ETV-MVS		96.54 145	95.27 173	98.02 57	99.07 59	97.48 155	98.16 108	98.19 59	87.33 243	97.58 47	92.67 231	95.93 191	96.22 103	98.49 62	98.46 47	98.91 57	96.50 130

Effi-MVS+		96.46 147	95.28 172	97.85 67	98.64 92	97.16 168	97.15 190	98.75 23	90.27 215	98.03 34	93.93 219	96.21 186	96.55 93	96.34 150	96.69 128	97.97 131	96.33 134

IterMVS-LS		96.35 148	95.85 163	96.93 134	97.53 184	98.00 117	97.37 174	97.97 80	95.49 97	96.71 94	98.94 72	93.23 215	94.82 167	93.15 224	95.05 184	97.17 183	97.12 101
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs_AUTHOR		96.30 149	96.79 129	95.73 191	97.43 195	97.06 177	97.24 184	95.65 206	95.76 78	92.97 236	99.35 35	99.21 44	93.99 182	95.61 178	94.85 188	97.09 186	95.65 172

USDC		96.30 149	95.64 166	97.07 121	97.62 180	96.35 207	97.17 189	95.71 204	95.52 95	99.17 7	98.11 122	97.46 161	95.67 126	95.44 187	93.60 211	97.09 186	92.99 223

Vis-MVSNet (Re-imp)		96.29 151	96.50 140	96.05 174	97.96 154	97.83 131	97.30 179	97.86 91	93.14 169	88.90 262	96.80 155	95.28 197	95.15 154	98.37 69	98.25 65	99.12 37	95.84 160

viewmamba		96.27 152	96.61 139	95.87 182	97.38 199	97.07 176	97.40 172	95.73 203	95.71 81	93.65 219	99.12 58	99.00 66	93.81 186	95.94 165	94.27 197	97.27 177	95.13 186

MSDG		96.27 152	96.17 151	96.38 167	97.85 161	96.27 209	96.55 215	94.41 236	94.55 132	95.62 153	97.56 136	97.80 148	96.22 103	97.17 121	96.27 143	97.67 155	93.60 214

CNLPA		96.24 154	95.97 158	96.57 158	97.48 193	97.10 175	96.75 207	94.95 227	94.92 117	96.20 118	94.81 201	96.61 180	96.25 101	96.94 131	95.64 170	97.79 144	95.74 170

EIA-MVS		96.23 155	94.85 185	97.84 68	99.08 57	98.21 91	97.69 146	98.03 76	85.68 253	98.09 33	91.75 242	97.07 172	95.66 128	97.58 101	97.72 93	98.47 90	95.91 156

onestephybrid01		96.10 156	96.33 144	95.84 185	97.29 206	97.01 179	97.61 154	95.69 205	93.41 163	93.45 224	98.91 74	98.92 76	93.62 190	96.06 162	94.68 193	97.35 175	95.34 180

PLC	92.55 15	96.10 156	95.36 169	96.96 131	98.13 137	96.88 183	96.49 216	96.67 176	94.07 151	95.71 147	91.14 245	96.09 188	96.84 78	96.70 140	96.58 135	97.92 134	96.03 151
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test20.03		96.08 158	96.80 128	95.25 209	99.19 40	97.58 146	97.24 184	97.56 107	94.95 115	91.91 248	98.58 101	98.03 141	87.88 251	97.43 106	96.94 118	97.69 153	94.05 205

FA-MVS(training)		96.07 159	95.59 167	96.63 153	98.00 150	97.44 157	97.36 176	98.53 28	92.21 185	95.97 128	96.18 170	94.22 210	92.98 201	96.79 136	96.70 127	96.95 195	95.56 175

TSAR-MVS + COLMAP		96.05 160	95.94 159	96.18 172	97.46 194	96.41 201	97.26 183	95.83 197	94.69 125	95.30 163	98.31 113	96.52 181	94.71 169	95.48 186	94.87 187	96.54 208	95.33 182

EU-MVSNet		96.03 161	96.23 147	95.80 188	95.48 256	94.18 236	98.99 37	91.51 252	97.22 28	97.66 45	99.15 54	98.51 118	98.08 30	95.92 166	92.88 219	93.09 244	95.72 171

dtuplus		95.99 162	96.16 152	95.80 188	97.37 200	96.47 198	97.23 186	95.76 202	94.81 121	93.04 234	98.67 97	98.88 81	93.93 183	95.14 193	93.69 209	97.49 163	95.44 178

PCF-MVS	92.69 14	95.98 163	95.05 180	97.06 122	98.43 101	97.56 150	97.76 138	96.65 177	89.95 220	95.70 148	96.18 170	98.48 120	95.74 121	93.64 214	93.35 216	98.09 121	96.18 140
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HQP-MVS		95.97 164	95.01 182	97.08 120	98.72 81	97.19 166	97.07 193	96.69 175	91.49 198	95.77 143	92.19 237	97.93 145	96.15 108	94.66 200	94.16 200	98.10 119	97.45 85

Effi-MVS+-dtu		95.94 165	95.08 179	96.94 133	98.54 96	97.38 160	96.66 211	97.89 88	88.68 229	95.92 131	92.90 230	97.28 165	94.18 178	96.68 142	96.13 150	98.45 92	96.51 129

usedtu_dtu_shiyan1		95.91 166	95.40 168	96.50 161	96.40 231	97.12 172	97.95 123	96.35 182	93.25 166	96.07 124	97.21 144	97.22 167	94.48 172	93.47 216	95.28 180	97.74 147	94.28 200

diffmvs		95.86 167	96.21 149	95.44 202	97.25 208	96.85 186	96.99 197	95.23 220	94.96 114	92.82 239	98.89 77	98.85 85	93.52 193	94.21 209	94.25 198	96.84 198	95.49 177
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		95.85 168	94.65 189	97.26 106	98.70 83	97.20 165	97.33 178	97.30 137	91.28 202	95.90 132	88.16 254	96.17 187	96.60 87	97.34 110	96.82 121	97.71 150	95.60 174

viewmambaseed2359dif		95.80 169	95.87 162	95.73 191	97.17 210	96.55 194	97.15 190	95.60 208	93.77 158	93.06 232	98.63 99	98.66 107	94.03 179	94.76 198	93.36 215	97.37 172	95.34 180

hybridnocas07		95.78 170	96.24 146	95.26 208	97.02 215	96.76 190	96.93 200	95.26 218	93.98 152	92.77 240	99.05 62	98.86 84	92.56 209	95.70 175	94.18 199	97.00 192	95.13 186

FMVSNet2		95.77 171	96.20 150	95.27 206	96.77 222	98.18 93	97.28 180	97.90 86	93.12 170	91.37 250	98.25 117	96.05 189	90.04 230	94.96 197	95.94 159	98.28 103	96.90 108

OpenMVS	94.63 9	95.75 172	95.04 181	96.58 157	97.85 161	97.55 151	96.71 209	96.07 186	90.15 218	96.47 104	90.77 250	95.95 190	94.41 175	97.01 128	96.95 117	98.00 125	96.90 108

pmmvs5		95.70 173	95.22 174	96.26 170	96.55 230	97.24 163	97.50 162	94.99 226	90.95 207	96.87 82	98.47 106	97.40 162	94.45 173	92.86 225	94.98 185	97.23 180	94.64 194

Anonymous20231206		95.69 174	95.68 164	95.70 193	98.32 108	96.95 181	97.37 174	96.65 177	93.33 164	93.61 220	98.70 96	98.03 141	91.04 218	95.07 195	94.59 196	97.20 181	93.09 222

hybrid		95.66 175	96.07 154	95.19 211	97.03 213	96.68 192	96.90 204	95.12 221	94.10 147	92.85 238	98.82 84	98.71 103	92.52 212	95.42 188	93.82 208	96.72 203	94.93 189

MAR-MVS		95.51 176	94.49 193	96.71 147	97.92 156	96.40 202	96.72 208	98.04 75	86.74 247	96.72 91	92.52 234	95.14 199	94.02 181	96.81 135	96.54 136	96.85 196	97.25 97
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		95.48 177	94.51 191	96.61 154	97.13 211	97.30 162	98.05 116	96.79 167	93.75 159	95.08 172	96.38 165	89.76 237	94.95 163	93.97 213	94.82 192	97.64 157	95.63 173

MDA-MVSNet-bldmvs		95.45 178	95.20 175	95.74 190	94.24 261	96.38 205	97.93 126	94.80 228	95.56 93	96.87 82	98.29 114	95.24 198	96.50 95	98.65 50	90.38 232	94.09 236	91.93 230

PVSNet_BlendedMVS		95.44 179	95.09 177	95.86 183	97.31 204	97.13 170	96.31 221	95.01 224	88.55 232	96.23 115	94.55 210	97.75 149	92.56 209	96.42 147	95.44 177	97.71 150	95.81 161

PVSNet_Blended		95.44 179	95.09 177	95.86 183	97.31 204	97.13 170	96.31 221	95.01 224	88.55 232	96.23 115	94.55 210	97.75 149	92.56 209	96.42 147	95.44 177	97.71 150	95.81 161

pmmvs4		95.37 181	94.25 194	96.67 152	97.01 216	95.28 229	97.60 155	96.07 186	93.11 171	97.29 62	98.09 123	94.23 209	95.21 150	91.56 236	93.91 206	96.82 201	93.59 215

MVS_Test		95.34 182	94.88 184	95.89 181	96.93 217	96.84 187	96.66 211	97.08 152	90.06 219	94.02 210	97.61 132	96.64 179	93.59 192	92.73 228	94.02 204	97.03 190	96.24 137

GBi-Net		95.21 183	95.35 170	95.04 213	96.77 222	98.18 93	97.28 180	97.58 104	88.43 234	90.28 255	96.01 174	92.43 223	90.04 230	97.67 95	97.86 87	98.28 103	96.90 108

test1		95.21 183	95.35 170	95.04 213	96.77 222	98.18 93	97.28 180	97.58 104	88.43 234	90.28 255	96.01 174	92.43 223	90.04 230	97.67 95	97.86 87	98.28 103	96.90 108

IterMVS-SCA-FT		95.16 185	93.95 198	96.56 159	97.89 158	96.69 191	96.94 199	96.05 188	93.06 174	97.35 59	98.79 87	91.45 228	95.93 119	92.78 226	91.00 229	95.22 232	93.91 208

HyFIR lowres test		95.05 186	93.54 203	96.81 142	97.81 169	96.88 183	98.18 105	97.46 116	94.28 143	94.98 179	96.57 161	92.89 221	96.15 108	90.90 241	91.87 225	96.28 215	91.35 231

CHOSEN 1792x2688		94.98 187	94.69 188	95.31 204	97.27 207	95.58 221	97.90 129	95.56 210	95.03 110	93.77 218	95.65 185	99.29 31	95.30 146	91.51 237	91.28 228	92.05 254	94.50 196

CANet_DTU		94.96 188	94.62 190	95.35 203	98.03 144	96.11 211	96.92 202	95.60 208	88.59 231	97.27 63	95.27 190	96.50 182	88.77 246	95.53 182	95.59 171	95.54 230	94.78 190

CDS-MVSNet		94.91 189	95.17 176	94.60 223	97.85 161	96.21 210	96.90 204	96.39 180	90.81 208	93.40 225	97.24 143	94.54 204	85.78 261	96.25 153	96.15 147	97.26 178	95.01 188
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
DPM-MVS		94.86 190	93.90 200	95.99 176	98.19 129	96.52 196	96.29 223	95.95 190	93.11 171	94.61 191	88.17 253	96.44 183	93.77 189	93.33 219	93.54 213	97.11 185	96.22 138

MS-PatchMatch		94.84 191	94.76 187	94.94 216	96.38 232	94.69 235	95.90 229	94.03 238	92.49 179	93.81 215	95.79 182	96.38 184	94.54 170	94.70 199	94.85 188	94.97 234	94.43 198

thisisatest0530		94.81 192	93.06 209	96.85 140	98.01 146	97.18 167	96.93 200	97.36 130	89.73 221	95.80 141	94.98 196	77.88 258	94.89 164	96.73 138	97.35 102	98.13 117	97.54 80

tttt0517		94.81 192	93.04 210	96.88 139	98.15 133	97.37 161	96.99 197	97.36 130	89.51 224	95.74 144	94.89 198	77.53 260	94.89 164	96.94 131	97.35 102	98.17 113	97.70 70

testgi		94.81 192	96.05 156	93.35 235	99.06 60	96.87 185	97.57 157	96.70 174	95.77 77	88.60 265	93.19 228	98.87 83	81.21 269	97.03 127	96.64 133	96.97 194	93.99 207

PatchMatch-RL		94.79 195	93.75 202	96.00 175	96.80 221	95.00 232	95.47 240	95.25 219	90.68 210	95.80 141	92.97 229	93.64 212	95.67 126	96.13 159	95.81 167	96.99 193	92.01 229

FPMVS		94.70 196	94.99 183	94.37 225	95.84 245	93.20 241	96.00 228	91.93 251	95.03 110	94.64 190	94.68 202	93.29 214	90.95 219	98.07 78	97.34 105	96.85 196	93.29 218

new-patchmatchnet		94.48 197	94.02 196	95.02 215	97.51 191	95.00 232	95.68 234	94.26 237	97.32 24	95.73 146	99.60 12	98.22 134	91.30 214	94.13 210	84.41 251	95.65 228	89.45 243

IterMVS		94.48 197	93.46 205	95.66 194	97.52 187	96.43 199	97.20 187	94.73 231	92.91 177	96.44 105	98.75 92	91.10 230	94.53 171	92.10 232	90.10 234	93.51 240	92.84 227
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MDTV_nov1_ep13_2view		94.39 199	93.34 206	95.63 195	97.23 209	95.33 228	97.76 138	96.84 164	94.55 132	97.47 52	98.96 68	97.70 152	93.88 185	92.27 230	86.81 241	90.56 256	87.73 253

Fast-Effi-MVS+-dtu		94.34 200	93.26 208	95.62 196	97.82 167	95.97 214	95.86 231	99.01 13	86.88 245	93.39 226	90.83 248	95.46 196	90.61 223	94.46 205	94.68 193	97.01 191	94.51 195

thres600view7		94.34 200	92.31 219	96.70 149	98.19 129	98.12 102	97.85 134	97.45 118	91.49 198	93.98 212	84.27 258	82.02 249	94.24 177	97.04 124	98.76 35	98.49 87	94.47 197

EPNet		94.33 202	93.52 204	95.27 206	98.81 76	94.71 234	96.77 206	98.20 57	88.12 237	96.53 102	92.53 233	91.19 229	85.25 265	95.22 191	95.26 181	96.09 220	97.63 77
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test2506		94.29 203	91.43 233	97.64 81	98.66 88	98.83 36	98.50 81	98.40 37	96.04 61	94.45 194	94.88 199	55.05 282	96.70 82	99.28 14	99.04 20	99.14 33	96.87 112

GA-MVS		94.18 204	92.98 211	95.58 197	97.36 201	96.42 200	96.21 224	95.86 194	90.29 214	95.08 172	96.19 169	85.37 241	92.82 205	94.01 212	94.14 201	96.16 219	94.41 199

gg-mvs-nofinetune		94.13 205	93.93 199	94.37 225	97.99 151	95.86 215	95.45 243	99.22 9	97.61 18	95.10 171	99.50 19	84.50 242	81.73 268	95.31 189	94.12 202	96.71 205	90.59 235

baseline		94.07 206	94.50 192	93.57 233	96.34 233	93.40 240	95.56 238	92.39 245	92.07 188	94.00 211	98.24 118	97.51 160	89.19 238	91.75 234	92.72 220	93.96 238	95.79 164

FMVSNet3		94.06 207	93.85 201	94.31 228	95.46 257	97.80 138	96.34 219	97.58 104	88.43 234	90.28 255	96.01 174	92.43 223	88.67 247	91.82 233	93.96 205	97.53 159	96.50 130

thres400		94.04 208	91.94 225	96.50 161	97.98 153	97.82 135	97.66 150	96.96 157	90.96 206	94.20 202	83.24 260	82.82 247	93.80 187	96.50 145	98.09 73	98.38 100	94.15 202

dmvs_re		94.02 209	92.39 217	95.91 180	97.71 174	95.43 223	97.00 196	95.94 191	82.49 262	94.61 191	83.69 259	93.01 220	92.71 206	97.83 85	97.56 96	97.50 162	96.73 118

CVMVSNet		94.01 210	94.25 194	93.73 232	94.36 260	92.44 244	97.45 165	88.56 257	95.59 88	93.06 232	98.88 78	90.03 236	94.84 166	94.08 211	93.45 214	94.09 236	95.31 183

thres200		93.98 211	91.90 226	96.40 166	97.66 175	98.12 102	97.20 187	97.45 118	90.16 217	93.82 214	83.08 261	83.74 245	93.80 187	97.04 124	97.48 100	98.49 87	93.70 211

gbinet_0.2-2-1-0.02		93.92 212	92.20 223	95.93 179	96.24 234	95.75 216	98.05 116	93.85 240	91.55 197	96.68 95	96.95 152	92.86 222	95.06 159	88.67 248	85.96 245	95.71 227	93.65 213

blended_shiyan8		93.92 212	92.28 221	95.83 186	95.93 243	95.67 219	97.71 142	92.63 243	92.35 182	96.92 78	95.99 178	93.23 215	95.60 132	88.33 249	86.73 242	96.18 217	93.70 211

blended_shiyan6		93.92 212	92.29 220	95.82 187	95.95 241	95.66 220	97.72 141	92.62 244	92.31 183	96.89 81	95.96 179	93.33 213	95.55 134	88.31 250	86.73 242	96.17 218	93.73 209

baseline1		93.89 215	92.82 213	95.14 212	97.62 180	96.97 180	96.12 225	96.36 181	91.30 200	91.53 249	94.68 202	80.72 251	90.80 221	95.71 174	96.29 142	98.44 96	94.09 204

tfpn200view9		93.80 216	91.75 229	96.20 171	97.52 187	98.15 100	97.48 164	97.47 115	87.65 239	93.56 222	83.03 262	84.12 243	92.62 208	97.04 124	98.09 73	98.52 86	94.17 201

dtuonlycased		93.74 217	94.84 186	92.45 243	97.52 187	96.82 188	97.55 158	92.73 242	94.41 139	78.03 274	97.60 133	98.13 135	95.20 151	93.57 215	90.51 231	93.69 239	92.83 228

MIMVSNet		93.68 218	93.96 197	93.35 235	97.82 167	96.08 212	96.34 219	98.46 34	91.28 202	86.67 270	94.95 197	94.87 201	84.39 266	94.53 201	94.65 195	96.45 212	91.34 232

pmnet_mix02		93.59 219	92.65 214	94.69 221	96.76 225	94.16 237	97.03 195	93.00 241	95.79 75	96.03 127	98.91 74	97.69 153	92.99 200	90.03 246	84.10 254	92.35 252	87.89 252

wanda-best-256-512		93.50 220	91.78 227	95.51 199	95.64 249	95.41 224	97.43 167	92.21 246	91.80 190	96.77 88	95.73 183	93.11 217	95.28 147	87.72 252	85.73 246	95.75 223	92.99 223

FE-blended-shiyan7		93.50 220	91.78 227	95.51 199	95.64 249	95.41 224	97.43 167	92.21 246	91.80 190	96.77 88	95.73 183	93.11 217	95.28 147	87.72 252	85.73 246	95.75 223	92.99 223

EPNet_dtu		93.45 222	92.51 216	94.55 224	98.39 103	91.67 255	95.46 241	97.50 111	86.56 248	97.38 57	93.52 222	94.20 211	85.82 260	93.31 221	92.53 221	92.72 247	95.76 168
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IB-MVS	92.44 16	93.33 223	92.15 224	94.70 220	97.42 196	96.39 204	95.57 235	94.67 232	86.40 251	93.59 221	78.28 269	95.76 194	89.59 236	95.88 168	95.98 157	97.39 170	96.34 133
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		93.18 224	90.80 236	95.95 177	96.05 238	96.07 213	96.92 202	96.51 179	89.34 225	95.63 151	94.08 215	72.31 275	93.13 198	94.33 207	94.83 190	97.44 166	94.65 193

thres100view900		92.93 225	90.89 235	95.31 204	97.52 187	96.82 188	96.41 217	95.08 222	87.65 239	93.56 222	83.03 262	84.12 243	91.12 217	94.53 201	96.91 119	98.17 113	93.21 220

N_pmnet		92.46 226	92.38 218	92.55 241	97.91 157	93.47 239	97.42 170	94.01 239	96.40 52	88.48 266	98.50 103	98.07 140	88.14 250	91.04 240	84.30 252	89.35 262	84.85 260

TAMVS		92.46 226	93.34 206	91.44 252	97.03 213	93.84 238	94.68 256	90.60 254	90.44 213	85.31 271	97.14 148	93.03 219	85.78 261	94.34 206	93.67 210	95.22 232	90.93 234

CMPMVS	71.81 19	92.34 228	92.85 212	91.75 249	92.70 265	90.43 263	88.84 273	88.56 257	85.87 252	94.35 198	90.98 246	95.89 193	91.14 216	96.14 157	94.83 190	94.93 235	95.78 167
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
baseline2		92.06 229	89.82 239	94.68 222	97.32 202	95.72 217	94.97 252	95.08 222	84.75 256	94.34 200	90.68 251	77.75 259	90.13 229	93.38 217	93.58 212	96.25 216	92.90 226

dtuonly		91.97 230	91.47 231	92.55 241	96.68 226	91.24 257	95.21 248	91.44 253	91.11 205	94.12 208	97.19 146	95.93 191	89.16 239	90.89 242	87.43 240	88.71 264	86.52 256

MVSTER		91.97 230	90.31 237	93.91 230	96.81 220	96.91 182	94.22 257	95.64 207	84.98 254	92.98 235	93.42 223	72.56 273	86.64 259	95.11 194	93.89 207	97.16 184	95.31 183

CR-MVSNet		91.94 232	88.50 242	95.94 178	96.14 236	92.08 250	95.23 246	98.47 32	84.30 258	96.44 105	94.58 206	75.57 261	92.92 202	90.22 244	92.22 222	96.43 213	90.56 236

gm-plane-assit		91.85 233	87.91 244	96.44 164	99.13 50	98.25 86	99.02 32	97.38 128	95.57 90	98.31 25	99.34 37	51.00 283	88.93 243	93.16 223	91.57 226	95.85 221	86.50 257

PMMVS		91.67 234	91.47 231	91.91 248	89.43 270	88.61 269	94.99 251	85.67 262	87.50 241	93.80 216	94.42 213	94.88 200	90.71 222	92.26 231	92.96 218	96.83 199	89.65 241

CHOSEN 280x420		91.55 235	90.27 238	93.05 238	94.61 259	88.01 270	96.56 214	94.62 234	88.04 238	94.20 202	92.66 232	86.60 239	90.82 220	95.06 196	91.89 224	87.49 268	89.61 242

PatchT		91.40 236	88.54 241	94.74 218	91.48 269	92.18 247	97.42 170	97.51 109	84.96 255	96.44 105	94.16 214	75.47 262	92.92 202	90.22 244	92.22 222	92.66 250	90.56 236

pmmvs3		91.20 237	91.40 234	90.96 254	91.71 268	91.08 258	95.41 244	81.34 269	87.36 242	94.57 193	95.02 194	94.30 208	90.42 224	94.28 208	89.26 236	92.30 253	88.49 249

test0.0.03 1		91.17 238	91.50 230	90.80 255	98.01 146	95.46 222	94.22 257	95.80 198	86.55 249	81.75 273	90.83 248	87.93 238	78.48 270	94.51 204	94.11 203	96.50 209	91.08 233

SCA		91.15 239	87.65 246	95.23 210	96.15 235	95.68 218	96.68 210	98.18 61	90.46 212	97.21 66	92.44 235	80.17 253	93.51 194	86.04 260	83.58 257	89.68 260	85.21 259

new_pmnet		90.85 240	92.26 222	89.21 261	93.68 264	89.05 268	93.20 266	84.16 266	92.99 175	84.25 272	97.72 129	94.60 202	86.80 258	93.20 222	91.30 227	93.21 242	86.94 255

RPMNet		90.52 241	86.27 257	95.48 201	95.95 241	92.08 250	95.55 239	98.12 67	84.30 258	95.60 154	87.49 256	72.78 272	91.24 215	87.93 251	89.34 235	96.41 214	89.98 239

MDTV_nov1_ep13		90.30 242	87.32 250	93.78 231	96.00 240	92.97 242	95.46 241	95.39 213	88.61 230	95.41 160	94.45 212	80.39 252	89.87 233	86.58 258	83.54 258	90.56 256	84.71 262

FE-MVSNET3		90.29 243	86.44 254	94.78 217	95.64 249	95.41 224	97.43 167	92.21 246	91.80 190	92.27 243	77.48 271	73.25 268	95.41 138	87.72 252	85.73 246	95.75 223	93.73 209

PatchmatchNet		89.98 244	86.23 258	94.36 227	96.56 229	91.90 254	96.07 226	96.72 172	90.18 216	96.87 82	93.36 226	78.06 257	91.46 213	84.71 265	81.40 262	88.45 265	83.97 266
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
usedtu_blend_shiyan5		89.91 245	86.39 255	94.01 229	95.64 249	95.41 224	92.79 269	92.21 246	91.80 190	92.27 243	77.47 272	73.25 268	95.41 138	87.72 252	85.73 246	95.75 223	93.36 216

ADS-MVSNet		89.89 246	87.70 245	92.43 245	95.52 254	90.91 261	95.57 235	95.33 216	93.19 168	91.21 251	93.41 224	82.12 248	89.05 240	86.21 259	83.77 256	87.92 266	84.31 263

tpm		89.84 247	86.81 252	93.36 234	96.60 228	91.92 253	95.02 250	97.39 126	86.79 246	96.54 101	95.03 193	69.70 276	87.66 252	88.79 247	86.19 244	86.95 270	89.27 244

test-LLR		89.77 248	87.47 248	92.45 243	98.01 146	89.77 265	93.25 264	95.80 198	81.56 264	89.19 260	92.08 238	79.59 254	85.77 263	91.47 238	89.04 238	92.69 248	88.75 245

FMVSNet5		89.65 249	87.60 247	92.04 247	95.63 253	96.61 193	94.82 254	94.75 229	80.11 268	87.72 268	77.73 270	73.81 265	83.81 267	95.64 176	96.08 152	95.49 231	93.21 220

EPMVS		89.28 250	86.28 256	92.79 240	96.01 239	92.00 252	95.83 232	95.85 196	90.78 209	91.00 253	94.58 206	74.65 263	88.93 243	85.00 263	82.88 260	89.09 263	84.09 265

test-mter		89.16 251	88.14 243	90.37 257	94.79 258	91.05 259	93.60 263	85.26 263	81.65 263	88.32 267	92.22 236	79.35 256	87.03 256	92.28 229	90.12 233	93.19 243	90.29 238

CostFormer		89.06 252	85.65 259	93.03 239	95.88 244	92.40 245	95.30 245	95.86 194	86.49 250	93.12 231	93.40 225	74.18 264	88.25 248	82.99 266	81.46 261	89.77 259	88.66 247

MVS-HIRNet		88.72 253	86.49 253	91.33 253	91.81 267	85.66 271	87.02 275	96.25 183	81.48 266	94.82 184	96.31 168	92.14 226	90.32 226	87.60 256	83.82 255	87.74 267	78.42 270

TESTMET0.1,1		88.60 254	87.47 248	89.93 259	94.23 262	89.77 265	93.25 264	84.47 265	81.56 264	89.19 260	92.08 238	79.59 254	85.77 263	91.47 238	89.04 238	92.69 248	88.75 245

dps		88.36 255	84.32 262	93.07 237	93.86 263	92.29 246	94.89 253	95.93 192	83.50 260	93.13 229	91.87 240	67.79 279	90.32 226	85.99 261	83.22 259	90.28 258	85.56 258

tpmrst		87.60 256	84.13 263	91.66 251	95.65 248	89.73 267	93.77 260	94.74 230	88.85 227	93.35 228	95.60 186	72.37 274	87.40 253	81.24 267	78.19 267	85.02 273	82.90 269

blend_shiyan4		87.32 257	83.58 264	91.68 250	85.86 274	95.01 231	90.28 270	90.47 255	74.69 273	92.27 243	77.47 272	73.25 268	95.41 138	85.88 262	85.38 250	95.81 222	93.36 216

tpm cat1		87.19 258	82.78 265	92.33 246	95.66 247	90.61 262	94.19 259	95.27 217	86.97 244	94.38 196	90.91 247	69.40 277	87.21 254	79.57 270	77.82 268	87.25 269	84.18 264

E-PMN		86.94 259	85.10 260	89.09 263	95.77 246	83.54 274	89.89 272	86.55 259	92.18 186	87.34 269	94.02 216	83.42 246	89.63 235	93.32 220	77.11 269	85.33 271	72.09 272

EMVS		86.63 260	84.48 261	89.15 262	95.51 255	83.66 273	90.19 271	86.14 261	91.78 194	88.68 263	93.83 220	81.97 250	89.05 240	92.76 227	76.09 270	85.31 272	71.28 273

PMMVS2		86.47 261	92.62 215	79.29 265	92.01 266	85.63 272	93.74 261	86.37 260	93.95 155	54.18 279	98.19 119	97.39 163	58.46 271	96.57 144	93.07 217	90.99 255	83.55 268

0.4-1-1-0.1		86.09 262	82.27 266	90.55 256	88.91 271	92.09 249	93.74 261	84.65 264	77.28 270	92.48 242	81.76 265	73.62 266	90.27 228	80.00 269	81.27 263	93.27 241	89.84 240

MVE	72.99 18	85.37 263	89.43 240	80.63 264	74.43 275	71.94 276	88.25 274	89.81 256	93.27 165	67.32 277	96.32 167	91.83 227	90.40 225	93.36 218	90.79 230	73.55 276	88.49 249
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		85.22 264	81.12 268	90.00 258	88.32 272	91.29 256	93.16 267	83.68 267	76.11 271	92.27 243	79.38 267	73.25 268	89.78 234	78.77 272	80.48 264	92.78 246	88.53 248

0.4-1-1-0.2		85.13 265	81.17 267	89.76 260	88.18 273	90.98 260	92.83 268	83.39 268	75.70 272	92.15 247	80.54 266	73.62 266	89.49 237	78.89 271	80.15 265	92.48 251	88.30 251

test_method		61.30 266	70.45 269	50.62 266	22.69 279	30.92 280	68.31 278	25.76 272	80.56 267	68.71 275	82.80 264	91.08 231	44.64 272	80.50 268	56.70 272	73.64 275	70.58 274

GG-mvs-BLEND		61.03 267	87.02 251	30.71 269	0.74 284	90.01 264	78.90 277	0.74 278	84.56 257	9.46 281	79.17 268	90.69 234	1.37 280	91.74 235	89.13 237	93.04 245	83.83 267

VLMVS_CLIP		47.10 268	56.61 271	36.00 268	68.27 276	53.74 277	23.32 280	41.33 270	49.20 275	16.41 280	60.43 276	65.92 280	41.60 274	57.24 274	51.06 273	25.09 278	58.65 275

MVS_clip		41.82 269	60.29 270	20.28 270	37.55 278	34.42 279	13.98 282	10.87 274	57.10 274	3.35 285	69.38 274	68.28 278	42.17 273	61.55 273	58.12 271	13.76 279	73.17 271

VLMVS		14.77 270	20.38 273	8.23 271	16.10 280	13.23 281	4.49 283	4.94 275	21.12 277	3.97 283	19.38 278	25.63 285	14.96 277	16.63 275	16.14 274	4.91 280	30.50 277

MVS_baseline		13.50 271	21.89 272	3.71 272	5.00 281	2.85 282	0.84 286	0.00 279	22.97 276	0.00 286	24.73 277	30.02 284	16.36 276	12.07 276	11.97 275	0.08 283	48.63 276

testmvs		4.99 272	6.88 274	2.78 274	1.73 282	2.04 284	3.10 284	1.71 276	7.27 278	3.92 284	12.18 279	6.71 286	3.31 279	6.94 277	5.51 277	2.94 281	7.51 278

test123		4.41 273	5.71 275	2.88 273	1.28 283	2.21 283	3.09 285	1.65 277	6.35 279	4.98 282	8.53 280	3.88 287	3.46 278	5.79 278	5.71 276	2.85 282	7.50 279

uanet_test		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet-low-res		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

ACM-MVS					97.41 197	96.54 195	95.87 230		89.59 223	94.92 180	93.23 227	97.08 171	88.95 242			96.58 207	97.28 94

PatchmatchNet2					97.56 183	92.12 248	97.08 192
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												98.01 143	88.25 248	90.84 243	84.30 252	89.36 261	84.73 261
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										88.62 264	98.50 103
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							98.92 44	97.17 144		94.34 200						98.14 115

TPM-MVS					97.49 192	96.32 208	95.05 249			94.36 197	91.82 241	96.92 177	88.89 245			96.67 206	96.22 138
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												96.98 175

SR-MVS					99.33 31			98.40 37				98.90 77

Anonymous202405211			97.39 80		98.85 72	98.59 63	97.89 131	97.93 83	94.41 139		97.37 140	96.99 174	93.09 199	98.61 53	98.46 47	99.11 38	97.27 95

our_test_3					97.32 202	95.13 230	97.59 156

ambc			96.78 130		99.01 62	97.11 174	95.73 233		95.91 69	99.25 3	98.56 102	97.17 169	97.04 72	96.76 137	95.22 183	96.72 203	96.73 118

MTAPA										97.43 56		99.27 35

MTMP										97.63 46		99.03 63

Patchmatch-RL test							17.42 281

tmp_tt				45.72 267	60.00 277	38.74 278	45.50 279	12.18 273	79.58 269	68.42 276	67.62 275	65.04 281	22.12 275	84.83 264	78.72 266	66.08 277

XVS					99.48 19	98.76 48	99.22 21			96.40 109		98.78 96				98.94 55

X-MVStestdata					99.48 19	98.76 48	99.22 21			96.40 109		98.78 96				98.94 55

mPP-MVS					99.58 7							98.98 68

NP-MVS									89.27 226

Patchmtry						92.70 243	95.23 246	98.47 32		96.44 105

DeepMVS_CX						72.99 275	80.14 276	37.34 271	83.46 261	60.13 278	84.40 257	85.48 240	86.93 257	87.22 257		79.61 274	87.32 254

High-resolution multi-view benchmark