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	95.06 1	97.73 1	98.39 1	96.95 1	96.33 51	96.94 37	98.30 20	94.90 15	98.61 1	97.73 3	97.97 26	98.57 36	95.74 4	99.24 1	98.70 4	98.72 7	98.70 2
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
TDRefinement		97.59 2	98.32 2	96.73 4	95.90 67	98.10 2	99.08 2	93.92 31	98.24 3	96.44 13	98.12 21	97.86 72	96.06 2	99.24 1	98.93 1	99.00 2	97.77 5

WR-MVS		97.53 3	98.20 3	96.76 3	96.93 29	98.17 1	98.60 10	96.67 7	96.39 15	94.46 32	99.14 1	98.92 16	94.57 15	99.06 3	98.80 2	99.32 1	96.92 28

SixPastTwentyTwo		97.36 4	97.73 10	96.92 2	97.36 13	96.15 58	98.29 21	94.43 23	96.50 13	96.96 7	98.74 5	98.74 28	96.04 3	99.03 5	97.74 16	98.44 23	97.22 14

PS-CasMVS		97.22 5	97.84 7	96.50 5	97.08 25	97.92 6	98.17 32	97.02 2	94.71 30	95.32 21	98.52 12	98.97 15	92.91 43	99.04 4	98.47 5	98.49 19	97.24 13

PEN-MVS		97.16 6	97.87 6	96.33 11	97.20 21	97.97 4	98.25 25	96.86 6	95.09 26	94.93 26	98.66 7	99.16 7	92.27 53	98.98 6	98.39 7	98.49 19	96.83 32

DTE-MVSNet		97.16 6	97.75 9	96.47 6	97.40 12	97.95 5	98.20 28	96.89 5	95.30 21	95.15 24	98.66 7	98.80 23	92.77 47	98.97 7	98.27 9	98.44 23	96.28 43

COLMAP_ROB	93.74 2	97.09 8	97.98 4	96.05 17	95.97 63	97.78 9	98.56 11	91.72 89	97.53 7	96.01 15	98.14 20	98.76 27	95.28 5	98.76 11	98.23 10	98.77 5	96.67 36
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
WR-MVS_H		97.06 9	97.78 8	96.23 13	96.74 37	98.04 3	98.25 25	97.32 1	94.40 40	93.71 51	98.55 10	98.89 18	92.97 40	98.91 9	98.45 6	98.38 28	97.19 15

CP-MVSNet		96.97 10	97.42 14	96.44 7	97.06 26	97.82 8	98.12 35	96.98 3	93.50 57	95.21 23	97.98 25	98.44 39	92.83 46	98.93 8	98.37 8	98.46 22	96.91 29

DVP-MVS++		96.63 11	97.92 5	95.12 40	97.77 6	97.52 16	98.29 21	93.83 34	96.72 9	92.52 75	98.10 22	99.07 13	90.87 79	97.83 31	97.44 28	97.44 61	98.76 1

ACMH	90.17 8	96.61 12	97.69 12	95.35 30	95.29 83	96.94 37	98.43 14	92.05 74	98.04 4	95.38 19	98.07 23	99.25 4	93.23 33	98.35 16	97.16 39	97.72 51	96.00 49
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UA-Net		96.56 13	96.73 24	96.36 9	98.99 1	97.90 7	97.79 45	95.64 10	92.78 76	92.54 74	96.23 89	95.02 151	94.31 18	98.43 15	98.12 11	98.89 3	98.58 3

ACMMPR		96.54 14	96.71 26	96.35 10	97.55 9	97.63 11	98.62 9	94.54 19	94.45 37	94.19 38	95.04 117	97.35 89	94.92 10	97.85 28	97.50 25	98.26 29	97.17 16

v7n		96.49 15	97.20 18	95.65 22	95.57 77	96.04 60	97.93 40	92.49 58	96.40 14	97.13 6	98.99 2	99.41 3	93.79 25	97.84 30	96.15 66	97.00 83	95.60 57

DeepC-MVS	92.47 4	96.44 16	96.75 23	96.08 16	97.57 7	97.19 32	97.96 39	94.28 24	95.29 22	94.92 27	98.31 17	96.92 99	93.69 27	96.81 68	96.50 57	98.06 40	96.27 44
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMM	90.06 9	96.31 17	96.42 33	96.19 14	97.21 20	97.16 34	98.71 5	93.79 37	94.35 41	93.81 45	92.80 155	98.23 51	95.11 6	98.07 20	97.45 27	98.51 18	96.86 31
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	89.90 10	96.27 18	97.52 13	94.81 47	95.19 86	97.18 33	97.97 38	92.52 56	96.72 9	90.50 128	97.31 55	99.11 10	94.10 19	98.67 12	97.90 14	98.56 15	95.79 53

APDe-MVS		96.23 19	97.22 17	95.08 41	96.66 41	97.56 14	98.63 8	93.69 41	94.62 33	89.80 140	97.73 36	98.13 55	93.84 24	97.79 33	97.63 18	97.87 47	97.08 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CP-MVS		96.21 20	96.16 44	96.27 12	97.56 8	97.13 35	98.43 14	94.70 18	92.62 80	94.13 40	92.71 156	98.03 61	94.54 16	98.00 24	97.60 20	98.23 31	97.05 24

HFP-MVS		96.18 21	96.53 30	95.77 20	97.34 16	97.26 29	98.16 33	94.54 19	94.45 37	92.52 75	95.05 115	96.95 98	93.89 22	97.28 49	97.46 26	98.19 33	97.25 11

UniMVSNet_ETH3D		96.15 22	97.71 11	94.33 55	97.31 17	96.71 42	95.06 119	96.91 4	97.86 5	90.42 129	98.55 10	99.60 1	88.01 120	98.51 13	97.81 15	98.26 29	94.95 69

MP-MVS		96.13 23	95.93 48	96.37 8	98.19 3	97.31 28	98.49 13	94.53 22	91.39 116	94.38 34	94.32 132	96.43 113	94.59 14	97.75 35	97.44 28	98.04 41	96.88 30
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ACMMP		96.12 24	96.27 40	95.93 18	97.20 21	97.60 12	98.64 7	93.74 38	92.47 84	93.13 65	93.23 147	98.06 58	94.51 17	97.99 25	97.57 22	98.39 27	96.99 25
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
DVP-MVS		96.10 25	97.23 16	94.79 49	96.28 54	97.49 17	97.90 41	93.60 43	95.47 19	89.57 146	97.32 54	97.72 75	93.89 22	97.74 36	97.53 23	97.51 57	97.34 9
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
LGP-MVS_train		96.10 25	96.29 37	95.87 19	96.72 38	97.35 27	98.43 14	93.83 34	90.81 131	92.67 73	95.05 115	98.86 21	95.01 7	98.11 18	97.37 35	98.52 17	96.50 38

CSCG		96.07 27	97.15 19	94.81 47	96.06 62	97.58 13	96.52 76	90.98 100	96.51 12	93.60 53	97.13 65	98.55 37	93.01 37	97.17 53	95.36 83	98.68 9	97.78 4

DPE-MVS		96.00 28	96.80 22	95.06 42	95.87 70	97.47 22	98.25 25	93.73 39	92.38 88	91.57 103	97.55 47	97.97 64	92.98 38	97.49 47	97.61 19	97.96 45	97.16 17
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SMA-MVS		95.99 29	96.48 31	95.41 29	97.43 11	97.36 25	97.55 50	93.70 40	94.05 50	93.79 46	97.02 68	94.53 156	92.28 52	97.53 45	97.19 37	97.73 50	97.67 7
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
TSAR-MVS + MP.		95.99 29	96.57 29	95.31 32	96.87 30	96.50 49	98.71 5	91.58 90	93.25 65	92.71 70	96.86 72	96.57 111	93.92 20	98.09 19	97.91 13	98.08 38	96.81 33
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
OPM-MVS		95.96 31	96.59 28	95.23 35	96.67 40	96.52 48	97.86 43	93.28 47	95.27 24	93.46 55	96.26 86	98.85 22	92.89 44	97.09 54	96.37 61	97.22 75	95.78 54
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SteuartSystems-ACMMP		95.96 31	96.13 45	95.76 21	97.06 26	97.36 25	98.40 18	94.24 26	91.49 109	91.91 93	94.50 128	96.89 100	94.99 8	98.01 23	97.44 28	97.97 44	97.25 11
Skip Steuart: Steuart Systems R&D Blog.
ACMP	89.62 11	95.96 31	96.28 38	95.59 23	96.58 43	97.23 31	98.26 24	93.22 48	92.33 92	92.31 83	94.29 133	98.73 29	94.68 12	98.04 21	97.14 40	98.47 21	96.17 46
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PGM-MVS		95.90 34	95.72 52	96.10 15	97.53 10	97.45 23	98.55 12	94.12 28	90.25 136	93.71 51	93.20 148	97.18 93	94.63 13	97.68 39	97.34 36	98.08 38	96.97 26

PMVS	87.16 16	95.88 35	96.47 32	95.19 37	97.00 28	96.02 61	96.70 67	91.57 91	94.43 39	95.33 20	97.16 63	95.37 139	92.39 49	98.89 10	98.72 3	98.17 35	94.71 75
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ACMMP_NAP		95.86 36	96.18 41	95.47 28	97.11 24	97.26 29	98.37 19	93.48 45	93.49 58	93.99 43	95.61 99	94.11 160	92.49 48	97.87 27	97.44 28	97.40 64	97.52 8

Gipuma		95.86 36	96.17 42	95.50 27	95.92 66	94.59 108	94.77 130	92.50 57	97.82 6	97.90 2	95.56 103	97.88 70	94.71 11	98.02 22	94.81 98	97.23 74	94.48 81
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LS3D		95.83 38	96.35 35	95.22 36	96.47 47	97.49 17	97.99 36	92.35 61	94.92 29	94.58 30	94.88 122	95.11 149	91.52 64	98.48 14	98.05 12	98.42 25	95.49 58

SD-MVS		95.77 39	96.17 42	95.30 33	96.72 38	96.19 57	97.01 59	93.04 49	94.03 51	92.71 70	96.45 84	96.78 107	93.91 21	96.79 69	95.89 72	98.42 25	97.09 22
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
SED-MVS		95.73 40	96.98 20	94.28 56	96.08 60	97.39 24	98.18 31	93.80 36	94.20 43	89.61 145	97.29 58	97.49 85	90.69 83	97.74 36	97.41 32	97.32 69	97.34 9

TranMVSNet+NR-MVSNet		95.72 41	96.42 33	94.91 46	96.21 55	96.77 41	96.90 64	94.99 13	92.62 80	91.92 92	98.51 13	98.63 33	90.82 80	97.27 50	96.83 45	98.63 12	94.31 82

DU-MVS		95.51 42	95.68 53	95.33 31	96.45 48	96.44 51	96.61 73	95.32 11	89.97 142	93.78 47	97.46 50	98.07 57	91.19 71	97.03 57	96.53 54	98.61 13	94.22 83

ME-MVS		95.48 43	96.73 24	94.02 64	95.47 79	97.55 15	98.20 28	91.80 85	93.84 53	89.07 155	98.30 18	97.53 84	92.98 38	96.86 67	96.68 52	96.59 92	96.33 41

UniMVSNet (Re)		95.46 44	95.86 50	95.00 45	96.09 58	96.60 43	96.68 71	94.99 13	90.36 135	92.13 86	97.64 42	98.13 55	91.38 65	96.90 62	96.74 47	98.73 6	94.63 77

RPSCF		95.46 44	96.95 21	93.73 80	95.72 74	95.94 65	95.58 103	88.08 161	95.31 20	91.34 106	96.26 86	98.04 60	93.63 28	98.28 17	97.67 17	98.01 42	97.13 18

anonymousdsp		95.45 46	96.70 27	93.99 68	88.43 235	92.05 171	99.18 1	85.42 201	94.29 42	96.10 14	98.63 9	99.08 12	96.11 1	97.77 34	97.41 32	98.70 8	97.69 6

APD-MVS		95.38 47	95.68 53	95.03 43	97.30 18	96.90 39	97.83 44	93.92 31	89.40 149	90.35 130	95.41 107	97.69 77	92.97 40	97.24 52	97.17 38	97.83 48	95.96 50
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
UniMVSNet_NR-MVSNet		95.34 48	95.51 57	95.14 39	95.80 72	96.55 44	96.61 73	94.79 16	90.04 141	93.78 47	97.51 49	97.25 90	91.19 71	96.68 71	96.31 63	98.65 11	94.22 83

X-MVS		95.33 49	95.13 65	95.57 25	97.35 14	97.48 19	98.43 14	94.28 24	92.30 93	93.28 58	86.89 218	96.82 103	91.87 58	97.85 28	97.59 21	98.19 33	96.95 27

MSP-MVS		95.32 50	96.28 38	94.19 59	96.87 30	97.77 10	98.27 23	93.88 33	94.15 49	89.63 144	95.36 108	98.37 42	90.73 81	94.37 120	97.53 23	95.77 127	96.40 39
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
3Dnovator+	92.82 3	95.22 51	95.16 63	95.29 34	96.17 56	96.55 44	97.64 47	94.02 30	94.16 48	94.29 36	92.09 163	93.71 168	91.90 56	96.68 71	96.51 55	97.70 53	96.40 39

HPM-MVS++		95.21 52	94.89 68	95.59 23	97.79 5	95.39 83	97.68 46	94.05 29	91.91 101	94.35 35	93.38 144	95.07 150	92.94 42	96.01 84	95.88 73	96.73 87	96.61 37

TSAR-MVS + ACMM		95.17 53	95.95 46	94.26 57	96.07 61	96.46 50	95.67 100	94.21 27	93.84 53	90.99 116	97.18 61	95.24 147	93.55 29	96.60 74	95.61 80	95.06 147	96.69 35

CPTT-MVS		95.00 54	94.52 82	95.57 25	96.84 34	96.78 40	97.88 42	93.67 42	92.20 94	92.35 82	85.87 225	97.56 83	94.98 9	96.96 60	96.07 69	97.70 53	96.18 45

SF-MVS		94.88 55	95.87 49	93.73 80	95.30 81	95.93 66	94.80 129	91.76 87	93.11 69	91.93 91	95.83 95	97.07 95	91.11 74	96.62 73	96.44 59	97.46 58	96.13 47

Baseline_NR-MVSNet		94.85 56	95.35 61	94.26 57	96.45 48	93.86 127	96.70 67	94.54 19	90.07 140	90.17 136	98.77 4	97.89 67	90.64 86	97.03 57	96.16 65	97.04 82	93.67 96

EG-PatchMatch MVS		94.81 57	95.53 56	93.97 69	95.89 69	94.62 106	95.55 105	88.18 159	92.77 77	94.88 28	97.04 67	98.61 34	93.31 30	96.89 63	95.19 88	95.99 119	93.56 99

CS-MVS		94.76 58	94.41 87	95.18 38	94.95 92	95.99 62	97.28 52	91.99 76	85.51 190	94.55 31	93.07 150	97.69 77	93.77 26	97.08 55	96.79 46	98.53 16	94.72 73

OMC-MVS		94.74 59	95.46 59	93.91 72	94.62 104	96.26 55	96.64 72	89.36 143	94.20 43	94.15 39	94.02 137	97.73 74	91.34 67	96.15 81	95.04 92	97.37 66	94.80 71

DeepC-MVS_fast	91.38 6	94.73 60	94.98 66	94.44 51	96.83 36	96.12 59	96.69 69	92.17 67	92.98 74	93.72 49	94.14 134	95.45 137	90.49 92	95.73 91	95.30 85	96.71 88	95.13 67
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PHI-MVS		94.65 61	94.84 70	94.44 51	94.95 92	96.55 44	96.46 79	91.10 98	88.96 152	96.00 16	94.55 127	95.32 142	90.67 84	96.97 59	96.69 51	97.44 61	94.84 70

SPE-MVS-test		94.63 62	94.30 93	95.02 44	94.63 102	95.71 73	98.15 34	92.13 69	85.62 189	94.22 37	93.63 142	97.63 82	93.08 36	97.50 46	96.51 55	97.88 46	93.50 100

pmmvs6		94.58 63	97.30 15	91.40 134	94.84 96	94.61 107	93.40 171	92.43 60	98.51 2	85.61 187	98.73 6	99.53 2	84.40 171	97.88 26	97.03 41	97.72 51	94.79 72

DeepPCF-MVS	90.68 7	94.56 64	94.92 67	94.15 60	94.11 117	95.71 73	97.03 58	90.65 105	93.39 63	94.08 41	95.29 112	94.15 159	93.21 34	95.22 104	94.92 96	95.82 126	95.75 55

NR-MVSNet		94.55 65	95.66 55	93.25 92	94.26 113	96.44 51	96.69 69	95.32 11	89.97 142	91.79 98	97.46 50	98.39 41	82.85 184	96.87 65	96.48 58	98.57 14	93.98 89

MGCNet		94.43 66	94.78 74	94.02 64	96.14 57	97.09 36	97.52 51	92.66 54	90.12 138	93.12 66	95.31 110	93.19 173	87.75 122	96.14 82	95.60 81	96.96 84	96.01 48

Vis-MVSNet		94.39 67	95.85 51	92.68 100	90.91 210	95.88 68	97.62 49	91.41 92	91.95 100	89.20 152	97.29 58	96.26 116	90.60 91	96.95 61	95.91 70	96.32 105	96.71 34
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TSAR-MVS + GP.		94.25 68	94.81 72	93.60 82	96.52 46	95.80 71	94.37 142	92.47 59	90.89 127	88.92 157	95.34 109	94.38 157	92.85 45	96.36 79	95.62 79	96.47 98	95.28 64

CNVR-MVS		94.24 69	94.47 83	93.96 70	96.56 44	95.67 75	96.43 80	91.95 78	92.08 97	91.28 108	90.51 177	95.35 140	91.20 70	96.34 80	95.50 82	96.34 103	95.88 52

EC-MVSNet		94.23 70	93.81 116	94.71 50	94.85 95	96.23 56	97.14 54	93.40 46	81.79 213	91.58 102	93.29 146	95.21 148	93.13 35	97.73 38	96.95 42	98.20 32	95.45 59

v1192		93.98 71	93.94 108	94.01 66	93.91 126	94.63 105	97.00 60	89.75 128	91.01 125	96.50 10	97.93 27	98.26 48	91.74 60	92.06 163	92.05 146	95.18 142	91.66 144

v10		93.96 72	94.12 101	93.77 79	93.37 147	95.45 79	96.83 66	91.13 97	89.70 146	95.02 25	97.88 32	98.23 51	91.27 68	92.39 158	92.18 141	94.99 152	93.00 109

CDPH-MVS		93.96 72	93.86 110	94.08 62	96.31 52	95.84 69	96.92 62	91.85 81	87.21 170	91.25 110	92.83 152	96.06 124	91.05 76	95.57 94	94.81 98	97.12 77	94.72 73

MSLP-MVS++		93.91 74	94.30 93	93.45 84	95.51 78	95.83 70	93.12 181	91.93 80	91.45 112	91.40 105	87.42 213	96.12 123	93.27 31	96.57 75	96.40 60	95.49 130	96.29 42

v1921920		93.90 75	93.82 114	94.00 67	93.74 133	94.31 113	97.12 55	89.33 144	91.13 122	96.77 9	97.90 30	98.06 58	91.95 55	91.93 170	91.54 158	95.10 145	91.85 136

train_agg		93.89 76	93.46 129	94.40 53	97.35 14	93.78 130	97.63 48	92.19 66	88.12 159	90.52 127	93.57 143	95.78 130	92.31 51	94.78 112	93.46 123	96.36 101	94.70 76

v144192		93.89 76	93.85 111	93.94 71	93.50 141	94.33 112	97.12 55	89.49 135	90.89 127	96.49 11	97.78 34	98.27 47	91.89 57	92.17 162	91.70 155	95.19 141	91.78 139

v1240		93.89 76	93.72 119	94.09 61	93.98 122	94.31 113	97.12 55	89.37 140	90.74 133	96.92 8	98.05 24	97.89 67	92.15 54	91.53 180	91.60 156	94.99 152	91.93 133

NCCC		93.87 79	93.42 130	94.40 53	96.84 34	95.42 80	96.47 78	92.62 55	92.36 90	92.05 88	83.83 233	95.55 133	91.84 59	95.89 86	95.23 87	96.56 95	95.63 56

v1144		93.83 80	93.87 109	93.78 78	93.72 134	94.57 109	96.85 65	89.98 120	91.31 118	95.90 17	97.89 31	98.40 40	91.13 73	92.01 166	92.01 148	95.10 145	90.94 162

MVS_111021_HR		93.82 81	94.26 97	93.31 87	95.01 90	93.97 123	95.73 97	89.75 128	92.06 98	92.49 77	94.01 138	96.05 125	90.61 90	95.95 85	94.78 101	96.28 106	93.04 108

thisisatest0515		93.79 82	94.41 87	93.06 97	94.14 114	92.50 163	95.56 104	88.55 155	91.61 105	92.45 78	96.84 73	95.71 131	90.62 88	94.58 115	95.07 90	97.05 80	94.58 78

TAPA-MVS	88.94 13	93.78 83	94.31 92	93.18 94	94.14 114	95.99 62	95.74 96	86.98 183	93.43 62	93.88 44	90.16 184	96.88 101	91.05 76	94.33 121	93.95 114	97.28 72	95.40 60
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		93.72 84	93.62 124	93.84 73	94.75 99	94.90 99	97.24 53	91.81 84	86.97 176	92.74 69	93.83 140	97.24 92	90.46 93	95.10 108	94.09 113	96.08 116	93.18 106

casdiffseed414692147		93.69 85	94.80 73	92.40 103	93.85 128	94.47 110	95.64 101	90.17 113	92.40 87	89.43 148	97.16 63	99.09 11	89.22 105	94.45 118	93.37 126	96.09 115	92.66 121

EPP-MVSNet		93.63 86	93.95 107	93.26 90	95.15 87	96.54 47	96.18 87	91.97 77	91.74 102	85.76 185	94.95 120	84.27 220	91.60 63	97.61 43	97.38 34	98.87 4	95.18 66

v8		93.60 87	93.82 114	93.34 85	93.13 159	95.06 92	96.39 81	90.75 103	89.90 144	94.03 42	97.70 38	98.21 53	91.08 75	92.36 159	91.47 159	94.63 169	92.07 129

MCST-MVS		93.60 87	93.40 132	93.83 74	95.30 81	95.40 82	96.49 77	90.87 101	90.08 139	91.72 99	90.28 182	95.99 126	91.69 61	93.94 132	92.99 132	96.93 85	95.13 67

PVSNet_Blended_VisFu		93.60 87	93.41 131	93.83 74	96.31 52	95.65 76	95.71 98	90.58 107	88.08 161	93.17 63	95.29 112	92.20 178	90.72 82	94.69 114	93.41 125	96.51 97	94.54 79

TransMVSNet (Re)		93.55 90	96.32 36	90.32 155	94.38 109	94.05 118	93.30 178	89.53 134	97.15 8	85.12 192	98.83 3	97.89 67	82.21 191	96.75 70	96.14 67	97.35 67	93.46 101

E6new		93.49 91	94.68 78	92.10 112	93.52 138	93.87 125	95.80 93	89.59 132	95.07 27	91.10 112	97.93 27	99.22 5	87.59 124	93.32 141	91.86 150	95.00 150	91.49 148

E6		93.49 91	94.68 78	92.10 112	93.52 138	93.87 125	95.80 93	89.59 132	95.07 27	91.10 112	97.93 27	99.22 5	87.59 124	93.32 141	91.86 150	95.00 150	91.49 148

DCV-MVSNet		93.49 91	95.15 64	91.55 126	94.05 118	95.92 67	95.15 117	91.21 94	92.76 78	87.01 180	89.71 188	97.16 94	83.90 177	97.65 40	96.87 44	97.99 43	95.95 51

v2v482		93.42 94	93.49 128	93.32 86	93.44 146	94.05 118	96.36 84	89.76 127	91.41 114	95.24 22	97.63 43	98.34 44	90.44 94	91.65 178	91.76 154	94.69 166	89.62 176

sasdasda		93.38 95	94.36 89	92.24 107	93.94 124	96.41 53	94.18 152	90.47 108	93.07 72	88.47 168	88.66 199	93.78 165	88.80 109	95.74 89	95.75 76	97.57 55	97.13 18

canonicalmvs		93.38 95	94.36 89	92.24 107	93.94 124	96.41 53	94.18 152	90.47 108	93.07 72	88.47 168	88.66 199	93.78 165	88.80 109	95.74 89	95.75 76	97.57 55	97.13 18

3Dnovator	91.81 5	93.36 97	94.27 96	92.29 106	92.99 166	95.03 93	95.76 95	87.79 165	93.82 55	92.38 81	92.19 162	93.37 172	88.14 119	95.26 103	94.85 97	96.69 89	95.40 60

pm-mvs1		93.27 98	95.94 47	90.16 156	94.13 116	93.66 133	92.61 197	89.91 123	95.73 18	84.28 203	98.51 13	98.29 46	82.80 185	96.44 77	95.76 75	97.25 73	93.21 105

casdiffmvs_mvg		93.27 98	94.83 71	91.45 132	93.59 137	94.47 110	94.91 125	89.83 126	92.04 99	87.14 178	97.57 46	98.47 38	86.03 149	94.07 130	94.44 108	97.21 76	92.76 115
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test1111		93.25 100	94.43 85	91.88 116	95.09 89	94.97 97	94.58 137	92.81 51	93.60 56	83.79 208	97.17 62	89.25 205	87.59 124	97.54 44	96.57 53	97.42 63	91.89 134

Anonymous20231211		93.19 101	95.50 58	90.49 152	93.77 131	95.29 85	94.36 146	90.04 119	91.44 113	84.59 198	96.72 76	97.65 80	82.45 190	97.25 51	96.32 62	97.74 49	93.79 92

TinyColmap		93.17 102	93.33 133	93.00 98	93.84 129	92.76 155	94.75 133	88.90 150	93.97 52	97.48 4	95.28 114	95.29 143	88.37 115	95.31 102	91.58 157	94.65 168	89.10 180

E4		93.16 103	94.30 93	91.84 117	93.48 143	93.69 132	95.42 107	89.49 135	94.67 32	90.67 123	97.52 48	99.01 14	86.97 129	92.46 157	91.21 163	94.98 154	91.54 147

viewmacassd2359aftdt		93.16 103	94.69 77	91.39 135	93.30 151	93.71 131	95.03 121	87.70 166	94.69 31	89.53 147	97.63 43	98.92 16	87.73 123	93.63 137	92.14 143	95.05 148	92.08 128

MVS_111021_LR		93.15 105	93.65 121	92.56 101	93.89 127	92.28 166	95.09 118	86.92 185	91.26 121	92.99 68	94.46 130	96.22 119	90.64 86	95.11 107	93.45 124	95.85 124	92.74 116

FE-MVSNET2		93.14 106	94.47 83	91.60 125	91.62 198	93.79 129	95.37 110	89.92 122	94.18 45	90.83 117	96.68 79	98.24 50	85.30 159	93.77 133	94.37 111	96.58 94	90.24 172

CNLPA		93.14 106	93.67 120	92.53 102	94.62 104	94.73 102	95.00 123	86.57 190	92.85 75	92.43 79	90.94 172	94.67 153	90.35 95	95.41 97	93.70 120	96.23 109	93.37 103

PLC	87.27 15	93.08 108	92.92 141	93.26 90	94.67 100	95.03 93	94.38 141	90.10 114	91.69 103	92.14 85	87.24 214	93.91 163	91.61 62	95.05 109	94.73 104	96.67 90	92.80 112
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CANet		93.07 109	93.05 139	93.10 95	95.90 67	95.41 81	95.88 90	91.94 79	84.77 196	93.36 56	94.05 136	95.25 146	86.25 145	94.33 121	93.94 115	95.30 135	93.58 98

TSAR-MVS + COLMAP		93.06 110	93.65 121	92.36 104	94.62 104	94.28 115	95.36 112	89.46 138	92.18 95	91.64 100	95.55 104	95.27 145	88.60 113	93.24 143	92.50 137	94.46 173	92.55 123

viewdifsd2359ckpt09		93.05 111	93.85 111	92.11 111	93.66 136	95.22 88	95.50 106	89.84 125	90.44 134	88.67 166	94.97 119	97.67 79	89.07 107	93.11 149	93.35 127	95.94 121	92.23 126

ECVR-MVS		93.05 111	94.25 98	91.65 122	94.76 97	95.23 86	94.26 149	92.80 52	92.49 82	83.90 206	96.75 75	89.99 196	86.84 134	97.62 41	96.72 48	97.32 69	90.92 163

E5new		92.97 113	94.09 102	91.68 120	93.48 143	93.65 135	95.26 113	89.37 140	94.47 34	90.54 125	97.30 56	98.79 25	86.56 140	92.00 167	90.74 174	94.86 159	91.65 145

E5		92.97 113	94.09 102	91.68 120	93.48 143	93.65 135	95.26 113	89.37 140	94.47 34	90.54 125	97.30 56	98.79 25	86.56 140	92.00 167	90.74 174	94.86 159	91.65 145

Effi-MVS+		92.93 115	92.16 154	93.83 74	94.29 111	93.53 145	95.04 120	92.98 50	85.27 193	94.46 32	90.24 183	95.34 141	89.99 98	93.72 134	94.23 112	96.22 110	92.79 113

Fast-Effi-MVS+		92.93 115	92.64 147	93.27 89	93.81 130	93.88 124	95.90 89	90.61 106	83.98 202	92.71 70	92.81 154	96.22 119	90.67 84	94.90 111	93.92 116	95.92 122	92.77 114

HQP-MVS		92.87 117	92.49 148	93.31 87	95.75 73	95.01 96	95.64 101	91.06 99	88.54 156	91.62 101	88.16 205	96.25 117	89.47 102	92.26 161	91.81 152	96.34 103	95.40 60

FMVSNet1		92.86 118	95.26 62	90.06 158	92.40 183	95.16 89	94.37 142	92.22 63	93.18 68	82.16 218	96.76 74	97.48 87	81.85 195	95.32 99	94.98 93	97.34 68	93.93 90

CLD-MVS		92.81 119	94.32 91	91.05 142	95.39 80	95.31 84	95.82 92	81.44 236	89.40 149	91.94 90	95.86 93	97.36 88	85.83 152	95.35 98	94.59 106	95.85 124	92.34 124
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
IS_MVSNet		92.76 120	93.25 135	92.19 109	94.91 94	95.56 77	95.86 91	92.12 70	88.10 160	82.71 213	93.15 149	88.30 208	88.86 108	97.29 48	96.95 42	98.66 10	93.38 102

E3new		92.75 121	93.78 117	91.55 126	93.35 148	93.54 143	95.17 115	89.17 145	93.49 58	90.29 135	97.00 70	98.65 30	86.58 138	91.86 172	90.64 176	94.75 162	91.27 152

E3		92.75 121	93.78 117	91.55 126	93.35 148	93.54 143	95.16 116	89.17 145	93.48 61	90.32 132	97.01 69	98.65 30	86.58 138	91.86 172	90.64 176	94.75 162	91.27 152

FC-MVSNet-train		92.75 121	95.40 60	89.66 167	95.21 85	94.82 100	97.00 60	89.40 139	91.13 122	81.71 220	97.72 37	96.43 113	77.57 224	96.89 63	96.72 48	97.05 80	94.09 86

V42		92.67 124	93.50 127	91.71 119	91.41 200	92.96 153	95.71 98	85.00 204	89.67 147	93.22 61	97.67 41	98.01 62	91.02 78	92.65 153	92.12 144	93.86 184	91.42 150

PM-MVS		92.65 125	93.20 137	92.00 114	92.11 191	90.16 205	95.99 88	84.81 209	91.31 118	92.41 80	95.87 92	96.64 109	92.35 50	93.65 136	92.91 133	94.34 177	91.85 136

QAPM		92.57 126	93.51 126	91.47 131	92.91 168	94.82 100	93.01 183	87.51 171	91.49 109	91.21 111	92.24 160	91.70 183	88.74 111	94.54 117	94.39 110	95.41 132	95.37 63

MIMVSNet1		92.52 127	94.88 69	89.77 163	96.09 58	91.99 172	96.92 62	89.68 130	95.92 17	84.55 199	96.64 80	98.21 53	78.44 216	96.08 83	95.10 89	92.91 208	90.22 173

viewmanbaseed2359cas		92.46 128	93.85 111	90.83 145	93.07 161	93.47 147	94.55 139	87.10 181	92.76 78	88.70 165	96.72 76	98.35 43	86.85 133	92.70 151	91.22 162	94.71 165	91.76 141

tfpnnormal		92.45 129	94.77 75	89.74 164	93.95 123	93.44 149	93.25 179	88.49 157	95.27 24	83.20 211	96.51 82	96.23 118	83.17 182	95.47 96	94.52 107	96.38 100	91.97 132

PCF-MVS	87.46 14	92.44 130	91.80 156	93.19 93	94.66 101	95.80 71	96.37 82	90.19 112	87.57 166	92.23 84	89.26 193	93.97 162	89.24 103	91.32 183	90.82 173	96.46 99	93.86 91
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		92.42 131	93.99 106	90.60 150	93.25 153	93.82 128	94.28 148	88.73 153	91.53 107	84.53 201	97.74 35	98.64 32	86.60 137	93.21 145	91.20 164	96.21 111	91.76 141
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewcassd2359sk11		92.41 132	93.33 133	91.34 137	93.24 154	93.43 150	94.96 124	88.94 149	92.44 86	90.07 137	96.53 81	98.31 45	86.27 144	91.34 182	90.17 183	94.57 171	91.11 158

AdaColmap		92.41 132	91.49 160	93.48 83	95.96 64	95.02 95	95.37 110	91.73 88	87.97 163	91.28 108	82.82 237	91.04 189	90.62 88	95.82 88	95.07 90	95.95 120	92.67 117

v148		92.38 134	92.78 145	91.91 115	92.86 169	92.13 169	94.84 127	87.03 182	91.47 111	93.07 67	96.92 71	98.89 18	90.10 97	92.05 164	89.69 188	93.56 189	88.27 191

pmmvs-eth3d		92.34 135	92.33 149	92.34 105	92.67 174	90.67 195	96.37 82	89.06 147	90.98 126	93.60 53	97.13 65	97.02 97	88.29 116	90.20 192	91.42 160	94.07 180	88.89 185

DELS-MVS		92.33 136	93.61 125	90.83 145	92.84 171	95.13 91	94.76 131	87.22 179	87.78 165	88.42 171	95.78 96	95.28 144	85.71 155	94.44 119	93.91 117	96.01 118	92.97 110
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
Effi-MVS+-dtu		92.32 137	91.66 158	93.09 96	95.13 88	94.73 102	94.57 138	92.14 68	81.74 214	90.33 131	88.13 206	95.91 127	89.24 103	94.23 126	93.65 122	97.12 77	93.23 104

MGCFI-Net		92.31 138	94.25 98	90.04 161	93.75 132	95.96 64	93.32 176	90.28 111	93.28 64	80.57 230	88.79 197	93.78 165	84.89 166	95.55 95	95.31 84	97.45 60	97.10 21

UGNet		92.31 138	94.70 76	89.53 169	90.99 208	95.53 78	96.19 86	92.10 72	91.35 117	85.76 185	95.31 110	95.48 136	76.84 229	95.22 104	94.79 100	95.32 134	95.19 65
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
viewdifsd2359ckpt13		92.24 140	93.22 136	91.10 141	93.01 165	93.63 137	94.65 136	87.69 167	90.81 131	88.80 163	95.59 102	97.98 63	87.51 127	91.98 169	90.83 172	94.94 155	91.74 143

USDC		92.17 141	92.17 153	92.18 110	92.93 167	92.22 167	93.66 163	87.41 174	93.49 58	97.99 1	94.10 135	96.68 108	86.46 142	92.04 165	89.18 194	94.61 170	87.47 197

ETV-MVS		92.12 142	90.44 170	94.08 62	96.36 50	93.63 137	96.27 85	92.00 75	78.90 233	92.13 86	85.29 227	89.85 199	90.26 96	97.07 56	96.29 64	97.46 58	92.04 130

IterMVS-LS		92.10 143	92.33 149	91.82 118	93.18 155	93.66 133	92.80 193	92.27 62	90.82 129	90.59 124	97.19 60	90.97 190	87.76 121	89.60 199	90.94 169	94.34 177	93.16 107
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
E2		92.09 144	92.90 142	91.16 140	93.16 158	93.35 151	94.76 131	88.75 152	91.40 115	89.85 138	95.98 91	97.95 66	85.98 151	90.86 186	89.74 186	94.43 174	90.99 161

MSDG		92.09 144	92.84 144	91.22 139	92.55 176	92.97 152	93.42 170	85.43 200	90.24 137	91.83 95	94.70 124	94.59 154	88.48 114	94.91 110	93.31 129	95.59 129	89.15 179

EIA-MVS		91.95 146	90.36 172	93.81 77	96.54 45	94.65 104	95.38 109	90.40 110	78.01 238	93.72 49	86.70 221	91.95 180	89.93 99	95.67 93	94.72 105	96.89 86	90.79 165

MAR-MVS		91.86 147	91.14 165	92.71 99	94.29 111	94.24 116	94.91 125	91.82 83	81.66 215	93.32 57	84.51 230	93.42 171	86.86 132	95.16 106	94.44 108	95.05 148	94.53 80
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
viewdifsd2359ckpt11		91.80 148	94.01 104	89.22 175	92.52 177	91.95 173	93.78 159	84.14 214	93.11 69	83.97 204	97.68 39	99.12 8	86.05 147	94.17 127	90.89 170	94.88 157	91.18 156

viewmsd2359difaftdt		91.80 148	94.01 104	89.22 175	92.52 177	91.95 173	93.78 159	84.14 214	93.11 69	83.97 204	97.68 39	99.12 8	86.05 147	94.16 128	90.89 170	94.88 157	91.18 156

EU-MVSNet		91.63 150	92.73 146	90.35 154	88.36 236	87.89 217	96.53 75	81.51 235	92.45 85	91.82 96	96.44 85	97.05 96	93.26 32	94.10 129	88.94 199	90.61 216	92.24 125

viewdifsd2359ckpt07		91.59 151	93.64 123	89.19 177	92.86 169	92.58 161	94.25 151	84.97 205	94.17 47	85.53 188	97.60 45	98.59 35	85.99 150	91.85 174	88.85 200	91.52 213	91.87 135

FC-MVSNet-test		91.49 152	94.43 85	88.07 198	94.97 91	90.53 198	95.42 107	91.18 96	93.24 66	72.94 250	98.37 15	93.86 164	78.78 209	97.82 32	96.13 68	95.13 143	91.05 159

FA-MVS(training)		91.38 153	91.18 164	91.62 124	93.49 142	92.38 164	95.03 121	90.81 102	87.20 171	91.46 104	93.00 151	89.47 202	84.19 173	93.20 147	92.08 145	94.74 164	90.90 164

FE-MVSNET		91.21 154	92.90 142	89.24 174	90.93 209	91.69 177	93.46 168	87.85 164	92.35 91	85.06 194	94.84 123	96.63 110	82.80 185	92.98 150	93.22 130	95.36 133	88.58 187

usedtu_dtu_shiyan2		91.17 155	93.05 139	88.98 180	95.95 65	92.70 159	93.66 163	91.85 81	96.05 16	82.16 218	93.34 145	98.87 20	76.62 231	93.56 138	92.03 147	93.66 188	84.77 213

OpenMVS	89.22 12	91.09 156	91.42 161	90.71 148	92.79 173	93.61 140	92.74 195	85.47 199	86.10 186	90.73 118	85.71 226	93.07 176	86.69 136	94.07 130	93.34 128	95.86 123	94.02 88

diffmvs_AUTHOR		91.06 157	93.06 138	88.71 188	91.67 196	91.66 178	92.77 194	85.36 202	91.29 120	85.38 190	97.45 52	98.26 48	83.74 178	91.81 175	89.70 187	93.37 200	91.27 152

FPMVS		90.81 158	91.60 159	89.88 162	92.52 177	88.18 213	93.31 177	83.62 218	91.59 106	88.45 170	88.96 196	89.73 201	86.96 130	96.42 78	95.69 78	94.43 174	90.65 166

DI_MVS_pp		90.68 159	90.40 171	91.00 143	92.43 182	92.61 160	94.17 154	88.98 148	88.32 158	88.76 164	93.67 141	87.58 210	86.44 143	89.74 197	90.33 180	95.24 138	90.56 169

Vis-MVSNet (Re-imp)		90.68 159	92.18 152	88.92 183	94.63 102	92.75 156	92.91 186	91.20 95	89.21 151	75.01 246	93.96 139	89.07 206	82.72 188	95.88 87	95.30 85	97.08 79	89.08 181

DPM-MVS		90.67 161	89.86 176	91.63 123	95.29 83	94.16 117	94.52 140	89.63 131	89.59 148	89.67 143	81.95 239	88.64 207	85.75 154	90.46 189	90.43 179	94.91 156	93.77 93

diffmvs		90.44 162	92.23 151	88.35 194	91.36 202	91.38 183	92.45 201	84.84 208	89.88 145	85.09 193	96.69 78	97.71 76	83.33 181	90.01 196	88.96 198	93.03 206	91.00 160
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
FMVSNet2		90.28 163	92.04 155	88.23 196	91.22 204	94.05 118	92.88 187	90.69 104	86.53 179	79.89 234	94.38 131	92.73 177	78.54 212	91.64 179	92.26 140	96.17 112	92.67 117

IterMVS-SCA-FT		90.24 164	89.37 182	91.26 138	92.50 180	92.11 170	91.69 212	87.48 172	87.05 175	91.82 96	95.76 97	87.25 211	91.36 66	89.02 205	85.53 216	92.68 209	88.90 184

MVS_Test		90.19 165	90.58 166	89.74 164	92.12 190	91.74 176	92.51 198	88.54 156	82.80 208	87.50 176	94.62 125	95.02 151	83.97 175	88.69 208	89.32 192	93.79 185	91.85 136

EPNet		90.17 166	89.07 184	91.45 132	97.25 19	90.62 197	94.84 127	93.54 44	80.96 217	91.85 94	86.98 217	85.88 216	77.79 221	92.30 160	92.58 136	93.41 195	94.20 85
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
viewmambaseed2359dif		90.16 167	91.38 162	88.72 186	91.64 197	90.75 191	92.73 196	85.32 203	87.92 164	84.90 195	95.63 98	97.49 85	84.05 174	90.27 191	87.28 205	93.71 187	90.35 171

PVSNet_BlendedMVS		90.09 168	90.12 174	90.05 159	92.40 183	92.74 157	91.74 208	85.89 195	80.54 220	90.30 133	88.54 201	95.51 134	84.69 169	92.64 154	90.25 181	95.28 136	90.61 167

PVSNet_Blended		90.09 168	90.12 174	90.05 159	92.40 183	92.74 157	91.74 208	85.89 195	80.54 220	90.30 133	88.54 201	95.51 134	84.69 169	92.64 154	90.25 181	95.28 136	90.61 167

usedtu_dtu_shiyan1		90.01 170	90.53 169	89.39 172	90.47 214	91.62 180	93.36 172	87.13 180	87.52 167	87.00 181	92.63 157	94.03 161	82.94 183	89.33 203	91.00 168	95.46 131	87.61 194

pmmvs4		89.95 171	89.32 183	90.69 149	91.60 199	89.17 210	94.37 142	87.63 168	88.07 162	91.02 115	94.50 128	90.50 194	86.13 146	86.33 222	89.40 191	93.39 197	87.29 201

MDA-MVSNet-bldmvs		89.75 172	91.67 157	87.50 203	74.25 259	90.88 189	94.68 134	85.89 195	91.64 104	91.03 114	95.86 93	94.35 158	89.10 106	96.87 65	86.37 212	90.04 218	85.72 210

WB-MVS		89.70 173	94.13 100	84.54 225	88.16 238	92.57 162	88.90 232	88.32 158	96.67 11	73.61 249	98.29 19	98.80 23	80.60 201	95.73 91	92.18 141	87.66 232	84.64 214

tttt0517		89.64 174	88.05 196	91.49 130	93.52 138	91.65 179	93.67 162	87.53 169	82.77 209	89.39 150	90.37 181	70.05 245	88.21 117	93.71 135	93.79 118	96.63 91	94.04 87

PatchMatch-RL		89.59 175	88.80 188	90.51 151	92.20 189	88.00 216	91.72 210	86.64 187	84.75 197	88.25 172	87.10 216	90.66 193	89.85 101	93.23 144	92.28 139	94.41 176	85.60 211

Fast-Effi-MVS+-dtu		89.57 176	88.42 192	90.92 144	93.35 148	91.57 181	93.01 183	95.71 9	78.94 232	87.65 175	84.68 229	93.14 175	82.00 193	90.84 187	91.01 167	93.78 186	88.77 186

thisisatest0530		89.54 177	87.99 200	91.35 136	93.17 156	91.31 184	93.45 169	87.53 169	82.96 207	89.17 154	90.45 178	70.32 244	88.21 117	93.37 140	93.79 118	96.54 96	93.71 95

test2506		89.51 178	87.77 203	91.55 126	94.76 97	95.23 86	94.26 149	92.80 52	92.49 82	83.31 210	89.97 186	50.93 265	86.84 134	97.62 41	96.72 48	97.32 69	91.42 150

GBi-Net		89.35 179	90.58 166	87.91 199	91.22 204	94.05 118	92.88 187	90.05 116	79.40 224	78.60 237	90.58 174	87.05 212	78.54 212	95.32 99	94.98 93	96.17 112	92.67 117

test1		89.35 179	90.58 166	87.91 199	91.22 204	94.05 118	92.88 187	90.05 116	79.40 224	78.60 237	90.58 174	87.05 212	78.54 212	95.32 99	94.98 93	96.17 112	92.67 117

thres600view7		89.14 181	88.83 186	89.51 170	93.71 135	93.55 141	93.93 158	88.02 162	87.30 169	82.40 214	81.18 240	80.63 231	82.69 189	94.27 123	95.90 71	96.27 107	88.94 183

CVMVSNet		88.97 182	89.73 178	88.10 197	87.33 243	85.22 229	94.68 134	78.68 238	88.94 153	86.98 182	95.55 104	85.71 217	89.87 100	91.19 184	89.69 188	91.05 214	91.78 139

CANet_DTU		88.95 183	89.51 181	88.29 195	93.12 160	91.22 187	93.61 165	83.47 221	80.07 223	90.71 122	89.19 194	93.68 169	76.27 234	91.44 181	91.17 166	92.59 210	89.83 175

gbinet_0.2-2-1-0.02		88.79 184	88.26 193	89.40 171	89.67 223	91.24 185	94.03 156	84.65 211	85.76 188	89.02 156	92.83 152	90.75 192	85.62 156	85.86 224	82.42 223	93.41 195	88.98 182

GA-MVS		88.76 185	88.04 198	89.59 168	92.32 186	91.46 182	92.28 203	86.62 188	83.82 204	89.84 139	92.51 159	81.94 225	83.53 180	89.41 201	89.27 193	92.95 207	87.90 192

pmmvs5		88.63 186	89.70 179	87.39 204	89.24 225	90.64 196	91.87 207	82.13 231	83.34 205	87.86 174	94.58 126	96.15 122	79.87 205	87.33 217	89.07 197	93.39 197	86.76 204

thres400		88.54 187	88.15 195	88.98 180	93.17 156	92.84 154	93.56 166	86.93 184	86.45 180	82.37 215	79.96 242	81.46 228	81.83 196	93.21 145	94.76 102	96.04 117	88.39 189

blended_shiyan8		88.52 188	88.03 199	89.08 178	89.78 221	90.69 192	93.34 174	82.82 224	87.12 173	89.21 151	91.51 166	91.71 182	85.38 157	85.01 228	82.73 222	93.96 181	87.47 197

blended_shiyan6		88.52 188	88.05 196	89.07 179	89.79 219	90.69 192	93.34 174	82.81 225	87.12 173	89.19 153	91.48 167	91.81 181	85.32 158	84.98 229	82.74 221	93.95 182	87.52 195

CDS-MVSNet		88.41 190	89.79 177	86.79 210	94.55 107	90.82 190	92.50 199	89.85 124	83.26 206	80.52 231	91.05 168	89.93 198	69.11 245	93.17 148	92.71 135	94.21 179	87.63 193
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gg-mvs-nofinetune		88.32 191	88.81 187	87.75 201	93.07 161	89.37 209	89.06 231	95.94 8	95.29 22	87.15 177	97.38 53	76.38 234	68.05 248	91.04 185	89.10 196	93.24 202	83.10 221

IterMVS		88.32 191	88.25 194	88.41 193	90.83 211	91.24 185	93.07 182	81.69 233	86.77 177	88.55 167	95.61 99	86.91 215	87.01 128	87.38 216	83.77 218	89.29 222	86.06 209
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres200		88.29 193	87.88 201	88.76 185	92.50 180	93.55 141	92.47 200	88.02 162	84.80 195	81.44 221	79.28 244	82.20 224	81.83 196	94.27 123	93.67 121	96.27 107	87.40 199

IB-MVS	86.01 17	88.24 194	87.63 204	88.94 182	92.03 192	91.77 175	92.40 202	85.58 198	78.24 235	84.85 196	71.99 251	93.45 170	83.96 176	93.48 139	92.33 138	94.84 161	92.15 127
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
MDTV_nov1_ep13_2view		88.22 195	87.85 202	88.65 189	91.40 201	86.75 221	94.07 155	84.97 205	88.86 155	93.20 62	96.11 90	96.21 121	83.70 179	87.29 218	80.29 233	84.56 241	79.46 237

test20.03		88.20 196	91.26 163	84.63 223	96.64 42	89.39 208	90.73 219	89.97 121	91.07 124	72.02 252	94.98 118	95.45 137	69.35 244	92.70 151	91.19 165	89.06 224	84.02 215

HyFIR lowres test		88.19 197	86.56 213	90.09 157	91.24 203	92.17 168	94.30 147	88.79 151	84.06 199	85.45 189	89.52 191	85.64 218	88.64 112	85.40 226	87.28 205	92.14 212	81.87 225

ET-MVSNet_ETH3D		88.06 198	85.75 218	90.74 147	92.82 172	90.68 194	93.77 161	88.59 154	81.22 216	89.78 141	89.15 195	66.79 258	84.29 172	91.72 177	91.34 161	95.22 139	89.36 178

wanda-best-256-512		87.94 199	87.36 208	88.61 190	89.23 226	90.35 200	92.84 190	82.30 226	86.26 182	88.91 158	90.96 170	91.43 185	84.94 163	84.27 230	81.61 226	93.45 190	86.67 206

FE-blended-shiyan7		87.94 199	87.36 208	88.61 190	89.23 226	90.35 200	92.84 190	82.30 226	86.26 182	88.91 158	90.96 170	91.43 185	84.94 163	84.27 230	81.61 226	93.45 190	86.67 206

tfpn200view9		87.94 199	87.51 206	88.44 192	92.28 187	93.63 137	93.35 173	88.11 160	80.90 218	80.89 227	78.25 245	82.25 222	79.65 207	94.27 123	94.76 102	96.36 101	88.48 188

FMVSNet3		87.90 202	88.63 190	87.04 206	89.78 221	93.46 148	91.62 213	90.05 116	79.40 224	78.60 237	90.58 174	87.05 212	77.07 228	88.03 213	89.86 185	95.12 144	92.04 130

MS-PatchMatch		87.72 203	88.62 191	86.66 211	90.81 212	88.18 213	90.92 216	82.25 230	85.86 187	80.40 232	90.14 185	89.29 204	84.93 165	89.39 202	89.12 195	90.67 215	88.34 190

Anonymous20231206		87.45 204	89.66 180	84.87 220	94.00 119	87.73 219	91.36 214	86.41 192	88.89 154	75.03 245	92.59 158	96.82 103	72.48 242	89.72 198	88.06 202	89.93 219	83.81 217

EPNet_dtu		87.40 205	86.27 214	88.72 186	95.68 75	83.37 236	92.09 205	90.08 115	78.11 237	91.29 107	86.33 222	89.74 200	75.39 237	89.07 204	87.89 203	87.81 229	89.38 177
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
baseline1		86.96 206	87.58 205	86.24 214	93.07 161	90.44 199	89.24 230	86.85 186	85.14 194	77.26 243	90.45 178	76.09 236	75.79 235	91.80 176	91.81 152	95.20 140	87.35 200

baseline		86.71 207	88.89 185	84.16 226	87.85 239	85.23 228	89.82 224	77.69 241	84.03 201	84.75 197	94.91 121	94.59 154	77.19 227	86.57 221	86.51 211	87.66 232	90.36 170

CHOSEN 1792x2688		86.64 208	86.62 211	86.65 212	90.33 216	87.86 218	93.19 180	83.30 222	83.95 203	82.32 216	87.93 208	89.34 203	86.92 131	85.64 225	84.95 217	83.85 245	86.68 205

dmvs_re		86.51 209	86.14 216	86.95 208	93.07 161	86.11 224	92.01 206	86.04 194	72.70 248	79.10 235	75.37 248	89.99 196	78.10 220	94.56 116	93.01 131	93.35 201	91.26 155

testgi		86.49 210	90.31 173	82.03 232	95.63 76	88.18 213	93.47 167	84.89 207	93.23 67	69.54 256	87.16 215	97.96 65	60.66 252	91.90 171	89.90 184	87.99 227	83.84 216

thres100view900		86.46 211	86.00 217	86.99 207	92.28 187	91.03 188	91.09 215	84.49 212	80.90 218	80.89 227	78.25 245	82.25 222	77.57 224	90.17 193	92.84 134	95.63 128	86.57 208

gm-plane-assit		86.15 212	82.51 226	90.40 153	95.81 71	92.29 165	97.99 36	84.66 210	92.15 96	93.15 64	97.84 33	44.65 266	78.60 211	88.02 214	85.95 213	92.20 211	76.69 245

CMPMVS	66.55 18	85.55 213	87.46 207	83.32 228	84.99 245	81.97 241	79.19 257	75.93 243	79.32 227	88.82 161	85.09 228	91.07 188	82.12 192	92.56 156	89.63 190	88.84 225	92.56 122
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CR-MVSNet		85.32 214	81.58 228	89.69 166	90.36 215	84.79 232	86.72 247	92.22 63	75.38 243	90.73 118	90.41 180	67.88 249	84.86 167	83.76 235	85.74 214	93.24 202	83.14 219

baseline2		84.95 215	82.68 225	87.59 202	92.64 175	88.41 212	90.09 221	84.25 213	75.88 241	85.23 191	82.49 238	71.15 242	80.14 204	88.21 212	87.21 209	93.21 205	85.39 212

pmnet_mix02		84.85 216	86.58 212	82.83 229	90.19 217	81.10 244	88.52 235	78.58 239	91.50 108	80.32 233	96.48 83	95.86 128	75.42 236	85.17 227	76.44 243	83.91 244	79.51 236

MVSTER		84.79 217	83.79 221	85.96 216	89.14 230	89.80 206	89.39 228	82.99 223	74.16 247	82.78 212	85.97 224	66.81 257	76.84 229	90.77 188	88.83 201	94.66 167	90.19 174

MIMVSNet		84.76 218	86.75 210	82.44 231	91.71 195	85.95 225	89.74 226	89.49 135	85.28 192	69.69 255	87.93 208	90.88 191	64.85 250	88.26 211	87.74 204	89.18 223	81.24 226

SCA		84.69 219	81.10 229	88.87 184	89.02 231	90.31 204	92.21 204	92.09 73	82.72 210	89.68 142	86.83 219	73.08 238	85.80 153	80.50 244	77.51 239	84.45 243	76.80 244

new-patchmatchnet		84.45 220	88.75 189	79.43 240	93.28 152	81.87 242	81.68 254	83.48 220	94.47 34	71.53 253	98.33 16	97.88 70	58.61 255	90.35 190	77.33 240	87.99 227	81.05 228

FE-MVSNET3		83.78 221	80.73 232	87.34 205	89.23 226	90.35 200	92.84 190	82.30 226	86.26 182	81.00 223	68.18 254	66.96 252	85.24 160	84.27 230	81.61 226	93.45 190	87.52 195

PatchT		83.44 222	81.10 229	86.18 215	77.92 257	82.58 240	89.87 223	87.39 175	75.88 241	90.73 118	89.86 187	66.71 259	84.86 167	83.76 235	85.74 214	86.33 238	83.14 219

RPMNet		83.42 223	78.40 240	89.28 173	89.79 219	84.79 232	90.64 220	92.11 71	75.38 243	87.10 179	79.80 243	61.99 264	82.79 187	81.88 242	82.07 225	93.23 204	82.87 222

usedtu_blend_shiyan5		83.28 224	80.64 233	86.37 213	89.23 226	90.35 200	87.00 245	82.30 226	86.26 182	81.00 223	68.18 254	66.96 252	85.24 160	84.27 230	81.61 226	93.45 190	86.85 202

TAMVS		82.96 225	86.15 215	79.24 243	90.57 213	83.12 239	87.29 241	75.12 245	84.06 199	65.81 257	92.22 161	88.27 209	69.11 245	88.72 206	87.26 208	87.56 234	79.38 238

PatchmatchNet		82.44 226	78.69 239	86.83 209	89.81 218	81.55 243	90.78 218	87.27 178	82.39 212	88.85 160	88.31 204	70.96 243	81.90 194	78.58 248	74.33 251	82.35 249	74.69 248
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13		82.33 227	79.66 234	85.45 218	88.83 233	83.88 234	90.09 221	81.98 232	79.07 231	88.82 161	88.70 198	73.77 237	78.41 217	80.29 246	76.08 244	84.56 241	75.83 246

CostFormer		82.15 228	79.54 235	85.20 219	88.92 232	85.70 226	90.87 217	86.26 193	79.19 230	83.87 207	87.89 210	69.20 247	76.62 231	77.50 251	75.28 247	84.69 240	82.02 224

PMMVS		81.93 229	83.48 223	80.12 239	72.35 260	75.05 253	88.54 234	64.01 253	77.02 240	82.22 217	87.51 212	91.12 187	79.70 206	86.59 219	86.64 210	93.88 183	80.41 231

pmmvs3		81.69 230	83.83 220	79.19 244	78.33 256	78.57 247	89.53 227	58.71 256	78.88 234	84.34 202	88.36 203	91.96 179	77.69 223	87.48 215	82.42 223	86.54 237	79.18 239

tpm		81.58 231	78.84 237	84.79 222	91.11 207	79.50 245	89.79 225	83.75 216	79.30 228	92.05 88	90.98 169	64.78 261	74.54 238	80.50 244	76.67 241	77.49 254	80.15 234

test0.0.03 1		81.51 232	83.30 224	79.42 241	93.99 120	86.50 222	85.93 251	87.32 176	78.16 236	61.62 258	80.78 241	81.78 226	59.87 253	88.40 210	87.27 207	87.78 231	80.19 233

dps		81.42 233	77.88 245	85.56 217	87.67 241	85.17 230	88.37 237	87.46 173	74.37 246	84.55 199	86.80 220	62.18 263	80.20 203	81.13 243	77.52 238	85.10 239	77.98 242

test-LLR		80.62 234	77.20 248	84.62 224	93.99 120	75.11 251	87.04 243	87.32 176	70.11 251	78.59 240	83.17 235	71.60 240	73.88 240	82.32 239	79.20 235	86.91 235	78.87 240

blend_shiyan4		80.12 235	77.11 250	83.63 227	78.60 255	89.75 207	83.59 253	79.95 237	64.53 257	81.00 223	68.18 254	66.96 252	85.24 160	82.23 241	81.29 231	93.38 199	86.85 202

tpm cat1		80.03 236	75.93 252	84.81 221	89.31 224	83.26 238	88.86 233	86.55 191	79.24 229	86.10 184	84.22 231	63.62 262	77.37 226	73.43 255	70.88 254	80.67 250	76.87 243

N_pmnet		79.33 237	84.22 219	73.62 250	91.72 194	73.72 254	86.11 249	76.36 242	92.38 88	53.38 259	95.54 106	95.62 132	59.14 254	84.23 234	74.84 250	75.03 257	73.25 252

EPMVS		79.26 238	78.20 243	80.49 237	87.04 244	78.86 246	86.08 250	83.51 219	82.63 211	73.94 248	89.59 189	68.67 248	72.03 243	78.17 249	75.08 249	80.37 251	74.37 249

CHOSEN 280x420		79.24 239	78.26 242	80.38 238	79.60 254	68.80 259	89.32 229	75.38 244	77.25 239	78.02 242	75.57 247	76.17 235	81.19 199	88.61 209	81.39 230	78.79 252	80.03 235

ADS-MVSNet		79.11 240	79.38 236	78.80 246	81.90 250	75.59 250	84.36 252	83.69 217	87.31 168	76.76 244	87.58 211	76.90 233	68.55 247	78.70 247	75.56 246	77.53 253	74.07 250

FMVSNet5		79.08 241	78.83 238	79.38 242	87.52 242	86.78 220	87.64 239	78.15 240	69.54 253	70.64 254	65.97 258	65.44 260	63.87 251	90.17 193	90.46 178	88.48 226	83.45 218

0.4-1-1-0.1		78.93 242	75.69 253	82.71 230	82.54 248	86.31 223	88.34 238	74.63 246	67.88 254	81.41 222	73.65 249	67.37 250	79.03 208	75.97 252	76.53 242	90.33 217	82.09 223

tpmrst		78.81 243	76.18 251	81.87 234	88.56 234	77.45 248	86.74 246	81.52 234	80.08 222	83.48 209	90.84 173	66.88 256	74.54 238	73.04 256	71.02 253	76.38 255	73.95 251

test-mter		78.71 244	78.35 241	79.12 245	84.03 246	76.58 249	88.51 236	59.06 255	71.06 249	78.87 236	83.73 234	71.83 239	76.44 233	83.41 238	80.61 232	87.79 230	81.24 226

MVS-HIRNet		78.28 245	75.28 254	81.79 235	80.33 253	69.38 258	76.83 258	86.59 189	70.76 250	86.66 183	89.57 190	81.04 229	77.74 222	77.81 250	71.65 252	82.62 247	66.73 256

0.3-1-1-0.015		77.85 246	74.34 256	81.96 233	81.59 251	85.29 227	87.54 240	73.36 247	66.50 255	81.00 223	70.68 252	66.96 252	78.53 215	74.61 254	75.58 245	89.73 220	80.73 229

E-PMN		77.81 247	77.88 245	77.73 249	88.26 237	70.48 257	80.19 256	71.20 250	86.66 178	72.89 251	88.09 207	81.74 227	78.75 210	90.02 195	68.30 255	75.10 256	59.85 257

0.4-1-1-0.2		77.70 248	74.35 255	81.60 236	81.26 252	84.89 231	87.05 242	72.99 248	65.96 256	80.75 229	72.00 250	67.32 251	78.19 219	74.64 253	75.15 248	89.36 221	80.50 230

EMVS		77.65 249	77.49 247	77.83 247	87.75 240	71.02 256	81.13 255	70.54 251	86.38 181	74.52 247	89.38 192	80.19 232	78.22 218	89.48 200	67.13 256	74.83 258	58.84 258

TESTMET0.1,1		77.47 250	77.20 248	77.78 248	81.94 249	75.11 251	87.04 243	58.33 257	70.11 251	78.59 240	83.17 235	71.60 240	73.88 240	82.32 239	79.20 235	86.91 235	78.87 240

new_pmnet		76.65 251	83.52 222	68.63 251	82.60 247	72.08 255	76.76 259	64.17 252	84.41 198	49.73 261	91.77 164	91.53 184	56.16 256	86.59 219	83.26 220	82.37 248	75.02 247

MVE	60.41 19	73.21 252	80.84 231	64.30 252	56.34 261	57.24 261	75.28 261	72.76 249	87.14 172	41.39 263	86.31 223	85.30 219	80.66 200	86.17 223	83.36 219	59.35 260	80.38 232
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		69.86 253	82.14 227	55.52 253	75.19 258	63.08 260	75.52 260	60.97 254	88.50 157	25.11 265	91.77 164	96.44 112	25.43 258	88.70 207	79.34 234	70.93 259	67.17 255

GG-mvs-BLEND		54.28 254	77.89 244	26.72 256	0.37 266	83.31 237	70.04 262	0.39 263	74.71 245	5.36 266	68.78 253	83.06 221	0.62 262	83.73 237	78.99 237	83.55 246	72.68 254

test_method		43.16 255	51.13 257	33.85 254	7.35 263	12.38 264	51.70 264	11.91 259	62.51 259	47.64 262	62.49 259	80.78 230	28.84 257	59.55 259	34.48 258	55.68 261	45.72 259

testmvs		2.38 256	3.35 258	1.26 258	0.83 264	0.96 266	1.53 267	0.83 261	3.59 261	1.63 268	6.03 261	2.93 268	1.55 261	3.49 260	2.51 260	1.21 265	3.92 261

test123		2.16 257	2.82 259	1.41 257	0.62 265	1.18 265	1.53 267	0.82 262	2.78 262	2.27 267	4.18 262	1.98 269	1.64 260	2.58 261	3.01 259	1.56 264	4.00 260

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							98.20 28	91.80 85		87.87 173						96.59 92

TPM-MVS					94.35 110	93.52 146	92.94 185			89.43 148	84.20 232	90.07 195	80.21 202			94.56 172	93.77 93
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										97.21 5

9.14												93.19 173

SR-MVS					97.13 23			94.77 17				97.77 73

Anonymous202405211			94.63 80		94.51 108	94.96 98	93.94 157	91.35 93	90.82 129		95.60 101	95.85 129	81.74 198	96.47 76	95.84 74	97.39 65	92.85 111

our_test_3					91.78 193	88.87 211	94.37 142

ambc			94.61 81		98.09 4	95.14 90	91.71 211		94.18 45	96.46 12	96.26 86	96.30 115	91.26 69	94.70 113	92.00 149	93.45 190	93.67 96

MTAPA										94.88 28		96.88 101

MTMP										95.43 18		97.25 90

Patchmatch-RL test							8.96 266

tmp_tt				28.44 255	36.05 262	15.86 263	21.29 265	6.40 260	54.52 260	51.96 260	50.37 260	38.68 267	9.55 259	61.75 258	59.66 257	45.36 263

XVS					96.86 32	97.48 19	98.73 3			93.28 58		96.82 103				98.17 35

X-MVStestdata					96.86 32	97.48 19	98.73 3			93.28 58		96.82 103				98.17 35

mPP-MVS					98.24 2							97.65 80

NP-MVS									85.48 191

Patchmtry						83.74 235	86.72 247	92.22 63		90.73 118

DeepMVS_CX						47.68 262	53.20 263	19.21 258	63.24 258	26.96 264	66.50 257	69.82 246	66.91 249	64.27 257		54.91 262	72.72 253

High-resolution multi-view benchmark