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 38	98.30 20	94.90 15	98.61 1	97.73 3	97.97 28	98.57 37	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 22	97.86 76	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 59	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 31	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 27	94.93 26	98.66 7	99.16 7	92.27 54	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 22	95.15 24	98.66 7	98.80 23	92.77 48	98.97 7	98.27 9	98.44 23	96.28 44

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 90	97.53 7	96.01 15	98.14 21	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 41	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 60	95.21 23	97.98 26	98.44 40	92.83 47	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 23	99.07 13	90.87 80	97.83 31	97.44 28	97.44 62	98.76 1

ACMH	90.17 8	96.61 12	97.69 12	95.35 30	95.29 85	96.94 38	98.43 14	92.05 75	98.04 4	95.38 19	98.07 24	99.25 4	93.23 33	98.35 16	97.16 39	97.72 52	96.00 50
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UA-Net		96.56 13	96.73 25	96.36 9	98.99 1	97.90 7	97.79 45	95.64 10	92.78 79	92.54 74	96.23 94	95.02 161	94.31 18	98.43 15	98.12 11	98.89 3	98.58 3

ACMMPR		96.54 14	96.71 27	96.35 10	97.55 9	97.63 11	98.62 9	94.54 19	94.45 38	94.19 38	95.04 126	97.35 96	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 78	96.04 61	97.93 40	92.49 59	96.40 14	97.13 6	98.99 2	99.41 3	93.79 25	97.84 30	96.15 67	97.00 84	95.60 58

DeepC-MVS	92.47 4	96.44 16	96.75 24	96.08 16	97.57 7	97.19 33	97.96 39	94.28 24	95.29 23	94.92 27	98.31 17	96.92 107	93.69 27	96.81 69	96.50 58	98.06 40	96.27 45
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 34	96.19 14	97.21 20	97.16 35	98.71 5	93.79 37	94.35 42	93.81 45	92.80 165	98.23 53	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 88	97.18 34	97.97 38	92.52 57	96.72 9	90.50 128	97.31 58	99.11 10	94.10 19	98.67 12	97.90 14	98.56 15	95.79 54

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 34	89.80 141	97.73 39	98.13 57	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 45	96.27 12	97.56 8	97.13 36	98.43 14	94.70 18	92.62 83	94.13 40	92.71 166	98.03 64	94.54 16	98.00 24	97.60 20	98.23 31	97.05 24

HFP-MVS		96.18 21	96.53 31	95.77 20	97.34 16	97.26 30	98.16 33	94.54 19	94.45 38	92.52 75	95.05 124	96.95 106	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 56	97.31 17	96.71 43	95.06 122	96.91 4	97.86 5	90.42 129	98.55 10	99.60 1	88.01 122	98.51 13	97.81 15	98.26 29	94.95 72

MP-MVS		96.13 23	95.93 49	96.37 8	98.19 3	97.31 29	98.49 13	94.53 22	91.39 119	94.38 34	94.32 141	96.43 121	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 41	95.93 18	97.20 21	97.60 12	98.64 7	93.74 38	92.47 87	93.13 65	93.23 157	98.06 61	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	89.57 147	97.32 57	97.72 81	93.89 22	97.74 36	97.53 23	97.51 58	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 38	95.87 19	96.72 38	97.35 28	98.43 14	93.83 34	90.81 134	92.67 73	95.05 124	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 77	90.98 102	96.51 12	93.60 53	97.13 68	98.55 38	93.01 37	97.17 54	95.36 84	98.68 9	97.78 4

DPE-MVS		96.00 28	96.80 23	95.06 42	95.87 70	97.47 22	98.25 25	93.73 39	92.38 91	91.57 103	97.55 50	97.97 67	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 32	95.41 29	97.43 11	97.36 26	97.55 51	93.70 40	94.05 51	93.79 46	97.02 71	94.53 167	92.28 53	97.53 45	97.19 37	97.73 51	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 30	95.31 32	96.87 30	96.50 50	98.71 5	91.58 91	93.25 68	92.71 70	96.86 76	96.57 119	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 29	95.23 35	96.67 40	96.52 49	97.86 43	93.28 47	95.27 25	93.46 55	96.26 91	98.85 22	92.89 44	97.09 55	96.37 62	97.21 76	95.78 55
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SteuartSystems-ACMMP		95.96 31	96.13 46	95.76 21	97.06 26	97.36 26	98.40 18	94.24 26	91.49 112	91.91 93	94.50 137	96.89 108	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 39	95.59 23	96.58 43	97.23 32	98.26 24	93.22 48	92.33 95	92.31 83	94.29 142	98.73 29	94.68 12	98.04 21	97.14 40	98.47 21	96.17 47
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PGM-MVS		95.90 34	95.72 53	96.10 15	97.53 10	97.45 23	98.55 12	94.12 28	90.25 140	93.71 51	93.20 158	97.18 100	94.63 13	97.68 39	97.34 36	98.08 38	96.97 26

PMVS	87.16 16	95.88 35	96.47 33	95.19 37	97.00 28	96.02 62	96.70 68	91.57 92	94.43 40	95.33 20	97.16 66	95.37 149	92.39 50	98.89 10	98.72 3	98.17 35	94.71 78
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ACMMP_NAP		95.86 36	96.18 42	95.47 28	97.11 24	97.26 30	98.37 19	93.48 45	93.49 61	93.99 43	95.61 107	94.11 171	92.49 49	97.87 27	97.44 28	97.40 65	97.52 8

Gipuma		95.86 36	96.17 43	95.50 27	95.92 66	94.59 111	94.77 133	92.50 58	97.82 6	97.90 2	95.56 111	97.88 74	94.71 11	98.02 22	94.81 100	97.23 75	94.48 84
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LS3D		95.83 38	96.35 36	95.22 36	96.47 47	97.49 17	97.99 36	92.35 62	94.92 30	94.58 30	94.88 131	95.11 159	91.52 65	98.48 14	98.05 12	98.42 25	95.49 59

MED-MVS		95.79 39	96.97 21	94.41 53	95.58 77	97.44 24	97.73 46	93.05 49	95.33 20	89.42 151	98.30 18	97.12 102	92.87 45	97.26 51	96.99 42	97.83 48	96.33 41

SD-MVS		95.77 40	96.17 43	95.30 33	96.72 38	96.19 58	97.01 60	93.04 50	94.03 52	92.71 70	96.45 89	96.78 115	93.91 21	96.79 70	95.89 73	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 41	96.98 20	94.28 57	96.08 60	97.39 25	98.18 31	93.80 36	94.20 44	89.61 146	97.29 61	97.49 92	90.69 84	97.74 36	97.41 32	97.32 70	97.34 9

TranMVSNet+NR-MVSNet		95.72 42	96.42 34	94.91 46	96.21 55	96.77 42	96.90 65	94.99 13	92.62 83	91.92 92	98.51 13	98.63 34	90.82 81	97.27 50	96.83 46	98.63 12	94.31 85

DU-MVS		95.51 43	95.68 54	95.33 31	96.45 48	96.44 52	96.61 74	95.32 11	89.97 146	93.78 47	97.46 53	98.07 59	91.19 72	97.03 58	96.53 55	98.61 13	94.22 86

aaEdge-Enhanced		95.48 44	96.73 25	94.02 65	95.47 81	97.55 15	98.20 28	91.80 86	93.84 54	89.07 157	98.30 18	97.53 91	92.98 38	96.86 68	96.68 53	96.59 94	96.33 41

UniMVSNet (Re)		95.46 45	95.86 51	95.00 45	96.09 58	96.60 44	96.68 72	94.99 13	90.36 139	92.13 86	97.64 45	98.13 57	91.38 66	96.90 63	96.74 48	98.73 6	94.63 80

RPSCF		95.46 45	96.95 22	93.73 81	95.72 74	95.94 66	95.58 105	88.08 165	95.31 21	91.34 106	96.26 91	98.04 63	93.63 28	98.28 17	97.67 17	98.01 42	97.13 18

anonymousdsp		95.45 47	96.70 28	93.99 69	88.43 247	92.05 177	99.18 1	85.42 208	94.29 43	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 48	95.68 54	95.03 43	97.30 18	96.90 40	97.83 44	93.92 31	89.40 154	90.35 130	95.41 116	97.69 83	92.97 40	97.24 53	97.17 38	97.83 48	95.96 51
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
UniMVSNet_NR-MVSNet		95.34 49	95.51 58	95.14 39	95.80 72	96.55 45	96.61 74	94.79 16	90.04 145	93.78 47	97.51 52	97.25 97	91.19 72	96.68 72	96.31 64	98.65 11	94.22 86

X-MVS		95.33 50	95.13 67	95.57 25	97.35 14	97.48 19	98.43 14	94.28 24	92.30 96	93.28 58	86.89 230	96.82 111	91.87 59	97.85 28	97.59 21	98.19 33	96.95 27

MSP-MVS		95.32 51	96.28 39	94.19 60	96.87 30	97.77 10	98.27 23	93.88 33	94.15 50	89.63 145	95.36 117	98.37 44	90.73 82	94.37 123	97.53 23	95.77 129	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 52	95.16 65	95.29 34	96.17 56	96.55 45	97.64 48	94.02 30	94.16 49	94.29 36	92.09 173	93.71 179	91.90 57	96.68 72	96.51 56	97.70 54	96.40 39

HPM-MVS++		95.21 53	94.89 70	95.59 23	97.79 5	95.39 85	97.68 47	94.05 29	91.91 104	94.35 35	93.38 153	95.07 160	92.94 42	96.01 85	95.88 74	96.73 88	96.61 37

TSAR-MVS + ACMM		95.17 54	95.95 47	94.26 58	96.07 61	96.46 51	95.67 102	94.21 27	93.84 54	90.99 116	97.18 64	95.24 157	93.55 29	96.60 75	95.61 81	95.06 151	96.69 35

CPTT-MVS		95.00 55	94.52 85	95.57 25	96.84 34	96.78 41	97.88 42	93.67 42	92.20 97	92.35 82	85.87 238	97.56 90	94.98 9	96.96 61	96.07 70	97.70 54	96.18 46

SF-MVS		94.88 56	95.87 50	93.73 81	95.30 83	95.93 67	94.80 132	91.76 88	93.11 72	91.93 91	95.83 102	97.07 103	91.11 75	96.62 74	96.44 60	97.46 59	96.13 48

Baseline_NR-MVSNet		94.85 57	95.35 63	94.26 58	96.45 48	93.86 131	96.70 68	94.54 19	90.07 144	90.17 136	98.77 4	97.89 71	90.64 87	97.03 58	96.16 66	97.04 83	93.67 99

EG-PatchMatch MVS		94.81 58	95.53 57	93.97 70	95.89 69	94.62 109	95.55 107	88.18 163	92.77 80	94.88 28	97.04 70	98.61 35	93.31 30	96.89 64	95.19 90	95.99 121	93.56 102

CS-MVS		94.76 59	94.41 90	95.18 38	94.95 94	95.99 63	97.28 53	91.99 77	85.51 200	94.55 31	93.07 160	97.69 83	93.77 26	97.08 56	96.79 47	98.53 16	94.72 76

OMC-MVS		94.74 60	95.46 61	93.91 73	94.62 107	96.26 56	96.64 73	89.36 146	94.20 44	94.15 39	94.02 146	97.73 80	91.34 68	96.15 82	95.04 94	97.37 67	94.80 74

DeepC-MVS_fast	91.38 6	94.73 61	94.98 68	94.44 51	96.83 36	96.12 60	96.69 70	92.17 68	92.98 77	93.72 49	94.14 143	95.45 147	90.49 93	95.73 92	95.30 86	96.71 90	95.13 68
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 62	94.84 72	94.44 51	94.95 94	96.55 45	96.46 80	91.10 100	88.96 158	96.00 16	94.55 136	95.32 152	90.67 85	96.97 60	96.69 52	97.44 62	94.84 73

SPE-MVS-test		94.63 63	94.30 96	95.02 44	94.63 105	95.71 74	98.15 34	92.13 70	85.62 199	94.22 37	93.63 151	97.63 88	93.08 36	97.50 46	96.51 56	97.88 46	93.50 103

pmmvs6		94.58 64	97.30 15	91.40 137	94.84 98	94.61 110	93.40 179	92.43 61	98.51 2	85.61 193	98.73 6	99.53 2	84.40 176	97.88 26	97.03 41	97.72 52	94.79 75

DeepPCF-MVS	90.68 7	94.56 65	94.92 69	94.15 61	94.11 121	95.71 74	97.03 59	90.65 107	93.39 66	94.08 41	95.29 121	94.15 170	93.21 34	95.22 106	94.92 98	95.82 128	95.75 56

NR-MVSNet		94.55 66	95.66 56	93.25 93	94.26 116	96.44 52	96.69 70	95.32 11	89.97 146	91.79 98	97.46 53	98.39 43	82.85 192	96.87 66	96.48 59	98.57 14	93.98 92

MGCNet		94.43 67	94.78 76	94.02 65	96.14 57	97.09 37	97.52 52	92.66 55	90.12 142	93.12 66	95.31 119	93.19 184	87.75 124	96.14 83	95.60 82	96.96 85	96.01 49

Vis-MVSNet		94.39 68	95.85 52	92.68 101	90.91 219	95.88 69	97.62 50	91.41 93	91.95 103	89.20 154	97.29 61	96.26 124	90.60 92	96.95 62	95.91 71	96.32 107	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 69	94.81 74	93.60 83	96.52 46	95.80 72	94.37 145	92.47 60	90.89 130	88.92 160	95.34 118	94.38 168	92.85 46	96.36 80	95.62 80	96.47 100	95.28 65

CNVR-MVS		94.24 70	94.47 86	93.96 71	96.56 44	95.67 76	96.43 81	91.95 79	92.08 100	91.28 108	90.51 189	95.35 150	91.20 71	96.34 81	95.50 83	96.34 105	95.88 53

EC-MVSNet		94.23 71	93.81 119	94.71 50	94.85 97	96.23 57	97.14 55	93.40 46	81.79 225	91.58 102	93.29 156	95.21 158	93.13 35	97.73 38	96.95 43	98.20 32	95.45 60

v1192		93.98 72	93.94 111	94.01 67	93.91 130	94.63 108	97.00 61	89.75 130	91.01 128	96.50 10	97.93 29	98.26 50	91.74 61	92.06 169	92.05 150	95.18 146	91.66 149

Casviewmamba		93.97 73	95.50 59	92.18 111	94.23 117	95.44 81	95.94 90	91.14 98	93.80 57	86.49 187	97.98 26	98.66 30	88.55 115	95.26 104	94.08 116	96.73 88	93.30 107

v10		93.96 74	94.12 104	93.77 80	93.37 152	95.45 80	96.83 67	91.13 99	89.70 151	95.02 25	97.88 35	98.23 53	91.27 69	92.39 164	92.18 145	94.99 156	93.00 113

CDPH-MVS		93.96 74	93.86 113	94.08 63	96.31 52	95.84 70	96.92 63	91.85 82	87.21 178	91.25 110	92.83 162	96.06 132	91.05 77	95.57 95	94.81 100	97.12 78	94.72 76

MSLP-MVS++		93.91 76	94.30 96	93.45 85	95.51 79	95.83 71	93.12 189	91.93 81	91.45 115	91.40 105	87.42 225	96.12 131	93.27 31	96.57 76	96.40 61	95.49 134	96.29 43

v1921920		93.90 77	93.82 117	94.00 68	93.74 137	94.31 117	97.12 56	89.33 147	91.13 125	96.77 9	97.90 32	98.06 61	91.95 56	91.93 176	91.54 162	95.10 149	91.85 141

train_agg		93.89 78	93.46 132	94.40 54	97.35 14	93.78 134	97.63 49	92.19 67	88.12 167	90.52 127	93.57 152	95.78 138	92.31 52	94.78 115	93.46 126	96.36 103	94.70 79

v144192		93.89 78	93.85 114	93.94 72	93.50 146	94.33 115	97.12 56	89.49 138	90.89 130	96.49 11	97.78 37	98.27 49	91.89 58	92.17 168	91.70 159	95.19 145	91.78 144

v1240		93.89 78	93.72 122	94.09 62	93.98 126	94.31 117	97.12 56	89.37 143	90.74 136	96.92 8	98.05 25	97.89 71	92.15 55	91.53 187	91.60 160	94.99 156	91.93 137

NCCC		93.87 81	93.42 133	94.40 54	96.84 34	95.42 82	96.47 79	92.62 56	92.36 93	92.05 88	83.83 246	95.55 143	91.84 60	95.89 87	95.23 88	96.56 97	95.63 57

v1144		93.83 82	93.87 112	93.78 79	93.72 138	94.57 112	96.85 66	89.98 122	91.31 121	95.90 17	97.89 33	98.40 42	91.13 74	92.01 172	92.01 152	95.10 149	90.94 167

MVS_111021_HR		93.82 83	94.26 100	93.31 88	95.01 92	93.97 127	95.73 99	89.75 130	92.06 101	92.49 77	94.01 147	96.05 133	90.61 91	95.95 86	94.78 103	96.28 108	93.04 112

thisisatest0515		93.79 84	94.41 90	93.06 98	94.14 118	92.50 168	95.56 106	88.55 159	91.61 108	92.45 78	96.84 77	95.71 139	90.62 89	94.58 118	95.07 92	97.05 81	94.58 81

TAPA-MVS	88.94 13	93.78 85	94.31 95	93.18 95	94.14 118	95.99 63	95.74 98	86.98 188	93.43 65	93.88 44	90.16 196	96.88 109	91.05 77	94.33 124	93.95 117	97.28 73	95.40 61
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		93.72 86	93.62 127	93.84 74	94.75 102	94.90 102	97.24 54	91.81 85	86.97 185	92.74 69	93.83 149	97.24 99	90.46 94	95.10 110	94.09 115	96.08 118	93.18 110

casdiffseed414692147		93.69 87	94.80 75	92.40 104	93.85 132	94.47 113	95.64 103	90.17 115	92.40 90	89.43 149	97.16 66	99.09 11	89.22 106	94.45 121	93.37 129	96.09 117	92.66 125

EPP-MVSNet		93.63 88	93.95 110	93.26 91	95.15 89	96.54 48	96.18 88	91.97 78	91.74 105	85.76 191	94.95 129	84.27 233	91.60 64	97.61 43	97.38 34	98.87 4	95.18 67

v8		93.60 89	93.82 117	93.34 86	93.13 164	95.06 95	96.39 82	90.75 105	89.90 149	94.03 42	97.70 41	98.21 55	91.08 76	92.36 165	91.47 163	94.63 173	92.07 133

MCST-MVS		93.60 89	93.40 135	93.83 75	95.30 83	95.40 84	96.49 78	90.87 103	90.08 143	91.72 99	90.28 194	95.99 134	91.69 62	93.94 136	92.99 135	96.93 86	95.13 68

PVSNet_Blended_VisFu		93.60 89	93.41 134	93.83 75	96.31 52	95.65 77	95.71 100	90.58 109	88.08 169	93.17 63	95.29 121	92.20 189	90.72 83	94.69 117	93.41 128	96.51 99	94.54 82

TransMVSNet (Re)		93.55 92	96.32 37	90.32 159	94.38 112	94.05 122	93.30 186	89.53 137	97.15 8	85.12 198	98.83 3	97.89 71	82.21 199	96.75 71	96.14 68	97.35 68	93.46 104

E6new		93.49 93	94.68 81	92.10 114	93.52 143	93.87 129	95.80 95	89.59 135	95.07 28	91.10 112	97.93 29	99.22 5	87.59 127	93.32 145	91.86 154	95.00 154	91.49 153

E6		93.49 93	94.68 81	92.10 114	93.52 143	93.87 129	95.80 95	89.59 135	95.07 28	91.10 112	97.93 29	99.22 5	87.59 127	93.32 145	91.86 154	95.00 154	91.49 153

DCV-MVSNet		93.49 93	95.15 66	91.55 129	94.05 122	95.92 68	95.15 119	91.21 95	92.76 81	87.01 183	89.71 200	97.16 101	83.90 185	97.65 40	96.87 45	97.99 43	95.95 52

v2v482		93.42 96	93.49 131	93.32 87	93.44 151	94.05 122	96.36 85	89.76 129	91.41 117	95.24 22	97.63 46	98.34 46	90.44 95	91.65 185	91.76 158	94.69 170	89.62 186

sasdasda		93.38 97	94.36 92	92.24 108	93.94 128	96.41 54	94.18 156	90.47 110	93.07 75	88.47 171	88.66 211	93.78 176	88.80 110	95.74 90	95.75 77	97.57 56	97.13 18

canonicalmvs		93.38 97	94.36 92	92.24 108	93.94 128	96.41 54	94.18 156	90.47 110	93.07 75	88.47 171	88.66 211	93.78 176	88.80 110	95.74 90	95.75 77	97.57 56	97.13 18

3Dnovator	91.81 5	93.36 99	94.27 99	92.29 107	92.99 171	95.03 96	95.76 97	87.79 169	93.82 56	92.38 81	92.19 172	93.37 183	88.14 121	95.26 104	94.85 99	96.69 91	95.40 61

pm-mvs1		93.27 100	95.94 48	90.16 160	94.13 120	93.66 138	92.61 206	89.91 125	95.73 18	84.28 213	98.51 13	98.29 48	82.80 193	96.44 78	95.76 76	97.25 74	93.21 109

casdiffmvs_mvg		93.27 100	94.83 73	91.45 135	93.59 142	94.47 113	94.91 128	89.83 128	92.04 102	87.14 181	97.57 49	98.47 39	86.03 154	94.07 134	94.44 110	97.21 76	92.76 119
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		93.25 102	94.43 88	91.88 118	95.09 91	94.97 100	94.58 140	92.81 52	93.60 59	83.79 218	97.17 65	89.25 218	87.59 127	97.54 44	96.57 54	97.42 64	91.89 138

Anonymous20231211		93.19 103	95.50 59	90.49 156	93.77 135	95.29 87	94.36 149	90.04 121	91.44 116	84.59 208	96.72 80	97.65 86	82.45 198	97.25 52	96.32 63	97.74 50	93.79 95

TinyColmap		93.17 104	93.33 136	93.00 99	93.84 133	92.76 160	94.75 136	88.90 154	93.97 53	97.48 4	95.28 123	95.29 153	88.37 117	95.31 103	91.58 161	94.65 172	89.10 190

E4		93.16 105	94.30 96	91.84 119	93.48 148	93.69 136	95.42 109	89.49 138	94.67 33	90.67 123	97.52 51	99.01 14	86.97 134	92.46 163	91.21 167	94.98 158	91.54 152

viewmacassd2359aftdt		93.16 105	94.69 80	91.39 138	93.30 156	93.71 135	95.03 124	87.70 170	94.69 32	89.53 148	97.63 46	98.92 16	87.73 125	93.63 141	92.14 147	95.05 152	92.08 132

MVS_111021_LR		93.15 107	93.65 124	92.56 102	93.89 131	92.28 171	95.09 120	86.92 190	91.26 124	92.99 68	94.46 139	96.22 127	90.64 87	95.11 109	93.45 127	95.85 126	92.74 120

FE-MVSNET2		93.14 108	94.47 86	91.60 128	91.62 206	93.79 133	95.37 112	89.92 124	94.18 46	90.83 117	96.68 83	98.24 52	85.30 164	93.77 137	94.37 113	96.58 96	90.24 180

CNLPA		93.14 108	93.67 123	92.53 103	94.62 107	94.73 105	95.00 126	86.57 196	92.85 78	92.43 79	90.94 183	94.67 164	90.35 96	95.41 98	93.70 123	96.23 111	93.37 106

PLC	87.27 15	93.08 110	92.92 145	93.26 91	94.67 103	95.03 96	94.38 144	90.10 116	91.69 106	92.14 85	87.24 226	93.91 174	91.61 63	95.05 111	94.73 106	96.67 92	92.80 116
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CANet		93.07 111	93.05 143	93.10 96	95.90 67	95.41 83	95.88 92	91.94 80	84.77 207	93.36 56	94.05 145	95.25 156	86.25 150	94.33 124	93.94 118	95.30 139	93.58 101

TSAR-MVS + COLMAP		93.06 112	93.65 124	92.36 105	94.62 107	94.28 119	95.36 114	89.46 141	92.18 98	91.64 100	95.55 112	95.27 155	88.60 114	93.24 147	92.50 141	94.46 177	92.55 127

viewdifsd2359ckpt09		93.05 113	93.85 114	92.11 113	93.66 141	95.22 90	95.50 108	89.84 127	90.44 138	88.67 169	94.97 128	97.67 85	89.07 108	93.11 153	93.35 130	95.94 123	92.23 130

ECVR-MVS		93.05 113	94.25 101	91.65 125	94.76 100	95.23 88	94.26 153	92.80 53	92.49 85	83.90 216	96.75 79	89.99 208	86.84 139	97.62 41	96.72 49	97.32 70	90.92 168

hybridcas		93.00 115	94.72 78	91.00 146	93.68 140	94.33 115	95.09 120	89.23 148	93.77 58	84.96 202	97.89 33	98.43 41	87.27 131	94.08 133	92.63 139	95.77 129	91.88 139

E5new		92.97 116	94.09 105	91.68 123	93.48 148	93.65 140	95.26 115	89.37 143	94.47 35	90.54 125	97.30 59	98.79 25	86.56 145	92.00 173	90.74 178	94.86 163	91.65 150

E5		92.97 116	94.09 105	91.68 123	93.48 148	93.65 140	95.26 115	89.37 143	94.47 35	90.54 125	97.30 59	98.79 25	86.56 145	92.00 173	90.74 178	94.86 163	91.65 150

Effi-MVS+		92.93 118	92.16 160	93.83 75	94.29 114	93.53 150	95.04 123	92.98 51	85.27 203	94.46 32	90.24 195	95.34 151	89.99 99	93.72 138	94.23 114	96.22 112	92.79 117

Fast-Effi-MVS+		92.93 118	92.64 152	93.27 90	93.81 134	93.88 128	95.90 91	90.61 108	83.98 213	92.71 70	92.81 164	96.22 127	90.67 85	94.90 114	93.92 119	95.92 124	92.77 118

HQP-MVS		92.87 120	92.49 153	93.31 88	95.75 73	95.01 99	95.64 103	91.06 101	88.54 162	91.62 101	88.16 217	96.25 125	89.47 103	92.26 167	91.81 156	96.34 105	95.40 61

FMVSNet1		92.86 121	95.26 64	90.06 162	92.40 188	95.16 91	94.37 145	92.22 64	93.18 71	82.16 228	96.76 78	97.48 94	81.85 203	95.32 100	94.98 95	97.34 69	93.93 93

CLD-MVS		92.81 122	94.32 94	91.05 145	95.39 82	95.31 86	95.82 94	81.44 245	89.40 154	91.94 90	95.86 100	97.36 95	85.83 157	95.35 99	94.59 108	95.85 126	92.34 128
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
IS_MVSNet		92.76 123	93.25 138	92.19 110	94.91 96	95.56 78	95.86 93	92.12 71	88.10 168	82.71 223	93.15 159	88.30 221	88.86 109	97.29 48	96.95 43	98.66 10	93.38 105

E3new		92.75 124	93.78 120	91.55 129	93.35 153	93.54 148	95.17 117	89.17 149	93.49 61	90.29 135	97.00 73	98.65 31	86.58 143	91.86 179	90.64 180	94.75 166	91.27 157

E3		92.75 124	93.78 120	91.55 129	93.35 153	93.54 148	95.16 118	89.17 149	93.48 64	90.32 132	97.01 72	98.65 31	86.58 143	91.86 179	90.64 180	94.75 166	91.27 157

FC-MVSNet-train		92.75 124	95.40 62	89.66 171	95.21 87	94.82 103	97.00 61	89.40 142	91.13 125	81.71 230	97.72 40	96.43 121	77.57 235	96.89 64	96.72 49	97.05 81	94.09 89

V42		92.67 127	93.50 130	91.71 122	91.41 208	92.96 158	95.71 100	85.00 211	89.67 152	93.22 61	97.67 44	98.01 65	91.02 79	92.65 158	92.12 148	93.86 191	91.42 155

PM-MVS		92.65 128	93.20 141	92.00 116	92.11 196	90.16 216	95.99 89	84.81 216	91.31 121	92.41 80	95.87 99	96.64 117	92.35 51	93.65 140	92.91 136	94.34 182	91.85 141

MVSMamba_PlusPlus		92.57 129	93.24 139	91.79 121	95.49 80	95.10 94	93.82 164	89.60 134	86.44 190	89.06 158	90.82 185	94.93 163	87.09 132	95.00 112	95.23 88	95.68 131	95.13 68

QAPM		92.57 129	93.51 129	91.47 134	92.91 173	94.82 103	93.01 191	87.51 175	91.49 112	91.21 111	92.24 170	91.70 194	88.74 112	94.54 120	94.39 112	95.41 136	95.37 64

MIMVSNet1		92.52 131	94.88 71	89.77 167	96.09 58	91.99 178	96.92 63	89.68 132	95.92 17	84.55 209	96.64 84	98.21 55	78.44 227	96.08 84	95.10 91	92.91 217	90.22 181

viewmanbaseed2359cas		92.46 132	93.85 114	90.83 149	93.07 166	93.47 152	94.55 142	87.10 186	92.76 81	88.70 168	96.72 80	98.35 45	86.85 138	92.70 156	91.22 166	94.71 169	91.76 146

tfpnnormal		92.45 133	94.77 77	89.74 168	93.95 127	93.44 154	93.25 187	88.49 161	95.27 25	83.20 221	96.51 87	96.23 126	83.17 190	95.47 97	94.52 109	96.38 102	91.97 136

PCF-MVS	87.46 14	92.44 134	91.80 163	93.19 94	94.66 104	95.80 72	96.37 83	90.19 114	87.57 174	92.23 84	89.26 205	93.97 173	89.24 104	91.32 191	90.82 177	96.46 101	93.86 94
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		92.42 135	93.99 109	90.60 154	93.25 158	93.82 132	94.28 151	88.73 157	91.53 110	84.53 211	97.74 38	98.64 33	86.60 142	93.21 149	91.20 168	96.21 113	91.76 146
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		92.41 136	93.33 136	91.34 140	93.24 159	93.43 155	94.96 127	88.94 153	92.44 89	90.07 138	96.53 86	98.31 47	86.27 149	91.34 190	90.17 188	94.57 175	91.11 163

AdaColmap		92.41 136	91.49 169	93.48 84	95.96 64	95.02 98	95.37 112	91.73 89	87.97 171	91.28 108	82.82 250	91.04 201	90.62 89	95.82 89	95.07 92	95.95 122	92.67 121

v148		92.38 138	92.78 150	91.91 117	92.86 174	92.13 174	94.84 130	87.03 187	91.47 114	93.07 67	96.92 75	98.89 18	90.10 98	92.05 170	89.69 193	93.56 197	88.27 201

pmmvs-eth3d		92.34 139	92.33 155	92.34 106	92.67 179	90.67 204	96.37 83	89.06 151	90.98 129	93.60 53	97.13 68	97.02 105	88.29 118	90.20 202	91.42 164	94.07 185	88.89 195

DELS-MVS		92.33 140	93.61 128	90.83 149	92.84 176	95.13 93	94.76 134	87.22 183	87.78 173	88.42 174	95.78 103	95.28 154	85.71 160	94.44 122	93.91 120	96.01 120	92.97 114
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
Effi-MVS+-dtu		92.32 141	91.66 167	93.09 97	95.13 90	94.73 105	94.57 141	92.14 69	81.74 226	90.33 131	88.13 218	95.91 135	89.24 104	94.23 129	93.65 125	97.12 78	93.23 108

MGCFI-Net		92.31 142	94.25 101	90.04 165	93.75 136	95.96 65	93.32 184	90.28 113	93.28 67	80.57 241	88.79 209	93.78 176	84.89 171	95.55 96	95.31 85	97.45 61	97.10 21

UGNet		92.31 142	94.70 79	89.53 173	90.99 216	95.53 79	96.19 87	92.10 73	91.35 120	85.76 191	95.31 119	95.48 146	76.84 240	95.22 106	94.79 102	95.32 138	95.19 66
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		92.24 144	93.22 140	91.10 144	93.01 170	93.63 142	94.65 139	87.69 171	90.81 134	88.80 166	95.59 110	97.98 66	87.51 130	91.98 175	90.83 176	94.94 159	91.74 148

USDC		92.17 145	92.17 159	92.18 111	92.93 172	92.22 172	93.66 170	87.41 178	93.49 61	97.99 1	94.10 144	96.68 116	86.46 147	92.04 171	89.18 200	94.61 174	87.47 208

ETV-MVS		92.12 146	90.44 180	94.08 63	96.36 50	93.63 142	96.27 86	92.00 76	78.90 245	92.13 86	85.29 240	89.85 212	90.26 97	97.07 57	96.29 65	97.46 59	92.04 134

IterMVS-LS		92.10 147	92.33 155	91.82 120	93.18 160	93.66 138	92.80 202	92.27 63	90.82 132	90.59 124	97.19 63	90.97 202	87.76 123	89.60 209	90.94 173	94.34 182	93.16 111
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
E2		92.09 148	92.90 146	91.16 143	93.16 163	93.35 156	94.76 134	88.75 156	91.40 118	89.85 139	95.98 97	97.95 69	85.98 156	90.86 196	89.74 191	94.43 178	90.99 166

MSDG		92.09 148	92.84 149	91.22 142	92.55 181	92.97 157	93.42 178	85.43 207	90.24 141	91.83 95	94.70 133	94.59 165	88.48 116	94.91 113	93.31 132	95.59 133	89.15 189

EIA-MVS		91.95 150	90.36 182	93.81 78	96.54 45	94.65 107	95.38 111	90.40 112	78.01 250	93.72 49	86.70 233	91.95 191	89.93 100	95.67 94	94.72 107	96.89 87	90.79 171

MAR-MVS		91.86 151	91.14 174	92.71 100	94.29 114	94.24 120	94.91 128	91.82 84	81.66 227	93.32 57	84.51 243	93.42 182	86.86 137	95.16 108	94.44 110	95.05 152	94.53 83
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		91.80 152	94.01 107	89.22 181	92.52 182	91.95 180	93.78 165	84.14 223	93.11 72	83.97 214	97.68 42	99.12 8	86.05 152	94.17 130	90.89 174	94.88 161	91.18 161

viewmsd2359difaftdt		91.80 152	94.01 107	89.22 181	92.52 182	91.95 180	93.78 165	84.14 223	93.11 72	83.97 214	97.68 42	99.12 8	86.05 152	94.16 131	90.89 174	94.88 161	91.18 161

EU-MVSNet		91.63 154	92.73 151	90.35 158	88.36 248	87.89 228	96.53 76	81.51 244	92.45 88	91.82 96	96.44 90	97.05 104	93.26 32	94.10 132	88.94 205	90.61 226	92.24 129

viewdifsd2359ckpt07		91.59 155	93.64 126	89.19 183	92.86 174	92.58 166	94.25 155	84.97 212	94.17 48	85.52 194	97.60 48	98.59 36	85.99 155	91.85 181	88.85 207	91.52 223	91.87 140

FC-MVSNet-test		91.49 156	94.43 88	88.07 205	94.97 93	90.53 209	95.42 109	91.18 97	93.24 69	72.94 261	98.37 15	93.86 175	78.78 220	97.82 32	96.13 69	95.13 147	91.05 164

FA-MVS(training)		91.38 157	91.18 173	91.62 127	93.49 147	92.38 169	95.03 124	90.81 104	87.20 179	91.46 104	93.00 161	89.47 215	84.19 179	93.20 151	92.08 149	94.74 168	90.90 169

viewmamba		91.25 158	92.87 148	89.36 178	91.65 204	91.96 179	93.62 172	86.76 192	90.57 137	86.42 188	97.00 73	98.07 59	83.99 182	92.49 162	89.54 196	93.75 194	90.44 176

FE-MVSNET		91.21 159	92.90 146	89.24 180	90.93 218	91.69 184	93.46 176	87.85 168	92.35 94	85.06 201	94.84 132	96.63 118	82.80 193	92.98 154	93.22 133	95.36 137	88.58 197

usedtu_dtu_shiyan2		91.17 160	93.05 143	88.98 186	95.95 65	92.70 164	93.66 170	91.85 82	96.05 16	82.16 228	93.34 155	98.87 20	76.62 242	93.56 142	92.03 151	93.66 196	84.77 224

OpenMVS	89.22 12	91.09 161	91.42 170	90.71 152	92.79 178	93.61 145	92.74 204	85.47 206	86.10 196	90.73 118	85.71 239	93.07 187	86.69 141	94.07 134	93.34 131	95.86 125	94.02 91

onestephybrid01		91.06 162	92.45 154	89.44 175	91.76 200	92.07 176	93.67 168	87.22 183	87.19 180	85.83 190	96.07 96	97.93 70	84.20 178	92.82 155	90.21 187	93.99 186	90.87 170

diffmvs_AUTHOR		91.06 162	93.06 142	88.71 195	91.67 203	91.66 185	92.77 203	85.36 209	91.29 123	85.38 196	97.45 55	98.26 50	83.74 186	91.81 182	89.70 192	93.37 208	91.27 157

FPMVS		90.81 164	91.60 168	89.88 166	92.52 182	88.18 224	93.31 185	83.62 227	91.59 109	88.45 173	88.96 208	89.73 214	86.96 135	96.42 79	95.69 79	94.43 178	90.65 172

DI_MVS_pp		90.68 165	90.40 181	91.00 146	92.43 187	92.61 165	94.17 158	88.98 152	88.32 166	88.76 167	93.67 150	87.58 223	86.44 148	89.74 207	90.33 184	95.24 142	90.56 175

Vis-MVSNet (Re-imp)		90.68 165	92.18 158	88.92 189	94.63 105	92.75 161	92.91 195	91.20 96	89.21 157	75.01 257	93.96 148	89.07 219	82.72 196	95.88 88	95.30 86	97.08 80	89.08 191

DPM-MVS		90.67 167	89.86 186	91.63 126	95.29 85	94.16 121	94.52 143	89.63 133	89.59 153	89.67 144	81.95 252	88.64 220	85.75 159	90.46 199	90.43 183	94.91 160	93.77 96

dtuplus		90.47 168	91.79 164	88.92 189	91.92 198	90.59 208	92.93 194	85.60 204	89.34 156	85.12 198	95.71 105	97.78 78	84.05 180	90.93 195	87.82 212	93.88 189	90.39 177

diffmvs		90.44 169	92.23 157	88.35 201	91.36 210	91.38 191	92.45 210	84.84 215	89.88 150	85.09 200	96.69 82	97.71 82	83.33 189	90.01 206	88.96 204	93.03 214	91.00 165
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		90.28 170	92.04 162	88.23 203	91.22 212	94.05 122	92.88 196	90.69 106	86.53 188	79.89 245	94.38 140	92.73 188	78.54 223	91.64 186	92.26 144	96.17 114	92.67 121

IterMVS-SCA-FT		90.24 171	89.37 192	91.26 141	92.50 185	92.11 175	91.69 223	87.48 176	87.05 184	91.82 96	95.76 104	87.25 224	91.36 67	89.02 215	85.53 226	92.68 218	88.90 194

MVS_Test		90.19 172	90.58 176	89.74 168	92.12 195	91.74 183	92.51 207	88.54 160	82.80 219	87.50 179	94.62 134	95.02 161	83.97 183	88.69 218	89.32 198	93.79 192	91.85 141

EPNet		90.17 173	89.07 194	91.45 135	97.25 19	90.62 207	94.84 130	93.54 44	80.96 229	91.85 94	86.98 229	85.88 229	77.79 232	92.30 166	92.58 140	93.41 203	94.20 88
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
viewmambaseed2359dif		90.16 174	91.38 171	88.72 193	91.64 205	90.75 200	92.73 205	85.32 210	87.92 172	84.90 203	95.63 106	97.49 92	84.05 180	90.27 201	87.28 214	93.71 195	90.35 179

hybridnocas07		90.14 175	92.12 161	87.83 208	90.95 217	90.85 198	92.22 213	84.61 219	88.53 163	84.79 206	96.64 84	97.86 76	81.44 208	91.88 178	88.90 206	92.97 215	90.17 183

PVSNet_BlendedMVS		90.09 176	90.12 184	90.05 163	92.40 188	92.74 162	91.74 219	85.89 201	80.54 232	90.30 133	88.54 213	95.51 144	84.69 174	92.64 159	90.25 185	95.28 140	90.61 173

PVSNet_Blended		90.09 176	90.12 184	90.05 163	92.40 188	92.74 162	91.74 219	85.89 201	80.54 232	90.30 133	88.54 213	95.51 144	84.69 174	92.64 159	90.25 185	95.28 140	90.61 173

usedtu_dtu_shiyan1		90.01 178	90.53 179	89.39 177	90.47 225	91.62 188	93.36 180	87.13 185	87.52 175	87.00 184	92.63 167	94.03 172	82.94 191	89.33 213	91.00 172	95.46 135	87.61 204

pmmvs4		89.95 179	89.32 193	90.69 153	91.60 207	89.17 221	94.37 145	87.63 172	88.07 170	91.02 115	94.50 137	90.50 206	86.13 151	86.33 232	89.40 197	93.39 205	87.29 212

hybrid		89.90 180	91.77 165	87.72 210	90.87 220	90.63 206	92.16 215	84.26 221	88.34 165	84.87 204	95.91 98	97.63 88	81.53 207	91.51 188	88.47 209	92.61 219	89.87 184

MDA-MVSNet-bldmvs		89.75 181	91.67 166	87.50 212	74.25 272	90.88 197	94.68 137	85.89 201	91.64 107	91.03 114	95.86 100	94.35 169	89.10 107	96.87 66	86.37 221	90.04 228	85.72 221

WB-MVS		89.70 182	94.13 103	84.54 234	88.16 250	92.57 167	88.90 244	88.32 162	96.67 11	73.61 260	98.29 20	98.80 23	80.60 211	95.73 92	92.18 145	87.66 243	84.64 225

tttt0517		89.64 183	88.05 206	91.49 133	93.52 143	91.65 186	93.67 168	87.53 173	82.77 220	89.39 152	90.37 193	70.05 258	88.21 119	93.71 139	93.79 121	96.63 93	94.04 90

PatchMatch-RL		89.59 184	88.80 198	90.51 155	92.20 194	88.00 227	91.72 221	86.64 193	84.75 208	88.25 175	87.10 228	90.66 205	89.85 102	93.23 148	92.28 143	94.41 180	85.60 222

Fast-Effi-MVS+-dtu		89.57 185	88.42 202	90.92 148	93.35 153	91.57 189	93.01 191	95.71 9	78.94 244	87.65 178	84.68 242	93.14 186	82.00 201	90.84 197	91.01 171	93.78 193	88.77 196

thisisatest0530		89.54 186	87.99 210	91.35 139	93.17 161	91.31 192	93.45 177	87.53 173	82.96 218	89.17 156	90.45 190	70.32 257	88.21 119	93.37 144	93.79 121	96.54 98	93.71 98

test2506		89.51 187	87.77 213	91.55 129	94.76 100	95.23 88	94.26 153	92.80 53	92.49 85	83.31 220	89.97 198	50.93 278	86.84 139	97.62 41	96.72 49	97.32 70	91.42 155

GBi-Net		89.35 188	90.58 176	87.91 206	91.22 212	94.05 122	92.88 196	90.05 118	79.40 236	78.60 248	90.58 186	87.05 225	78.54 223	95.32 100	94.98 95	96.17 114	92.67 121

test1		89.35 188	90.58 176	87.91 206	91.22 212	94.05 122	92.88 196	90.05 118	79.40 236	78.60 248	90.58 186	87.05 225	78.54 223	95.32 100	94.98 95	96.17 114	92.67 121

thres600view7		89.14 190	88.83 196	89.51 174	93.71 139	93.55 146	93.93 163	88.02 166	87.30 177	82.40 224	81.18 253	80.63 244	82.69 197	94.27 126	95.90 72	96.27 109	88.94 193

CVMVSNet		88.97 191	89.73 188	88.10 204	87.33 255	85.22 240	94.68 137	78.68 247	88.94 159	86.98 185	95.55 112	85.71 230	89.87 101	91.19 192	89.69 193	91.05 224	91.78 144

CANet_DTU		88.95 192	89.51 191	88.29 202	93.12 165	91.22 195	93.61 173	83.47 230	80.07 235	90.71 122	89.19 206	93.68 180	76.27 245	91.44 189	91.17 170	92.59 220	89.83 185

gbinet_0.2-2-1-0.02		88.79 193	88.26 203	89.40 176	89.67 234	91.24 193	94.03 160	84.65 218	85.76 198	89.02 159	92.83 162	90.75 204	85.62 161	85.86 234	82.42 233	93.41 203	88.98 192

GA-MVS		88.76 194	88.04 208	89.59 172	92.32 191	91.46 190	92.28 212	86.62 194	83.82 215	89.84 140	92.51 169	81.94 238	83.53 188	89.41 211	89.27 199	92.95 216	87.90 202

pmmvs5		88.63 195	89.70 189	87.39 213	89.24 237	90.64 205	91.87 218	82.13 240	83.34 216	87.86 177	94.58 135	96.15 130	79.87 216	87.33 227	89.07 203	93.39 205	86.76 215

thres400		88.54 196	88.15 205	88.98 186	93.17 161	92.84 159	93.56 174	86.93 189	86.45 189	82.37 225	79.96 255	81.46 241	81.83 204	93.21 149	94.76 104	96.04 119	88.39 199

blended_shiyan8		88.52 197	88.03 209	89.08 184	89.78 232	90.69 201	93.34 182	82.82 233	87.12 182	89.21 153	91.51 176	91.71 193	85.38 162	85.01 238	82.73 232	93.96 187	87.47 208

blended_shiyan6		88.52 197	88.05 206	89.07 185	89.79 230	90.69 201	93.34 182	82.81 234	87.12 182	89.19 155	91.48 177	91.81 192	85.32 163	84.98 239	82.74 231	93.95 188	87.52 206

CDS-MVSNet		88.41 199	89.79 187	86.79 219	94.55 110	90.82 199	92.50 208	89.85 126	83.26 217	80.52 242	91.05 179	89.93 211	69.11 257	93.17 152	92.71 138	94.21 184	87.63 203
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gg-mvs-nofinetune		88.32 200	88.81 197	87.75 209	93.07 166	89.37 220	89.06 243	95.94 8	95.29 23	87.15 180	97.38 56	76.38 247	68.05 260	91.04 193	89.10 202	93.24 210	83.10 232

IterMVS		88.32 200	88.25 204	88.41 200	90.83 221	91.24 193	93.07 190	81.69 242	86.77 186	88.55 170	95.61 107	86.91 228	87.01 133	87.38 226	83.77 228	89.29 232	86.06 220
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres200		88.29 202	87.88 211	88.76 192	92.50 185	93.55 146	92.47 209	88.02 166	84.80 206	81.44 232	79.28 257	82.20 237	81.83 204	94.27 126	93.67 124	96.27 109	87.40 210

IB-MVS	86.01 17	88.24 203	87.63 214	88.94 188	92.03 197	91.77 182	92.40 211	85.58 205	78.24 247	84.85 205	71.99 264	93.45 181	83.96 184	93.48 143	92.33 142	94.84 165	92.15 131
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		88.22 204	87.85 212	88.65 196	91.40 209	86.75 232	94.07 159	84.97 212	88.86 161	93.20 62	96.11 95	96.21 129	83.70 187	87.29 228	80.29 243	84.56 252	79.46 248

test20.03		88.20 205	91.26 172	84.63 232	96.64 42	89.39 219	90.73 230	89.97 123	91.07 127	72.02 263	94.98 127	95.45 147	69.35 256	92.70 156	91.19 169	89.06 234	84.02 226

HyFIR lowres test		88.19 206	86.56 223	90.09 161	91.24 211	92.17 173	94.30 150	88.79 155	84.06 210	85.45 195	89.52 203	85.64 231	88.64 113	85.40 236	87.28 214	92.14 222	81.87 236

ET-MVSNet_ETH3D		88.06 207	85.75 228	90.74 151	92.82 177	90.68 203	93.77 167	88.59 158	81.22 228	89.78 142	89.15 207	66.79 271	84.29 177	91.72 184	91.34 165	95.22 143	89.36 188

wanda-best-256-512		87.94 208	87.36 218	88.61 197	89.23 238	90.35 211	92.84 199	82.30 235	86.26 192	88.91 161	90.96 181	91.43 196	84.94 168	84.27 240	81.61 236	93.45 198	86.67 217

FE-blended-shiyan7		87.94 208	87.36 218	88.61 197	89.23 238	90.35 211	92.84 199	82.30 235	86.26 192	88.91 161	90.96 181	91.43 196	84.94 168	84.27 240	81.61 236	93.45 198	86.67 217

tfpn200view9		87.94 208	87.51 216	88.44 199	92.28 192	93.63 142	93.35 181	88.11 164	80.90 230	80.89 238	78.25 258	82.25 235	79.65 218	94.27 126	94.76 104	96.36 103	88.48 198

FMVSNet3		87.90 211	88.63 200	87.04 215	89.78 232	93.46 153	91.62 224	90.05 118	79.40 236	78.60 248	90.58 186	87.05 225	77.07 239	88.03 223	89.85 190	95.12 148	92.04 134

MS-PatchMatch		87.72 212	88.62 201	86.66 220	90.81 222	88.18 224	90.92 227	82.25 239	85.86 197	80.40 243	90.14 197	89.29 217	84.93 170	89.39 212	89.12 201	90.67 225	88.34 200

Anonymous20231206		87.45 213	89.66 190	84.87 229	94.00 123	87.73 230	91.36 225	86.41 198	88.89 160	75.03 256	92.59 168	96.82 111	72.48 254	89.72 208	88.06 210	89.93 229	83.81 228

EPNet_dtu		87.40 214	86.27 224	88.72 193	95.68 75	83.37 247	92.09 216	90.08 117	78.11 249	91.29 107	86.33 234	89.74 213	75.39 249	89.07 214	87.89 211	87.81 239	89.38 187
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
baseline1		86.96 215	87.58 215	86.24 223	93.07 166	90.44 210	89.24 242	86.85 191	85.14 205	77.26 254	90.45 190	76.09 249	75.79 246	91.80 183	91.81 156	95.20 144	87.35 211

dtuonlycased		86.78 216	90.70 175	82.21 241	89.31 235	91.65 186	94.27 152	75.13 254	89.94 148	59.16 270	93.38 153	95.67 140	87.63 126	90.99 194	85.76 223	87.74 242	87.53 205

baseline		86.71 217	88.89 195	84.16 235	87.85 251	85.23 239	89.82 236	77.69 250	84.03 212	84.75 207	94.91 130	94.59 165	77.19 238	86.57 231	86.51 220	87.66 243	90.36 178

CHOSEN 1792x2688		86.64 218	86.62 221	86.65 221	90.33 227	87.86 229	93.19 188	83.30 231	83.95 214	82.32 226	87.93 220	89.34 216	86.92 136	85.64 235	84.95 227	83.85 256	86.68 216

dmvs_re		86.51 219	86.14 226	86.95 217	93.07 166	86.11 235	92.01 217	86.04 200	72.70 260	79.10 246	75.37 261	89.99 208	78.10 231	94.56 119	93.01 134	93.35 209	91.26 160

testgi		86.49 220	90.31 183	82.03 242	95.63 76	88.18 224	93.47 175	84.89 214	93.23 70	69.54 267	87.16 227	97.96 68	60.66 264	91.90 177	89.90 189	87.99 237	83.84 227

thres100view900		86.46 221	86.00 227	86.99 216	92.28 192	91.03 196	91.09 226	84.49 220	80.90 230	80.89 238	78.25 258	82.25 235	77.57 235	90.17 203	92.84 137	95.63 132	86.57 219

gm-plane-assit		86.15 222	82.51 237	90.40 157	95.81 71	92.29 170	97.99 36	84.66 217	92.15 99	93.15 64	97.84 36	44.65 280	78.60 222	88.02 224	85.95 222	92.20 221	76.69 257

CMPMVS	66.55 18	85.55 223	87.46 217	83.32 237	84.99 258	81.97 252	79.19 270	75.93 252	79.32 239	88.82 164	85.09 241	91.07 200	82.12 200	92.56 161	89.63 195	88.84 235	92.56 126
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CR-MVSNet		85.32 224	81.58 239	89.69 170	90.36 226	84.79 243	86.72 259	92.22 64	75.38 255	90.73 118	90.41 192	67.88 262	84.86 172	83.76 247	85.74 224	93.24 210	83.14 230

baseline2		84.95 225	82.68 236	87.59 211	92.64 180	88.41 223	90.09 232	84.25 222	75.88 253	85.23 197	82.49 251	71.15 255	80.14 214	88.21 222	87.21 218	93.21 213	85.39 223

pmnet_mix02		84.85 226	86.58 222	82.83 238	90.19 228	81.10 255	88.52 247	78.58 248	91.50 111	80.32 244	96.48 88	95.86 136	75.42 248	85.17 237	76.44 254	83.91 255	79.51 247

MVSTER		84.79 227	83.79 231	85.96 225	89.14 242	89.80 217	89.39 240	82.99 232	74.16 259	82.78 222	85.97 237	66.81 270	76.84 240	90.77 198	88.83 208	94.66 171	90.19 182

MIMVSNet		84.76 228	86.75 220	82.44 240	91.71 202	85.95 236	89.74 238	89.49 138	85.28 202	69.69 266	87.93 220	90.88 203	64.85 262	88.26 221	87.74 213	89.18 233	81.24 237

SCA		84.69 229	81.10 240	88.87 191	89.02 243	90.31 215	92.21 214	92.09 74	82.72 221	89.68 143	86.83 231	73.08 251	85.80 158	80.50 256	77.51 250	84.45 254	76.80 256

new-patchmatchnet		84.45 230	88.75 199	79.43 251	93.28 157	81.87 253	81.68 267	83.48 229	94.47 35	71.53 264	98.33 16	97.88 74	58.61 268	90.35 200	77.33 251	87.99 237	81.05 239

FE-MVSNET3		83.78 231	80.73 243	87.34 214	89.23 238	90.35 211	92.84 199	82.30 235	86.26 192	81.00 234	68.18 267	66.96 265	85.24 165	84.27 240	81.61 236	93.45 198	87.52 206

PatchT		83.44 232	81.10 240	86.18 224	77.92 270	82.58 251	89.87 235	87.39 179	75.88 253	90.73 118	89.86 199	66.71 272	84.86 172	83.76 247	85.74 224	86.33 249	83.14 230

RPMNet		83.42 233	78.40 251	89.28 179	89.79 230	84.79 243	90.64 231	92.11 72	75.38 255	87.10 182	79.80 256	61.99 277	82.79 195	81.88 254	82.07 235	93.23 212	82.87 233

usedtu_blend_shiyan5		83.28 234	80.64 244	86.37 222	89.23 238	90.35 211	87.00 257	82.30 235	86.26 192	81.00 234	68.18 267	66.96 265	85.24 165	84.27 240	81.61 236	93.45 198	86.85 213

TAMVS		82.96 235	86.15 225	79.24 254	90.57 224	83.12 250	87.29 253	75.12 255	84.06 210	65.81 268	92.22 171	88.27 222	69.11 257	88.72 216	87.26 217	87.56 245	79.38 249

PatchmatchNet		82.44 236	78.69 250	86.83 218	89.81 229	81.55 254	90.78 229	87.27 182	82.39 224	88.85 163	88.31 216	70.96 256	81.90 202	78.58 260	74.33 263	82.35 260	74.69 260
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13		82.33 237	79.66 245	85.45 227	88.83 245	83.88 245	90.09 232	81.98 241	79.07 243	88.82 164	88.70 210	73.77 250	78.41 228	80.29 258	76.08 255	84.56 252	75.83 258

CostFormer		82.15 238	79.54 246	85.20 228	88.92 244	85.70 237	90.87 228	86.26 199	79.19 242	83.87 217	87.89 222	69.20 260	76.62 242	77.50 263	75.28 258	84.69 251	82.02 235

dtuonly		82.04 239	83.24 235	80.64 247	86.49 257	76.95 260	90.09 232	69.99 262	82.43 223	81.66 231	91.23 178	91.26 198	75.79 246	83.81 246	79.65 244	79.82 263	77.38 254

PMMVS		81.93 240	83.48 233	80.12 250	72.35 273	75.05 265	88.54 246	64.01 264	77.02 252	82.22 227	87.51 224	91.12 199	79.70 217	86.59 229	86.64 219	93.88 189	80.41 242

pmmvs3		81.69 241	83.83 230	79.19 255	78.33 269	78.57 258	89.53 239	58.71 267	78.88 246	84.34 212	88.36 215	91.96 190	77.69 234	87.48 225	82.42 233	86.54 248	79.18 250

tpm		81.58 242	78.84 248	84.79 231	91.11 215	79.50 256	89.79 237	83.75 225	79.30 240	92.05 88	90.98 180	64.78 274	74.54 250	80.50 256	76.67 252	77.49 266	80.15 245

test0.0.03 1		81.51 243	83.30 234	79.42 252	93.99 124	86.50 233	85.93 263	87.32 180	78.16 248	61.62 269	80.78 254	81.78 239	59.87 265	88.40 220	87.27 216	87.78 241	80.19 244

dps		81.42 244	77.88 256	85.56 226	87.67 253	85.17 241	88.37 249	87.46 177	74.37 258	84.55 209	86.80 232	62.18 276	80.20 213	81.13 255	77.52 249	85.10 250	77.98 253

test-LLR		80.62 245	77.20 259	84.62 233	93.99 124	75.11 263	87.04 255	87.32 180	70.11 263	78.59 251	83.17 248	71.60 253	73.88 252	82.32 251	79.20 246	86.91 246	78.87 251

blend_shiyan4		80.12 246	77.11 261	83.63 236	78.60 268	89.75 218	83.59 266	79.95 246	64.53 269	81.00 234	68.18 267	66.96 265	85.24 165	82.23 253	81.29 241	93.38 207	86.85 213

tpm cat1		80.03 247	75.93 263	84.81 230	89.31 235	83.26 249	88.86 245	86.55 197	79.24 241	86.10 189	84.22 244	63.62 275	77.37 237	73.43 267	70.88 266	80.67 261	76.87 255

N_pmnet		79.33 248	84.22 229	73.62 261	91.72 201	73.72 266	86.11 261	76.36 251	92.38 91	53.38 272	95.54 114	95.62 142	59.14 266	84.23 244	74.84 262	75.02 270	73.25 264

EPMVS		79.26 249	78.20 254	80.49 248	87.04 256	78.86 257	86.08 262	83.51 228	82.63 222	73.94 259	89.59 201	68.67 261	72.03 255	78.17 261	75.08 260	80.37 262	74.37 261

CHOSEN 280x420		79.24 250	78.26 253	80.38 249	79.60 267	68.80 272	89.32 241	75.38 253	77.25 251	78.02 253	75.57 260	76.17 248	81.19 209	88.61 219	81.39 240	78.79 264	80.03 246

ADS-MVSNet		79.11 251	79.38 247	78.80 257	81.90 263	75.59 262	84.36 265	83.69 226	87.31 176	76.76 255	87.58 223	76.90 246	68.55 259	78.70 259	75.56 257	77.53 265	74.07 262

FMVSNet5		79.08 252	78.83 249	79.38 253	87.52 254	86.78 231	87.64 251	78.15 249	69.54 265	70.64 265	65.97 271	65.44 273	63.87 263	90.17 203	90.46 182	88.48 236	83.45 229

0.4-1-1-0.1		78.93 253	75.69 264	82.71 239	82.54 261	86.31 234	88.34 250	74.63 256	67.88 266	81.41 233	73.65 262	67.37 263	79.03 219	75.97 264	76.53 253	90.33 227	82.09 234

tpmrst		78.81 254	76.18 262	81.87 244	88.56 246	77.45 259	86.74 258	81.52 243	80.08 234	83.48 219	90.84 184	66.88 269	74.54 250	73.04 268	71.02 265	76.38 267	73.95 263

test-mter		78.71 255	78.35 252	79.12 256	84.03 259	76.58 261	88.51 248	59.06 266	71.06 261	78.87 247	83.73 247	71.83 252	76.44 244	83.41 250	80.61 242	87.79 240	81.24 237

MVS-HIRNet		78.28 256	75.28 265	81.79 245	80.33 266	69.38 271	76.83 271	86.59 195	70.76 262	86.66 186	89.57 202	81.04 242	77.74 233	77.81 262	71.65 264	82.62 258	66.73 269

0.3-1-1-0.015		77.85 257	74.34 267	81.96 243	81.59 264	85.29 238	87.54 252	73.36 257	66.50 267	81.00 234	70.68 265	66.96 265	78.53 226	74.61 266	75.58 256	89.73 230	80.73 240

E-PMN		77.81 258	77.88 256	77.73 260	88.26 249	70.48 270	80.19 269	71.20 260	86.66 187	72.89 262	88.09 219	81.74 240	78.75 221	90.02 205	68.30 267	75.10 268	59.85 270

0.4-1-1-0.2		77.70 259	74.35 266	81.60 246	81.26 265	84.89 242	87.05 254	72.99 258	65.96 268	80.75 240	72.00 263	67.32 264	78.19 230	74.64 265	75.15 259	89.36 231	80.50 241

EMVS		77.65 260	77.49 258	77.83 258	87.75 252	71.02 269	81.13 268	70.54 261	86.38 191	74.52 258	89.38 204	80.19 245	78.22 229	89.48 210	67.13 268	74.83 271	58.84 271

TESTMET0.1,1		77.47 261	77.20 259	77.78 259	81.94 262	75.11 263	87.04 255	58.33 268	70.11 263	78.59 251	83.17 248	71.60 253	73.88 252	82.32 251	79.20 246	86.91 246	78.87 251

new_pmnet		76.65 262	83.52 232	68.63 262	82.60 260	72.08 267	76.76 272	64.17 263	84.41 209	49.73 274	91.77 174	91.53 195	56.16 269	86.59 229	83.26 230	82.37 259	75.02 259

MVE	60.41 19	73.21 263	80.84 242	64.30 263	56.34 274	57.24 274	75.28 274	72.76 259	87.14 181	41.39 276	86.31 235	85.30 232	80.66 210	86.17 233	83.36 229	59.35 273	80.38 243
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		69.86 264	82.14 238	55.52 264	75.19 271	63.08 273	75.52 273	60.97 265	88.50 164	25.11 278	91.77 174	96.44 120	25.43 273	88.70 217	79.34 245	70.93 272	67.17 268

GG-mvs-BLEND		54.28 265	77.89 255	26.72 267	0.37 283	83.31 248	70.04 275	0.39 277	74.71 257	5.36 280	68.78 266	83.06 234	0.62 279	83.73 249	78.99 248	83.55 257	72.68 267

test_method		43.16 266	51.13 268	33.85 265	7.35 278	12.38 279	51.70 277	11.91 271	62.51 271	47.64 275	62.49 272	80.78 243	28.84 270	59.55 271	34.48 271	55.68 274	45.72 273

VLMVS_CLIP		30.30 267	36.13 270	23.51 268	54.32 275	31.52 276	8.97 279	27.94 269	31.32 274	8.68 279	37.87 275	39.37 281	28.52 271	37.60 273	32.88 272	12.63 277	42.36 274

MVS_clip		27.15 268	40.54 269	11.53 269	22.06 277	19.49 277	6.62 281	6.19 273	39.03 273	1.66 283	50.77 273	48.60 279	25.91 272	38.89 272	35.93 270	6.77 278	51.09 272

MVS_baseline		7.97 269	13.11 271	1.98 271	2.61 280	1.13 282	0.40 285	0.00 278	13.03 275	0.00 285	14.70 276	17.39 283	8.80 275	5.37 275	6.00 273	0.05 282	34.14 275

VLMVS		6.39 270	8.96 272	3.39 270	6.72 279	4.83 280	1.89 282	1.88 274	9.81 276	1.97 282	8.48 277	12.35 284	5.85 276	6.19 274	5.45 274	2.01 279	15.59 276

testmvs		2.38 271	3.35 273	1.26 273	0.83 281	0.96 283	1.53 283	0.83 275	3.59 277	1.63 284	6.03 278	2.93 285	1.55 278	3.49 276	2.51 276	1.21 281	3.92 278

test123		2.16 272	2.82 274	1.41 272	0.62 282	1.18 281	1.53 283	0.82 276	2.78 278	2.27 281	4.18 279	1.98 286	1.64 277	2.58 277	3.01 275	1.56 280	4.00 277

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

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

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

ACM-MVS					94.83 99	93.67 137	93.96 161		85.15 204	90.16 137	86.10 236	89.98 210	80.09 215			94.35 181	94.99 71

PatchmatchNet2					90.67 223	71.56 268	85.25 264
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												95.63 141	59.14 266	83.89 245	74.87 261	75.05 269	73.16 265
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										53.40 271	95.51 115
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							98.20 28	91.80 86		87.87 176						96.59 94

TPM-MVS					94.35 113	93.52 151	92.94 193			89.43 149	84.20 245	90.07 207	80.21 212			94.56 176	93.77 96
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												93.19 184

SR-MVS					97.13 23			94.77 17				97.77 79

Anonymous202405211			94.63 83		94.51 111	94.96 101	93.94 162	91.35 94	90.82 132		95.60 109	95.85 137	81.74 206	96.47 77	95.84 75	97.39 66	92.85 115

our_test_3					91.78 199	88.87 222	94.37 145

ambc			94.61 84		98.09 4	95.14 92	91.71 222		94.18 46	96.46 12	96.26 91	96.30 123	91.26 70	94.70 116	92.00 153	93.45 198	93.67 99

MTAPA										94.88 28		96.88 109

MTMP										95.43 18		97.25 97

Patchmatch-RL test							8.96 280

tmp_tt				28.44 266	36.05 276	15.86 278	21.29 278	6.40 272	54.52 272	51.96 273	50.37 274	38.68 282	9.55 274	61.75 270	59.66 269	45.36 276

XVS					96.86 32	97.48 19	98.73 3			93.28 58		96.82 111				98.17 35

X-MVStestdata					96.86 32	97.48 19	98.73 3			93.28 58		96.82 111				98.17 35

mPP-MVS					98.24 2							97.65 86

NP-MVS									85.48 201

Patchmtry						83.74 246	86.72 259	92.22 64		90.73 118

DeepMVS_CX						47.68 275	53.20 276	19.21 270	63.24 270	26.96 277	66.50 270	69.82 259	66.91 261	64.27 269		54.91 275	72.72 266

High-resolution multi-view benchmark