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 52	96.94 39	98.30 20	94.90 15	98.61 1	97.73 3	97.97 29	98.57 38	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 68	98.10 2	99.08 2	93.92 32	98.24 3	96.44 13	98.12 23	97.86 77	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 30	98.17 1	98.60 10	96.67 7	96.39 15	94.46 32	99.14 1	98.92 17	94.57 15	99.06 3	98.80 2	99.32 1	96.92 29

SixPastTwentyTwo		97.36 4	97.73 11	96.92 2	97.36 14	96.15 60	98.29 21	94.43 23	96.50 13	96.96 7	98.74 5	98.74 29	96.04 3	99.03 5	97.74 17	98.44 23	97.22 14

PS-CasMVS		97.22 5	97.84 7	96.50 5	97.08 26	97.92 6	98.17 32	97.02 2	94.71 32	95.32 21	98.52 12	98.97 16	92.91 44	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 22	97.97 4	98.25 25	96.86 6	95.09 28	94.93 26	98.66 7	99.16 7	92.27 55	98.98 6	98.39 7	98.49 19	96.83 33

DTE-MVSNet		97.16 6	97.75 9	96.47 6	97.40 13	97.95 5	98.20 28	96.89 5	95.30 23	95.15 24	98.66 7	98.80 24	92.77 49	98.97 7	98.27 9	98.44 23	96.28 45

COLMAP_ROB	93.74 2	97.09 8	97.98 4	96.05 17	95.97 64	97.78 9	98.56 11	91.72 91	97.53 7	96.01 15	98.14 21	98.76 28	95.28 5	98.76 11	98.23 10	98.77 5	96.67 37
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 38	98.04 3	98.25 25	97.32 1	94.40 42	93.71 51	98.55 10	98.89 19	92.97 41	98.91 9	98.45 6	98.38 28	97.19 15

CP-MVSNet		96.97 10	97.42 15	96.44 7	97.06 27	97.82 8	98.12 35	96.98 3	93.50 61	95.21 23	97.98 27	98.44 41	92.83 48	98.93 8	98.37 8	98.46 22	96.91 30

DVP-MVS++		96.63 11	97.92 5	95.12 41	97.77 7	97.52 16	98.29 21	93.83 35	96.72 9	92.52 75	98.10 24	99.07 13	90.87 81	97.83 32	97.44 29	97.44 63	98.76 1

ACMH	90.17 8	96.61 12	97.69 13	95.35 30	95.29 86	96.94 39	98.43 14	92.05 76	98.04 4	95.38 19	98.07 25	99.25 4	93.23 33	98.35 16	97.16 40	97.72 53	96.00 51
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
RA-MVS		96.58 13	97.75 9	95.21 37	98.09 4	97.30 30	97.04 59	94.04 30	96.34 16	91.10 112	98.14 21	99.01 14	93.18 35	98.21 18	98.17 11	97.79 50	97.09 22

UA-Net		96.56 14	96.73 26	96.36 9	98.99 1	97.90 7	97.79 45	95.64 10	92.78 80	92.54 74	96.23 95	95.02 162	94.31 18	98.43 15	98.12 12	98.89 3	98.58 3

ACMMPR		96.54 15	96.71 28	96.35 10	97.55 10	97.63 11	98.62 9	94.54 19	94.45 39	94.19 38	95.04 127	97.35 97	94.92 10	97.85 29	97.50 26	98.26 29	97.17 16

v7n		96.49 16	97.20 19	95.65 22	95.57 79	96.04 62	97.93 40	92.49 60	96.40 14	97.13 6	98.99 2	99.41 3	93.79 25	97.84 31	96.15 68	97.00 85	95.60 59

DeepC-MVS	92.47 4	96.44 17	96.75 25	96.08 16	97.57 8	97.19 34	97.96 39	94.28 24	95.29 24	94.92 27	98.31 17	96.92 108	93.69 27	96.81 70	96.50 59	98.06 40	96.27 46
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 18	96.42 35	96.19 14	97.21 21	97.16 36	98.71 5	93.79 38	94.35 43	93.81 45	92.80 166	98.23 54	95.11 6	98.07 21	97.45 28	98.51 18	96.86 32
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	89.90 10	96.27 19	97.52 14	94.81 48	95.19 89	97.18 35	97.97 38	92.52 58	96.72 9	90.50 129	97.31 59	99.11 10	94.10 19	98.67 12	97.90 15	98.56 15	95.79 55

APDe-MVS		96.23 20	97.22 18	95.08 42	96.66 42	97.56 14	98.63 8	93.69 42	94.62 35	89.80 142	97.73 40	98.13 58	93.84 24	97.79 34	97.63 19	97.87 47	97.08 24
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CP-MVS		96.21 21	96.16 46	96.27 12	97.56 9	97.13 37	98.43 14	94.70 18	92.62 84	94.13 40	92.71 167	98.03 65	94.54 16	98.00 25	97.60 21	98.23 31	97.05 25

HFP-MVS		96.18 22	96.53 32	95.77 20	97.34 17	97.26 31	98.16 33	94.54 19	94.45 39	92.52 75	95.05 125	96.95 107	93.89 22	97.28 50	97.46 27	98.19 33	97.25 11

UniMVSNet_ETH3D		96.15 23	97.71 12	94.33 57	97.31 18	96.71 44	95.06 123	96.91 4	97.86 5	90.42 130	98.55 10	99.60 1	88.01 123	98.51 13	97.81 16	98.26 29	94.95 73

MP-MVS		96.13 24	95.93 50	96.37 8	98.19 3	97.31 29	98.49 13	94.53 22	91.39 120	94.38 34	94.32 142	96.43 122	94.59 14	97.75 36	97.44 29	98.04 41	96.88 31
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ACMMP		96.12 25	96.27 42	95.93 18	97.20 22	97.60 12	98.64 7	93.74 39	92.47 88	93.13 65	93.23 158	98.06 62	94.51 17	97.99 26	97.57 23	98.39 27	96.99 26
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 26	97.23 17	94.79 50	96.28 55	97.49 17	97.90 41	93.60 44	95.47 20	89.57 148	97.32 58	97.72 82	93.89 22	97.74 37	97.53 24	97.51 59	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 26	96.29 39	95.87 19	96.72 39	97.35 28	98.43 14	93.83 35	90.81 135	92.67 73	95.05 125	98.86 22	95.01 7	98.11 19	97.37 36	98.52 17	96.50 39

CSCG		96.07 28	97.15 20	94.81 48	96.06 63	97.58 13	96.52 78	90.98 103	96.51 12	93.60 53	97.13 69	98.55 39	93.01 38	97.17 55	95.36 85	98.68 9	97.78 4

DPE-MVS		96.00 29	96.80 24	95.06 43	95.87 71	97.47 22	98.25 25	93.73 40	92.38 92	91.57 103	97.55 51	97.97 68	92.98 39	97.49 48	97.61 20	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 30	96.48 33	95.41 29	97.43 12	97.36 26	97.55 51	93.70 41	94.05 52	93.79 46	97.02 72	94.53 168	92.28 54	97.53 46	97.19 38	97.73 52	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 30	96.57 31	95.31 32	96.87 31	96.50 51	98.71 5	91.58 92	93.25 69	92.71 70	96.86 77	96.57 120	93.92 20	98.09 20	97.91 14	98.08 38	96.81 34
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 32	96.59 30	95.23 35	96.67 41	96.52 50	97.86 43	93.28 48	95.27 26	93.46 55	96.26 92	98.85 23	92.89 45	97.09 56	96.37 63	97.21 77	95.78 56
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SteuartSystems-ACMMP		95.96 32	96.13 47	95.76 21	97.06 27	97.36 26	98.40 18	94.24 26	91.49 113	91.91 93	94.50 138	96.89 109	94.99 8	98.01 24	97.44 29	97.97 44	97.25 11
Skip Steuart: Steuart Systems R&D Blog.
ACMP	89.62 11	95.96 32	96.28 40	95.59 23	96.58 44	97.23 33	98.26 24	93.22 49	92.33 96	92.31 83	94.29 143	98.73 30	94.68 12	98.04 22	97.14 41	98.47 21	96.17 48
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PGM-MVS		95.90 35	95.72 54	96.10 15	97.53 11	97.45 23	98.55 12	94.12 28	90.25 141	93.71 51	93.20 159	97.18 101	94.63 13	97.68 40	97.34 37	98.08 38	96.97 27

PMVS	87.16 16	95.88 36	96.47 34	95.19 38	97.00 29	96.02 63	96.70 69	91.57 93	94.43 41	95.33 20	97.16 67	95.37 150	92.39 51	98.89 10	98.72 3	98.17 35	94.71 79
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ACMMP_NAP		95.86 37	96.18 43	95.47 28	97.11 25	97.26 31	98.37 19	93.48 46	93.49 62	93.99 43	95.61 108	94.11 172	92.49 50	97.87 28	97.44 29	97.40 66	97.52 8

Gipuma		95.86 37	96.17 44	95.50 27	95.92 67	94.59 112	94.77 134	92.50 59	97.82 6	97.90 2	95.56 112	97.88 75	94.71 11	98.02 23	94.81 101	97.23 76	94.48 85
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LS3D		95.83 39	96.35 37	95.22 36	96.47 48	97.49 17	97.99 36	92.35 63	94.92 31	94.58 30	94.88 132	95.11 160	91.52 66	98.48 14	98.05 13	98.42 25	95.49 60

MED-MVS		95.79 40	96.97 22	94.41 54	95.58 78	97.44 24	97.73 46	93.05 50	95.33 21	89.42 152	98.30 18	97.12 103	92.87 46	97.26 52	96.99 43	97.83 48	96.33 42

SD-MVS		95.77 41	96.17 44	95.30 33	96.72 39	96.19 59	97.01 61	93.04 51	94.03 53	92.71 70	96.45 90	96.78 116	93.91 21	96.79 71	95.89 74	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 42	96.98 21	94.28 58	96.08 61	97.39 25	98.18 31	93.80 37	94.20 45	89.61 147	97.29 62	97.49 93	90.69 85	97.74 37	97.41 33	97.32 71	97.34 9

TranMVSNet+NR-MVSNet		95.72 43	96.42 35	94.91 47	96.21 56	96.77 43	96.90 66	94.99 13	92.62 84	91.92 92	98.51 13	98.63 35	90.82 82	97.27 51	96.83 47	98.63 12	94.31 86

DU-MVS		95.51 44	95.68 55	95.33 31	96.45 49	96.44 53	96.61 75	95.32 11	89.97 147	93.78 47	97.46 54	98.07 60	91.19 73	97.03 59	96.53 56	98.61 13	94.22 87

aaEdge-Enhanced		95.48 45	96.73 26	94.02 66	95.47 82	97.55 15	98.20 28	91.80 87	93.84 55	89.07 158	98.30 18	97.53 92	92.98 39	96.86 69	96.68 54	96.59 95	96.33 42

UniMVSNet (Re)		95.46 46	95.86 52	95.00 46	96.09 59	96.60 45	96.68 73	94.99 13	90.36 140	92.13 86	97.64 46	98.13 58	91.38 67	96.90 64	96.74 49	98.73 6	94.63 81

RPSCF		95.46 46	96.95 23	93.73 82	95.72 75	95.94 67	95.58 106	88.08 166	95.31 22	91.34 106	96.26 92	98.04 64	93.63 28	98.28 17	97.67 18	98.01 42	97.13 18

anonymousdsp		95.45 48	96.70 29	93.99 70	88.43 248	92.05 178	99.18 1	85.42 209	94.29 44	96.10 14	98.63 9	99.08 12	96.11 1	97.77 35	97.41 33	98.70 8	97.69 6

APD-MVS		95.38 49	95.68 55	95.03 44	97.30 19	96.90 41	97.83 44	93.92 32	89.40 155	90.35 131	95.41 117	97.69 84	92.97 41	97.24 54	97.17 39	97.83 48	95.96 52
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
UniMVSNet_NR-MVSNet		95.34 50	95.51 59	95.14 40	95.80 73	96.55 46	96.61 75	94.79 16	90.04 146	93.78 47	97.51 53	97.25 98	91.19 73	96.68 73	96.31 65	98.65 11	94.22 87

X-MVS		95.33 51	95.13 68	95.57 25	97.35 15	97.48 19	98.43 14	94.28 24	92.30 97	93.28 58	86.89 231	96.82 112	91.87 60	97.85 29	97.59 22	98.19 33	96.95 28

MSP-MVS		95.32 52	96.28 40	94.19 61	96.87 31	97.77 10	98.27 23	93.88 34	94.15 51	89.63 146	95.36 118	98.37 45	90.73 83	94.37 124	97.53 24	95.77 130	96.40 40
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 53	95.16 66	95.29 34	96.17 57	96.55 46	97.64 48	94.02 31	94.16 50	94.29 36	92.09 174	93.71 180	91.90 58	96.68 73	96.51 57	97.70 55	96.40 40

HPM-MVS++		95.21 54	94.89 71	95.59 23	97.79 6	95.39 86	97.68 47	94.05 29	91.91 105	94.35 35	93.38 154	95.07 161	92.94 43	96.01 86	95.88 75	96.73 89	96.61 38

TSAR-MVS + ACMM		95.17 55	95.95 48	94.26 59	96.07 62	96.46 52	95.67 103	94.21 27	93.84 55	90.99 117	97.18 65	95.24 158	93.55 29	96.60 76	95.61 82	95.06 152	96.69 36

CPTT-MVS		95.00 56	94.52 86	95.57 25	96.84 35	96.78 42	97.88 42	93.67 43	92.20 98	92.35 82	85.87 239	97.56 91	94.98 9	96.96 62	96.07 71	97.70 55	96.18 47

SF-MVS		94.88 57	95.87 51	93.73 82	95.30 84	95.93 68	94.80 133	91.76 89	93.11 73	91.93 91	95.83 103	97.07 104	91.11 76	96.62 75	96.44 61	97.46 60	96.13 49

Baseline_NR-MVSNet		94.85 58	95.35 64	94.26 59	96.45 49	93.86 132	96.70 69	94.54 19	90.07 145	90.17 137	98.77 4	97.89 72	90.64 88	97.03 59	96.16 67	97.04 84	93.67 100

EG-PatchMatch MVS		94.81 59	95.53 58	93.97 71	95.89 70	94.62 110	95.55 108	88.18 164	92.77 81	94.88 28	97.04 71	98.61 36	93.31 30	96.89 65	95.19 91	95.99 122	93.56 103

CS-MVS		94.76 60	94.41 91	95.18 39	94.95 95	95.99 64	97.28 53	91.99 78	85.51 201	94.55 31	93.07 161	97.69 84	93.77 26	97.08 57	96.79 48	98.53 16	94.72 77

OMC-MVS		94.74 61	95.46 62	93.91 74	94.62 108	96.26 57	96.64 74	89.36 147	94.20 45	94.15 39	94.02 147	97.73 81	91.34 69	96.15 83	95.04 95	97.37 68	94.80 75

DeepC-MVS_fast	91.38 6	94.73 62	94.98 69	94.44 52	96.83 37	96.12 61	96.69 71	92.17 69	92.98 78	93.72 49	94.14 144	95.45 148	90.49 94	95.73 93	95.30 87	96.71 91	95.13 69
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 63	94.84 73	94.44 52	94.95 95	96.55 46	96.46 81	91.10 101	88.96 159	96.00 16	94.55 137	95.32 153	90.67 86	96.97 61	96.69 53	97.44 63	94.84 74

SPE-MVS-test		94.63 64	94.30 97	95.02 45	94.63 106	95.71 75	98.15 34	92.13 71	85.62 200	94.22 37	93.63 152	97.63 89	93.08 37	97.50 47	96.51 57	97.88 46	93.50 104

pmmvs6		94.58 65	97.30 16	91.40 138	94.84 99	94.61 111	93.40 180	92.43 62	98.51 2	85.61 194	98.73 6	99.53 2	84.40 177	97.88 27	97.03 42	97.72 53	94.79 76

DeepPCF-MVS	90.68 7	94.56 66	94.92 70	94.15 62	94.11 122	95.71 75	97.03 60	90.65 108	93.39 67	94.08 41	95.29 122	94.15 171	93.21 34	95.22 107	94.92 99	95.82 129	95.75 57

NR-MVSNet		94.55 67	95.66 57	93.25 94	94.26 117	96.44 53	96.69 71	95.32 11	89.97 147	91.79 98	97.46 54	98.39 44	82.85 193	96.87 67	96.48 60	98.57 14	93.98 93

MGCNet		94.43 68	94.78 77	94.02 66	96.14 58	97.09 38	97.52 52	92.66 56	90.12 143	93.12 66	95.31 120	93.19 185	87.75 125	96.14 84	95.60 83	96.96 86	96.01 50

Vis-MVSNet		94.39 69	95.85 53	92.68 102	90.91 220	95.88 70	97.62 50	91.41 94	91.95 104	89.20 155	97.29 62	96.26 125	90.60 93	96.95 63	95.91 72	96.32 108	96.71 35
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TSAR-MVS + GP.		94.25 70	94.81 75	93.60 84	96.52 47	95.80 73	94.37 146	92.47 61	90.89 131	88.92 161	95.34 119	94.38 169	92.85 47	96.36 81	95.62 81	96.47 101	95.28 66

CNVR-MVS		94.24 71	94.47 87	93.96 72	96.56 45	95.67 77	96.43 82	91.95 80	92.08 101	91.28 108	90.51 190	95.35 151	91.20 72	96.34 82	95.50 84	96.34 106	95.88 54

EC-MVSNet		94.23 72	93.81 120	94.71 51	94.85 98	96.23 58	97.14 55	93.40 47	81.79 226	91.58 102	93.29 157	95.21 159	93.13 36	97.73 39	96.95 44	98.20 32	95.45 61

v1192		93.98 73	93.94 112	94.01 68	93.91 131	94.63 109	97.00 62	89.75 131	91.01 129	96.50 10	97.93 30	98.26 51	91.74 62	92.06 170	92.05 151	95.18 147	91.66 150

Casviewmamba		93.97 74	95.50 60	92.18 112	94.23 118	95.44 82	95.94 91	91.14 99	93.80 58	86.49 188	97.98 27	98.66 31	88.55 116	95.26 105	94.08 117	96.73 89	93.30 108

v10		93.96 75	94.12 105	93.77 81	93.37 153	95.45 81	96.83 68	91.13 100	89.70 152	95.02 25	97.88 36	98.23 54	91.27 70	92.39 165	92.18 146	94.99 157	93.00 114

CDPH-MVS		93.96 75	93.86 114	94.08 64	96.31 53	95.84 71	96.92 64	91.85 83	87.21 179	91.25 110	92.83 163	96.06 133	91.05 78	95.57 96	94.81 101	97.12 79	94.72 77

MSLP-MVS++		93.91 77	94.30 97	93.45 86	95.51 80	95.83 72	93.12 190	91.93 82	91.45 116	91.40 105	87.42 226	96.12 132	93.27 31	96.57 77	96.40 62	95.49 135	96.29 44

v1921920		93.90 78	93.82 118	94.00 69	93.74 138	94.31 118	97.12 56	89.33 148	91.13 126	96.77 9	97.90 33	98.06 62	91.95 57	91.93 177	91.54 163	95.10 150	91.85 142

train_agg		93.89 79	93.46 133	94.40 55	97.35 15	93.78 135	97.63 49	92.19 68	88.12 168	90.52 128	93.57 153	95.78 139	92.31 53	94.78 116	93.46 127	96.36 104	94.70 80

v144192		93.89 79	93.85 115	93.94 73	93.50 147	94.33 116	97.12 56	89.49 139	90.89 131	96.49 11	97.78 38	98.27 50	91.89 59	92.17 169	91.70 160	95.19 146	91.78 145

v1240		93.89 79	93.72 123	94.09 63	93.98 127	94.31 118	97.12 56	89.37 144	90.74 137	96.92 8	98.05 26	97.89 72	92.15 56	91.53 188	91.60 161	94.99 157	91.93 138

NCCC		93.87 82	93.42 134	94.40 55	96.84 35	95.42 83	96.47 80	92.62 57	92.36 94	92.05 88	83.83 247	95.55 144	91.84 61	95.89 88	95.23 89	96.56 98	95.63 58

v1144		93.83 83	93.87 113	93.78 80	93.72 139	94.57 113	96.85 67	89.98 123	91.31 122	95.90 17	97.89 34	98.40 43	91.13 75	92.01 173	92.01 153	95.10 150	90.94 168

MVS_111021_HR		93.82 84	94.26 101	93.31 89	95.01 93	93.97 128	95.73 100	89.75 131	92.06 102	92.49 77	94.01 148	96.05 134	90.61 92	95.95 87	94.78 104	96.28 109	93.04 113

thisisatest0515		93.79 85	94.41 91	93.06 99	94.14 119	92.50 169	95.56 107	88.55 160	91.61 109	92.45 78	96.84 78	95.71 140	90.62 90	94.58 119	95.07 93	97.05 82	94.58 82

TAPA-MVS	88.94 13	93.78 86	94.31 96	93.18 96	94.14 119	95.99 64	95.74 99	86.98 189	93.43 66	93.88 44	90.16 197	96.88 110	91.05 78	94.33 125	93.95 118	97.28 74	95.40 62
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		93.72 87	93.62 128	93.84 75	94.75 103	94.90 103	97.24 54	91.81 86	86.97 186	92.74 69	93.83 150	97.24 100	90.46 95	95.10 111	94.09 116	96.08 119	93.18 111

casdiffseed414692147		93.69 88	94.80 76	92.40 105	93.85 133	94.47 114	95.64 104	90.17 116	92.40 91	89.43 150	97.16 67	99.09 11	89.22 107	94.45 122	93.37 130	96.09 118	92.66 126

EPP-MVSNet		93.63 89	93.95 111	93.26 92	95.15 90	96.54 49	96.18 89	91.97 79	91.74 106	85.76 192	94.95 130	84.27 234	91.60 65	97.61 44	97.38 35	98.87 4	95.18 68

v8		93.60 90	93.82 118	93.34 87	93.13 165	95.06 96	96.39 83	90.75 106	89.90 150	94.03 42	97.70 42	98.21 56	91.08 77	92.36 166	91.47 164	94.63 174	92.07 134

MCST-MVS		93.60 90	93.40 136	93.83 76	95.30 84	95.40 85	96.49 79	90.87 104	90.08 144	91.72 99	90.28 195	95.99 135	91.69 63	93.94 137	92.99 136	96.93 87	95.13 69

PVSNet_Blended_VisFu		93.60 90	93.41 135	93.83 76	96.31 53	95.65 78	95.71 101	90.58 110	88.08 170	93.17 63	95.29 122	92.20 190	90.72 84	94.69 118	93.41 129	96.51 100	94.54 83

TransMVSNet (Re)		93.55 93	96.32 38	90.32 160	94.38 113	94.05 123	93.30 187	89.53 138	97.15 8	85.12 199	98.83 3	97.89 72	82.21 200	96.75 72	96.14 69	97.35 69	93.46 105

E6new		93.49 94	94.68 82	92.10 115	93.52 144	93.87 130	95.80 96	89.59 136	95.07 29	91.10 112	97.93 30	99.22 5	87.59 128	93.32 146	91.86 155	95.00 155	91.49 154

E6		93.49 94	94.68 82	92.10 115	93.52 144	93.87 130	95.80 96	89.59 136	95.07 29	91.10 112	97.93 30	99.22 5	87.59 128	93.32 146	91.86 155	95.00 155	91.49 154

DCV-MVSNet		93.49 94	95.15 67	91.55 130	94.05 123	95.92 69	95.15 120	91.21 96	92.76 82	87.01 184	89.71 201	97.16 102	83.90 186	97.65 41	96.87 46	97.99 43	95.95 53

v2v482		93.42 97	93.49 132	93.32 88	93.44 152	94.05 123	96.36 86	89.76 130	91.41 118	95.24 22	97.63 47	98.34 47	90.44 96	91.65 186	91.76 159	94.69 171	89.62 187

sasdasda		93.38 98	94.36 93	92.24 109	93.94 129	96.41 55	94.18 157	90.47 111	93.07 76	88.47 172	88.66 212	93.78 177	88.80 111	95.74 91	95.75 78	97.57 57	97.13 18

canonicalmvs		93.38 98	94.36 93	92.24 109	93.94 129	96.41 55	94.18 157	90.47 111	93.07 76	88.47 172	88.66 212	93.78 177	88.80 111	95.74 91	95.75 78	97.57 57	97.13 18

3Dnovator	91.81 5	93.36 100	94.27 100	92.29 108	92.99 172	95.03 97	95.76 98	87.79 170	93.82 57	92.38 81	92.19 173	93.37 184	88.14 122	95.26 105	94.85 100	96.69 92	95.40 62

pm-mvs1		93.27 101	95.94 49	90.16 161	94.13 121	93.66 139	92.61 207	89.91 126	95.73 19	84.28 214	98.51 13	98.29 49	82.80 194	96.44 79	95.76 77	97.25 75	93.21 110

casdiffmvs_mvg		93.27 101	94.83 74	91.45 136	93.59 143	94.47 114	94.91 129	89.83 129	92.04 103	87.14 182	97.57 50	98.47 40	86.03 155	94.07 135	94.44 111	97.21 77	92.76 120
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		93.25 103	94.43 89	91.88 119	95.09 92	94.97 101	94.58 141	92.81 53	93.60 60	83.79 219	97.17 66	89.25 219	87.59 128	97.54 45	96.57 55	97.42 65	91.89 139

Anonymous20231211		93.19 104	95.50 60	90.49 157	93.77 136	95.29 88	94.36 150	90.04 122	91.44 117	84.59 209	96.72 81	97.65 87	82.45 199	97.25 53	96.32 64	97.74 51	93.79 96

TinyColmap		93.17 105	93.33 137	93.00 100	93.84 134	92.76 161	94.75 137	88.90 155	93.97 54	97.48 4	95.28 124	95.29 154	88.37 118	95.31 104	91.58 162	94.65 173	89.10 191

E4		93.16 106	94.30 97	91.84 120	93.48 149	93.69 137	95.42 110	89.49 139	94.67 34	90.67 124	97.52 52	99.01 14	86.97 135	92.46 164	91.21 168	94.98 159	91.54 153

viewmacassd2359aftdt		93.16 106	94.69 81	91.39 139	93.30 157	93.71 136	95.03 125	87.70 171	94.69 33	89.53 149	97.63 47	98.92 17	87.73 126	93.63 142	92.14 148	95.05 153	92.08 133

MVS_111021_LR		93.15 108	93.65 125	92.56 103	93.89 132	92.28 172	95.09 121	86.92 191	91.26 125	92.99 68	94.46 140	96.22 128	90.64 88	95.11 110	93.45 128	95.85 127	92.74 121

FE-MVSNET2		93.14 109	94.47 87	91.60 129	91.62 207	93.79 134	95.37 113	89.92 125	94.18 47	90.83 118	96.68 84	98.24 53	85.30 165	93.77 138	94.37 114	96.58 97	90.24 181

CNLPA		93.14 109	93.67 124	92.53 104	94.62 108	94.73 106	95.00 127	86.57 197	92.85 79	92.43 79	90.94 184	94.67 165	90.35 97	95.41 99	93.70 124	96.23 112	93.37 107

PLC	87.27 15	93.08 111	92.92 146	93.26 92	94.67 104	95.03 97	94.38 145	90.10 117	91.69 107	92.14 85	87.24 227	93.91 175	91.61 64	95.05 112	94.73 107	96.67 93	92.80 117
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CANet		93.07 112	93.05 144	93.10 97	95.90 68	95.41 84	95.88 93	91.94 81	84.77 208	93.36 56	94.05 146	95.25 157	86.25 151	94.33 125	93.94 119	95.30 140	93.58 102

TSAR-MVS + COLMAP		93.06 113	93.65 125	92.36 106	94.62 108	94.28 120	95.36 115	89.46 142	92.18 99	91.64 100	95.55 113	95.27 156	88.60 115	93.24 148	92.50 142	94.46 178	92.55 128

viewdifsd2359ckpt09		93.05 114	93.85 115	92.11 114	93.66 142	95.22 91	95.50 109	89.84 128	90.44 139	88.67 170	94.97 129	97.67 86	89.07 109	93.11 154	93.35 131	95.94 124	92.23 131

ECVR-MVS		93.05 114	94.25 102	91.65 126	94.76 101	95.23 89	94.26 154	92.80 54	92.49 86	83.90 217	96.75 80	89.99 209	86.84 140	97.62 42	96.72 50	97.32 71	90.92 169

hybridcas		93.00 116	94.72 79	91.00 147	93.68 141	94.33 116	95.09 121	89.23 149	93.77 59	84.96 203	97.89 34	98.43 42	87.27 132	94.08 134	92.63 140	95.77 130	91.88 140

E5new		92.97 117	94.09 106	91.68 124	93.48 149	93.65 141	95.26 116	89.37 144	94.47 36	90.54 126	97.30 60	98.79 26	86.56 146	92.00 174	90.74 179	94.86 164	91.65 151

E5		92.97 117	94.09 106	91.68 124	93.48 149	93.65 141	95.26 116	89.37 144	94.47 36	90.54 126	97.30 60	98.79 26	86.56 146	92.00 174	90.74 179	94.86 164	91.65 151

Effi-MVS+		92.93 119	92.16 161	93.83 76	94.29 115	93.53 151	95.04 124	92.98 52	85.27 204	94.46 32	90.24 196	95.34 152	89.99 100	93.72 139	94.23 115	96.22 113	92.79 118

Fast-Effi-MVS+		92.93 119	92.64 153	93.27 91	93.81 135	93.88 129	95.90 92	90.61 109	83.98 214	92.71 70	92.81 165	96.22 128	90.67 86	94.90 115	93.92 120	95.92 125	92.77 119

HQP-MVS		92.87 121	92.49 154	93.31 89	95.75 74	95.01 100	95.64 104	91.06 102	88.54 163	91.62 101	88.16 218	96.25 126	89.47 104	92.26 168	91.81 157	96.34 106	95.40 62

FMVSNet1		92.86 122	95.26 65	90.06 163	92.40 189	95.16 92	94.37 146	92.22 65	93.18 72	82.16 229	96.76 79	97.48 95	81.85 204	95.32 101	94.98 96	97.34 70	93.93 94

CLD-MVS		92.81 123	94.32 95	91.05 146	95.39 83	95.31 87	95.82 95	81.44 246	89.40 155	91.94 90	95.86 101	97.36 96	85.83 158	95.35 100	94.59 109	95.85 127	92.34 129
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
IS_MVSNet		92.76 124	93.25 139	92.19 111	94.91 97	95.56 79	95.86 94	92.12 72	88.10 169	82.71 224	93.15 160	88.30 222	88.86 110	97.29 49	96.95 44	98.66 10	93.38 106

E3new		92.75 125	93.78 121	91.55 130	93.35 154	93.54 149	95.17 118	89.17 150	93.49 62	90.29 136	97.00 74	98.65 32	86.58 144	91.86 180	90.64 181	94.75 167	91.27 158

E3		92.75 125	93.78 121	91.55 130	93.35 154	93.54 149	95.16 119	89.17 150	93.48 65	90.32 133	97.01 73	98.65 32	86.58 144	91.86 180	90.64 181	94.75 167	91.27 158

FC-MVSNet-train		92.75 125	95.40 63	89.66 172	95.21 88	94.82 104	97.00 62	89.40 143	91.13 126	81.71 231	97.72 41	96.43 122	77.57 236	96.89 65	96.72 50	97.05 82	94.09 90

V42		92.67 128	93.50 131	91.71 123	91.41 209	92.96 159	95.71 101	85.00 212	89.67 153	93.22 61	97.67 45	98.01 66	91.02 80	92.65 159	92.12 149	93.86 192	91.42 156

PM-MVS		92.65 129	93.20 142	92.00 117	92.11 197	90.16 217	95.99 90	84.81 217	91.31 122	92.41 80	95.87 100	96.64 118	92.35 52	93.65 141	92.91 137	94.34 183	91.85 142

MVSMamba_PlusPlus		92.57 130	93.24 140	91.79 122	95.49 81	95.10 95	93.82 165	89.60 135	86.44 191	89.06 159	90.82 186	94.93 164	87.09 133	95.00 113	95.23 89	95.68 132	95.13 69

QAPM		92.57 130	93.51 130	91.47 135	92.91 174	94.82 104	93.01 192	87.51 176	91.49 113	91.21 111	92.24 171	91.70 195	88.74 113	94.54 121	94.39 113	95.41 137	95.37 65

MIMVSNet1		92.52 132	94.88 72	89.77 168	96.09 59	91.99 179	96.92 64	89.68 133	95.92 18	84.55 210	96.64 85	98.21 56	78.44 228	96.08 85	95.10 92	92.91 218	90.22 182

viewmanbaseed2359cas		92.46 133	93.85 115	90.83 150	93.07 167	93.47 153	94.55 143	87.10 187	92.76 82	88.70 169	96.72 81	98.35 46	86.85 139	92.70 157	91.22 167	94.71 170	91.76 147

tfpnnormal		92.45 134	94.77 78	89.74 169	93.95 128	93.44 155	93.25 188	88.49 162	95.27 26	83.20 222	96.51 88	96.23 127	83.17 191	95.47 98	94.52 110	96.38 103	91.97 137

PCF-MVS	87.46 14	92.44 135	91.80 164	93.19 95	94.66 105	95.80 73	96.37 84	90.19 115	87.57 175	92.23 84	89.26 206	93.97 174	89.24 105	91.32 192	90.82 178	96.46 102	93.86 95
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		92.42 136	93.99 110	90.60 155	93.25 159	93.82 133	94.28 152	88.73 158	91.53 111	84.53 212	97.74 39	98.64 34	86.60 143	93.21 150	91.20 169	96.21 114	91.76 147
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		92.41 137	93.33 137	91.34 141	93.24 160	93.43 156	94.96 128	88.94 154	92.44 90	90.07 139	96.53 87	98.31 48	86.27 150	91.34 191	90.17 189	94.57 176	91.11 164

AdaColmap		92.41 137	91.49 170	93.48 85	95.96 65	95.02 99	95.37 113	91.73 90	87.97 172	91.28 108	82.82 251	91.04 202	90.62 90	95.82 90	95.07 93	95.95 123	92.67 122

v148		92.38 139	92.78 151	91.91 118	92.86 175	92.13 175	94.84 131	87.03 188	91.47 115	93.07 67	96.92 76	98.89 19	90.10 99	92.05 171	89.69 194	93.56 198	88.27 202

pmmvs-eth3d		92.34 140	92.33 156	92.34 107	92.67 180	90.67 205	96.37 84	89.06 152	90.98 130	93.60 53	97.13 69	97.02 106	88.29 119	90.20 203	91.42 165	94.07 186	88.89 196

DELS-MVS		92.33 141	93.61 129	90.83 150	92.84 177	95.13 94	94.76 135	87.22 184	87.78 174	88.42 175	95.78 104	95.28 155	85.71 161	94.44 123	93.91 121	96.01 121	92.97 115
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		92.32 142	91.66 168	93.09 98	95.13 91	94.73 106	94.57 142	92.14 70	81.74 227	90.33 132	88.13 219	95.91 136	89.24 105	94.23 130	93.65 126	97.12 79	93.23 109

MGCFI-Net		92.31 143	94.25 102	90.04 166	93.75 137	95.96 66	93.32 185	90.28 114	93.28 68	80.57 242	88.79 210	93.78 177	84.89 172	95.55 97	95.31 86	97.45 62	97.10 21

UGNet		92.31 143	94.70 80	89.53 174	90.99 217	95.53 80	96.19 88	92.10 74	91.35 121	85.76 192	95.31 120	95.48 147	76.84 241	95.22 107	94.79 103	95.32 139	95.19 67
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		92.24 145	93.22 141	91.10 145	93.01 171	93.63 143	94.65 140	87.69 172	90.81 135	88.80 167	95.59 111	97.98 67	87.51 131	91.98 176	90.83 177	94.94 160	91.74 149

USDC		92.17 146	92.17 160	92.18 112	92.93 173	92.22 173	93.66 171	87.41 179	93.49 62	97.99 1	94.10 145	96.68 117	86.46 148	92.04 172	89.18 201	94.61 175	87.47 209

ETV-MVS		92.12 147	90.44 181	94.08 64	96.36 51	93.63 143	96.27 87	92.00 77	78.90 246	92.13 86	85.29 241	89.85 213	90.26 98	97.07 58	96.29 66	97.46 60	92.04 135

IterMVS-LS		92.10 148	92.33 156	91.82 121	93.18 161	93.66 139	92.80 203	92.27 64	90.82 133	90.59 125	97.19 64	90.97 203	87.76 124	89.60 210	90.94 174	94.34 183	93.16 112
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
E2		92.09 149	92.90 147	91.16 144	93.16 164	93.35 157	94.76 135	88.75 157	91.40 119	89.85 140	95.98 98	97.95 70	85.98 157	90.86 197	89.74 192	94.43 179	90.99 167

MSDG		92.09 149	92.84 150	91.22 143	92.55 182	92.97 158	93.42 179	85.43 208	90.24 142	91.83 95	94.70 134	94.59 166	88.48 117	94.91 114	93.31 133	95.59 134	89.15 190

EIA-MVS		91.95 151	90.36 183	93.81 79	96.54 46	94.65 108	95.38 112	90.40 113	78.01 251	93.72 49	86.70 234	91.95 192	89.93 101	95.67 95	94.72 108	96.89 88	90.79 172

MAR-MVS		91.86 152	91.14 175	92.71 101	94.29 115	94.24 121	94.91 129	91.82 85	81.66 228	93.32 57	84.51 244	93.42 183	86.86 138	95.16 109	94.44 111	95.05 153	94.53 84
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		91.80 153	94.01 108	89.22 182	92.52 183	91.95 181	93.78 166	84.14 224	93.11 73	83.97 215	97.68 43	99.12 8	86.05 153	94.17 131	90.89 175	94.88 162	91.18 162

viewmsd2359difaftdt		91.80 153	94.01 108	89.22 182	92.52 183	91.95 181	93.78 166	84.14 224	93.11 73	83.97 215	97.68 43	99.12 8	86.05 153	94.16 132	90.89 175	94.88 162	91.18 162

EU-MVSNet		91.63 155	92.73 152	90.35 159	88.36 249	87.89 229	96.53 77	81.51 245	92.45 89	91.82 96	96.44 91	97.05 105	93.26 32	94.10 133	88.94 206	90.61 227	92.24 130

viewdifsd2359ckpt07		91.59 156	93.64 127	89.19 184	92.86 175	92.58 167	94.25 156	84.97 213	94.17 49	85.52 195	97.60 49	98.59 37	85.99 156	91.85 182	88.85 208	91.52 224	91.87 141

FC-MVSNet-test		91.49 157	94.43 89	88.07 206	94.97 94	90.53 210	95.42 110	91.18 98	93.24 70	72.94 262	98.37 15	93.86 176	78.78 221	97.82 33	96.13 70	95.13 148	91.05 165

FA-MVS(training)		91.38 158	91.18 174	91.62 128	93.49 148	92.38 170	95.03 125	90.81 105	87.20 180	91.46 104	93.00 162	89.47 216	84.19 180	93.20 152	92.08 150	94.74 169	90.90 170

viewmamba		91.25 159	92.87 149	89.36 179	91.65 205	91.96 180	93.62 173	86.76 193	90.57 138	86.42 189	97.00 74	98.07 60	83.99 183	92.49 163	89.54 197	93.75 195	90.44 177

FE-MVSNET		91.21 160	92.90 147	89.24 181	90.93 219	91.69 185	93.46 177	87.85 169	92.35 95	85.06 202	94.84 133	96.63 119	82.80 194	92.98 155	93.22 134	95.36 138	88.58 198

usedtu_dtu_shiyan2		91.17 161	93.05 144	88.98 187	95.95 66	92.70 165	93.66 171	91.85 83	96.05 17	82.16 229	93.34 156	98.87 21	76.62 243	93.56 143	92.03 152	93.66 197	84.77 225

OpenMVS	89.22 12	91.09 162	91.42 171	90.71 153	92.79 179	93.61 146	92.74 205	85.47 207	86.10 197	90.73 119	85.71 240	93.07 188	86.69 142	94.07 135	93.34 132	95.86 126	94.02 92

onestephybrid01		91.06 163	92.45 155	89.44 176	91.76 201	92.07 177	93.67 169	87.22 184	87.19 181	85.83 191	96.07 97	97.93 71	84.20 179	92.82 156	90.21 188	93.99 187	90.87 171

diffmvs_AUTHOR		91.06 163	93.06 143	88.71 196	91.67 204	91.66 186	92.77 204	85.36 210	91.29 124	85.38 197	97.45 56	98.26 51	83.74 187	91.81 183	89.70 193	93.37 209	91.27 158

FPMVS		90.81 165	91.60 169	89.88 167	92.52 183	88.18 225	93.31 186	83.62 228	91.59 110	88.45 174	88.96 209	89.73 215	86.96 136	96.42 80	95.69 80	94.43 179	90.65 173

DI_MVS_pp		90.68 166	90.40 182	91.00 147	92.43 188	92.61 166	94.17 159	88.98 153	88.32 167	88.76 168	93.67 151	87.58 224	86.44 149	89.74 208	90.33 185	95.24 143	90.56 176

Vis-MVSNet (Re-imp)		90.68 166	92.18 159	88.92 190	94.63 106	92.75 162	92.91 196	91.20 97	89.21 158	75.01 258	93.96 149	89.07 220	82.72 197	95.88 89	95.30 87	97.08 81	89.08 192

DPM-MVS		90.67 168	89.86 187	91.63 127	95.29 86	94.16 122	94.52 144	89.63 134	89.59 154	89.67 145	81.95 253	88.64 221	85.75 160	90.46 200	90.43 184	94.91 161	93.77 97

dtuplus		90.47 169	91.79 165	88.92 190	91.92 199	90.59 209	92.93 195	85.60 205	89.34 157	85.12 199	95.71 106	97.78 79	84.05 181	90.93 196	87.82 213	93.88 190	90.39 178

diffmvs		90.44 170	92.23 158	88.35 202	91.36 211	91.38 192	92.45 211	84.84 216	89.88 151	85.09 201	96.69 83	97.71 83	83.33 190	90.01 207	88.96 205	93.03 215	91.00 166
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		90.28 171	92.04 163	88.23 204	91.22 213	94.05 123	92.88 197	90.69 107	86.53 189	79.89 246	94.38 141	92.73 189	78.54 224	91.64 187	92.26 145	96.17 115	92.67 122

IterMVS-SCA-FT		90.24 172	89.37 193	91.26 142	92.50 186	92.11 176	91.69 224	87.48 177	87.05 185	91.82 96	95.76 105	87.25 225	91.36 68	89.02 216	85.53 227	92.68 219	88.90 195

MVS_Test		90.19 173	90.58 177	89.74 169	92.12 196	91.74 184	92.51 208	88.54 161	82.80 220	87.50 180	94.62 135	95.02 162	83.97 184	88.69 219	89.32 199	93.79 193	91.85 142

EPNet		90.17 174	89.07 195	91.45 136	97.25 20	90.62 208	94.84 131	93.54 45	80.96 230	91.85 94	86.98 230	85.88 230	77.79 233	92.30 167	92.58 141	93.41 204	94.20 89
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
viewmambaseed2359dif		90.16 175	91.38 172	88.72 194	91.64 206	90.75 201	92.73 206	85.32 211	87.92 173	84.90 204	95.63 107	97.49 93	84.05 181	90.27 202	87.28 215	93.71 196	90.35 180

hybridnocas07		90.14 176	92.12 162	87.83 209	90.95 218	90.85 199	92.22 214	84.61 220	88.53 164	84.79 207	96.64 85	97.86 77	81.44 209	91.88 179	88.90 207	92.97 216	90.17 184

PVSNet_BlendedMVS		90.09 177	90.12 185	90.05 164	92.40 189	92.74 163	91.74 220	85.89 202	80.54 233	90.30 134	88.54 214	95.51 145	84.69 175	92.64 160	90.25 186	95.28 141	90.61 174

PVSNet_Blended		90.09 177	90.12 185	90.05 164	92.40 189	92.74 163	91.74 220	85.89 202	80.54 233	90.30 134	88.54 214	95.51 145	84.69 175	92.64 160	90.25 186	95.28 141	90.61 174

usedtu_dtu_shiyan1		90.01 179	90.53 180	89.39 178	90.47 226	91.62 189	93.36 181	87.13 186	87.52 176	87.00 185	92.63 168	94.03 173	82.94 192	89.33 214	91.00 173	95.46 136	87.61 205

pmmvs4		89.95 180	89.32 194	90.69 154	91.60 208	89.17 222	94.37 146	87.63 173	88.07 171	91.02 116	94.50 138	90.50 207	86.13 152	86.33 233	89.40 198	93.39 206	87.29 213

hybrid		89.90 181	91.77 166	87.72 211	90.87 221	90.63 207	92.16 216	84.26 222	88.34 166	84.87 205	95.91 99	97.63 89	81.53 208	91.51 189	88.47 210	92.61 220	89.87 185

MDA-MVSNet-bldmvs		89.75 182	91.67 167	87.50 213	74.25 273	90.88 198	94.68 138	85.89 202	91.64 108	91.03 115	95.86 101	94.35 170	89.10 108	96.87 67	86.37 222	90.04 229	85.72 222

WB-MVS		89.70 183	94.13 104	84.54 235	88.16 251	92.57 168	88.90 245	88.32 163	96.67 11	73.61 261	98.29 20	98.80 24	80.60 212	95.73 93	92.18 146	87.66 244	84.64 226

tttt0517		89.64 184	88.05 207	91.49 134	93.52 144	91.65 187	93.67 169	87.53 174	82.77 221	89.39 153	90.37 194	70.05 259	88.21 120	93.71 140	93.79 122	96.63 94	94.04 91

PatchMatch-RL		89.59 185	88.80 199	90.51 156	92.20 195	88.00 228	91.72 222	86.64 194	84.75 209	88.25 176	87.10 229	90.66 206	89.85 103	93.23 149	92.28 144	94.41 181	85.60 223

Fast-Effi-MVS+-dtu		89.57 186	88.42 203	90.92 149	93.35 154	91.57 190	93.01 192	95.71 9	78.94 245	87.65 179	84.68 243	93.14 187	82.00 202	90.84 198	91.01 172	93.78 194	88.77 197

thisisatest0530		89.54 187	87.99 211	91.35 140	93.17 162	91.31 193	93.45 178	87.53 174	82.96 219	89.17 157	90.45 191	70.32 258	88.21 120	93.37 145	93.79 122	96.54 99	93.71 99

test2506		89.51 188	87.77 214	91.55 130	94.76 101	95.23 89	94.26 154	92.80 54	92.49 86	83.31 221	89.97 199	50.93 279	86.84 140	97.62 42	96.72 50	97.32 71	91.42 156

GBi-Net		89.35 189	90.58 177	87.91 207	91.22 213	94.05 123	92.88 197	90.05 119	79.40 237	78.60 249	90.58 187	87.05 226	78.54 224	95.32 101	94.98 96	96.17 115	92.67 122

test1		89.35 189	90.58 177	87.91 207	91.22 213	94.05 123	92.88 197	90.05 119	79.40 237	78.60 249	90.58 187	87.05 226	78.54 224	95.32 101	94.98 96	96.17 115	92.67 122

thres600view7		89.14 191	88.83 197	89.51 175	93.71 140	93.55 147	93.93 164	88.02 167	87.30 178	82.40 225	81.18 254	80.63 245	82.69 198	94.27 127	95.90 73	96.27 110	88.94 194

CVMVSNet		88.97 192	89.73 189	88.10 205	87.33 256	85.22 241	94.68 138	78.68 248	88.94 160	86.98 186	95.55 113	85.71 231	89.87 102	91.19 193	89.69 194	91.05 225	91.78 145

CANet_DTU		88.95 193	89.51 192	88.29 203	93.12 166	91.22 196	93.61 174	83.47 231	80.07 236	90.71 123	89.19 207	93.68 181	76.27 246	91.44 190	91.17 171	92.59 221	89.83 186

gbinet_0.2-2-1-0.02		88.79 194	88.26 204	89.40 177	89.67 235	91.24 194	94.03 161	84.65 219	85.76 199	89.02 160	92.83 163	90.75 205	85.62 162	85.86 235	82.42 234	93.41 204	88.98 193

GA-MVS		88.76 195	88.04 209	89.59 173	92.32 192	91.46 191	92.28 213	86.62 195	83.82 216	89.84 141	92.51 170	81.94 239	83.53 189	89.41 212	89.27 200	92.95 217	87.90 203

pmmvs5		88.63 196	89.70 190	87.39 214	89.24 238	90.64 206	91.87 219	82.13 241	83.34 217	87.86 178	94.58 136	96.15 131	79.87 217	87.33 228	89.07 204	93.39 206	86.76 216

thres400		88.54 197	88.15 206	88.98 187	93.17 162	92.84 160	93.56 175	86.93 190	86.45 190	82.37 226	79.96 256	81.46 242	81.83 205	93.21 150	94.76 105	96.04 120	88.39 200

blended_shiyan8		88.52 198	88.03 210	89.08 185	89.78 233	90.69 202	93.34 183	82.82 234	87.12 183	89.21 154	91.51 177	91.71 194	85.38 163	85.01 239	82.73 233	93.96 188	87.47 209

blended_shiyan6		88.52 198	88.05 207	89.07 186	89.79 231	90.69 202	93.34 183	82.81 235	87.12 183	89.19 156	91.48 178	91.81 193	85.32 164	84.98 240	82.74 232	93.95 189	87.52 207

CDS-MVSNet		88.41 200	89.79 188	86.79 220	94.55 111	90.82 200	92.50 209	89.85 127	83.26 218	80.52 243	91.05 180	89.93 212	69.11 258	93.17 153	92.71 139	94.21 185	87.63 204
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gg-mvs-nofinetune		88.32 201	88.81 198	87.75 210	93.07 167	89.37 221	89.06 244	95.94 8	95.29 24	87.15 181	97.38 57	76.38 248	68.05 261	91.04 194	89.10 203	93.24 211	83.10 233

IterMVS		88.32 201	88.25 205	88.41 201	90.83 222	91.24 194	93.07 191	81.69 243	86.77 187	88.55 171	95.61 108	86.91 229	87.01 134	87.38 227	83.77 229	89.29 233	86.06 221
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres200		88.29 203	87.88 212	88.76 193	92.50 186	93.55 147	92.47 210	88.02 167	84.80 207	81.44 233	79.28 258	82.20 238	81.83 205	94.27 127	93.67 125	96.27 110	87.40 211

IB-MVS	86.01 17	88.24 204	87.63 215	88.94 189	92.03 198	91.77 183	92.40 212	85.58 206	78.24 248	84.85 206	71.99 265	93.45 182	83.96 185	93.48 144	92.33 143	94.84 166	92.15 132
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
MDTV_nov1_ep13_2view		88.22 205	87.85 213	88.65 197	91.40 210	86.75 233	94.07 160	84.97 213	88.86 162	93.20 62	96.11 96	96.21 130	83.70 188	87.29 229	80.29 244	84.56 253	79.46 249

test20.03		88.20 206	91.26 173	84.63 233	96.64 43	89.39 220	90.73 231	89.97 124	91.07 128	72.02 264	94.98 128	95.45 148	69.35 257	92.70 157	91.19 170	89.06 235	84.02 227

HyFIR lowres test		88.19 207	86.56 224	90.09 162	91.24 212	92.17 174	94.30 151	88.79 156	84.06 211	85.45 196	89.52 204	85.64 232	88.64 114	85.40 237	87.28 215	92.14 223	81.87 237

ET-MVSNet_ETH3D		88.06 208	85.75 229	90.74 152	92.82 178	90.68 204	93.77 168	88.59 159	81.22 229	89.78 143	89.15 208	66.79 272	84.29 178	91.72 185	91.34 166	95.22 144	89.36 189

wanda-best-256-512		87.94 209	87.36 219	88.61 198	89.23 239	90.35 212	92.84 200	82.30 236	86.26 193	88.91 162	90.96 182	91.43 197	84.94 169	84.27 241	81.61 237	93.45 199	86.67 218

FE-blended-shiyan7		87.94 209	87.36 219	88.61 198	89.23 239	90.35 212	92.84 200	82.30 236	86.26 193	88.91 162	90.96 182	91.43 197	84.94 169	84.27 241	81.61 237	93.45 199	86.67 218

tfpn200view9		87.94 209	87.51 217	88.44 200	92.28 193	93.63 143	93.35 182	88.11 165	80.90 231	80.89 239	78.25 259	82.25 236	79.65 219	94.27 127	94.76 105	96.36 104	88.48 199

FMVSNet3		87.90 212	88.63 201	87.04 216	89.78 233	93.46 154	91.62 225	90.05 119	79.40 237	78.60 249	90.58 187	87.05 226	77.07 240	88.03 224	89.85 191	95.12 149	92.04 135

MS-PatchMatch		87.72 213	88.62 202	86.66 221	90.81 223	88.18 225	90.92 228	82.25 240	85.86 198	80.40 244	90.14 198	89.29 218	84.93 171	89.39 213	89.12 202	90.67 226	88.34 201

Anonymous20231206		87.45 214	89.66 191	84.87 230	94.00 124	87.73 231	91.36 226	86.41 199	88.89 161	75.03 257	92.59 169	96.82 112	72.48 255	89.72 209	88.06 211	89.93 230	83.81 229

EPNet_dtu		87.40 215	86.27 225	88.72 194	95.68 76	83.37 248	92.09 217	90.08 118	78.11 250	91.29 107	86.33 235	89.74 214	75.39 250	89.07 215	87.89 212	87.81 240	89.38 188
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
baseline1		86.96 216	87.58 216	86.24 224	93.07 167	90.44 211	89.24 243	86.85 192	85.14 206	77.26 255	90.45 191	76.09 250	75.79 247	91.80 184	91.81 157	95.20 145	87.35 212

dtuonlycased		86.78 217	90.70 176	82.21 242	89.31 236	91.65 187	94.27 153	75.13 255	89.94 149	59.16 271	93.38 154	95.67 141	87.63 127	90.99 195	85.76 224	87.74 243	87.53 206

baseline		86.71 218	88.89 196	84.16 236	87.85 252	85.23 240	89.82 237	77.69 251	84.03 213	84.75 208	94.91 131	94.59 166	77.19 239	86.57 232	86.51 221	87.66 244	90.36 179

CHOSEN 1792x2688		86.64 219	86.62 222	86.65 222	90.33 228	87.86 230	93.19 189	83.30 232	83.95 215	82.32 227	87.93 221	89.34 217	86.92 137	85.64 236	84.95 228	83.85 257	86.68 217

dmvs_re		86.51 220	86.14 227	86.95 218	93.07 167	86.11 236	92.01 218	86.04 201	72.70 261	79.10 247	75.37 262	89.99 209	78.10 232	94.56 120	93.01 135	93.35 210	91.26 161

testgi		86.49 221	90.31 184	82.03 243	95.63 77	88.18 225	93.47 176	84.89 215	93.23 71	69.54 268	87.16 228	97.96 69	60.66 265	91.90 178	89.90 190	87.99 238	83.84 228

thres100view900		86.46 222	86.00 228	86.99 217	92.28 193	91.03 197	91.09 227	84.49 221	80.90 231	80.89 239	78.25 259	82.25 236	77.57 236	90.17 204	92.84 138	95.63 133	86.57 220

gm-plane-assit		86.15 223	82.51 238	90.40 158	95.81 72	92.29 171	97.99 36	84.66 218	92.15 100	93.15 64	97.84 37	44.65 281	78.60 223	88.02 225	85.95 223	92.20 222	76.69 258

CMPMVS	66.55 18	85.55 224	87.46 218	83.32 238	84.99 259	81.97 253	79.19 271	75.93 253	79.32 240	88.82 165	85.09 242	91.07 201	82.12 201	92.56 162	89.63 196	88.84 236	92.56 127
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CR-MVSNet		85.32 225	81.58 240	89.69 171	90.36 227	84.79 244	86.72 260	92.22 65	75.38 256	90.73 119	90.41 193	67.88 263	84.86 173	83.76 248	85.74 225	93.24 211	83.14 231

baseline2		84.95 226	82.68 237	87.59 212	92.64 181	88.41 224	90.09 233	84.25 223	75.88 254	85.23 198	82.49 252	71.15 256	80.14 215	88.21 223	87.21 219	93.21 214	85.39 224

pmnet_mix02		84.85 227	86.58 223	82.83 239	90.19 229	81.10 256	88.52 248	78.58 249	91.50 112	80.32 245	96.48 89	95.86 137	75.42 249	85.17 238	76.44 255	83.91 256	79.51 248

MVSTER		84.79 228	83.79 232	85.96 226	89.14 243	89.80 218	89.39 241	82.99 233	74.16 260	82.78 223	85.97 238	66.81 271	76.84 241	90.77 199	88.83 209	94.66 172	90.19 183

MIMVSNet		84.76 229	86.75 221	82.44 241	91.71 203	85.95 237	89.74 239	89.49 139	85.28 203	69.69 267	87.93 221	90.88 204	64.85 263	88.26 222	87.74 214	89.18 234	81.24 238

SCA		84.69 230	81.10 241	88.87 192	89.02 244	90.31 216	92.21 215	92.09 75	82.72 222	89.68 144	86.83 232	73.08 252	85.80 159	80.50 257	77.51 251	84.45 255	76.80 257

new-patchmatchnet		84.45 231	88.75 200	79.43 252	93.28 158	81.87 254	81.68 268	83.48 230	94.47 36	71.53 265	98.33 16	97.88 75	58.61 269	90.35 201	77.33 252	87.99 238	81.05 240

FE-MVSNET3		83.78 232	80.73 244	87.34 215	89.23 239	90.35 212	92.84 200	82.30 236	86.26 193	81.00 235	68.18 268	66.96 266	85.24 166	84.27 241	81.61 237	93.45 199	87.52 207

PatchT		83.44 233	81.10 241	86.18 225	77.92 271	82.58 252	89.87 236	87.39 180	75.88 254	90.73 119	89.86 200	66.71 273	84.86 173	83.76 248	85.74 225	86.33 250	83.14 231

RPMNet		83.42 234	78.40 252	89.28 180	89.79 231	84.79 244	90.64 232	92.11 73	75.38 256	87.10 183	79.80 257	61.99 278	82.79 196	81.88 255	82.07 236	93.23 213	82.87 234

usedtu_blend_shiyan5		83.28 235	80.64 245	86.37 223	89.23 239	90.35 212	87.00 258	82.30 236	86.26 193	81.00 235	68.18 268	66.96 266	85.24 166	84.27 241	81.61 237	93.45 199	86.85 214

TAMVS		82.96 236	86.15 226	79.24 255	90.57 225	83.12 251	87.29 254	75.12 256	84.06 211	65.81 269	92.22 172	88.27 223	69.11 258	88.72 217	87.26 218	87.56 246	79.38 250

PatchmatchNet		82.44 237	78.69 251	86.83 219	89.81 230	81.55 255	90.78 230	87.27 183	82.39 225	88.85 164	88.31 217	70.96 257	81.90 203	78.58 261	74.33 264	82.35 261	74.69 261
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13		82.33 238	79.66 246	85.45 228	88.83 246	83.88 246	90.09 233	81.98 242	79.07 244	88.82 165	88.70 211	73.77 251	78.41 229	80.29 259	76.08 256	84.56 253	75.83 259

CostFormer		82.15 239	79.54 247	85.20 229	88.92 245	85.70 238	90.87 229	86.26 200	79.19 243	83.87 218	87.89 223	69.20 261	76.62 243	77.50 264	75.28 259	84.69 252	82.02 236

dtuonly		82.04 240	83.24 236	80.64 248	86.49 258	76.95 261	90.09 233	69.99 263	82.43 224	81.66 232	91.23 179	91.26 199	75.79 247	83.81 247	79.65 245	79.82 264	77.38 255

PMMVS		81.93 241	83.48 234	80.12 251	72.35 274	75.05 266	88.54 247	64.01 265	77.02 253	82.22 228	87.51 225	91.12 200	79.70 218	86.59 230	86.64 220	93.88 190	80.41 243

pmmvs3		81.69 242	83.83 231	79.19 256	78.33 270	78.57 259	89.53 240	58.71 268	78.88 247	84.34 213	88.36 216	91.96 191	77.69 235	87.48 226	82.42 234	86.54 249	79.18 251

tpm		81.58 243	78.84 249	84.79 232	91.11 216	79.50 257	89.79 238	83.75 226	79.30 241	92.05 88	90.98 181	64.78 275	74.54 251	80.50 257	76.67 253	77.49 267	80.15 246

test0.0.03 1		81.51 244	83.30 235	79.42 253	93.99 125	86.50 234	85.93 264	87.32 181	78.16 249	61.62 270	80.78 255	81.78 240	59.87 266	88.40 221	87.27 217	87.78 242	80.19 245

dps		81.42 245	77.88 257	85.56 227	87.67 254	85.17 242	88.37 250	87.46 178	74.37 259	84.55 210	86.80 233	62.18 277	80.20 214	81.13 256	77.52 250	85.10 251	77.98 254

test-LLR		80.62 246	77.20 260	84.62 234	93.99 125	75.11 264	87.04 256	87.32 181	70.11 264	78.59 252	83.17 249	71.60 254	73.88 253	82.32 252	79.20 247	86.91 247	78.87 252

blend_shiyan4		80.12 247	77.11 262	83.63 237	78.60 269	89.75 219	83.59 267	79.95 247	64.53 270	81.00 235	68.18 268	66.96 266	85.24 166	82.23 254	81.29 242	93.38 208	86.85 214

tpm cat1		80.03 248	75.93 264	84.81 231	89.31 236	83.26 250	88.86 246	86.55 198	79.24 242	86.10 190	84.22 245	63.62 276	77.37 238	73.43 268	70.88 267	80.67 262	76.87 256

N_pmnet		79.33 249	84.22 230	73.62 262	91.72 202	73.72 267	86.11 262	76.36 252	92.38 92	53.38 273	95.54 115	95.62 143	59.14 267	84.23 245	74.84 263	75.02 271	73.25 265

EPMVS		79.26 250	78.20 255	80.49 249	87.04 257	78.86 258	86.08 263	83.51 229	82.63 223	73.94 260	89.59 202	68.67 262	72.03 256	78.17 262	75.08 261	80.37 263	74.37 262

CHOSEN 280x420		79.24 251	78.26 254	80.38 250	79.60 268	68.80 273	89.32 242	75.38 254	77.25 252	78.02 254	75.57 261	76.17 249	81.19 210	88.61 220	81.39 241	78.79 265	80.03 247

ADS-MVSNet		79.11 252	79.38 248	78.80 258	81.90 264	75.59 263	84.36 266	83.69 227	87.31 177	76.76 256	87.58 224	76.90 247	68.55 260	78.70 260	75.56 258	77.53 266	74.07 263

FMVSNet5		79.08 253	78.83 250	79.38 254	87.52 255	86.78 232	87.64 252	78.15 250	69.54 266	70.64 266	65.97 272	65.44 274	63.87 264	90.17 204	90.46 183	88.48 237	83.45 230

0.4-1-1-0.1		78.93 254	75.69 265	82.71 240	82.54 262	86.31 235	88.34 251	74.63 257	67.88 267	81.41 234	73.65 263	67.37 264	79.03 220	75.97 265	76.53 254	90.33 228	82.09 235

tpmrst		78.81 255	76.18 263	81.87 245	88.56 247	77.45 260	86.74 259	81.52 244	80.08 235	83.48 220	90.84 185	66.88 270	74.54 251	73.04 269	71.02 266	76.38 268	73.95 264

test-mter		78.71 256	78.35 253	79.12 257	84.03 260	76.58 262	88.51 249	59.06 267	71.06 262	78.87 248	83.73 248	71.83 253	76.44 245	83.41 251	80.61 243	87.79 241	81.24 238

MVS-HIRNet		78.28 257	75.28 266	81.79 246	80.33 267	69.38 272	76.83 272	86.59 196	70.76 263	86.66 187	89.57 203	81.04 243	77.74 234	77.81 263	71.65 265	82.62 259	66.73 270

0.3-1-1-0.015		77.85 258	74.34 268	81.96 244	81.59 265	85.29 239	87.54 253	73.36 258	66.50 268	81.00 235	70.68 266	66.96 266	78.53 227	74.61 267	75.58 257	89.73 231	80.73 241

E-PMN		77.81 259	77.88 257	77.73 261	88.26 250	70.48 271	80.19 270	71.20 261	86.66 188	72.89 263	88.09 220	81.74 241	78.75 222	90.02 206	68.30 268	75.10 269	59.85 271

0.4-1-1-0.2		77.70 260	74.35 267	81.60 247	81.26 266	84.89 243	87.05 255	72.99 259	65.96 269	80.75 241	72.00 264	67.32 265	78.19 231	74.64 266	75.15 260	89.36 232	80.50 242

EMVS		77.65 261	77.49 259	77.83 259	87.75 253	71.02 270	81.13 269	70.54 262	86.38 192	74.52 259	89.38 205	80.19 246	78.22 230	89.48 211	67.13 269	74.83 272	58.84 272

TESTMET0.1,1		77.47 262	77.20 260	77.78 260	81.94 263	75.11 264	87.04 256	58.33 269	70.11 264	78.59 252	83.17 249	71.60 254	73.88 253	82.32 252	79.20 247	86.91 247	78.87 252

new_pmnet		76.65 263	83.52 233	68.63 263	82.60 261	72.08 268	76.76 273	64.17 264	84.41 210	49.73 275	91.77 175	91.53 196	56.16 270	86.59 230	83.26 231	82.37 260	75.02 260

MVE	60.41 19	73.21 264	80.84 243	64.30 264	56.34 275	57.24 275	75.28 275	72.76 260	87.14 182	41.39 277	86.31 236	85.30 233	80.66 211	86.17 234	83.36 230	59.35 274	80.38 244
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		69.86 265	82.14 239	55.52 265	75.19 272	63.08 274	75.52 274	60.97 266	88.50 165	25.11 279	91.77 175	96.44 121	25.43 274	88.70 218	79.34 246	70.93 273	67.17 269

GG-mvs-BLEND		54.28 266	77.89 256	26.72 268	0.37 284	83.31 249	70.04 276	0.39 278	74.71 258	5.36 281	68.78 267	83.06 235	0.62 280	83.73 250	78.99 249	83.55 258	72.68 268

test_method		43.16 267	51.13 269	33.85 266	7.35 279	12.38 280	51.70 278	11.91 272	62.51 272	47.64 276	62.49 273	80.78 244	28.84 271	59.55 272	34.48 272	55.68 275	45.72 274

VLMVS_CLIP		30.30 268	36.13 271	23.51 269	54.32 276	31.52 277	8.97 280	27.94 270	31.32 275	8.68 280	37.87 276	39.37 282	28.52 272	37.60 274	32.88 273	12.63 278	42.36 275

MVS_clip		27.15 269	40.54 270	11.53 270	22.06 278	19.49 278	6.62 282	6.19 274	39.03 274	1.66 284	50.77 274	48.60 280	25.91 273	38.89 273	35.93 271	6.77 279	51.09 273

MVS_baseline		7.97 270	13.11 272	1.98 272	2.61 281	1.13 283	0.40 286	0.00 279	13.03 276	0.00 286	14.70 277	17.39 284	8.80 276	5.37 276	6.00 274	0.05 283	34.14 276

VLMVS		6.39 271	8.96 273	3.39 271	6.72 280	4.83 281	1.89 283	1.88 275	9.81 277	1.97 283	8.48 278	12.35 285	5.85 277	6.19 275	5.45 275	2.01 280	15.59 277

testmvs		2.38 272	3.35 274	1.26 274	0.83 282	0.96 284	1.53 284	0.83 276	3.59 278	1.63 285	6.03 279	2.93 286	1.55 279	3.49 277	2.51 277	1.21 282	3.92 279

test123		2.16 273	2.82 275	1.41 273	0.62 283	1.18 282	1.53 284	0.82 277	2.78 279	2.27 282	4.18 280	1.98 287	1.64 278	2.58 278	3.01 276	1.56 281	4.00 278

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

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

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

ACM-MVS					94.83 100	93.67 138	93.96 162		85.15 205	90.16 138	86.10 237	89.98 211	80.09 216			94.35 182	94.99 72

PatchmatchNet2					90.67 224	71.56 269	85.25 265
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												95.63 142	59.14 267	83.89 246	74.87 262	75.05 270	73.16 266
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										53.40 272	95.51 116
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							98.20 28	91.80 87		87.87 177						96.59 95

TPM-MVS					94.35 114	93.52 152	92.94 194			89.43 150	84.20 246	90.07 208	80.21 213			94.56 177	93.77 97
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												93.19 185

SR-MVS					97.13 24			94.77 17				97.77 80

Anonymous202405211			94.63 84		94.51 112	94.96 102	93.94 163	91.35 95	90.82 133		95.60 110	95.85 138	81.74 207	96.47 78	95.84 76	97.39 67	92.85 116

our_test_3					91.78 200	88.87 223	94.37 146

ambc			94.61 85		98.09 4	95.14 93	91.71 223		94.18 47	96.46 12	96.26 92	96.30 124	91.26 71	94.70 117	92.00 154	93.45 199	93.67 100

MTAPA										94.88 28		96.88 110

MTMP										95.43 18		97.25 98

Patchmatch-RL test							8.96 281

tmp_tt				28.44 267	36.05 277	15.86 279	21.29 279	6.40 273	54.52 273	51.96 274	50.37 275	38.68 283	9.55 275	61.75 271	59.66 270	45.36 277

XVS					96.86 33	97.48 19	98.73 3			93.28 58		96.82 112				98.17 35

X-MVStestdata					96.86 33	97.48 19	98.73 3			93.28 58		96.82 112				98.17 35

mPP-MVS					98.24 2							97.65 87

NP-MVS									85.48 202

Patchmtry						83.74 247	86.72 260	92.22 65		90.73 119

DeepMVS_CX						47.68 276	53.20 277	19.21 271	63.24 271	26.96 278	66.50 271	69.82 260	66.91 262	64.27 270		54.91 276	72.72 267

High-resolution multi-view benchmark