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 35	98.30 20	94.90 15	98.61 1	97.73 3	97.97 24	98.57 22	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 66	98.10 2	99.08 2	93.92 31	98.24 3	96.44 13	98.12 19	97.86 52	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 14	94.46 32	99.14 1	98.92 10	94.57 15	99.06 3	98.80 2	99.32 1	96.92 26

SixPastTwentyTwo		97.36 4	97.73 10	96.92 2	97.36 13	96.15 55	98.29 21	94.43 23	96.50 12	96.96 7	98.74 5	98.74 17	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 30	97.02 2	94.71 26	95.32 21	98.52 12	98.97 9	92.91 42	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 24	94.93 26	98.66 7	99.16 5	92.27 52	98.98 6	98.39 7	98.49 19	96.83 30

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 19	95.15 24	98.66 7	98.80 15	92.77 46	98.97 7	98.27 9	98.44 23	96.28 40

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 86	97.53 7	96.01 15	98.14 18	98.76 16	95.28 5	98.76 11	98.23 10	98.77 5	96.67 34
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 32	93.71 52	98.55 10	98.89 11	92.97 39	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 33	96.98 3	93.50 46	95.21 23	97.98 23	98.44 25	92.83 45	98.93 8	98.37 8	98.46 22	96.91 27

DVP-MVS++		96.63 11	97.92 5	95.12 40	97.77 6	97.52 15	98.29 21	93.83 34	96.72 9	92.52 75	98.10 20	99.07 8	90.87 78	97.83 31	97.44 28	97.44 59	98.76 1

ACMH	90.17 8	96.61 12	97.69 12	95.35 30	95.29 81	96.94 35	98.43 14	92.05 74	98.04 4	95.38 19	98.07 21	99.25 4	93.23 33	98.35 16	97.16 39	97.72 51	96.00 45
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UA-Net		96.56 13	96.73 24	96.36 9	98.99 1	97.90 7	97.79 43	95.64 10	92.78 59	92.54 74	96.23 71	95.02 128	94.31 18	98.43 15	98.12 11	98.89 3	98.58 3

ACMMPR		96.54 14	96.71 25	96.35 10	97.55 9	97.63 11	98.62 9	94.54 19	94.45 29	94.19 39	95.04 95	97.35 66	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 76	96.04 57	97.93 38	92.49 58	96.40 13	97.13 6	98.99 2	99.41 3	93.79 25	97.84 30	96.15 65	97.00 81	95.60 53

DeepC-MVS	92.47 4	96.44 16	96.75 23	96.08 16	97.57 7	97.19 31	97.96 37	94.28 24	95.29 20	94.92 27	98.31 17	96.92 77	93.69 27	96.81 67	96.50 56	98.06 40	96.27 41
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 32	96.19 14	97.21 20	97.16 33	98.71 5	93.79 37	94.35 33	93.81 46	92.80 130	98.23 33	95.11 6	98.07 20	97.45 27	98.51 18	96.86 29
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 84	97.18 32	97.97 36	92.52 56	96.72 9	90.50 122	97.31 45	99.11 6	94.10 19	98.67 12	97.90 14	98.56 15	95.79 49

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 27	89.80 130	97.73 32	98.13 37	93.84 24	97.79 33	97.63 18	97.87 47	97.08 21

CP-MVS		96.21 20	96.16 43	96.27 12	97.56 8	97.13 34	98.43 14	94.70 18	92.62 62	94.13 41	92.71 131	98.03 43	94.54 16	98.00 24	97.60 20	98.23 31	97.05 22

HFP-MVS		96.18 21	96.53 29	95.77 20	97.34 16	97.26 28	98.16 31	94.54 19	94.45 29	92.52 75	95.05 93	96.95 76	93.89 22	97.28 49	97.46 26	98.19 33	97.25 11

UniMVSNet_ETH3D		96.15 22	97.71 11	94.33 55	97.31 17	96.71 40	95.06 107	96.91 4	97.86 5	90.42 123	98.55 10	99.60 1	88.01 117	98.51 13	97.81 15	98.26 29	94.95 65

MP-MVS		96.13 23	95.93 47	96.37 8	98.19 3	97.31 27	98.49 13	94.53 22	91.39 94	94.38 35	94.32 108	96.43 90	94.59 14	97.75 35	97.44 28	98.04 41	96.88 28
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ACMMP		96.12 24	96.27 39	95.93 18	97.20 21	97.60 12	98.64 7	93.74 38	92.47 66	93.13 66	93.23 123	98.06 40	94.51 17	97.99 25	97.57 22	98.39 27	96.99 23
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 16	97.90 39	93.60 43	95.47 17	89.57 136	97.32 44	97.72 55	93.89 22	97.74 36	97.53 23	97.51 56	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 36	95.87 19	96.72 38	97.35 26	98.43 14	93.83 34	90.81 108	92.67 73	95.05 93	98.86 13	95.01 7	98.11 18	97.37 35	98.52 17	96.50 36

CSCG		96.07 27	97.15 19	94.81 47	96.06 61	97.58 13	96.52 73	90.98 97	96.51 11	93.60 54	97.13 52	98.55 23	93.01 37	97.17 53	95.36 80	98.68 9	97.78 4

DPE-MVS		96.00 28	96.80 22	95.06 42	95.87 69	97.47 21	98.25 25	93.73 39	92.38 68	91.57 103	97.55 39	97.97 45	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 30	95.41 29	97.43 11	97.36 24	97.55 48	93.70 40	94.05 40	93.79 47	97.02 55	94.53 133	92.28 51	97.53 45	97.19 37	97.73 50	97.67 7
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
TSAR-MVS + MP.		95.99 29	96.57 28	95.31 32	96.87 30	96.50 47	98.71 5	91.58 87	93.25 51	92.71 70	96.86 57	96.57 88	93.92 20	98.09 19	97.91 13	98.08 38	96.81 31
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 27	95.23 35	96.67 40	96.52 46	97.86 41	93.28 47	95.27 22	93.46 56	96.26 68	98.85 14	92.89 43	97.09 54	96.37 60	97.22 73	95.78 50
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SteuartSystems-ACMMP		95.96 31	96.13 44	95.76 21	97.06 26	97.36 24	98.40 18	94.24 26	91.49 88	91.91 93	94.50 104	96.89 78	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 37	95.59 23	96.58 43	97.23 30	98.26 24	93.22 48	92.33 71	92.31 83	94.29 109	98.73 18	94.68 12	98.04 21	97.14 40	98.47 21	96.17 43
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PGM-MVS		95.90 34	95.72 51	96.10 15	97.53 10	97.45 22	98.55 12	94.12 28	90.25 111	93.71 52	93.20 124	97.18 70	94.63 13	97.68 39	97.34 36	98.08 38	96.97 24

PMVS	87.16 16	95.88 35	96.47 31	95.19 37	97.00 28	96.02 58	96.70 64	91.57 88	94.43 31	95.33 20	97.16 51	95.37 116	92.39 48	98.89 10	98.72 3	98.17 35	94.71 71
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ACMMP_NAP		95.86 36	96.18 40	95.47 28	97.11 24	97.26 28	98.37 19	93.48 45	93.49 47	93.99 44	95.61 79	94.11 137	92.49 47	97.87 27	97.44 28	97.40 62	97.52 8

Gipuma		95.86 36	96.17 41	95.50 27	95.92 65	94.59 104	94.77 116	92.50 57	97.82 6	97.90 2	95.56 82	97.88 50	94.71 11	98.02 22	94.81 94	97.23 72	94.48 78
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LS3D		95.83 38	96.35 34	95.22 36	96.47 47	97.49 16	97.99 34	92.35 61	94.92 25	94.58 30	94.88 99	95.11 126	91.52 63	98.48 14	98.05 12	98.42 25	95.49 54

SD-MVS		95.77 39	96.17 41	95.30 33	96.72 38	96.19 54	97.01 56	93.04 49	94.03 41	92.71 70	96.45 66	96.78 85	93.91 21	96.79 68	95.89 71	98.42 25	97.09 20
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
SED-MVS		95.73 40	96.98 20	94.28 56	96.08 59	97.39 23	98.18 29	93.80 36	94.20 35	89.61 135	97.29 46	97.49 63	90.69 82	97.74 36	97.41 32	97.32 67	97.34 9

TranMVSNet+NR-MVSNet		95.72 41	96.42 32	94.91 46	96.21 55	96.77 39	96.90 61	94.99 13	92.62 62	91.92 92	98.51 13	98.63 20	90.82 79	97.27 50	96.83 45	98.63 12	94.31 79

DU-MVS		95.51 42	95.68 52	95.33 31	96.45 48	96.44 49	96.61 70	95.32 11	89.97 116	93.78 48	97.46 41	98.07 39	91.19 70	97.03 57	96.53 53	98.61 13	94.22 80

UniMVSNet (Re)		95.46 43	95.86 49	95.00 45	96.09 57	96.60 41	96.68 68	94.99 13	90.36 110	92.13 86	97.64 36	98.13 37	91.38 64	96.90 62	96.74 47	98.73 6	94.63 74

RPSCF		95.46 43	96.95 21	93.73 79	95.72 73	95.94 62	95.58 98	88.08 143	95.31 18	91.34 106	96.26 68	98.04 42	93.63 28	98.28 17	97.67 17	98.01 42	97.13 18

anonymousdsp		95.45 45	96.70 26	93.99 67	88.43 200	92.05 149	99.18 1	85.42 177	94.29 34	96.10 14	98.63 9	99.08 7	96.11 1	97.77 34	97.41 32	98.70 8	97.69 6

APD-MVS		95.38 46	95.68 52	95.03 43	97.30 18	96.90 37	97.83 42	93.92 31	89.40 123	90.35 124	95.41 86	97.69 57	92.97 39	97.24 52	97.17 38	97.83 48	95.96 46
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
UniMVSNet_NR-MVSNet		95.34 47	95.51 56	95.14 39	95.80 71	96.55 42	96.61 70	94.79 16	90.04 115	93.78 48	97.51 40	97.25 67	91.19 70	96.68 70	96.31 62	98.65 11	94.22 80

X-MVS		95.33 48	95.13 64	95.57 25	97.35 14	97.48 18	98.43 14	94.28 24	92.30 72	93.28 59	86.89 186	96.82 81	91.87 57	97.85 28	97.59 21	98.19 33	96.95 25

MSP-MVS		95.32 49	96.28 37	94.19 59	96.87 30	97.77 10	98.27 23	93.88 33	94.15 39	89.63 134	95.36 87	98.37 28	90.73 80	94.37 114	97.53 23	95.77 120	96.40 37
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 50	95.16 62	95.29 34	96.17 56	96.55 42	97.64 45	94.02 30	94.16 38	94.29 37	92.09 137	93.71 142	91.90 55	96.68 70	96.51 54	97.70 53	96.40 37

HPM-MVS++		95.21 51	94.89 67	95.59 23	97.79 5	95.39 80	97.68 44	94.05 29	91.91 80	94.35 36	93.38 121	95.07 127	92.94 41	96.01 82	95.88 72	96.73 84	96.61 35

TSAR-MVS + ACMM		95.17 52	95.95 45	94.26 57	96.07 60	96.46 48	95.67 96	94.21 27	93.84 43	90.99 114	97.18 49	95.24 124	93.55 29	96.60 73	95.61 78	95.06 138	96.69 33

CPTT-MVS		95.00 53	94.52 76	95.57 25	96.84 34	96.78 38	97.88 40	93.67 42	92.20 73	92.35 82	85.87 193	97.56 62	94.98 9	96.96 60	96.07 68	97.70 53	96.18 42

SF-MVS		94.88 54	95.87 48	93.73 79	95.30 79	95.93 63	94.80 115	91.76 84	93.11 55	91.93 91	95.83 76	97.07 73	91.11 73	96.62 72	96.44 58	97.46 57	96.13 44

Baseline_NR-MVSNet		94.85 55	95.35 60	94.26 57	96.45 48	93.86 120	96.70 64	94.54 19	90.07 114	90.17 128	98.77 4	97.89 47	90.64 85	97.03 57	96.16 64	97.04 80	93.67 92

EG-PatchMatch MVS		94.81 56	95.53 55	93.97 68	95.89 68	94.62 102	95.55 100	88.18 141	92.77 60	94.88 28	97.04 54	98.61 21	93.31 30	96.89 63	95.19 84	95.99 113	93.56 95

CS-MVS		94.76 57	94.41 80	95.18 38	94.95 90	95.99 60	97.28 49	91.99 76	85.51 156	94.55 31	93.07 126	97.69 57	93.77 26	97.08 55	96.79 46	98.53 16	94.72 69

OMC-MVS		94.74 58	95.46 58	93.91 71	94.62 102	96.26 52	96.64 69	89.36 130	94.20 35	94.15 40	94.02 114	97.73 54	91.34 66	96.15 80	95.04 88	97.37 64	94.80 67

DeepC-MVS_fast	91.38 6	94.73 59	94.98 65	94.44 51	96.83 36	96.12 56	96.69 66	92.17 67	92.98 57	93.72 50	94.14 110	95.45 114	90.49 91	95.73 88	95.30 81	96.71 85	95.13 63
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 60	94.84 69	94.44 51	94.95 90	96.55 42	96.46 76	91.10 95	88.96 126	96.00 16	94.55 103	95.32 119	90.67 83	96.97 59	96.69 51	97.44 59	94.84 66

CS-MVS-test		94.63 61	94.30 85	95.02 44	94.63 100	95.71 70	98.15 32	92.13 69	85.62 155	94.22 38	93.63 119	97.63 61	93.08 36	97.50 46	96.51 54	97.88 46	93.50 96

pmmvs6		94.58 62	97.30 15	91.40 122	94.84 94	94.61 103	93.40 147	92.43 60	98.51 2	85.61 162	98.73 6	99.53 2	84.40 142	97.88 26	97.03 41	97.72 51	94.79 68

DeepPCF-MVS	90.68 7	94.56 63	94.92 66	94.15 60	94.11 114	95.71 70	97.03 55	90.65 102	93.39 50	94.08 42	95.29 90	94.15 136	93.21 34	95.22 99	94.92 92	95.82 119	95.75 51

NR-MVSNet		94.55 64	95.66 54	93.25 91	94.26 110	96.44 49	96.69 66	95.32 11	89.97 116	91.79 98	97.46 41	98.39 27	82.85 152	96.87 65	96.48 57	98.57 14	93.98 86

Vis-MVSNet		94.39 65	95.85 50	92.68 99	90.91 183	95.88 65	97.62 47	91.41 89	91.95 79	89.20 138	97.29 46	96.26 93	90.60 90	96.95 61	95.91 69	96.32 100	96.71 32
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TSAR-MVS + GP.		94.25 66	94.81 71	93.60 81	96.52 46	95.80 68	94.37 125	92.47 59	90.89 104	88.92 140	95.34 88	94.38 134	92.85 44	96.36 78	95.62 77	96.47 92	95.28 60

CNVR-MVS		94.24 67	94.47 77	93.96 69	96.56 44	95.67 72	96.43 77	91.95 78	92.08 76	91.28 108	90.51 147	95.35 117	91.20 69	96.34 79	95.50 79	96.34 98	95.88 48

DROMVSNet		94.23 68	93.81 99	94.71 50	94.85 93	96.23 53	97.14 51	93.40 46	81.79 179	91.58 102	93.29 122	95.21 125	93.13 35	97.73 38	96.95 42	98.20 32	95.45 55

v1192		93.98 69	93.94 93	94.01 65	93.91 122	94.63 101	97.00 57	89.75 120	91.01 102	96.50 10	97.93 25	98.26 32	91.74 59	92.06 146	92.05 136	95.18 133	91.66 134

v10		93.96 70	94.12 90	93.77 78	93.37 135	95.45 76	96.83 63	91.13 94	89.70 120	95.02 25	97.88 28	98.23 33	91.27 67	92.39 141	92.18 133	94.99 140	93.00 105

CDPH-MVS		93.96 70	93.86 95	94.08 62	96.31 52	95.84 66	96.92 59	91.85 81	87.21 142	91.25 110	92.83 128	96.06 101	91.05 75	95.57 90	94.81 94	97.12 75	94.72 69

MVS_0304		93.92 72	93.81 99	94.05 64	96.06 61	96.00 59	96.43 77	92.76 54	85.99 153	94.43 34	94.04 113	97.08 72	88.12 116	94.65 110	94.20 108	96.47 92	94.71 71

MSLP-MVS++		93.91 73	94.30 85	93.45 83	95.51 77	95.83 67	93.12 153	91.93 80	91.45 91	91.40 105	87.42 181	96.12 100	93.27 31	96.57 74	96.40 59	95.49 123	96.29 39

v1921920		93.90 74	93.82 97	94.00 66	93.74 127	94.31 108	97.12 52	89.33 131	91.13 99	96.77 9	97.90 26	98.06 40	91.95 54	91.93 150	91.54 145	95.10 136	91.85 128

train_agg		93.89 75	93.46 110	94.40 53	97.35 14	93.78 122	97.63 46	92.19 66	88.12 133	90.52 121	93.57 120	95.78 107	92.31 50	94.78 107	93.46 119	96.36 96	94.70 73

v144192		93.89 75	93.85 96	93.94 70	93.50 132	94.33 107	97.12 52	89.49 125	90.89 104	96.49 11	97.78 30	98.27 31	91.89 56	92.17 145	91.70 142	95.19 132	91.78 131

v1240		93.89 75	93.72 101	94.09 61	93.98 119	94.31 108	97.12 52	89.37 129	90.74 109	96.92 8	98.05 22	97.89 47	92.15 53	91.53 156	91.60 143	94.99 140	91.93 126

NCCC		93.87 78	93.42 111	94.40 53	96.84 34	95.42 77	96.47 75	92.62 55	92.36 70	92.05 88	83.83 200	95.55 110	91.84 58	95.89 84	95.23 83	96.56 89	95.63 52

v1144		93.83 79	93.87 94	93.78 77	93.72 128	94.57 105	96.85 62	89.98 114	91.31 96	95.90 17	97.89 27	98.40 26	91.13 72	92.01 149	92.01 137	95.10 136	90.94 139

MVS_111021_HR		93.82 80	94.26 88	93.31 86	95.01 88	93.97 118	95.73 93	89.75 120	92.06 77	92.49 77	94.01 115	96.05 102	90.61 89	95.95 83	94.78 97	96.28 101	93.04 104

thisisatest0515		93.79 81	94.41 80	93.06 96	94.14 111	92.50 141	95.56 99	88.55 138	91.61 84	92.45 78	96.84 58	95.71 108	90.62 87	94.58 111	95.07 86	97.05 78	94.58 75

TAPA-MVS	88.94 13	93.78 82	94.31 84	93.18 93	94.14 111	95.99 60	95.74 92	86.98 160	93.43 49	93.88 45	90.16 154	96.88 79	91.05 75	94.33 115	93.95 110	97.28 70	95.40 56
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		93.72 83	93.62 105	93.84 72	94.75 97	94.90 95	97.24 50	91.81 83	86.97 146	92.74 69	93.83 117	97.24 69	90.46 92	95.10 103	94.09 109	96.08 110	93.18 102

EPP-MVSNet		93.63 84	93.95 92	93.26 89	95.15 85	96.54 45	96.18 85	91.97 77	91.74 81	85.76 160	94.95 97	84.27 186	91.60 62	97.61 43	97.38 34	98.87 4	95.18 62

v8		93.60 85	93.82 97	93.34 84	93.13 142	95.06 88	96.39 79	90.75 100	89.90 118	94.03 43	97.70 34	98.21 35	91.08 74	92.36 142	91.47 146	94.63 148	92.07 122

MCST-MVS		93.60 85	93.40 113	93.83 73	95.30 79	95.40 79	96.49 74	90.87 98	90.08 113	91.72 99	90.28 152	95.99 103	91.69 60	93.94 124	92.99 124	96.93 82	95.13 63

PVSNet_Blended_VisFu		93.60 85	93.41 112	93.83 73	96.31 52	95.65 73	95.71 94	90.58 104	88.08 135	93.17 64	95.29 90	92.20 151	90.72 81	94.69 109	93.41 121	96.51 91	94.54 76

TransMVSNet (Re)		93.55 88	96.32 35	90.32 138	94.38 107	94.05 113	93.30 150	89.53 124	97.15 8	85.12 165	98.83 3	97.89 47	82.21 158	96.75 69	96.14 66	97.35 65	93.46 97

DCV-MVSNet		93.49 89	95.15 63	91.55 116	94.05 115	95.92 64	95.15 105	91.21 91	92.76 61	87.01 156	89.71 158	97.16 71	83.90 147	97.65 40	96.87 44	97.99 43	95.95 47

v2v482		93.42 90	93.49 109	93.32 85	93.44 134	94.05 113	96.36 82	89.76 119	91.41 93	95.24 22	97.63 37	98.34 29	90.44 93	91.65 154	91.76 141	94.69 145	89.62 151

canonicalmvs		93.38 91	94.36 82	92.24 105	93.94 121	96.41 51	94.18 134	90.47 105	93.07 56	88.47 146	88.66 168	93.78 141	88.80 106	95.74 87	95.75 75	97.57 55	97.13 18

3Dnovator	91.81 5	93.36 92	94.27 87	92.29 104	92.99 146	95.03 89	95.76 91	87.79 146	93.82 44	92.38 81	92.19 136	93.37 146	88.14 115	95.26 98	94.85 93	96.69 86	95.40 56

pm-mvs1		93.27 93	95.94 46	90.16 139	94.13 113	93.66 123	92.61 163	89.91 116	95.73 16	84.28 174	98.51 13	98.29 30	82.80 153	96.44 76	95.76 74	97.25 71	93.21 101

casdiffmvs_mvg		93.27 93	94.83 70	91.45 120	93.59 130	94.47 106	94.91 111	89.83 118	92.04 78	87.14 154	97.57 38	98.47 24	86.03 132	94.07 122	94.44 104	97.21 74	92.76 111
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 95	94.43 78	91.88 110	95.09 87	94.97 93	94.58 121	92.81 51	93.60 45	83.79 177	97.17 50	89.25 171	87.59 119	97.54 44	96.57 52	97.42 61	91.89 127

Anonymous20231211		93.19 96	95.50 57	90.49 135	93.77 126	95.29 82	94.36 129	90.04 113	91.44 92	84.59 169	96.72 61	97.65 59	82.45 157	97.25 51	96.32 61	97.74 49	93.79 89

TinyColmap		93.17 97	93.33 114	93.00 97	93.84 124	92.76 136	94.75 118	88.90 134	93.97 42	97.48 4	95.28 92	95.29 120	88.37 111	95.31 97	91.58 144	94.65 147	89.10 155

MVS_111021_LR		93.15 98	93.65 103	92.56 100	93.89 123	92.28 144	95.09 106	86.92 162	91.26 98	92.99 68	94.46 106	96.22 96	90.64 85	95.11 102	93.45 120	95.85 117	92.74 112

CNLPA		93.14 99	93.67 102	92.53 101	94.62 102	94.73 98	95.00 110	86.57 167	92.85 58	92.43 79	90.94 142	94.67 130	90.35 94	95.41 92	93.70 116	96.23 104	93.37 99

PLC	87.27 15	93.08 100	92.92 118	93.26 89	94.67 98	95.03 89	94.38 124	90.10 108	91.69 82	92.14 85	87.24 182	93.91 139	91.61 61	95.05 104	94.73 100	96.67 87	92.80 108
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CANet		93.07 101	93.05 117	93.10 94	95.90 66	95.41 78	95.88 88	91.94 79	84.77 162	93.36 57	94.05 112	95.25 123	86.25 130	94.33 115	93.94 111	95.30 126	93.58 94

TSAR-MVS + COLMAP		93.06 102	93.65 103	92.36 102	94.62 102	94.28 110	95.36 104	89.46 127	92.18 74	91.64 100	95.55 83	95.27 122	88.60 109	93.24 130	92.50 129	94.46 150	92.55 118

ECVR-MVS		93.05 103	94.25 89	91.65 113	94.76 95	95.23 83	94.26 132	92.80 52	92.49 64	83.90 175	96.75 60	89.99 163	86.84 124	97.62 41	96.72 48	97.32 67	90.92 140

Effi-MVS+		92.93 104	92.16 129	93.83 73	94.29 108	93.53 130	95.04 108	92.98 50	85.27 159	94.46 32	90.24 153	95.34 118	89.99 97	93.72 125	94.23 107	96.22 105	92.79 109

Fast-Effi-MVS+		92.93 104	92.64 122	93.27 88	93.81 125	93.88 119	95.90 87	90.61 103	83.98 168	92.71 70	92.81 129	96.22 96	90.67 83	94.90 106	93.92 112	95.92 115	92.77 110

HQP-MVS		92.87 106	92.49 123	93.31 86	95.75 72	95.01 92	95.64 97	91.06 96	88.54 130	91.62 101	88.16 173	96.25 94	89.47 101	92.26 144	91.81 139	96.34 98	95.40 56

FMVSNet1		92.86 107	95.26 61	90.06 141	92.40 160	95.16 85	94.37 125	92.22 63	93.18 54	82.16 187	96.76 59	97.48 64	81.85 162	95.32 94	94.98 89	97.34 66	93.93 87

CLD-MVS		92.81 108	94.32 83	91.05 126	95.39 78	95.31 81	95.82 90	81.44 200	89.40 123	91.94 90	95.86 74	97.36 65	85.83 133	95.35 93	94.59 102	95.85 117	92.34 119
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
IS_MVSNet		92.76 109	93.25 115	92.19 106	94.91 92	95.56 74	95.86 89	92.12 70	88.10 134	82.71 182	93.15 125	88.30 174	88.86 105	97.29 48	96.95 42	98.66 10	93.38 98

FC-MVSNet-train		92.75 110	95.40 59	89.66 149	95.21 83	94.82 96	97.00 57	89.40 128	91.13 99	81.71 188	97.72 33	96.43 90	77.57 185	96.89 63	96.72 48	97.05 78	94.09 83

V42		92.67 111	93.50 108	91.71 112	91.41 174	92.96 134	95.71 94	85.00 178	89.67 121	93.22 62	97.67 35	98.01 44	91.02 77	92.65 137	92.12 134	93.86 158	91.42 135

PM-MVS		92.65 112	93.20 116	92.00 108	92.11 168	90.16 170	95.99 86	84.81 182	91.31 96	92.41 80	95.87 73	96.64 87	92.35 49	93.65 127	92.91 125	94.34 153	91.85 128

QAPM		92.57 113	93.51 107	91.47 119	92.91 148	94.82 96	93.01 155	87.51 150	91.49 88	91.21 111	92.24 134	91.70 154	88.74 107	94.54 112	94.39 106	95.41 124	95.37 59

MIMVSNet1		92.52 114	94.88 68	89.77 145	96.09 57	91.99 150	96.92 59	89.68 122	95.92 15	84.55 170	96.64 63	98.21 35	78.44 179	96.08 81	95.10 85	92.91 172	90.22 148

tfpnnormal		92.45 115	94.77 72	89.74 146	93.95 120	93.44 132	93.25 151	88.49 140	95.27 22	83.20 180	96.51 64	96.23 95	83.17 151	95.47 91	94.52 103	96.38 95	91.97 125

PCF-MVS	87.46 14	92.44 116	91.80 131	93.19 92	94.66 99	95.80 68	96.37 80	90.19 107	87.57 139	92.23 84	89.26 163	93.97 138	89.24 102	91.32 158	90.82 154	96.46 94	93.86 88
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		92.42 117	93.99 91	90.60 133	93.25 138	93.82 121	94.28 131	88.73 136	91.53 86	84.53 172	97.74 31	98.64 19	86.60 127	93.21 132	91.20 149	96.21 106	91.76 133
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
AdaColmap		92.41 118	91.49 135	93.48 82	95.96 64	95.02 91	95.37 103	91.73 85	87.97 137	91.28 108	82.82 204	91.04 158	90.62 87	95.82 86	95.07 86	95.95 114	92.67 113

v148		92.38 119	92.78 120	91.91 109	92.86 149	92.13 147	94.84 113	87.03 159	91.47 90	93.07 67	96.92 56	98.89 11	90.10 96	92.05 147	89.69 162	93.56 161	88.27 164

pmmvs-eth3d		92.34 120	92.33 124	92.34 103	92.67 153	90.67 164	96.37 80	89.06 132	90.98 103	93.60 54	97.13 52	97.02 75	88.29 112	90.20 165	91.42 147	94.07 156	88.89 159

DELS-MVS		92.33 121	93.61 106	90.83 129	92.84 150	95.13 87	94.76 117	87.22 158	87.78 138	88.42 148	95.78 77	95.28 121	85.71 136	94.44 113	93.91 113	96.01 112	92.97 106
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		92.32 122	91.66 133	93.09 95	95.13 86	94.73 98	94.57 122	92.14 68	81.74 180	90.33 125	88.13 174	95.91 104	89.24 102	94.23 120	93.65 118	97.12 75	93.23 100

UGNet		92.31 123	94.70 73	89.53 151	90.99 182	95.53 75	96.19 84	92.10 72	91.35 95	85.76 160	95.31 89	95.48 113	76.84 190	95.22 99	94.79 96	95.32 125	95.19 61
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
USDC		92.17 124	92.17 128	92.18 107	92.93 147	92.22 145	93.66 141	87.41 153	93.49 47	97.99 1	94.10 111	96.68 86	86.46 128	92.04 148	89.18 168	94.61 149	87.47 167

ETV-MVS		92.12 125	90.44 143	94.08 62	96.36 50	93.63 125	96.27 83	92.00 75	78.90 199	92.13 86	85.29 195	89.85 165	90.26 95	97.07 56	96.29 63	97.46 57	92.04 123

IterMVS-LS		92.10 126	92.33 124	91.82 111	93.18 139	93.66 123	92.80 161	92.27 62	90.82 106	90.59 120	97.19 48	90.97 159	87.76 118	89.60 172	90.94 153	94.34 153	93.16 103
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		92.09 127	92.84 119	91.22 125	92.55 155	92.97 133	93.42 146	85.43 176	90.24 112	91.83 95	94.70 100	94.59 131	88.48 110	94.91 105	93.31 123	95.59 122	89.15 154

EIA-MVS		91.95 128	90.36 145	93.81 76	96.54 45	94.65 100	95.38 102	90.40 106	78.01 204	93.72 50	86.70 189	91.95 153	89.93 98	95.67 89	94.72 101	96.89 83	90.79 142

MAR-MVS		91.86 129	91.14 139	92.71 98	94.29 108	94.24 111	94.91 111	91.82 82	81.66 181	93.32 58	84.51 198	93.42 145	86.86 123	95.16 101	94.44 104	95.05 139	94.53 77
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
EU-MVSNet		91.63 130	92.73 121	90.35 137	88.36 201	87.89 181	96.53 72	81.51 199	92.45 67	91.82 96	96.44 67	97.05 74	93.26 32	94.10 121	88.94 173	90.61 179	92.24 120

FC-MVSNet-test		91.49 131	94.43 78	88.07 167	94.97 89	90.53 167	95.42 101	91.18 93	93.24 52	72.94 209	98.37 15	93.86 140	78.78 173	97.82 32	96.13 67	95.13 134	91.05 137

FA-MVS(training)		91.38 132	91.18 138	91.62 115	93.49 133	92.38 142	95.03 109	90.81 99	87.20 143	91.46 104	93.00 127	89.47 168	84.19 144	93.20 134	92.08 135	94.74 144	90.90 141

OpenMVS	89.22 12	91.09 133	91.42 136	90.71 131	92.79 152	93.61 127	92.74 162	85.47 175	86.10 152	90.73 115	85.71 194	93.07 149	86.69 126	94.07 122	93.34 122	95.86 116	94.02 85

FPMVS		90.81 134	91.60 134	89.88 144	92.52 156	88.18 177	93.31 149	83.62 188	91.59 85	88.45 147	88.96 166	89.73 167	86.96 121	96.42 77	95.69 76	94.43 151	90.65 143

DI_MVS_plusplus_trai		90.68 135	90.40 144	91.00 127	92.43 159	92.61 140	94.17 135	88.98 133	88.32 132	88.76 144	93.67 118	87.58 176	86.44 129	89.74 170	90.33 157	95.24 129	90.56 146

Vis-MVSNet (Re-imp)		90.68 135	92.18 127	88.92 156	94.63 100	92.75 137	92.91 157	91.20 92	89.21 125	75.01 206	93.96 116	89.07 172	82.72 155	95.88 85	95.30 81	97.08 77	89.08 156

DPM-MVS		90.67 137	89.86 149	91.63 114	95.29 81	94.16 112	94.52 123	89.63 123	89.59 122	89.67 133	81.95 206	88.64 173	85.75 135	90.46 163	90.43 156	94.91 142	93.77 90

diffmvs		90.44 138	92.23 126	88.35 163	91.36 176	91.38 156	92.45 167	84.84 181	89.88 119	85.09 166	96.69 62	97.71 56	83.33 150	90.01 169	88.96 172	93.03 170	91.00 138
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		90.28 139	92.04 130	88.23 165	91.22 178	94.05 113	92.88 158	90.69 101	86.53 149	79.89 195	94.38 107	92.73 150	78.54 176	91.64 155	92.26 132	96.17 107	92.67 113

IterMVS-SCA-FT		90.24 140	89.37 155	91.26 124	92.50 157	92.11 148	91.69 177	87.48 151	87.05 145	91.82 96	95.76 78	87.25 177	91.36 65	89.02 177	85.53 188	92.68 173	88.90 158

MVS_Test		90.19 141	90.58 140	89.74 146	92.12 167	91.74 152	92.51 164	88.54 139	82.80 174	87.50 152	94.62 101	95.02 128	83.97 145	88.69 180	89.32 166	93.79 159	91.85 128

EPNet		90.17 142	89.07 157	91.45 120	97.25 19	90.62 166	94.84 113	93.54 44	80.96 183	91.85 94	86.98 185	85.88 182	77.79 182	92.30 143	92.58 128	93.41 163	94.20 82
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		90.09 143	90.12 147	90.05 142	92.40 160	92.74 138	91.74 173	85.89 171	80.54 186	90.30 126	88.54 169	95.51 111	84.69 140	92.64 138	90.25 158	95.28 127	90.61 144

PVSNet_Blended		90.09 143	90.12 147	90.05 142	92.40 160	92.74 138	91.74 173	85.89 171	80.54 186	90.30 126	88.54 169	95.51 111	84.69 140	92.64 138	90.25 158	95.28 127	90.61 144

pmmvs4		89.95 145	89.32 156	90.69 132	91.60 173	89.17 174	94.37 125	87.63 147	88.07 136	91.02 113	94.50 104	90.50 162	86.13 131	86.33 194	89.40 165	93.39 164	87.29 170

MDA-MVSNet-bldmvs		89.75 146	91.67 132	87.50 172	74.25 219	90.88 161	94.68 119	85.89 171	91.64 83	91.03 112	95.86 74	94.35 135	89.10 104	96.87 65	86.37 184	90.04 180	85.72 175

tttt0517		89.64 147	88.05 168	91.49 118	93.52 131	91.65 153	93.67 140	87.53 148	82.77 175	89.39 137	90.37 151	70.05 211	88.21 113	93.71 126	93.79 114	96.63 88	94.04 84

PatchMatch-RL		89.59 148	88.80 161	90.51 134	92.20 166	88.00 180	91.72 175	86.64 164	84.75 163	88.25 149	87.10 184	90.66 161	89.85 100	93.23 131	92.28 131	94.41 152	85.60 176

Fast-Effi-MVS+-dtu		89.57 149	88.42 165	90.92 128	93.35 136	91.57 154	93.01 155	95.71 9	78.94 198	87.65 151	84.68 197	93.14 148	82.00 160	90.84 161	91.01 152	93.78 160	88.77 160

thisisatest0530		89.54 150	87.99 170	91.35 123	93.17 140	91.31 157	93.45 145	87.53 148	82.96 173	89.17 139	90.45 148	70.32 210	88.21 113	93.37 129	93.79 114	96.54 90	93.71 91

test2506		89.51 151	87.77 173	91.55 116	94.76 95	95.23 83	94.26 132	92.80 52	92.49 64	83.31 179	89.97 156	50.93 225	86.84 124	97.62 41	96.72 48	97.32 67	91.42 135

GBi-Net		89.35 152	90.58 140	87.91 168	91.22 178	94.05 113	92.88 158	90.05 110	79.40 190	78.60 197	90.58 144	87.05 178	78.54 176	95.32 94	94.98 89	96.17 107	92.67 113

test1		89.35 152	90.58 140	87.91 168	91.22 178	94.05 113	92.88 158	90.05 110	79.40 190	78.60 197	90.58 144	87.05 178	78.54 176	95.32 94	94.98 89	96.17 107	92.67 113

thres600view7		89.14 154	88.83 159	89.51 152	93.71 129	93.55 128	93.93 138	88.02 144	87.30 141	82.40 183	81.18 207	80.63 197	82.69 156	94.27 117	95.90 70	96.27 102	88.94 157

CVMVSNet		88.97 155	89.73 151	88.10 166	87.33 207	85.22 190	94.68 119	78.68 201	88.94 127	86.98 157	95.55 83	85.71 183	89.87 99	91.19 159	89.69 162	91.05 177	91.78 131

CANet_DTU		88.95 156	89.51 154	88.29 164	93.12 143	91.22 159	93.61 142	83.47 191	80.07 189	90.71 119	89.19 164	93.68 143	76.27 194	91.44 157	91.17 151	92.59 174	89.83 150

GA-MVS		88.76 157	88.04 169	89.59 150	92.32 163	91.46 155	92.28 169	86.62 165	83.82 170	89.84 129	92.51 133	81.94 191	83.53 149	89.41 174	89.27 167	92.95 171	87.90 165

pmmvs5		88.63 158	89.70 152	87.39 173	89.24 194	90.64 165	91.87 172	82.13 195	83.34 171	87.86 150	94.58 102	96.15 99	79.87 170	87.33 189	89.07 171	93.39 164	86.76 171

thres400		88.54 159	88.15 167	88.98 154	93.17 140	92.84 135	93.56 143	86.93 161	86.45 150	82.37 184	79.96 209	81.46 194	81.83 163	93.21 132	94.76 98	96.04 111	88.39 162

CDS-MVSNet		88.41 160	89.79 150	86.79 177	94.55 105	90.82 162	92.50 165	89.85 117	83.26 172	80.52 192	91.05 140	89.93 164	69.11 205	93.17 135	92.71 127	94.21 155	87.63 166
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gg-mvs-nofinetune		88.32 161	88.81 160	87.75 170	93.07 144	89.37 173	89.06 196	95.94 8	95.29 20	87.15 153	97.38 43	76.38 200	68.05 208	91.04 160	89.10 170	93.24 166	83.10 184

IterMVS		88.32 161	88.25 166	88.41 162	90.83 184	91.24 158	93.07 154	81.69 197	86.77 147	88.55 145	95.61 79	86.91 181	87.01 120	87.38 188	83.77 190	89.29 182	86.06 174
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres200		88.29 163	87.88 171	88.76 158	92.50 157	93.55 128	92.47 166	88.02 144	84.80 161	81.44 189	79.28 211	82.20 190	81.83 163	94.27 117	93.67 117	96.27 102	87.40 168

IB-MVS	86.01 17	88.24 164	87.63 174	88.94 155	92.03 169	91.77 151	92.40 168	85.58 174	78.24 201	84.85 167	71.99 215	93.45 144	83.96 146	93.48 128	92.33 130	94.84 143	92.15 121
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		88.22 165	87.85 172	88.65 160	91.40 175	86.75 185	94.07 136	84.97 179	88.86 129	93.20 63	96.11 72	96.21 98	83.70 148	87.29 190	80.29 197	84.56 200	79.46 197

test20.03		88.20 166	91.26 137	84.63 189	96.64 42	89.39 172	90.73 184	89.97 115	91.07 101	72.02 211	94.98 96	95.45 114	69.35 204	92.70 136	91.19 150	89.06 184	84.02 178

HyFIR lowres test		88.19 167	86.56 181	90.09 140	91.24 177	92.17 146	94.30 130	88.79 135	84.06 165	85.45 163	89.52 161	85.64 184	88.64 108	85.40 197	87.28 178	92.14 176	81.87 187

ET-MVSNet_ETH3D		88.06 168	85.75 185	90.74 130	92.82 151	90.68 163	93.77 139	88.59 137	81.22 182	89.78 131	89.15 165	66.79 218	84.29 143	91.72 153	91.34 148	95.22 130	89.36 153

tfpn200view9		87.94 169	87.51 176	88.44 161	92.28 164	93.63 125	93.35 148	88.11 142	80.90 184	80.89 190	78.25 212	82.25 188	79.65 172	94.27 117	94.76 98	96.36 96	88.48 161

FMVSNet3		87.90 170	88.63 163	87.04 174	89.78 192	93.46 131	91.62 178	90.05 110	79.40 190	78.60 197	90.58 144	87.05 178	77.07 189	88.03 185	89.86 161	95.12 135	92.04 123

MS-PatchMatch		87.72 171	88.62 164	86.66 178	90.81 185	88.18 177	90.92 181	82.25 194	85.86 154	80.40 193	90.14 155	89.29 170	84.93 137	89.39 175	89.12 169	90.67 178	88.34 163

Anonymous20231206		87.45 172	89.66 153	84.87 186	94.00 116	87.73 183	91.36 179	86.41 169	88.89 128	75.03 205	92.59 132	96.82 81	72.48 202	89.72 171	88.06 175	89.93 181	83.81 180

EPNet_dtu		87.40 173	86.27 182	88.72 159	95.68 74	83.37 196	92.09 171	90.08 109	78.11 203	91.29 107	86.33 190	89.74 166	75.39 197	89.07 176	87.89 176	87.81 189	89.38 152
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
baseline1		86.96 174	87.58 175	86.24 180	93.07 144	90.44 168	89.24 195	86.85 163	85.14 160	77.26 203	90.45 148	76.09 202	75.79 195	91.80 152	91.81 139	95.20 131	87.35 169

baseline		86.71 175	88.89 158	84.16 191	87.85 203	85.23 189	89.82 189	77.69 204	84.03 167	84.75 168	94.91 98	94.59 131	77.19 188	86.57 193	86.51 183	87.66 192	90.36 147

CHOSEN 1792x2688		86.64 176	86.62 179	86.65 179	90.33 188	87.86 182	93.19 152	83.30 192	83.95 169	82.32 185	87.93 176	89.34 169	86.92 122	85.64 196	84.95 189	83.85 204	86.68 172

testgi		86.49 177	90.31 146	82.03 195	95.63 75	88.18 177	93.47 144	84.89 180	93.23 53	69.54 215	87.16 183	97.96 46	60.66 212	91.90 151	89.90 160	87.99 187	83.84 179

thres100view900		86.46 178	86.00 184	86.99 175	92.28 164	91.03 160	91.09 180	84.49 184	80.90 184	80.89 190	78.25 212	82.25 188	77.57 185	90.17 166	92.84 126	95.63 121	86.57 173

gm-plane-assit		86.15 179	82.51 193	90.40 136	95.81 70	92.29 143	97.99 34	84.66 183	92.15 75	93.15 65	97.84 29	44.65 226	78.60 175	88.02 186	85.95 185	92.20 175	76.69 205

CMPMVS	66.55 18	85.55 180	87.46 177	83.32 192	84.99 209	81.97 201	79.19 216	75.93 206	79.32 193	88.82 142	85.09 196	91.07 157	82.12 159	92.56 140	89.63 164	88.84 185	92.56 117
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CR-MVSNet		85.32 181	81.58 195	89.69 148	90.36 187	84.79 192	86.72 207	92.22 63	75.38 209	90.73 115	90.41 150	67.88 215	84.86 138	83.76 200	85.74 186	93.24 166	83.14 182

baseline2		84.95 182	82.68 192	87.59 171	92.64 154	88.41 176	90.09 186	84.25 185	75.88 207	85.23 164	82.49 205	71.15 208	80.14 169	88.21 184	87.21 181	93.21 169	85.39 177

pmnet_mix02		84.85 183	86.58 180	82.83 193	90.19 189	81.10 204	88.52 199	78.58 202	91.50 87	80.32 194	96.48 65	95.86 105	75.42 196	85.17 198	76.44 206	83.91 203	79.51 196

MVSTER		84.79 184	83.79 188	85.96 182	89.14 195	89.80 171	89.39 193	82.99 193	74.16 213	82.78 181	85.97 192	66.81 217	76.84 190	90.77 162	88.83 174	94.66 146	90.19 149

MIMVSNet		84.76 185	86.75 178	82.44 194	91.71 172	85.95 187	89.74 191	89.49 125	85.28 158	69.69 214	87.93 176	90.88 160	64.85 210	88.26 183	87.74 177	89.18 183	81.24 188

SCA		84.69 186	81.10 196	88.87 157	89.02 196	90.31 169	92.21 170	92.09 73	82.72 176	89.68 132	86.83 187	73.08 204	85.80 134	80.50 208	77.51 203	84.45 202	76.80 204

new-patchmatchnet		84.45 187	88.75 162	79.43 201	93.28 137	81.87 202	81.68 213	83.48 190	94.47 28	71.53 212	98.33 16	97.88 50	58.61 215	90.35 164	77.33 204	87.99 187	81.05 190

PatchT		83.44 188	81.10 196	86.18 181	77.92 217	82.58 200	89.87 188	87.39 154	75.88 207	90.73 115	89.86 157	66.71 219	84.86 138	83.76 200	85.74 186	86.33 197	83.14 182

RPMNet		83.42 189	78.40 205	89.28 153	89.79 191	84.79 192	90.64 185	92.11 71	75.38 209	87.10 155	79.80 210	61.99 224	82.79 154	81.88 206	82.07 194	93.23 168	82.87 185

TAMVS		82.96 190	86.15 183	79.24 204	90.57 186	83.12 199	87.29 203	75.12 208	84.06 165	65.81 216	92.22 135	88.27 175	69.11 205	88.72 178	87.26 180	87.56 193	79.38 198

PatchmatchNet		82.44 191	78.69 204	86.83 176	89.81 190	81.55 203	90.78 183	87.27 157	82.39 178	88.85 141	88.31 172	70.96 209	81.90 161	78.58 212	74.33 212	82.35 208	74.69 208
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13		82.33 192	79.66 199	85.45 184	88.83 198	83.88 194	90.09 186	81.98 196	79.07 197	88.82 142	88.70 167	73.77 203	78.41 180	80.29 210	76.08 207	84.56 200	75.83 206

CostFormer		82.15 193	79.54 200	85.20 185	88.92 197	85.70 188	90.87 182	86.26 170	79.19 196	83.87 176	87.89 178	69.20 213	76.62 192	77.50 215	75.28 209	84.69 199	82.02 186

PMMVS		81.93 194	83.48 190	80.12 200	72.35 220	75.05 213	88.54 198	64.01 213	77.02 206	82.22 186	87.51 180	91.12 156	79.70 171	86.59 191	86.64 182	93.88 157	80.41 191

pmmvs3		81.69 195	83.83 187	79.19 205	78.33 216	78.57 207	89.53 192	58.71 216	78.88 200	84.34 173	88.36 171	91.96 152	77.69 184	87.48 187	82.42 193	86.54 196	79.18 199

tpm		81.58 196	78.84 202	84.79 188	91.11 181	79.50 205	89.79 190	83.75 186	79.30 194	92.05 88	90.98 141	64.78 221	74.54 198	80.50 208	76.67 205	77.49 213	80.15 194

test0.0.03 1		81.51 197	83.30 191	79.42 202	93.99 117	86.50 186	85.93 211	87.32 155	78.16 202	61.62 217	80.78 208	81.78 192	59.87 213	88.40 182	87.27 179	87.78 191	80.19 193

dps		81.42 198	77.88 210	85.56 183	87.67 205	85.17 191	88.37 201	87.46 152	74.37 212	84.55 170	86.80 188	62.18 223	80.20 168	81.13 207	77.52 202	85.10 198	77.98 202

test-LLR		80.62 199	77.20 213	84.62 190	93.99 117	75.11 211	87.04 204	87.32 155	70.11 216	78.59 200	83.17 202	71.60 206	73.88 200	82.32 204	79.20 199	86.91 194	78.87 200

tpm cat1		80.03 200	75.93 216	84.81 187	89.31 193	83.26 198	88.86 197	86.55 168	79.24 195	86.10 159	84.22 199	63.62 222	77.37 187	73.43 216	70.88 215	80.67 209	76.87 203

N_pmnet		79.33 201	84.22 186	73.62 211	91.72 171	73.72 214	86.11 209	76.36 205	92.38 68	53.38 218	95.54 85	95.62 109	59.14 214	84.23 199	74.84 211	75.03 216	73.25 212

EPMVS		79.26 202	78.20 208	80.49 198	87.04 208	78.86 206	86.08 210	83.51 189	82.63 177	73.94 208	89.59 159	68.67 214	72.03 203	78.17 213	75.08 210	80.37 210	74.37 209

CHOSEN 280x420		79.24 203	78.26 207	80.38 199	79.60 215	68.80 219	89.32 194	75.38 207	77.25 205	78.02 202	75.57 214	76.17 201	81.19 166	88.61 181	81.39 195	78.79 211	80.03 195

ADS-MVSNet		79.11 204	79.38 201	78.80 207	81.90 213	75.59 210	84.36 212	83.69 187	87.31 140	76.76 204	87.58 179	76.90 199	68.55 207	78.70 211	75.56 208	77.53 212	74.07 210

FMVSNet5		79.08 205	78.83 203	79.38 203	87.52 206	86.78 184	87.64 202	78.15 203	69.54 218	70.64 213	65.97 218	65.44 220	63.87 211	90.17 166	90.46 155	88.48 186	83.45 181

tpmrst		78.81 206	76.18 215	81.87 196	88.56 199	77.45 208	86.74 206	81.52 198	80.08 188	83.48 178	90.84 143	66.88 216	74.54 198	73.04 217	71.02 214	76.38 214	73.95 211

test-mter		78.71 207	78.35 206	79.12 206	84.03 210	76.58 209	88.51 200	59.06 215	71.06 214	78.87 196	83.73 201	71.83 205	76.44 193	83.41 203	80.61 196	87.79 190	81.24 188

MVS-HIRNet		78.28 208	75.28 217	81.79 197	80.33 214	69.38 218	76.83 217	86.59 166	70.76 215	86.66 158	89.57 160	81.04 195	77.74 183	77.81 214	71.65 213	82.62 206	66.73 216

E-PMN		77.81 209	77.88 210	77.73 210	88.26 202	70.48 217	80.19 215	71.20 210	86.66 148	72.89 210	88.09 175	81.74 193	78.75 174	90.02 168	68.30 216	75.10 215	59.85 217

EMVS		77.65 210	77.49 212	77.83 208	87.75 204	71.02 216	81.13 214	70.54 211	86.38 151	74.52 207	89.38 162	80.19 198	78.22 181	89.48 173	67.13 217	74.83 217	58.84 218

TESTMET0.1,1		77.47 211	77.20 213	77.78 209	81.94 212	75.11 211	87.04 204	58.33 217	70.11 216	78.59 200	83.17 202	71.60 206	73.88 200	82.32 204	79.20 199	86.91 194	78.87 200

new_pmnet		76.65 212	83.52 189	68.63 212	82.60 211	72.08 215	76.76 218	64.17 212	84.41 164	49.73 220	91.77 138	91.53 155	56.16 216	86.59 191	83.26 192	82.37 207	75.02 207

MVE	60.41 19	73.21 213	80.84 198	64.30 213	56.34 221	57.24 221	75.28 220	72.76 209	87.14 144	41.39 222	86.31 191	85.30 185	80.66 167	86.17 195	83.36 191	59.35 219	80.38 192
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		69.86 214	82.14 194	55.52 214	75.19 218	63.08 220	75.52 219	60.97 214	88.50 131	25.11 224	91.77 138	96.44 89	25.43 218	88.70 179	79.34 198	70.93 218	67.17 215

GG-mvs-BLEND		54.28 215	77.89 209	26.72 217	0.37 226	83.31 197	70.04 221	0.39 223	74.71 211	5.36 225	68.78 216	83.06 187	0.62 222	83.73 202	78.99 201	83.55 205	72.68 214

test_method		43.16 216	51.13 218	33.85 215	7.35 223	12.38 224	51.70 223	11.91 219	62.51 220	47.64 221	62.49 219	80.78 196	28.84 217	59.55 220	34.48 219	55.68 220	45.72 219

testmvs		2.38 217	3.35 219	1.26 219	0.83 224	0.96 226	1.53 226	0.83 221	3.59 222	1.63 227	6.03 221	2.93 228	1.55 221	3.49 221	2.51 221	1.21 224	3.92 221

test123		2.16 218	2.82 220	1.41 218	0.62 225	1.18 225	1.53 226	0.82 222	2.78 223	2.27 226	4.18 222	1.98 229	1.64 220	2.58 222	3.01 220	1.56 223	4.00 220

uanet_test		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 230	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

sosnet-low-res		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 230	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

sosnet		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 230	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

RE-MVS-def										97.21 5

9.14												93.19 147

SR-MVS					97.13 23			94.77 17				97.77 53

Anonymous202405211			94.63 74		94.51 106	94.96 94	93.94 137	91.35 90	90.82 106		95.60 81	95.85 106	81.74 165	96.47 75	95.84 73	97.39 63	92.85 107

our_test_3					91.78 170	88.87 175	94.37 125

ambc			94.61 75		98.09 4	95.14 86	91.71 176		94.18 37	96.46 12	96.26 68	96.30 92	91.26 68	94.70 108	92.00 138	93.45 162	93.67 92

MTAPA										94.88 28		96.88 79

MTMP										95.43 18		97.25 67

Patchmatch-RL test							8.96 225

tmp_tt				28.44 216	36.05 222	15.86 223	21.29 224	6.40 220	54.52 221	51.96 219	50.37 220	38.68 227	9.55 219	61.75 219	59.66 218	45.36 222

XVS					96.86 32	97.48 18	98.73 3			93.28 59		96.82 81				98.17 35

X-MVStestdata					96.86 32	97.48 18	98.73 3			93.28 59		96.82 81				98.17 35

mPP-MVS					98.24 2							97.65 59

NP-MVS									85.48 157

Patchmtry						83.74 195	86.72 207	92.22 63		90.73 115

DeepMVS_CX						47.68 222	53.20 222	19.21 218	63.24 219	26.96 223	66.50 217	69.82 212	66.91 209	64.27 218		54.91 221	72.72 213

High-resolution multi-view benchmark