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.

DPE-MVS		88.63 4	91.29 4	85.53 3	90.87 8	92.20 4	91.98 2	76.00 6	90.55 10	82.09 6	93.85 3	90.75 2	81.25 1	88.62 8	87.59 15	90.96 12	95.48 4
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS++		89.14 1	91.86 1	85.97 1	92.55 2	92.38 1	91.69 4	76.31 3	93.31 1	83.11 3	92.44 6	91.18 1	81.17 2	89.55 2	87.93 8	91.01 10	96.21 1

SED-MVS		88.85 2	91.59 3	85.67 2	90.54 15	92.29 3	91.71 3	76.40 2	92.41 3	83.24 2	92.50 5	90.64 4	81.10 3	89.53 3	88.02 7	91.00 11	95.73 3

MED-MVS		88.34 5	91.21 5	85.00 6	90.52 16	91.77 7	91.56 6	75.07 14	92.32 4	80.74 10	94.25 1	90.22 6	80.98 4	88.25 11	87.20 16	91.13 5	94.45 8

MSP-MVS		88.09 7	90.84 6	84.88 9	90.00 25	91.80 6	91.63 5	75.80 7	91.99 5	81.23 8	92.54 4	89.18 8	80.89 5	87.99 17	87.91 9	89.70 49	94.51 7
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
ME-MVS		88.11 6	90.84 6	84.92 8	90.52 16	91.48 9	91.33 7	75.06 15	90.82 8	80.74 10	94.25 1	90.29 5	80.86 6	87.82 18	86.80 24	91.03 7	94.45 8

APDe-MVS		88.00 8	90.50 8	85.08 5	90.95 7	91.58 8	92.03 1	75.53 12	91.15 6	80.10 17	92.27 7	88.34 13	80.80 7	88.00 16	86.99 20	91.09 6	95.16 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS		88.67 3	91.62 2	85.22 4	90.47 18	92.36 2	90.69 12	76.15 4	93.08 2	82.75 4	92.19 8	90.71 3	80.45 8	89.27 6	87.91 9	90.82 15	95.84 2
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
APD-MVS		86.84 14	88.91 16	84.41 12	90.66 11	90.10 15	90.78 10	75.64 9	87.38 18	78.72 21	90.68 12	86.82 19	80.15 9	87.13 27	86.45 31	90.51 24	93.83 16
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		86.88 13	89.23 12	84.14 14	89.78 28	88.67 32	90.59 13	73.46 29	88.99 13	80.52 14	91.26 9	88.65 11	79.91 10	86.96 31	86.22 33	90.59 23	93.83 16
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HPM-MVS++		87.09 11	88.92 15	84.95 7	92.61 1	87.91 42	90.23 18	76.06 5	88.85 14	81.20 9	87.33 15	87.93 14	79.47 11	88.59 9	88.23 5	90.15 38	93.60 22

SF-MVS		87.47 10	89.70 10	84.86 10	91.26 6	91.10 10	90.90 9	75.65 8	89.21 11	81.25 7	91.12 10	88.93 9	78.82 12	87.42 22	86.23 32	91.28 3	93.90 15

CNVR-MVS		86.36 16	88.19 19	84.23 13	91.33 5	89.84 17	90.34 14	75.56 10	87.36 19	78.97 20	81.19 31	86.76 20	78.74 13	89.30 5	88.58 2	90.45 30	94.33 12

SD-MVS		86.96 12	89.45 11	84.05 16	90.13 21	89.23 25	89.77 21	74.59 17	89.17 12	80.70 12	89.93 13	89.67 7	78.47 14	87.57 21	86.79 25	90.67 21	93.76 18
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
MCST-MVS		85.13 24	86.62 26	83.39 19	90.55 14	89.82 19	89.29 24	73.89 25	84.38 32	76.03 33	79.01 34	85.90 23	78.47 14	87.81 19	86.11 35	92.11 1	93.29 24

HFP-MVS		86.15 17	87.95 20	84.06 15	90.80 9	89.20 26	89.62 22	74.26 19	87.52 16	80.63 13	86.82 18	84.19 31	78.22 16	87.58 20	87.19 18	90.81 16	93.13 27

SMA-MVS		87.56 9	90.17 9	84.52 11	91.71 3	90.57 11	90.77 11	75.19 13	90.67 9	80.50 15	86.59 19	88.86 10	78.09 17	89.92 1	89.41 1	90.84 14	95.19 5
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
NCCC		85.34 21	86.59 27	83.88 17	91.48 4	88.88 27	89.79 20	75.54 11	86.67 22	77.94 26	76.55 37	84.99 27	78.07 18	88.04 14	87.68 13	90.46 29	93.31 23

TSAR-MVS + GP.		83.69 32	86.58 28	80.32 38	85.14 56	86.96 46	84.91 53	70.25 44	84.71 30	73.91 40	85.16 23	85.63 24	77.92 19	85.44 45	85.71 38	89.77 45	92.45 29

MSLP-MVS++		82.09 39	82.66 42	81.42 32	87.03 46	87.22 45	85.82 45	70.04 45	80.30 47	78.66 22	68.67 88	81.04 46	77.81 20	85.19 49	84.88 46	89.19 60	91.31 39

ACMMPR		85.52 19	87.53 22	83.17 23	90.13 21	89.27 23	89.30 23	73.97 23	86.89 21	77.14 28	86.09 20	83.18 34	77.74 21	87.42 22	87.20 16	90.77 17	92.63 28

DeepC-MVS_fast	78.24 3	84.27 31	85.50 33	82.85 24	90.46 19	89.24 24	87.83 36	74.24 20	84.88 27	76.23 32	75.26 42	81.05 45	77.62 22	88.02 15	87.62 14	90.69 20	92.41 30
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepC-MVS	78.47 2	84.81 27	86.03 31	83.37 20	89.29 34	90.38 14	88.61 29	76.50 1	86.25 24	77.22 27	75.12 43	80.28 47	77.59 23	88.39 10	88.17 6	91.02 9	93.66 20
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepPCF-MVS	79.04 1	85.30 22	88.93 14	81.06 34	88.77 38	90.48 13	85.46 49	73.08 31	90.97 7	73.77 41	84.81 24	85.95 22	77.43 24	88.22 12	87.73 11	87.85 103	94.34 11

MP-MVS		85.50 20	87.40 23	83.28 21	90.65 12	89.51 22	89.16 26	74.11 21	83.70 36	78.06 25	85.54 22	84.89 30	77.31 25	87.40 24	87.14 19	90.41 32	93.65 21
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
SteuartSystems-ACMMP		85.99 18	88.31 18	83.27 22	90.73 10	89.84 17	90.27 17	74.31 18	84.56 31	75.88 34	87.32 16	85.04 26	77.31 25	89.01 7	88.46 3	91.14 4	93.96 14
Skip Steuart: Steuart Systems R&D Blog.
CP-MVS		84.74 28	86.43 29	82.77 25	89.48 32	88.13 41	88.64 28	73.93 24	84.92 26	76.77 30	81.94 29	83.50 33	77.29 27	86.92 32	86.49 30	90.49 25	93.14 26

3Dnovator+	75.73 4	82.40 37	82.76 41	81.97 30	88.02 41	89.67 20	86.60 41	71.48 39	81.28 46	78.18 24	64.78 115	77.96 54	77.13 28	87.32 25	86.83 23	90.41 32	91.48 38

PGM-MVS		84.42 30	86.29 30	82.23 27	90.04 24	88.82 28	89.23 25	71.74 38	82.82 41	74.61 37	84.41 25	82.09 37	77.03 29	87.13 27	86.73 27	90.73 19	92.06 34

ACMMP_NAP		86.52 15	89.01 13	83.62 18	90.28 20	90.09 16	90.32 16	74.05 22	88.32 15	79.74 18	87.04 17	85.59 25	76.97 30	89.35 4	88.44 4	90.35 34	94.27 13

AdaColmap		79.74 49	78.62 68	81.05 35	89.23 35	86.06 55	84.95 52	71.96 36	79.39 51	75.51 35	63.16 121	68.84 123	76.51 31	83.55 65	82.85 62	88.13 84	86.46 88

CS-MVS		79.22 54	81.11 53	77.01 57	81.36 82	84.03 74	80.35 87	63.25 105	73.43 72	70.37 61	74.10 48	76.03 62	76.40 32	86.32 40	83.95 53	90.34 35	89.93 51

CPTT-MVS		81.77 40	83.10 40	80.21 39	85.93 52	86.45 52	87.72 38	70.98 41	82.54 43	71.53 52	74.23 47	81.49 42	76.31 33	82.85 75	81.87 70	88.79 70	92.26 32

EC-MVSNet		79.44 51	81.35 50	77.22 55	82.95 65	84.67 68	81.31 80	63.65 99	72.47 76	68.75 71	73.15 50	78.33 51	75.99 34	86.06 43	83.96 52	90.67 21	90.79 43

train_agg		84.86 26	87.21 25	82.11 28	90.59 13	85.47 60	89.81 19	73.55 28	83.95 33	73.30 42	89.84 14	87.23 17	75.61 35	86.47 36	85.46 41	89.78 44	92.06 34

ACMMP		83.42 33	85.27 34	81.26 33	88.47 40	88.49 35	88.31 34	72.09 35	83.42 37	72.77 44	82.65 26	78.22 52	75.18 36	86.24 41	85.76 37	90.74 18	92.13 33
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
SPE-MVS-test		78.79 61	80.72 55	76.53 61	81.11 88	83.88 77	79.69 99	63.72 98	73.80 68	69.95 66	75.40 41	76.17 59	74.85 37	84.50 56	82.78 63	89.87 43	88.54 63

MVSMamba_PlusPlus		80.48 43	82.51 44	78.11 51	82.79 67	86.47 51	83.22 60	66.95 70	77.74 53	70.45 60	73.88 49	77.56 55	74.81 38	86.85 33	85.52 39	90.43 31	89.55 57

TSAR-MVS + ACMM		85.10 25	88.81 17	80.77 37	89.55 31	88.53 34	88.59 30	72.55 33	87.39 17	71.90 46	90.95 11	87.55 15	74.57 39	87.08 29	86.54 29	87.47 113	93.67 19

MGCNet		84.63 29	87.25 24	81.59 31	88.58 39	90.50 12	87.82 37	69.16 55	83.82 35	78.46 23	82.32 27	84.97 28	74.56 40	88.16 13	87.72 12	90.94 13	93.24 25

CNLPA		77.20 70	77.54 77	76.80 60	82.63 69	84.31 71	79.77 94	64.64 87	85.17 25	73.18 43	56.37 160	69.81 114	74.53 41	81.12 102	78.69 136	86.04 155	87.29 75

OPM-MVS		79.68 50	79.28 66	80.15 40	87.99 42	86.77 48	88.52 31	72.72 32	64.55 129	67.65 80	67.87 94	74.33 71	74.31 42	86.37 38	85.25 43	89.73 48	89.81 53
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
3Dnovator	73.76 5	79.75 48	80.52 58	78.84 45	84.94 61	87.35 43	84.43 55	65.54 80	78.29 52	73.97 39	63.00 123	75.62 65	74.07 43	85.00 50	85.34 42	90.11 39	89.04 59

CSCG		85.28 23	87.68 21	82.49 26	89.95 26	91.99 5	88.82 27	71.20 40	86.41 23	79.63 19	79.26 32	88.36 12	73.94 44	86.64 34	86.67 28	91.40 2	94.41 10

PLC	68.99 11	75.68 90	75.31 109	76.12 65	82.94 66	81.26 117	79.94 92	66.10 74	77.15 56	66.86 89	59.13 143	68.53 125	73.73 45	80.38 121	79.04 129	87.13 121	81.68 158
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ACMM	72.26 8	78.86 60	78.13 72	79.71 42	86.89 47	83.40 85	86.02 43	70.50 42	75.28 60	71.49 53	63.01 122	69.26 117	73.57 46	84.11 59	83.98 51	89.76 46	87.84 68
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETV-MVS		77.32 69	78.81 67	75.58 73	82.24 75	83.64 83	79.98 90	64.02 95	69.64 95	63.90 107	70.89 64	69.94 113	73.41 47	85.39 48	83.91 54	89.92 41	88.31 64

OMC-MVS		80.26 44	82.59 43	77.54 53	83.04 64	85.54 59	83.25 59	65.05 85	87.32 20	72.42 45	72.04 57	78.97 49	73.30 48	83.86 60	81.60 75	88.15 83	88.83 61

MVS_111021_HR		80.13 45	81.46 49	78.58 47	85.77 53	85.17 64	83.45 58	69.28 52	74.08 66	70.31 62	74.31 46	75.26 66	73.13 49	86.46 37	85.15 44	89.53 51	89.81 53

PHI-MVS		82.36 38	85.89 32	78.24 49	86.40 50	89.52 21	85.52 47	69.52 51	82.38 44	65.67 92	81.35 30	82.36 36	73.07 50	87.31 26	86.76 26	89.24 56	91.56 37

DPM-MVS		83.30 34	84.33 37	82.11 28	89.56 30	88.49 35	90.33 15	73.24 30	83.85 34	76.46 31	72.43 55	82.65 35	73.02 51	86.37 38	86.91 21	90.03 40	89.62 55

CANet		81.62 41	83.41 38	79.53 43	87.06 45	88.59 33	85.47 48	67.96 61	76.59 57	74.05 38	74.69 44	81.98 38	72.98 52	86.14 42	85.47 40	89.68 50	90.42 48

QAPM		78.47 63	80.22 61	76.43 62	85.03 58	86.75 49	80.62 86	66.00 76	73.77 69	65.35 96	65.54 111	78.02 53	72.69 53	83.71 62	83.36 59	88.87 67	90.41 49

MVS_111021_LR		78.13 65	79.85 64	76.13 64	81.12 87	81.50 112	80.28 89	65.25 83	76.09 58	71.32 54	76.49 38	72.87 83	72.21 54	82.79 76	81.29 78	86.59 140	87.91 67

MAR-MVS		79.21 55	80.32 60	77.92 52	87.46 43	88.15 40	83.95 56	67.48 67	74.28 63	68.25 74	64.70 116	77.04 56	72.17 55	85.42 46	85.00 45	88.22 80	87.62 72
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
ET-MVSNet_ETH3D		72.46 119	74.19 116	70.44 123	62.50 236	81.17 118	79.90 93	62.46 137	64.52 130	57.52 132	71.49 61	59.15 162	72.08 56	78.61 153	81.11 80	88.16 82	83.29 144

ACMP	73.23 7	79.79 47	80.53 57	78.94 44	85.61 54	85.68 58	85.61 46	69.59 49	77.33 55	71.00 56	74.45 45	69.16 118	71.88 57	83.15 71	83.37 58	89.92 41	90.57 47
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TAPA-MVS	71.42 9	77.69 67	80.05 62	74.94 84	80.68 101	84.52 70	81.36 79	63.14 114	84.77 28	64.82 100	68.72 86	75.91 63	71.86 58	81.62 84	79.55 117	87.80 105	85.24 121
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CDPH-MVS		82.64 36	85.03 36	79.86 41	89.41 33	88.31 38	88.32 33	71.84 37	80.11 48	67.47 81	82.09 28	81.44 43	71.85 59	85.89 44	86.15 34	90.24 36	91.25 40

Casviewmamba		78.51 62	79.92 63	76.87 59	82.72 68	85.98 56	82.91 61	65.64 79	75.65 59	69.03 70	70.43 70	74.36 70	71.80 60	83.70 63	81.55 76	89.10 63	87.78 69

PCF-MVS	73.28 6	79.42 52	80.41 59	78.26 48	84.88 62	88.17 39	86.08 42	69.85 46	75.23 61	68.43 73	68.03 93	78.38 50	71.76 61	81.26 98	80.65 95	88.56 74	91.18 41
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
X-MVS		83.23 35	85.20 35	80.92 36	89.71 29	88.68 29	88.21 35	73.60 26	82.57 42	71.81 49	77.07 35	81.92 39	71.72 62	86.98 30	86.86 22	90.47 26	92.36 31

viewdifsd2359ckpt09		77.36 68	78.39 71	76.16 63	79.98 111	85.78 57	82.78 62	65.29 82	70.87 86	68.68 72	68.99 80	70.81 106	71.70 63	82.68 77	81.86 71	88.56 74	87.71 71

HQP-MVS		81.19 42	83.27 39	78.76 46	87.40 44	85.45 61	86.95 39	70.47 43	81.31 45	66.91 87	79.24 33	76.63 57	71.67 64	84.43 57	83.78 55	89.19 60	92.05 36

EIA-MVS		75.64 92	76.60 101	74.53 90	82.43 72	83.84 78	78.32 119	62.28 139	65.96 117	63.28 111	68.95 81	67.54 130	71.61 65	82.55 78	81.63 74	89.24 56	85.72 104

TSAR-MVS + COLMAP		78.34 64	81.64 48	74.48 92	80.13 110	85.01 65	81.73 75	65.93 78	84.75 29	61.68 113	85.79 21	66.27 136	71.39 66	82.91 74	80.78 86	86.01 156	85.98 92

LGP-MVS_train		79.83 46	81.22 52	78.22 50	86.28 51	85.36 63	86.76 40	69.59 49	77.34 54	65.14 97	75.68 39	70.79 107	71.37 67	84.60 53	84.01 50	90.18 37	90.74 44

TPM-MVS					90.07 23	88.36 37	88.45 32			77.10 29	75.60 40	83.98 32	71.33 68			89.75 47	89.62 55
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
Fast-Effi-MVS+		73.11 113	73.66 121	72.48 102	77.72 132	80.88 124	78.55 114	58.83 187	65.19 123	60.36 118	59.98 137	62.42 148	71.22 69	81.66 83	80.61 97	88.20 81	84.88 129

LS3D		74.08 104	73.39 124	74.88 85	85.05 57	82.62 105	79.71 97	68.66 56	72.82 73	58.80 123	57.61 154	61.31 152	71.07 70	80.32 122	78.87 134	86.00 157	80.18 174

casdiffseed414692147		75.68 90	75.69 108	75.67 71	81.52 79	84.14 73	81.64 77	64.19 94	68.92 98	67.29 84	61.24 127	67.12 132	71.02 71	81.17 99	80.83 85	88.36 76	86.40 89

Effi-MVS+		75.28 95	76.20 104	74.20 93	81.15 86	83.24 88	81.11 81	63.13 115	66.37 113	60.27 119	64.30 119	68.88 122	70.93 72	81.56 86	81.69 73	88.61 72	87.35 73

viewdifsd2359ckpt13		76.26 80	77.31 88	75.03 82	80.14 108	83.77 81	81.58 78	62.80 123	70.34 87	67.83 79	68.06 92	70.93 103	70.20 73	81.46 89	79.88 106	87.63 110	86.71 85

OpenMVS	70.44 10	76.15 86	76.82 96	75.37 80	85.01 59	84.79 66	78.99 109	62.07 141	71.27 82	67.88 78	57.91 153	72.36 85	70.15 74	82.23 82	81.41 77	88.12 85	87.78 69

hybridcas		76.97 71	78.42 70	75.27 81	81.21 84	84.20 72	81.90 71	62.85 121	74.06 67	66.89 88	68.88 82	73.96 73	70.06 75	82.31 81	79.54 118	88.71 71	85.99 91

DELS-MVS		79.15 58	81.07 54	76.91 58	83.54 63	87.31 44	84.45 54	64.92 86	69.98 88	69.34 69	71.62 59	76.26 58	69.84 76	86.57 35	85.90 36	89.39 53	89.88 52
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
E6new		76.06 87	76.54 102	75.51 76	80.71 96	83.10 91	81.74 73	63.03 116	68.89 99	69.71 67	66.73 106	70.84 104	69.76 77	80.88 106	79.61 113	88.11 87	85.72 104

E6		76.06 87	76.54 102	75.51 76	80.71 96	83.10 91	81.74 73	63.03 116	68.89 99	69.71 67	66.73 106	70.84 104	69.76 77	80.88 106	79.61 113	88.11 87	85.72 104

sasdasda		79.16 56	82.37 45	75.41 78	82.33 73	86.38 53	80.80 83	63.18 111	82.90 39	67.34 82	72.79 52	76.07 60	69.62 79	83.46 68	84.41 48	89.20 58	90.60 45

canonicalmvs		79.16 56	82.37 45	75.41 78	82.33 73	86.38 53	80.80 83	63.18 111	82.90 39	67.34 82	72.79 52	76.07 60	69.62 79	83.46 68	84.41 48	89.20 58	90.60 45

E3new		76.51 77	77.22 89	75.69 69	80.74 94	83.07 93	81.99 66	63.23 108	71.18 83	70.52 59	68.77 84	71.75 90	69.61 81	80.73 108	79.18 125	88.03 94	85.85 99

E3		76.51 77	77.21 90	75.69 69	80.74 94	83.06 96	81.98 67	63.22 109	71.17 84	70.55 58	68.77 84	71.76 89	69.61 81	80.73 108	79.18 125	88.03 94	85.84 101

E4		76.24 81	76.77 99	75.61 72	80.69 98	83.05 97	81.98 67	63.25 105	69.47 96	70.06 63	67.40 99	71.46 92	69.59 83	80.73 108	79.37 122	88.10 89	85.95 94

viewcassd2359sk11		76.64 74	77.43 84	75.72 68	80.75 93	83.07 93	81.95 69	63.20 110	72.02 81	70.88 57	69.50 77	72.02 88	69.58 84	80.68 113	78.98 131	87.97 96	85.74 102

E2		76.70 73	77.54 77	75.73 66	80.76 92	83.07 93	81.91 70	63.15 113	72.42 77	71.09 55	70.03 74	72.22 86	69.53 85	80.57 115	78.80 135	87.91 99	85.64 107

viewmanbaseed2359cas		76.36 79	77.87 74	74.60 89	79.81 112	82.88 102	81.69 76	61.02 154	72.14 80	67.97 76	69.61 76	72.45 84	69.53 85	81.53 87	79.83 108	87.57 111	86.65 86

PatchMatch-RL		67.78 168	66.65 189	69.10 140	73.01 183	72.69 212	68.49 210	61.85 144	62.93 143	60.20 120	56.83 159	50.42 232	69.52 87	75.62 184	74.46 195	81.51 212	73.62 229

casdiffmvs		76.76 72	78.46 69	74.77 86	80.32 106	83.73 82	80.65 85	63.24 107	73.58 70	66.11 91	69.39 79	74.09 72	69.49 88	82.52 79	79.35 124	88.84 69	86.52 87
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmacassd2359aftdt		75.85 89	77.01 94	74.49 91	79.69 114	82.87 103	81.77 72	61.06 152	69.37 97	67.26 85	66.73 106	71.63 91	69.48 89	81.51 88	80.20 101	87.69 107	86.77 84

E5new		76.23 82	76.79 97	75.58 73	80.69 98	83.05 97	82.00 64	63.37 102	69.73 91	70.01 64	67.77 96	71.43 95	69.37 90	80.50 116	79.13 127	88.04 91	85.92 95

E5		76.23 82	76.79 97	75.58 73	80.69 98	83.05 97	82.00 64	63.37 102	69.73 91	70.01 64	67.77 96	71.43 95	69.37 90	80.50 116	79.13 127	88.04 91	85.92 95

DI_MVS_pp		75.13 97	76.12 105	73.96 94	78.18 126	81.55 110	80.97 82	62.54 133	68.59 102	65.13 98	61.43 126	74.81 67	69.32 92	81.01 104	79.59 115	87.64 109	85.89 97

casdiffmvs_mvg		77.79 66	79.55 65	75.73 66	81.56 78	84.70 67	82.12 63	64.26 93	74.27 64	67.93 77	70.83 65	74.66 68	69.19 93	83.33 70	81.94 69	89.29 55	87.14 78
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_Test		75.37 93	77.13 92	73.31 97	79.07 120	81.32 115	79.98 90	60.12 169	69.72 93	64.11 106	70.53 69	73.22 78	68.90 94	80.14 129	79.48 120	87.67 108	85.50 114

Effi-MVS+-dtu		71.82 123	71.86 138	71.78 108	78.77 121	80.47 128	78.55 114	61.67 149	60.68 160	55.49 141	58.48 147	65.48 138	68.85 95	76.92 175	75.55 188	87.35 115	85.46 115

ACMH	65.37 14	70.71 134	70.00 149	71.54 109	82.51 71	82.47 106	77.78 123	68.13 58	56.19 192	46.06 209	54.30 174	51.20 228	68.68 96	80.66 114	80.72 88	86.07 151	84.45 135
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	66.54 13	71.36 130	70.09 148	72.85 99	82.59 70	81.13 119	78.56 113	68.04 59	61.55 154	52.52 169	51.50 209	54.14 201	68.56 97	78.85 150	79.50 119	86.82 129	83.94 138

CLD-MVS		79.35 53	81.23 51	77.16 56	85.01 59	86.92 47	85.87 44	60.89 156	80.07 50	75.35 36	72.96 51	73.21 79	68.43 98	85.41 47	84.63 47	87.41 114	85.44 116
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GeoE		74.23 103	74.84 114	73.52 95	80.42 105	81.46 113	79.77 94	61.06 152	67.23 110	63.67 108	59.56 140	68.74 124	67.90 99	80.25 127	79.37 122	88.31 77	87.26 76

HyFIR lowres test		69.47 149	68.94 163	70.09 129	76.77 141	82.93 101	76.63 137	60.17 167	59.00 169	54.03 149	40.54 246	65.23 139	67.89 100	76.54 181	78.30 144	85.03 184	80.07 175

viewdifsd2359ckpt07		74.55 100	76.09 106	72.75 100	79.51 116	81.32 115	80.29 88	58.44 190	68.61 101	65.63 93	68.17 91	71.24 100	67.64 101	80.13 130	77.62 155	84.96 188	85.56 110

FA-MVS(training)		73.66 107	74.95 112	72.15 103	78.63 124	80.46 129	78.92 111	54.79 215	69.71 94	65.37 95	62.04 124	66.89 134	67.10 102	80.72 111	79.87 107	88.10 89	84.97 126

PVSNet_Blended_VisFu		76.57 75	77.90 73	75.02 83	80.56 102	86.58 50	79.24 104	66.18 73	64.81 126	68.18 75	65.61 109	71.45 93	67.05 103	84.16 58	81.80 72	88.90 65	90.92 42

PVSNet_BlendedMVS		76.21 84	77.52 79	74.69 87	79.46 117	83.79 79	77.50 126	64.34 91	69.88 89	71.88 47	68.54 89	70.42 109	67.05 103	83.48 66	79.63 111	87.89 101	86.87 80

PVSNet_Blended		76.21 84	77.52 79	74.69 87	79.46 117	83.79 79	77.50 126	64.34 91	69.88 89	71.88 47	68.54 89	70.42 109	67.05 103	83.48 66	79.63 111	87.89 101	86.87 80

v10		70.22 140	69.76 153	70.74 114	74.79 165	80.30 133	79.22 105	59.81 173	57.71 178	56.58 138	54.22 180	55.31 189	66.95 106	78.28 156	77.47 160	87.12 123	85.07 124

v1192		69.50 148	68.83 164	70.29 125	74.49 169	80.92 123	78.55 114	60.54 160	55.04 202	54.21 146	52.79 198	52.33 221	66.92 107	77.88 163	77.35 165	87.04 124	85.51 113

CHOSEN 1792x2688		69.20 152	69.26 159	69.13 139	76.86 140	78.93 146	77.27 129	60.12 169	61.86 151	54.42 145	42.54 240	61.61 151	66.91 108	78.55 154	78.14 146	79.23 223	83.23 145

v1921920		69.03 153	68.32 172	69.86 131	74.03 174	80.37 130	77.55 124	60.25 166	54.62 206	53.59 160	52.36 205	51.50 227	66.75 109	77.17 172	76.69 174	86.96 125	85.56 110

v144192		69.34 150	68.68 168	70.12 128	74.06 173	80.54 126	78.08 122	60.54 160	54.99 204	54.13 148	52.92 196	52.80 219	66.73 110	77.13 173	76.72 172	87.15 117	85.63 109

v1240		68.64 158	67.89 179	69.51 136	73.89 176	80.26 134	76.73 136	59.97 172	53.43 214	53.08 164	51.82 208	50.84 230	66.62 111	76.79 177	76.77 171	86.78 132	85.34 119

diffmvs_AUTHOR		74.91 98	77.47 82	71.92 105	75.60 157	80.50 127	79.48 102	60.02 171	72.41 78	64.39 103	70.63 66	73.27 77	66.55 112	79.97 131	78.34 143	85.46 169	87.17 77

viewmambaseed2359dif		73.61 109	75.14 110	71.84 107	75.87 150	79.69 136	78.99 109	60.42 164	68.19 104	64.15 105	67.85 95	71.20 101	66.55 112	77.41 169	75.78 183	85.04 183	85.85 99

v1144		69.93 144	69.36 158	70.61 118	74.89 164	80.93 121	79.11 107	60.64 158	55.97 194	55.31 143	53.85 183	54.14 201	66.54 114	78.10 158	77.44 161	87.14 120	85.09 123

diffmvs		74.86 99	77.37 86	71.93 104	75.62 155	80.35 131	79.42 103	60.15 168	72.81 74	64.63 102	71.51 60	73.11 82	66.53 115	79.02 148	77.98 147	85.25 179	86.83 82
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt11		72.49 117	74.10 117	70.61 118	75.87 150	78.53 154	76.92 131	58.16 192	65.69 120	61.34 116	67.21 101	68.35 127	66.51 116	77.91 161	75.60 185	84.86 191	85.43 117

viewmsd2359difaftdt		72.49 117	74.10 117	70.61 118	75.87 150	78.53 154	76.92 131	58.16 192	65.69 120	61.33 117	67.21 101	68.34 128	66.51 116	77.91 161	75.60 185	84.86 191	85.42 118

viewmamba		75.22 96	77.49 81	72.57 101	76.60 142	81.01 120	79.77 94	61.77 145	73.47 71	65.40 94	70.61 67	73.19 80	66.50 118	79.78 134	78.52 139	85.35 172	85.88 98

dtuplus		73.53 110	74.92 113	71.90 106	76.10 144	79.51 139	79.17 106	60.44 163	67.27 109	64.19 104	66.90 105	71.30 99	66.48 119	77.95 160	75.99 181	85.02 185	85.54 112

v2v482		70.05 143	69.46 157	70.74 114	74.62 168	80.32 132	79.00 108	60.62 159	57.41 180	56.89 135	55.43 167	55.14 191	66.39 120	77.25 171	77.14 167	86.90 126	83.57 143

v8		70.23 139	69.86 151	70.67 117	74.69 167	79.82 135	78.79 112	59.18 180	58.80 170	58.20 129	55.00 169	57.33 176	66.31 121	77.51 167	76.71 173	86.82 129	83.88 139

onestephybrid01		75.35 94	77.46 83	72.88 98	77.26 137	81.58 109	79.70 98	62.48 136	71.05 85	66.34 90	70.12 73	73.78 74	66.25 122	80.29 123	78.58 137	85.23 180	86.83 82

IterMVS-LS		71.69 125	72.82 131	70.37 124	77.54 134	76.34 180	75.13 148	60.46 162	61.53 155	57.57 131	64.89 114	67.33 131	66.04 123	77.09 174	77.37 164	85.48 168	85.18 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		71.52 127	69.87 150	73.44 96	82.21 76	79.35 141	79.52 100	64.59 88	66.15 115	61.87 112	53.21 191	56.09 185	65.85 124	78.94 149	78.50 140	86.60 139	76.85 204

V42		68.76 157	69.63 154	67.74 152	64.93 232	78.01 158	78.30 120	56.48 205	58.65 171	56.30 139	54.26 178	57.03 179	64.85 125	77.47 168	77.01 169	85.60 164	84.96 127

hybridnocas07		74.37 102	77.06 93	71.23 110	75.13 161	79.34 142	78.54 117	59.23 179	72.65 75	64.95 99	71.17 62	73.19 80	64.72 126	79.45 141	77.65 154	84.81 194	85.97 93

hybrid		74.08 104	76.76 100	70.95 113	74.70 166	79.04 144	78.40 118	58.80 188	72.23 79	64.74 101	70.55 68	73.40 75	64.45 127	79.06 147	77.38 162	84.61 195	85.64 107

EPNet		79.08 59	80.62 56	77.28 54	88.90 37	83.17 90	83.65 57	72.41 34	74.41 62	67.15 86	76.78 36	74.37 69	64.43 128	83.70 63	83.69 56	87.15 117	88.19 65
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thisisatest0530		71.48 128	73.01 127	69.70 134	73.83 177	78.62 152	74.53 156	59.12 181	64.13 132	58.63 125	64.60 117	58.63 165	64.27 129	80.28 125	80.17 104	87.82 104	84.64 132

tttt0517		71.41 129	72.95 128	69.60 135	73.70 179	78.70 151	74.42 160	59.12 181	63.89 136	58.35 128	64.56 118	58.39 172	64.27 129	80.29 123	80.17 104	87.74 106	84.69 131

RPSCF		67.64 172	71.25 140	63.43 199	61.86 238	70.73 221	67.26 215	50.86 237	74.20 65	58.91 122	67.49 98	69.33 116	64.10 131	71.41 210	68.45 230	77.61 227	77.17 201

LTVRE_ROB	59.44 16	61.82 225	62.64 228	60.87 214	72.83 188	77.19 171	64.37 233	58.97 183	33.56 263	28.00 251	52.59 204	42.21 254	63.93 132	74.52 191	76.28 178	77.15 230	82.13 149
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
MVSTER		72.06 121	74.24 115	69.51 136	70.39 207	75.97 183	76.91 134	57.36 199	64.64 128	61.39 115	68.86 83	63.76 143	63.46 133	81.44 91	79.70 110	87.56 112	85.31 120

PMMVS		65.06 191	69.17 161	60.26 217	55.25 261	63.43 248	66.71 222	43.01 258	62.41 146	50.64 177	69.44 78	67.04 133	63.29 134	74.36 193	73.54 199	82.68 209	73.99 228

IterMVS-SCA-FT		66.89 181	69.22 160	64.17 190	71.30 202	75.64 185	71.33 191	53.17 223	57.63 179	49.08 187	60.72 131	60.05 158	63.09 135	74.99 189	73.92 196	77.07 231	81.57 159

EPP-MVSNet		74.00 106	77.41 85	70.02 130	80.53 103	83.91 76	74.99 151	62.68 131	65.06 124	49.77 183	68.68 87	72.09 87	63.06 136	82.49 80	80.73 87	89.12 62	88.91 60

CHOSEN 280x420		58.70 236	61.88 234	54.98 240	55.45 260	50.55 265	64.92 230	40.36 260	55.21 199	38.13 235	48.31 222	63.76 143	63.03 137	73.73 197	68.58 227	68.00 261	73.04 231

TinyColmap		62.84 208	61.03 237	64.96 184	69.61 212	71.69 217	68.48 211	59.76 174	55.41 197	47.69 199	47.33 230	34.20 264	62.76 138	74.52 191	72.59 205	81.44 213	71.47 233

Fast-Effi-MVS+-dtu		68.34 159	69.47 156	67.01 168	75.15 159	77.97 164	77.12 130	55.40 212	57.87 173	46.68 204	56.17 161	60.39 154	62.36 139	76.32 182	76.25 180	85.35 172	81.34 160

Anonymous20231211		71.90 122	72.48 133	71.21 111	80.14 108	81.53 111	76.92 131	62.89 120	64.46 131	58.94 121	43.80 236	70.98 102	62.22 140	80.70 112	80.19 103	86.18 147	85.73 103

DCV-MVSNet		73.65 108	75.78 107	71.16 112	80.19 107	79.27 143	77.45 128	61.68 148	66.73 112	58.72 124	65.31 112	69.96 112	62.19 141	81.29 97	80.97 82	86.74 133	86.91 79

USDC		67.36 176	67.90 178	66.74 173	71.72 194	75.23 192	71.58 190	60.28 165	67.45 108	50.54 179	60.93 129	45.20 249	62.08 142	76.56 180	74.50 194	84.25 197	75.38 218

Anonymous202405211			72.16 136		80.85 91	81.85 108	76.88 135	65.40 81	62.89 144		46.35 232	67.99 129	62.05 143	81.15 101	80.38 99	85.97 158	84.50 133

MS-PatchMatch		70.17 141	70.49 145	69.79 132	80.98 90	77.97 164	77.51 125	58.95 184	62.33 147	55.22 144	53.14 192	65.90 137	62.03 144	79.08 146	77.11 168	84.08 199	77.91 194

baseline2		69.69 145	70.27 147	69.01 141	75.72 154	77.13 172	73.82 171	58.94 185	61.35 156	57.09 134	61.68 125	57.17 178	61.99 145	78.10 158	76.58 175	86.48 143	79.85 176

v148		67.85 166	67.53 180	68.23 147	73.25 182	77.57 170	74.26 164	57.36 199	55.70 196	57.45 133	53.53 185	55.42 188	61.96 146	75.23 187	73.92 196	85.08 182	81.32 161

pmmvs4		67.89 165	67.39 184	68.48 146	71.60 198	73.57 209	74.45 157	60.98 155	64.65 127	57.97 130	54.95 170	51.73 226	61.88 147	73.78 196	75.11 190	83.99 201	77.91 194

CostFormer		68.92 154	69.58 155	68.15 148	75.98 148	76.17 182	78.22 121	51.86 232	65.80 118	61.56 114	63.57 120	62.83 146	61.85 148	70.40 226	68.67 223	79.42 221	79.62 180

tpm cat1		65.41 187	63.81 217	67.28 163	75.61 156	72.88 211	75.32 142	52.85 226	62.97 142	63.66 109	53.24 190	53.29 216	61.83 149	65.54 246	64.14 248	74.43 245	74.60 221

CANet_DTU		73.29 112	76.96 95	69.00 142	77.04 139	82.06 107	79.49 101	56.30 210	67.85 107	53.29 163	71.12 63	70.37 111	61.81 150	81.59 85	80.96 83	86.09 150	84.73 130

MGCFI-Net		76.55 76	81.71 47	70.52 122	81.71 77	84.62 69	75.02 150	62.17 140	82.91 38	53.58 161	72.78 54	75.87 64	61.75 151	82.96 73	82.61 65	88.86 68	90.26 50

baseline		70.45 137	74.09 119	66.20 176	70.95 204	75.67 184	74.26 164	53.57 219	68.33 103	58.42 126	69.87 75	71.45 93	61.55 152	74.84 190	74.76 193	78.42 225	83.72 141

SCA		65.40 188	66.58 190	64.02 193	70.65 205	73.37 210	67.35 214	53.46 221	63.66 137	54.14 147	60.84 130	60.20 157	61.50 153	69.96 231	68.14 232	77.01 232	69.91 236

GA-MVS		68.14 160	69.17 161	66.93 170	73.77 178	78.50 156	74.45 157	58.28 191	55.11 201	48.44 189	60.08 135	53.99 204	61.50 153	78.43 155	77.57 157	85.13 181	80.54 169

anonymousdsp		65.28 189	67.98 176	62.13 205	58.73 252	73.98 208	67.10 217	50.69 239	48.41 239	47.66 200	54.27 176	52.75 220	61.45 155	76.71 179	80.20 101	87.13 121	89.53 58

v7n		67.05 180	66.94 186	67.17 164	72.35 189	78.97 145	73.26 180	58.88 186	51.16 229	50.90 176	48.21 223	50.11 234	60.96 156	77.70 164	77.38 162	86.68 137	85.05 125

CR-MVSNet		64.83 193	65.54 196	64.01 194	70.64 206	69.41 225	65.97 226	52.74 227	57.81 175	52.65 166	54.27 176	56.31 184	60.92 157	72.20 205	73.09 201	81.12 216	75.69 213

PatchT		61.97 221	64.04 214	59.55 222	60.49 240	67.40 233	56.54 253	48.65 247	56.69 185	52.65 166	51.10 212	52.14 224	60.92 157	72.20 205	73.09 201	78.03 226	75.69 213

dps		64.00 202	62.99 224	65.18 180	73.29 181	72.07 215	68.98 206	53.07 225	57.74 177	58.41 127	55.55 165	47.74 242	60.89 159	69.53 234	67.14 241	76.44 235	71.19 234

IterMVS		66.36 182	68.30 173	64.10 191	69.48 214	74.61 199	73.41 178	50.79 238	57.30 181	48.28 191	60.64 132	59.92 159	60.85 160	74.14 194	72.66 204	81.80 211	78.82 185
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TDRefinement		66.09 184	65.03 204	67.31 161	69.73 211	76.75 175	75.33 141	64.55 89	60.28 164	49.72 184	45.63 234	42.83 253	60.46 161	75.75 183	75.95 182	84.08 199	78.04 193

PatchmatchNet		64.21 200	64.65 209	63.69 196	71.29 203	68.66 229	69.63 199	51.70 234	63.04 141	53.77 158	59.83 139	58.34 173	60.23 162	68.54 240	66.06 244	75.56 240	68.08 243
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
gm-plane-assit		57.00 240	57.62 247	56.28 235	76.10 144	62.43 254	47.62 264	46.57 253	33.84 262	23.24 257	37.52 247	40.19 258	59.61 163	79.81 133	77.55 158	84.55 196	72.03 232

0.3-1-1-0.015		65.09 190	65.15 201	65.01 183	66.63 225	75.00 195	71.90 187	54.57 216	56.32 191	53.88 152	53.63 184	58.58 167	59.47 164	68.39 242	68.46 229	83.62 203	75.64 215

0.4-1-1-0.1		65.57 186	65.82 193	65.29 179	67.19 219	75.61 186	72.13 186	55.16 214	57.12 182	53.84 156	54.57 172	58.80 164	59.40 165	69.22 237	69.01 220	83.99 201	76.43 207

0.4-1-1-0.2		64.94 192	65.02 205	64.85 185	66.45 226	74.76 196	71.66 188	54.40 217	55.85 195	53.84 156	53.97 181	58.62 166	59.33 166	68.27 243	68.20 231	83.40 205	75.47 217

IB-MVS	66.94 12	71.21 131	71.66 139	70.68 116	79.18 119	82.83 104	72.61 181	61.77 145	59.66 166	63.44 110	53.26 189	59.65 160	59.16 167	76.78 178	82.11 68	87.90 100	87.33 74
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
test2506		71.72 124	72.95 128	70.29 125	81.49 80	83.27 86	75.74 139	67.59 65	68.19 104	49.81 182	61.15 128	49.73 236	58.82 168	84.76 51	82.94 60	88.27 78	80.63 168

ECVR-MVS		72.20 120	73.91 120	70.20 127	81.49 80	83.27 86	75.74 139	67.59 65	68.19 104	49.31 186	55.77 162	62.00 150	58.82 168	84.76 51	82.94 60	88.27 78	80.41 172

dtuonly		61.60 227	64.61 211	58.09 227	59.71 242	62.36 255	72.50 183	42.52 259	58.12 172	43.84 221	54.51 173	62.39 149	58.60 170	71.88 208	69.50 215	71.34 254	73.52 230

UniMVSNet_NR-MVSNet		70.59 135	72.19 134	68.72 143	77.72 132	80.72 125	73.81 172	69.65 48	61.99 149	43.23 222	60.54 133	57.50 175	58.57 171	79.56 138	81.07 81	89.34 54	83.97 136

DU-MVS		69.63 146	70.91 142	68.13 149	75.99 146	79.54 137	73.81 172	69.20 53	61.20 158	43.23 222	58.52 145	53.50 208	58.57 171	79.22 144	80.45 98	87.97 96	83.97 136

COLMAP_ROB	62.73 15	67.66 170	66.76 188	68.70 144	80.49 104	77.98 162	75.29 143	62.95 119	63.62 138	49.96 180	47.32 231	50.72 231	58.57 171	76.87 176	75.50 189	84.94 189	75.33 219
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PM-MVS		60.48 230	60.94 238	59.94 218	58.85 250	66.83 236	64.27 234	51.39 235	55.03 203	48.03 192	50.00 217	40.79 257	58.26 174	69.20 238	67.13 242	78.84 224	77.60 198

SixPastTwentyTwo		61.84 223	62.45 230	61.12 213	69.20 215	72.20 214	62.03 242	57.40 197	46.54 246	38.03 236	57.14 158	41.72 255	58.12 175	69.67 233	71.58 208	81.94 210	78.30 187

thisisatest0515		67.40 175	68.78 165	65.80 178	70.02 209	75.24 191	69.36 201	57.37 198	54.94 205	53.67 159	55.53 166	54.85 196	58.00 176	78.19 157	78.91 133	86.39 144	83.78 140

test1111		71.56 126	73.44 123	69.38 138	81.16 85	82.95 100	74.99 151	67.68 63	66.89 111	46.33 206	55.19 168	60.91 153	57.99 177	84.59 54	82.70 64	88.12 85	80.85 165

CMPMVS	47.78 17	62.49 215	62.52 229	62.46 202	70.01 210	70.66 222	62.97 238	51.84 233	51.98 221	56.71 137	42.87 238	53.62 205	57.80 178	72.23 203	70.37 212	75.45 242	75.91 210
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
GBi-Net		70.78 132	73.37 125	67.76 150	72.95 184	78.00 159	75.15 145	62.72 126	64.13 132	51.44 171	58.37 148	69.02 119	57.59 179	81.33 94	80.72 88	86.70 134	82.02 150

test1		70.78 132	73.37 125	67.76 150	72.95 184	78.00 159	75.15 145	62.72 126	64.13 132	51.44 171	58.37 148	69.02 119	57.59 179	81.33 94	80.72 88	86.70 134	82.02 150

FMVSNet2		70.39 138	72.67 132	67.72 153	72.95 184	78.00 159	75.15 145	62.69 130	63.29 140	51.25 175	55.64 163	68.49 126	57.59 179	80.91 105	80.35 100	86.70 134	82.02 150

FMVSNet3		70.49 136	72.90 130	67.67 155	72.88 187	77.98 162	74.96 154	62.72 126	64.13 132	51.44 171	58.37 148	69.02 119	57.43 182	79.43 142	79.57 116	86.59 140	81.81 157

MDTV_nov1_ep13		64.37 197	65.24 198	63.37 200	68.94 216	70.81 220	72.40 185	50.29 241	60.10 165	53.91 151	60.07 136	59.15 162	57.21 183	69.43 236	67.30 239	77.47 228	69.78 238

FMVSNet1		68.84 155	70.47 146	66.94 169	71.35 201	77.68 167	74.71 155	62.35 138	56.93 184	49.94 181	50.01 215	64.59 140	57.07 184	81.33 94	80.72 88	86.25 145	82.00 153

dtuonlycased		57.34 238	58.57 243	55.91 236	58.42 253	71.89 216	66.93 218	44.93 256	50.31 232	32.39 244	37.40 248	54.78 197	57.03 185	60.42 256	60.80 254	75.75 237	74.39 223

UniMVSNet_ETH3D		67.18 179	67.03 185	67.36 160	74.44 170	78.12 157	74.07 167	66.38 71	52.22 219	46.87 201	48.64 221	51.84 225	56.96 186	77.29 170	78.53 138	85.42 170	82.59 147

pmmvs-eth3d		63.52 203	62.44 231	64.77 186	66.82 224	70.12 224	69.41 200	59.48 176	54.34 210	52.71 165	46.24 233	44.35 251	56.93 187	72.37 200	73.77 198	83.30 206	75.91 210

FC-MVSNet-train		72.60 116	75.07 111	69.71 133	81.10 89	78.79 150	73.74 174	65.23 84	66.10 116	53.34 162	70.36 71	63.40 145	56.92 188	81.44 91	80.96 83	87.93 98	84.46 134

tfpn200view9		68.11 161	68.72 167	67.40 159	77.83 130	78.93 146	74.28 162	62.81 122	56.64 186	46.82 202	52.65 202	53.47 211	56.59 189	80.41 118	78.43 141	86.11 148	80.52 170

thres400		67.95 164	68.62 169	67.17 164	77.90 127	78.59 153	74.27 163	62.72 126	56.34 190	45.77 212	53.00 194	53.35 214	56.46 190	80.21 128	78.43 141	85.91 160	80.43 171

thres200		67.98 163	68.55 170	67.30 162	77.89 129	78.86 148	74.18 166	62.75 124	56.35 189	46.48 205	52.98 195	53.54 207	56.46 190	80.41 118	77.97 148	86.05 153	79.78 178

usedtu_blend_shiyan5		64.27 198	64.70 208	63.77 195	59.06 245	74.03 204	71.65 189	56.37 206	51.17 225	53.88 152	52.71 199	58.58 167	56.43 192	70.13 227	68.14 232	85.26 175	78.14 191

blend_shiyan4		64.82 194	65.21 199	64.37 189	65.04 229	74.06 203	70.30 196	55.30 213	55.39 198	53.88 152	52.71 199	58.58 167	56.43 192	69.45 235	68.13 237	85.30 174	78.14 191

FE-MVSNET3		64.07 201	64.71 207	63.32 201	59.06 245	74.03 204	68.92 207	56.37 206	51.17 225	53.88 152	52.71 199	58.58 167	56.43 192	70.13 227	68.14 232	85.26 175	78.20 188

MVS-HIRNet		54.41 246	52.10 254	57.11 232	58.99 249	56.10 261	49.68 262	49.10 244	46.18 247	52.15 170	33.18 256	46.11 246	56.10 195	63.19 253	59.70 257	76.64 234	60.25 257

Baseline_NR-MVSNet		67.53 174	68.77 166	66.09 177	75.99 146	74.75 197	72.43 184	68.41 57	61.33 157	38.33 234	51.31 210	54.13 203	56.03 196	79.22 144	78.19 145	85.37 171	82.45 148

thres100view900		67.60 173	68.02 175	67.12 166	77.83 130	77.75 166	73.90 169	62.52 134	56.64 186	46.82 202	52.65 202	53.47 211	55.92 197	78.77 151	77.62 155	85.72 161	79.23 182

test-mter		60.84 229	64.62 210	56.42 234	55.99 259	64.18 242	65.39 228	34.23 264	54.39 209	46.21 208	57.40 157	59.49 161	55.86 198	71.02 217	69.65 214	80.87 218	76.20 209

tpmrst		62.00 220	62.35 232	61.58 209	71.62 197	64.14 243	69.07 203	48.22 251	62.21 148	53.93 150	58.26 152	55.30 190	55.81 199	63.22 252	62.62 251	70.85 255	70.70 235

TranMVSNet+NR-MVSNet		69.25 151	70.81 143	67.43 158	77.23 138	79.46 140	73.48 177	69.66 47	60.43 163	39.56 230	58.82 144	53.48 210	55.74 200	79.59 136	81.21 79	88.89 66	82.70 146

thres600view7		67.68 169	68.43 171	66.80 171	77.90 127	78.86 148	73.84 170	62.75 124	56.07 193	44.70 219	52.85 197	52.81 218	55.58 201	80.41 118	77.77 151	86.05 153	80.28 173

Vis-MVSNet		72.77 115	77.20 91	67.59 157	74.19 172	84.01 75	76.61 138	61.69 147	60.62 162	50.61 178	70.25 72	71.31 98	55.57 202	83.85 61	82.28 66	86.90 126	88.08 66
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EG-PatchMatch MVS		67.24 177	66.94 186	67.60 156	78.73 122	81.35 114	73.28 179	59.49 175	46.89 245	51.42 174	43.65 237	53.49 209	55.50 203	81.38 93	80.66 94	87.15 117	81.17 162

test-LLR		64.42 196	64.36 212	64.49 188	75.02 162	63.93 245	66.61 223	61.96 142	54.41 207	47.77 197	57.46 155	60.25 155	55.20 204	70.80 218	69.33 216	80.40 219	74.38 224

TESTMET0.1,1		61.10 228	64.36 212	57.29 230	57.53 254	63.93 245	66.61 223	36.22 263	54.41 207	47.77 197	57.46 155	60.25 155	55.20 204	70.80 218	69.33 216	80.40 219	74.38 224

wanda-best-256-512		62.84 208	63.46 221	62.12 206	59.06 245	74.03 204	68.92 207	56.37 206	51.17 225	48.02 193	48.12 224	54.93 194	55.08 206	70.13 227	68.14 232	85.26 175	77.73 196

FE-blended-shiyan7		62.84 208	63.46 221	62.12 206	59.06 245	74.03 204	68.92 207	56.37 206	51.17 225	48.02 193	48.12 224	54.93 194	55.08 206	70.13 227	68.14 232	85.26 175	77.73 196

blended_shiyan8		62.98 205	63.65 219	62.21 203	59.20 243	74.17 201	69.03 205	56.52 203	51.08 231	47.96 195	48.07 227	55.02 192	55.00 208	70.43 224	68.60 225	85.52 165	78.15 190

blended_shiyan6		62.98 205	63.66 218	62.19 204	59.20 243	74.17 201	69.04 204	56.52 203	51.09 230	47.91 196	48.11 226	55.02 192	54.98 209	70.43 224	68.59 226	85.51 166	78.20 188

dmvs_re		67.22 178	67.92 177	66.40 175	75.94 149	70.55 223	74.97 153	63.87 96	57.07 183	44.75 217	54.29 175	56.72 181	54.65 210	79.53 139	77.51 159	84.20 198	79.78 178

UA-Net		74.47 101	77.80 75	70.59 121	85.33 55	85.40 62	73.54 175	65.98 77	60.65 161	56.00 140	72.11 56	79.15 48	54.63 211	83.13 72	82.25 67	88.04 91	81.92 156

IS_MVSNet		73.33 111	77.34 87	68.65 145	81.29 83	83.47 84	74.45 157	63.58 101	65.75 119	48.49 188	67.11 104	70.61 108	54.63 211	84.51 55	83.58 57	89.48 52	86.34 90

baseline1		70.10 142	72.17 135	67.69 154	79.74 113	76.80 174	73.91 168	64.38 90	62.74 145	48.30 190	64.94 113	64.08 142	54.17 213	81.46 89	78.92 132	85.66 163	76.22 208

usedtu_dtu_shiyan1		66.26 183	68.15 174	64.06 192	67.01 220	76.52 178	70.61 195	61.10 150	61.86 151	44.86 215	49.77 218	56.69 182	53.97 214	77.58 166	77.88 149	86.80 131	76.78 205

gbinet_0.2-2-1-0.02		62.72 211	63.87 216	61.39 211	57.04 256	74.70 198	69.09 202	57.36 199	47.91 240	45.94 211	47.47 229	55.96 187	53.90 215	71.07 215	68.83 222	84.99 187	81.15 163

tpm		62.41 216	63.15 223	61.55 210	72.24 190	63.79 247	71.31 192	46.12 255	57.82 174	55.33 142	59.90 138	54.74 198	53.63 216	67.24 245	64.29 247	70.65 256	74.25 227

MDTV_nov1_ep13_2view		60.16 231	60.51 240	59.75 219	65.39 228	69.05 228	68.00 212	48.29 249	51.99 220	45.95 210	48.01 228	49.64 237	53.39 217	68.83 239	66.52 243	77.47 228	69.55 239

UniMVSNet (Re)		69.53 147	71.90 137	66.76 172	76.42 143	80.93 121	72.59 182	68.03 60	61.75 153	41.68 227	58.34 151	57.23 177	53.27 218	79.53 139	80.62 96	88.57 73	84.90 128

RPMNet		61.71 226	62.88 225	60.34 216	69.51 213	69.41 225	63.48 236	49.23 243	57.81 175	45.64 213	50.51 213	50.12 233	53.13 219	68.17 244	68.49 228	81.07 217	75.62 216

tfpnnormal		64.27 198	63.64 220	65.02 182	75.84 153	75.61 186	71.24 193	62.52 134	47.79 241	42.97 224	42.65 239	44.49 250	52.66 220	78.77 151	76.86 170	84.88 190	79.29 181

MDA-MVSNet-bldmvs		53.37 249	53.01 253	53.79 244	43.67 266	67.95 232	59.69 248	57.92 195	43.69 249	32.41 243	41.47 241	27.89 270	52.38 221	56.97 262	65.99 245	76.68 233	67.13 244

NR-MVSNet		68.79 156	70.56 144	66.71 174	77.48 135	79.54 137	73.52 176	69.20 53	61.20 158	39.76 229	58.52 145	50.11 234	51.37 222	80.26 126	80.71 92	88.97 64	83.59 142

EPMVS		60.00 232	61.97 233	57.71 229	68.46 217	63.17 251	64.54 232	48.23 250	63.30 139	44.72 218	60.19 134	56.05 186	50.85 223	65.27 249	62.02 252	69.44 258	63.81 251

CVMVSNet		62.55 213	65.89 191	58.64 225	66.95 222	69.15 227	66.49 225	56.29 211	52.46 218	32.70 242	59.27 142	58.21 174	50.09 224	71.77 209	71.39 209	79.31 222	78.99 184

pmmvs5		62.37 219	64.04 214	60.42 215	65.03 230	71.67 218	67.17 216	52.70 229	50.30 233	44.80 216	54.23 179	51.19 229	49.37 225	72.88 199	73.48 200	83.45 204	74.55 222

UGNet		72.78 114	77.67 76	67.07 167	71.65 196	83.24 88	75.20 144	63.62 100	64.93 125	56.72 136	71.82 58	73.30 76	49.02 226	81.02 103	80.70 93	86.22 146	88.67 62
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
pm-mvs1		65.62 185	67.42 182	63.53 198	73.66 180	76.39 179	69.66 198	60.87 157	49.73 236	43.97 220	51.24 211	57.00 180	48.16 227	79.89 132	77.84 150	84.85 193	79.82 177

gg-mvs-nofinetune		62.55 213	65.05 203	59.62 221	78.72 123	77.61 168	70.83 194	53.63 218	39.71 258	22.04 261	36.36 251	64.32 141	47.53 228	81.16 100	79.03 130	85.00 186	77.17 201

pmmvs6		62.41 216	62.88 225	61.87 208	71.38 200	75.18 194	67.76 213	59.45 177	41.64 253	42.52 226	37.33 249	52.91 217	46.87 229	77.67 165	76.26 179	83.23 207	79.18 183

ADS-MVSNet		55.94 243	58.01 244	53.54 245	62.48 237	58.48 258	59.12 250	46.20 254	59.65 167	42.88 225	52.34 206	53.31 215	46.31 230	62.00 254	60.02 256	64.23 263	60.24 258

pmmvs3		47.65 254	49.08 259	45.99 254	44.61 264	54.79 262	50.04 260	31.95 267	33.91 261	29.90 246	30.37 258	33.53 265	46.31 230	63.50 250	63.67 249	73.14 250	63.77 252

TransMVSNet (Re)		64.74 195	65.66 195	63.66 197	77.40 136	75.33 190	69.86 197	62.67 132	47.63 242	41.21 228	50.01 215	52.33 221	45.31 232	79.57 137	77.69 153	85.49 167	77.07 203

FE-MVSNET2		58.78 235	60.53 239	56.73 233	57.08 255	72.23 213	62.74 241	59.35 178	47.17 243	30.52 245	34.62 254	43.62 252	44.57 233	75.24 186	76.57 176	86.11 148	74.30 226

CDS-MVSNet		67.65 171	69.83 152	65.09 181	75.39 158	76.55 177	74.42 160	63.75 97	53.55 212	49.37 185	59.41 141	62.45 147	44.44 234	79.71 135	79.82 109	83.17 208	77.36 200
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		59.58 233	62.81 227	55.81 237	66.03 227	65.64 241	63.86 235	48.74 246	49.95 235	37.07 238	54.77 171	58.54 171	44.44 234	72.29 202	71.79 206	74.70 244	66.66 245

EPNet_dtu		68.08 162	71.00 141	64.67 187	79.64 115	68.62 230	75.05 149	63.30 104	66.36 114	45.27 214	67.40 99	66.84 135	43.64 236	75.37 185	74.98 192	81.15 215	77.44 199
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		57.24 239	60.02 241	53.99 243	56.45 258	62.74 252	65.27 229	47.03 252	55.14 200	39.55 231	40.88 243	53.42 213	41.83 237	72.35 201	71.10 211	73.79 247	64.50 250

ambc			53.42 251		64.99 231	63.36 249	49.96 261		47.07 244	37.12 237	28.97 260	16.36 273	41.82 238	75.10 188	67.34 238	71.55 253	75.72 212

FPMVS		51.87 251	50.00 257	54.07 242	66.83 223	57.25 259	60.25 247	50.91 236	50.25 234	34.36 240	36.04 252	32.02 266	41.49 239	58.98 259	56.07 259	70.56 257	59.36 259

CP-MVSNet		62.68 212	65.49 197	59.40 223	71.84 192	75.34 189	62.87 239	67.04 68	52.64 216	27.19 252	53.38 187	48.15 240	41.40 240	71.26 211	75.68 184	86.07 151	82.00 153

PS-CasMVS		62.38 218	65.06 202	59.25 224	71.73 193	75.21 193	62.77 240	66.99 69	51.94 223	26.96 253	52.00 207	47.52 243	41.06 241	71.16 214	75.60 185	85.97 158	81.97 155

PEN-MVS		62.96 207	65.77 194	59.70 220	73.98 175	75.45 188	63.39 237	67.61 64	52.49 217	25.49 254	53.39 186	49.12 238	40.85 242	71.94 207	77.26 166	86.86 128	80.72 167

MIMVSNet		58.52 237	61.34 236	55.22 239	60.76 239	67.01 235	66.81 220	49.02 245	56.43 188	38.90 232	40.59 245	54.54 200	40.57 243	73.16 198	71.65 207	75.30 243	66.00 246

pmnet_mix02		55.30 244	57.01 248	53.30 246	64.14 233	59.09 257	58.39 252	50.24 242	53.47 213	38.68 233	49.75 219	45.86 247	40.14 244	65.38 248	60.22 255	68.19 260	65.33 248

Vis-MVSNet (Re-imp)		67.83 167	73.52 122	61.19 212	78.37 125	76.72 176	66.80 221	62.96 118	65.50 122	34.17 241	67.19 103	69.68 115	39.20 245	79.39 143	79.44 121	85.68 162	76.73 206

FE-MVSNET		52.98 250	55.99 250	49.47 250	49.71 262	65.83 238	54.09 256	56.91 202	40.70 255	16.86 268	32.90 257	40.15 259	37.83 246	69.80 232	73.04 203	81.41 214	69.49 240

DTE-MVSNet		61.85 222	64.96 206	58.22 226	74.32 171	74.39 200	61.01 244	67.85 62	51.76 224	21.91 262	53.28 188	48.17 239	37.74 247	72.22 204	76.44 177	86.52 142	78.49 186

EU-MVSNet		54.63 245	58.69 242	49.90 249	56.99 257	62.70 253	56.41 254	50.64 240	45.95 248	23.14 258	50.42 214	46.51 245	36.63 248	65.51 247	64.85 246	75.57 239	74.91 220

Anonymous20231206		56.36 242	57.80 246	54.67 241	70.08 208	66.39 237	60.46 246	57.54 196	49.50 238	29.30 249	33.86 255	46.64 244	35.18 249	70.44 222	68.88 221	75.47 241	68.88 242

WR-MVS		63.03 204	67.40 183	57.92 228	75.14 160	77.60 169	60.56 245	66.10 74	54.11 211	23.88 255	53.94 182	53.58 206	34.50 250	73.93 195	77.71 152	87.35 115	80.94 164

usedtu_dtu_shiyan2		49.27 252	50.47 255	47.86 252	35.37 270	64.10 244	58.53 251	53.10 224	31.42 266	29.57 247	27.09 263	38.06 262	34.31 251	63.35 251	63.36 250	76.27 236	65.93 247

WR-MVS_H		61.83 224	65.87 192	57.12 231	71.72 194	76.87 173	61.45 243	66.19 72	51.97 222	22.92 259	53.13 193	52.30 223	33.80 252	71.03 216	75.00 191	86.65 138	80.78 166

PMVS	39.38 18	46.06 258	43.30 261	49.28 251	62.93 234	38.75 267	41.88 266	53.50 220	33.33 264	35.46 239	28.90 261	31.01 267	33.04 253	58.61 261	54.63 262	68.86 259	57.88 260
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test0.0.03 1		58.80 234	61.58 235	55.56 238	75.02 162	68.45 231	59.58 249	61.96 142	52.74 215	29.57 247	49.75 219	54.56 199	31.46 254	71.19 212	69.77 213	75.75 237	64.57 249

N_pmnet		47.35 255	50.13 256	44.11 256	59.98 241	51.64 264	51.86 259	44.80 257	49.58 237	20.76 263	40.65 244	40.05 260	29.64 255	59.84 257	55.15 260	57.63 264	54.00 261

DeepMVS_CX						18.74 273	18.55 272	8.02 269	26.96 267	7.33 271	23.81 265	13.05 274	25.99 256	25.17 268		22.45 274	36.25 267

MIMVSNet1		49.27 252	53.25 252	44.62 255	44.61 264	61.52 256	53.61 257	52.18 230	41.62 254	18.68 265	28.14 262	41.58 256	25.50 257	68.46 241	69.04 218	73.15 249	62.37 255

Gipuma		36.38 261	35.80 263	37.07 258	45.76 263	33.90 268	29.81 268	48.47 248	39.91 257	18.02 266	8.00 271	8.14 275	25.14 258	59.29 258	61.02 253	55.19 266	40.31 264
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testgi		54.39 247	57.86 245	50.35 248	71.59 199	67.24 234	54.95 255	53.25 222	43.36 250	23.78 256	44.64 235	47.87 241	24.96 259	70.45 221	68.66 224	73.60 248	62.78 254

new_pmnet		38.40 260	42.64 262	33.44 260	37.54 269	45.00 266	36.60 267	32.72 266	40.27 256	12.72 269	29.89 259	28.90 268	24.78 260	53.17 263	52.90 263	56.31 265	48.34 262

FC-MVSNet-test		56.90 241	65.20 200	47.21 253	66.98 221	63.20 250	49.11 263	58.60 189	59.38 168	11.50 270	65.60 110	56.68 183	24.66 261	71.17 213	71.36 210	72.38 251	69.02 241

test20.03		53.93 248	56.28 249	51.19 247	72.19 191	65.83 238	53.20 258	61.08 151	42.74 251	22.08 260	37.07 250	45.76 248	24.29 262	70.44 222	69.04 218	74.31 246	63.05 253

EMVS		20.98 265	17.15 268	25.44 262	39.51 268	19.37 272	12.66 273	39.59 262	19.10 269	6.62 273	9.27 269	4.40 277	22.43 263	17.99 270	24.40 268	31.81 271	25.53 269

E-PMN		21.77 264	18.24 267	25.89 261	40.22 267	19.58 271	12.46 274	39.87 261	18.68 270	6.71 272	9.57 268	4.31 278	22.36 264	19.89 269	27.28 267	33.73 270	28.34 268

new-patchmatchnet		46.97 256	49.47 258	44.05 257	62.82 235	56.55 260	45.35 265	52.01 231	42.47 252	17.04 267	35.73 253	35.21 263	21.84 265	61.27 255	54.83 261	65.26 262	60.26 256

test_method		22.26 263	25.94 265	17.95 265	3.24 274	7.17 274	23.83 270	7.27 270	37.35 260	20.44 264	21.87 266	39.16 261	18.67 266	34.56 265	20.84 269	34.28 269	20.64 270

MVE	19.12 19	20.47 266	23.27 266	17.20 266	12.66 273	25.41 270	10.52 275	34.14 265	14.79 271	6.53 274	8.79 270	4.68 276	16.64 267	29.49 267	41.63 264	22.73 273	38.11 265
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
WB-MVS		40.01 259	45.06 260	34.13 259	58.84 251	53.28 263	28.60 269	58.10 194	32.93 265	4.65 275	40.92 242	28.33 269	7.26 268	58.86 260	56.09 258	47.36 267	44.98 263

PMMVS2		25.60 262	29.75 264	20.76 264	28.00 271	30.93 269	23.10 271	29.18 268	23.14 268	1.46 276	18.23 267	16.54 272	5.08 269	40.22 264	41.40 265	37.76 268	37.79 266

tmp_tt				14.50 267	14.68 272	7.17 274	10.46 276	2.21 271	37.73 259	28.71 250	25.26 264	16.98 271	4.37 270	31.49 266	29.77 266	26.56 272

GG-mvs-BLEND		46.86 257	67.51 181	22.75 263	0.05 275	76.21 181	64.69 231	0.04 272	61.90 150	0.09 277	55.57 164	71.32 97	0.08 271	70.54 220	67.19 240	71.58 252	69.86 237

test123		0.09 267	0.14 270	0.02 268	0.00 277	0.02 276	0.02 279	0.01 273	0.09 273	0.00 279	0.30 272	0.00 280	0.08 271	0.03 272	0.09 271	0.01 275	0.45 271

testmvs		0.09 267	0.15 269	0.02 268	0.01 276	0.02 276	0.05 278	0.01 273	0.11 272	0.01 278	0.26 273	0.01 279	0.06 273	0.10 271	0.10 270	0.01 275	0.43 272

uanet_test		0.00 269	0.00 271	0.00 270	0.00 277	0.00 278	0.00 280	0.00 275	0.00 274	0.00 279	0.00 274	0.00 280	0.00 274	0.00 273	0.00 272	0.00 277	0.00 273

sosnet-low-res		0.00 269	0.00 271	0.00 270	0.00 277	0.00 278	0.00 280	0.00 275	0.00 274	0.00 279	0.00 274	0.00 280	0.00 274	0.00 273	0.00 272	0.00 277	0.00 273

sosnet		0.00 269	0.00 271	0.00 270	0.00 277	0.00 278	0.00 280	0.00 275	0.00 274	0.00 279	0.00 274	0.00 280	0.00 274	0.00 273	0.00 272	0.00 277	0.00 273

TestfortrainingZip							91.33 7	75.06 15		80.35 16						91.03 7

RE-MVS-def										46.24 207

9.14												86.88 18

SR-MVS					88.99 36			73.57 27				87.54 16

our_test_3					67.93 218	70.99 219	66.89 219

MTAPA										83.48 1		86.45 21

MTMP										82.66 5		84.91 29

Patchmatch-RL test							2.85 277

XVS					86.63 48	88.68 29	85.00 50			71.81 49		81.92 39				90.47 26

X-MVStestdata					86.63 48	88.68 29	85.00 50			71.81 49		81.92 39				90.47 26

mPP-MVS					89.90 27							81.29 44

NP-MVS									80.10 49

Patchmtry						65.80 240	65.97 226	52.74 227		52.65 166

High-resolution multi-view benchmark