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.

TDRefinement		93.16 1	95.57 1	90.36 1	88.79 52	93.57 1	97.27 1	78.23 21	95.55 1	93.00 1	93.98 18	96.01 38	87.53 1	97.69 1	96.81 1	97.33 1	95.34 4

XVS					91.28 25	91.23 8	96.89 2			87.14 25		94.53 72				95.84 15

X-MVStestdata					91.28 25	91.23 8	96.89 2			87.14 25		94.53 72				95.84 15

X-MVS		89.36 28	90.73 45	87.77 16	91.50 20	91.23 8	96.76 4	78.88 17	87.29 54	87.14 25	78.98 147	94.53 72	76.47 57	95.25 19	94.28 11	95.85 14	93.55 16

ACMMPR		91.30 4	92.88 11	89.46 4	91.92 11	91.61 5	96.60 5	79.46 14	90.08 31	88.53 13	89.54 66	95.57 48	84.25 7	95.24 20	94.27 12	95.97 11	93.85 8

MP-MVS		90.84 6	91.95 34	89.55 3	92.92 4	90.90 19	96.56 6	79.60 11	86.83 59	88.75 12	89.00 74	94.38 78	84.01 9	94.94 24	94.34 10	95.45 24	93.24 23
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PGM-MVS		90.42 11	91.58 37	89.05 5	91.77 14	91.06 13	96.51 7	78.94 16	85.41 71	87.67 18	87.02 97	95.26 57	83.62 12	95.01 23	93.94 15	95.79 19	93.40 20

SteuartSystems-ACMMP		90.00 17	91.73 35	87.97 12	91.21 29	90.29 28	96.51 7	78.00 23	86.33 62	85.32 40	88.23 83	94.67 70	82.08 20	95.13 22	93.88 16	94.72 35	93.59 13
Skip Steuart: Steuart Systems R&D Blog.
ACMMP		90.63 8	92.40 20	88.56 8	91.24 28	91.60 6	96.49 9	77.53 26	87.89 48	86.87 30	87.24 95	96.46 25	82.87 16	95.59 15	94.50 8	96.35 6	93.51 18
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
CP-MVS		91.09 5	92.33 25	89.65 2	92.16 10	90.41 27	96.46 10	80.38 8	88.26 45	89.17 10	87.00 98	96.34 30	83.95 10	95.77 11	94.72 7	95.81 17	93.78 10

ACMM	80.67 7	90.67 7	92.46 19	88.57 7	91.35 22	89.93 32	96.34 11	77.36 30	90.17 29	86.88 29	87.32 93	96.63 23	83.32 13	95.79 10	94.49 9	96.19 9	92.91 26
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
anonymousdsp		85.62 59	90.53 46	79.88 92	64.64 210	76.35 143	96.28 12	53.53 194	85.63 68	81.59 69	92.81 31	97.71 12	86.88 2	94.56 25	92.83 24	96.35 6	93.84 9

TSAR-MVS + MP.		89.67 24	92.25 28	86.65 25	91.53 18	90.98 17	96.15 13	73.30 56	87.88 49	81.83 66	92.92 30	95.15 61	82.23 18	93.58 34	92.25 33	94.87 29	93.01 25
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
APDe-MVS		89.85 20	92.91 10	86.29 26	90.47 38	91.34 7	96.04 14	76.41 39	91.11 17	78.50 89	93.44 22	95.82 42	81.55 23	93.16 37	91.90 38	94.77 32	93.58 15
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMP_NAP		89.86 19	91.96 33	87.42 19	91.00 30	90.08 30	96.00 15	76.61 36	89.28 35	87.73 17	90.04 59	91.80 113	78.71 38	94.36 28	93.82 17	94.48 37	94.32 6

CPTT-MVS		89.63 25	90.52 47	88.59 6	90.95 31	90.74 21	95.71 16	79.13 15	87.70 50	85.68 38	80.05 142	95.74 46	84.77 6	94.28 29	92.68 26	95.28 26	92.45 31

HFP-MVS		90.32 13	92.37 22	87.94 13	91.46 21	90.91 18	95.69 17	79.49 12	89.94 34	83.50 50	89.06 73	94.44 76	81.68 22	94.17 30	94.19 13	95.81 17	93.87 7

DPE-MVS		89.81 22	92.34 24	86.86 23	89.69 44	91.00 16	95.53 18	76.91 33	88.18 46	83.43 53	93.48 21	95.19 58	81.07 26	92.75 45	92.07 36	94.55 36	93.74 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
COLMAP_ROB	85.66 2	91.85 2	95.01 2	88.16 11	88.98 51	92.86 2	95.51 19	72.17 62	94.95 4	91.27 3	94.11 17	97.77 11	84.22 8	96.49 4	95.27 5	96.79 2	93.60 12
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
APD-MVS		89.14 29	91.25 42	86.67 24	91.73 15	91.02 15	95.50 20	77.74 24	84.04 83	79.47 82	91.48 46	94.85 67	81.14 25	92.94 41	92.20 35	94.47 38	92.24 32
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
LGP-MVS_train		90.56 9	92.38 21	88.43 9	90.88 32	91.15 11	95.35 21	77.65 25	86.26 64	87.23 23	90.45 56	97.35 17	83.20 14	95.44 16	93.41 20	96.28 8	92.63 27

DVP-MVS++		90.50 10	94.18 4	86.21 27	92.52 7	90.29 28	95.29 22	76.02 41	94.24 5	82.82 55	95.84 5	97.56 15	76.82 55	93.13 38	91.20 44	93.78 45	97.01 1

MSP-MVS		88.51 42	91.36 40	85.19 39	90.63 36	92.01 4	95.29 22	77.52 27	90.48 27	80.21 76	90.21 58	96.08 34	76.38 59	88.30 96	91.42 41	91.12 87	91.01 44
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
SMA-MVS		90.13 15	92.26 27	87.64 17	91.68 16	90.44 26	95.22 24	77.34 32	90.79 23	87.80 16	90.42 57	92.05 109	79.05 35	93.89 32	93.59 18	94.77 32	94.62 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
SED-MVS		88.96 37	92.37 22	84.99 40	88.64 54	89.65 37	95.11 25	75.98 42	90.73 24	80.15 77	94.21 15	94.51 75	76.59 56	92.94 41	91.17 45	93.46 50	93.37 22

HPM-MVS++		88.74 40	89.54 52	87.80 15	92.58 6	85.69 69	95.10 26	78.01 22	87.08 56	87.66 19	87.89 86	92.07 107	80.28 30	90.97 69	91.41 43	93.17 57	91.69 37

OPM-MVS		89.82 21	92.24 29	86.99 22	90.86 33	89.35 38	95.07 27	75.91 43	91.16 16	86.87 30	91.07 52	97.29 18	79.13 34	93.32 35	91.99 37	94.12 40	91.49 40
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMP	80.00 8	90.12 16	92.30 26	87.58 18	90.83 34	91.10 12	94.96 28	76.06 40	87.47 52	85.33 39	88.91 77	97.65 14	82.13 19	95.31 17	93.44 19	96.14 10	92.22 33
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
UA-Net		89.02 33	91.44 39	86.20 28	94.88 1	89.84 34	94.76 29	77.45 28	85.41 71	74.79 106	88.83 78	88.90 137	78.67 40	96.06 7	95.45 4	96.66 3	95.58 2

DeepC-MVS	83.59 4	90.37 12	92.56 18	87.82 14	91.26 27	92.33 3	94.72 30	80.04 9	90.01 32	84.61 42	93.33 23	94.22 79	80.59 27	92.90 43	92.52 28	95.69 21	92.57 28
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
train_agg		86.67 53	87.73 69	85.43 35	91.51 19	82.72 88	94.47 31	74.22 53	81.71 101	81.54 70	89.20 72	92.87 95	78.33 43	90.12 79	88.47 68	92.51 69	89.04 59

SD-MVS		89.91 18	92.23 30	87.19 21	91.31 24	89.79 35	94.31 32	75.34 47	89.26 37	81.79 67	92.68 32	95.08 63	83.88 11	93.10 39	92.69 25	96.54 4	93.02 24
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
3Dnovator+	83.71 3	88.13 44	90.00 50	85.94 29	86.82 71	91.06 13	94.26 33	75.39 46	88.85 41	85.76 37	85.74 110	86.92 146	78.02 45	93.03 40	92.21 34	95.39 25	92.21 34

DeepPCF-MVS	81.61 6	87.95 47	90.29 49	85.22 38	87.48 65	90.01 31	93.79 34	73.54 54	88.93 39	83.89 45	89.40 68	90.84 122	80.26 31	90.62 72	90.19 53	92.36 70	92.03 35

DVP-MVS		89.40 27	92.69 13	85.56 34	89.01 50	89.85 33	93.72 35	75.42 45	92.28 11	80.49 72	94.36 13	94.87 66	81.46 24	92.49 49	91.42 41	93.27 53	93.54 17
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
PMVS	79.51 9	90.23 14	92.67 14	87.39 20	90.16 39	88.75 42	93.64 36	75.78 44	90.00 33	83.70 47	92.97 29	92.22 104	86.13 4	97.01 3	96.79 2	94.94 28	90.96 45
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
LTVRE_ROB	86.82 1	91.55 3	94.43 3	88.19 10	83.19 112	86.35 65	93.60 37	78.79 18	95.48 3	91.79 2	93.08 27	97.21 20	86.34 3	97.06 2	96.27 3	95.46 23	95.56 3
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
WR-MVS		89.79 23	93.66 5	85.27 37	91.32 23	88.27 46	93.49 38	79.86 10	92.75 9	75.37 102	96.86 1	98.38 5	75.10 71	95.93 8	94.07 14	96.46 5	89.39 56

NCCC		86.74 52	87.97 68	85.31 36	90.64 35	87.25 58	93.27 39	74.59 49	86.50 60	83.72 46	75.92 173	92.39 101	77.08 53	91.72 53	90.68 48	92.57 67	91.30 42

CNVR-MVS		86.93 51	88.98 56	84.54 44	90.11 40	87.41 57	93.23 40	73.47 55	86.31 63	82.25 61	82.96 130	92.15 105	76.04 62	91.69 54	90.69 47	92.17 73	91.64 39

OMC-MVS		88.16 43	91.34 41	84.46 46	86.85 70	90.63 23	93.01 41	67.00 103	90.35 28	87.40 21	86.86 100	96.35 29	77.66 49	92.63 47	90.84 46	94.84 30	91.68 38

CDPH-MVS		86.66 54	88.52 59	84.48 45	89.61 45	88.27 46	92.86 42	72.69 61	80.55 119	82.71 56	86.92 99	93.32 90	75.55 67	91.00 68	89.85 56	93.47 49	89.71 53

DeepC-MVS_fast	81.78 5	87.38 49	89.64 51	84.75 41	89.89 42	90.70 22	92.74 43	74.45 50	86.02 65	82.16 64	86.05 107	91.99 111	75.84 65	91.16 63	90.44 49	93.41 51	91.09 43
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LS3D		89.02 33	91.69 36	85.91 30	89.72 43	90.81 20	92.56 44	71.69 66	90.83 22	87.24 22	89.71 64	92.07 107	78.37 42	94.43 27	92.59 27	95.86 13	91.35 41

ACMH+	79.05 11	89.62 26	93.08 8	85.58 32	88.58 55	89.26 39	92.18 45	74.23 52	93.55 8	82.66 58	92.32 37	98.35 7	80.29 29	95.28 18	92.34 31	95.52 22	90.43 48

WR-MVS_H		88.99 35	93.28 6	83.99 53	91.92 11	89.13 40	91.95 46	83.23 1	90.14 30	71.92 125	95.85 4	98.01 10	71.83 97	95.82 9	93.19 22	93.07 59	90.83 47

CS-MVS-test		83.59 79	84.86 101	82.10 69	83.04 114	81.05 105	91.58 47	67.48 102	72.52 155	78.42 90	84.75 120	91.82 112	78.62 41	91.98 50	87.54 76	93.48 48	84.35 93

MVS_0304		84.73 70	86.19 81	83.02 57	88.32 56	86.71 62	91.55 48	70.87 70	73.79 148	82.88 54	85.13 114	93.35 89	72.55 89	88.62 91	87.69 74	91.93 75	88.05 70

ACMH	78.40 12	88.94 38	92.62 16	84.65 42	86.45 74	87.16 59	91.47 49	68.79 87	95.49 2	89.74 6	93.55 20	98.50 2	77.96 46	94.14 31	89.57 61	93.49 47	89.94 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HQP-MVS		85.02 66	86.41 79	83.40 54	89.19 48	86.59 63	91.28 50	71.60 67	82.79 90	83.48 51	78.65 151	93.54 87	72.55 89	86.49 111	85.89 95	92.28 72	90.95 46

PCF-MVS	76.59 14	84.11 74	85.27 92	82.76 64	86.12 78	88.30 45	91.24 51	69.10 82	82.36 96	84.45 43	77.56 157	90.40 127	72.91 88	85.88 116	83.88 113	92.72 64	88.53 63
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TSAR-MVS + ACMM		89.14 29	92.11 32	85.67 31	89.27 47	90.61 24	90.98 52	79.48 13	88.86 40	79.80 79	93.01 28	93.53 88	83.17 15	92.75 45	92.45 29	91.32 82	93.59 13

DTE-MVSNet		88.99 35	92.77 12	84.59 43	93.31 2	88.10 49	90.96 53	83.09 2	91.38 14	76.21 96	96.03 2	98.04 8	70.78 106	95.65 14	92.32 32	93.18 56	87.84 71

CNLPA		85.50 61	88.58 57	81.91 71	84.55 91	87.52 56	90.89 54	63.56 139	88.18 46	84.06 44	83.85 127	91.34 119	76.46 58	91.27 60	89.00 66	91.96 74	88.88 61

PEN-MVS		88.86 39	92.92 9	84.11 52	92.92 4	88.05 51	90.83 55	82.67 5	91.04 18	74.83 105	95.97 3	98.47 3	70.38 107	95.70 13	92.43 30	93.05 60	88.78 62

SF-MVS		87.85 48	90.95 44	84.22 49	88.17 60	87.90 53	90.80 56	71.80 65	89.28 35	82.70 57	89.90 61	95.37 55	77.91 47	91.69 54	90.04 54	93.95 44	92.47 29

PHI-MVS		86.37 56	88.14 65	84.30 47	86.65 73	87.56 55	90.76 57	70.16 73	82.55 93	89.65 7	84.89 118	92.40 100	75.97 63	90.88 70	89.70 58	92.58 65	89.03 60

TAPA-MVS	78.00 13	85.88 58	88.37 61	82.96 60	84.69 87	88.62 43	90.62 58	64.22 129	89.15 38	88.05 14	78.83 149	93.71 83	76.20 61	90.11 80	88.22 71	94.00 41	89.97 51
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Vis-MVSNet		83.32 84	88.12 66	77.71 106	77.91 158	83.44 83	90.58 59	69.49 78	81.11 113	67.10 153	89.85 62	91.48 117	71.71 98	91.34 59	89.37 62	89.48 105	90.26 49
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CSCG		88.12 45	91.45 38	84.23 48	88.12 61	90.59 25	90.57 60	68.60 89	91.37 15	83.45 52	89.94 60	95.14 62	78.71 38	91.45 58	88.21 72	95.96 12	93.44 19

AdaColmap		84.15 73	85.14 95	83.00 59	89.08 49	87.14 60	90.56 61	70.90 69	82.40 95	80.41 73	73.82 184	84.69 157	75.19 70	91.58 57	89.90 55	91.87 76	86.48 78

PS-CasMVS		89.07 32	93.23 7	84.21 50	92.44 8	88.23 48	90.54 62	82.95 3	90.50 26	75.31 103	95.80 6	98.37 6	71.16 100	96.30 5	93.32 21	92.88 61	90.11 50

SixPastTwentyTwo		89.14 29	92.19 31	85.58 32	84.62 89	82.56 91	90.53 63	71.93 64	91.95 12	85.89 35	94.22 14	97.25 19	85.42 5	95.73 12	91.71 40	95.08 27	91.89 36

MVS_111021_HR		83.95 75	86.10 83	81.44 76	84.62 89	80.29 111	90.51 64	68.05 96	84.07 82	80.38 74	84.74 121	91.37 118	74.23 77	90.37 75	87.25 78	90.86 89	84.59 90

TSAR-MVS + COLMAP		85.51 60	88.36 62	82.19 67	86.05 79	87.69 54	90.50 65	70.60 72	86.40 61	82.33 59	89.69 65	92.52 99	74.01 81	87.53 100	86.84 83	89.63 102	87.80 72

CP-MVSNet		88.71 41	92.63 15	84.13 51	92.39 9	88.09 50	90.47 66	82.86 4	88.79 42	75.16 104	94.87 9	97.68 13	71.05 102	96.16 6	93.18 23	92.85 62	89.64 54

MCST-MVS		84.79 69	86.48 77	82.83 63	87.30 67	87.03 61	90.46 67	69.33 81	83.14 87	82.21 63	81.69 138	92.14 106	75.09 72	87.27 103	84.78 106	92.58 65	89.30 57

gm-plane-assit		71.56 170	69.99 186	73.39 138	84.43 95	73.21 165	90.42 68	51.36 201	84.08 81	76.00 98	91.30 49	37.09 228	59.01 159	73.65 190	70.24 189	79.09 181	60.37 203

CANet		82.84 90	84.60 106	80.78 81	87.30 67	85.20 72	90.23 69	69.00 83	72.16 158	78.73 88	84.49 123	90.70 125	69.54 112	87.65 99	86.17 90	89.87 99	85.84 83

CLD-MVS		82.75 93	87.22 74	77.54 109	88.01 62	85.76 68	90.23 69	54.52 188	82.28 97	82.11 65	88.48 81	95.27 56	63.95 139	89.41 85	88.29 70	86.45 144	81.01 126
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
DPM-MVS		81.42 104	82.11 132	80.62 86	87.54 64	85.30 71	90.18 71	68.96 84	81.00 115	79.15 84	70.45 200	83.29 161	67.67 121	82.81 144	83.46 117	90.19 93	88.48 64

RPSCF		88.05 46	92.61 17	82.73 65	84.24 96	88.40 44	90.04 72	66.29 107	91.46 13	82.29 60	88.93 76	96.01 38	79.38 32	95.15 21	94.90 6	94.15 39	93.40 20

v7n		87.11 50	90.46 48	83.19 56	85.22 85	83.69 80	90.03 73	68.20 95	91.01 19	86.71 33	94.80 10	98.46 4	77.69 48	91.10 65	85.98 92	91.30 83	88.19 66

GeoE		81.92 100	83.87 118	79.66 94	84.64 88	79.87 113	89.75 74	65.90 114	76.12 140	75.87 99	84.62 122	92.23 103	71.96 96	86.83 108	83.60 116	89.83 100	83.81 99

MVS_111021_LR		83.20 86	85.33 91	80.73 84	82.88 117	78.23 128	89.61 75	65.23 120	82.08 98	81.19 71	85.31 112	92.04 110	75.22 69	89.50 83	85.90 94	90.24 92	84.23 94

v1192		83.61 78	85.23 93	81.72 73	84.05 98	82.15 94	89.54 76	66.20 108	81.38 110	86.76 32	91.79 43	96.03 36	74.88 74	81.81 153	80.92 139	88.91 114	82.50 114

v1921920		83.49 82	84.94 99	81.80 72	83.78 105	81.20 103	89.50 77	65.91 113	81.64 103	87.18 24	91.70 44	95.39 54	75.85 64	81.56 156	80.27 145	88.60 119	82.80 110

v1240		83.57 80	84.94 99	81.97 70	84.05 98	81.27 101	89.46 78	66.06 110	81.31 111	87.50 20	91.88 42	95.46 52	76.25 60	81.16 158	80.51 143	88.52 124	82.98 108

v144192		83.43 83	84.97 98	81.63 75	83.43 108	81.23 102	89.42 79	66.04 112	81.45 109	86.40 34	91.46 47	95.70 47	75.76 66	82.14 149	80.23 146	88.74 116	82.57 113

MAR-MVS		81.98 99	82.92 128	80.88 80	85.18 86	85.85 67	89.13 80	69.52 76	71.21 162	82.25 61	71.28 194	88.89 138	69.69 109	88.71 89	86.96 79	89.52 104	87.57 73
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
TSAR-MVS + GP.		85.32 64	87.41 73	82.89 62	90.07 41	85.69 69	89.07 81	72.99 60	82.45 94	74.52 109	85.09 115	87.67 143	79.24 33	91.11 64	90.41 50	91.45 79	89.45 55

v1144		83.22 85	85.01 96	81.14 77	83.76 106	81.60 97	88.95 82	65.58 118	81.89 100	85.80 36	91.68 45	95.84 41	74.04 80	82.12 150	80.56 142	88.70 118	81.41 123

PLC	76.06 15	85.38 63	87.46 71	82.95 61	85.79 81	88.84 41	88.86 83	68.70 88	87.06 57	83.60 48	79.02 145	90.05 128	77.37 52	90.88 70	89.66 59	93.37 52	86.74 77
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ETV-MVS		79.01 127	77.98 149	80.22 91	86.69 72	79.73 116	88.80 84	68.27 94	63.22 196	71.56 127	70.25 202	73.63 195	73.66 84	90.30 78	86.77 84	92.33 71	81.95 119

v10		83.17 87	85.22 94	80.78 81	83.26 111	82.99 86	88.66 85	66.49 106	79.24 128	83.60 48	91.46 47	95.47 51	74.12 78	82.60 147	80.66 140	88.53 123	84.11 97

Effi-MVS+-dtu		82.04 98	83.39 125	80.48 89	85.48 83	86.57 64	88.40 86	68.28 93	69.04 173	73.13 118	76.26 168	91.11 121	74.74 75	88.40 94	87.76 73	92.84 63	84.57 91

EPNet		79.36 122	79.44 142	79.27 98	89.51 46	77.20 137	88.35 87	77.35 31	68.27 175	74.29 110	76.31 166	79.22 175	59.63 155	85.02 128	85.45 99	86.49 143	84.61 89
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
UniMVSNet (Re)		84.95 67	88.53 58	80.78 81	87.82 63	84.21 75	88.03 88	76.50 37	81.18 112	69.29 139	92.63 35	96.83 22	69.07 114	91.23 62	89.60 60	93.97 43	84.00 98

PVSNet_Blended_VisFu		83.00 88	84.16 115	81.65 74	82.17 124	86.01 66	88.03 88	71.23 68	76.05 141	79.54 81	83.88 126	83.44 159	77.49 51	87.38 101	84.93 104	91.41 80	87.40 75

Baseline_NR-MVSNet		82.79 91	86.51 76	78.44 103	88.30 57	75.62 151	87.81 90	74.97 48	81.53 105	66.84 154	94.71 12	96.46 25	66.90 125	91.79 51	83.37 122	85.83 153	82.09 117

Fast-Effi-MVS+		81.42 104	83.82 120	78.62 101	82.24 123	80.62 107	87.72 91	63.51 140	73.01 150	74.75 107	83.80 128	92.70 97	73.44 86	88.15 98	85.26 100	90.05 94	83.17 104

v2v482		82.20 96	84.26 111	79.81 93	82.67 120	80.18 112	87.67 92	63.96 136	81.69 102	84.73 41	91.27 50	96.33 31	72.05 95	81.94 152	79.56 150	87.79 130	78.84 143

TPM-MVS					86.18 77	83.43 84	87.57 93			78.77 87	69.75 204	84.63 158	62.24 148			89.88 98	88.48 64
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
Effi-MVS+		82.33 94	83.87 118	80.52 88	84.51 94	81.32 100	87.53 94	68.05 96	74.94 146	79.67 80	82.37 135	92.31 102	72.21 91	85.06 124	86.91 81	91.18 85	84.20 95

pmmvs-eth3d		79.64 118	82.06 133	76.83 112	80.05 136	72.64 167	87.47 95	66.59 104	80.83 116	73.50 114	89.32 70	93.20 91	67.78 119	80.78 161	81.64 135	85.58 156	76.01 154

TranMVSNet+NR-MVSNet		85.23 65	89.38 53	80.39 90	88.78 53	83.77 78	87.40 96	76.75 34	85.47 69	68.99 141	95.18 8	97.55 16	67.13 124	91.61 56	89.13 65	93.26 54	82.95 109

CS-MVS		83.57 80	84.79 103	82.14 68	83.83 104	81.48 98	87.29 97	66.54 105	72.73 154	80.05 78	84.04 125	93.12 94	80.35 28	89.50 83	86.34 88	94.76 34	86.32 81

v8		82.20 96	84.56 107	79.45 95	82.42 121	81.65 96	87.26 98	64.27 128	79.36 127	81.70 68	91.04 53	95.75 45	73.30 87	82.82 143	79.18 153	87.74 131	82.09 117

3Dnovator	79.41 10	82.21 95	86.07 84	77.71 106	79.31 143	84.61 73	87.18 99	61.02 161	85.65 67	76.11 97	85.07 116	85.38 155	70.96 104	87.22 104	86.47 85	91.66 77	88.12 69

PM-MVS		80.42 112	83.63 122	76.67 113	78.04 155	72.37 169	87.14 100	60.18 167	80.13 121	71.75 126	86.12 106	93.92 82	77.08 53	86.56 110	85.12 102	85.83 153	81.18 124

NR-MVSNet		82.89 89	87.43 72	77.59 108	83.91 102	83.59 81	87.10 101	78.35 19	80.64 117	68.85 142	92.67 33	96.50 24	54.19 180	87.19 106	88.68 67	93.16 58	82.75 111

UniMVSNet_NR-MVSNet		84.62 71	88.00 67	80.68 85	88.18 59	83.83 77	87.06 102	76.47 38	81.46 108	70.49 133	93.24 24	95.56 49	68.13 117	90.43 73	88.47 68	93.78 45	83.02 106

DU-MVS		84.88 68	88.27 64	80.92 79	88.30 57	83.59 81	87.06 102	78.35 19	80.64 117	70.49 133	92.67 33	96.91 21	68.13 117	91.79 51	89.29 64	93.20 55	83.02 106

MSLP-MVS++		86.29 57	89.10 55	83.01 58	85.71 82	89.79 35	87.04 104	74.39 51	85.17 73	78.92 86	77.59 156	93.57 86	82.60 17	93.23 36	91.88 39	89.42 107	92.46 30

EG-PatchMatch MVS		84.35 72	87.55 70	80.62 86	86.38 75	82.24 93	86.75 105	64.02 134	84.24 79	78.17 92	89.38 69	95.03 65	78.78 37	89.95 81	86.33 89	89.59 103	85.65 85

UGNet		79.62 119	85.91 86	72.28 143	73.52 180	83.91 76	86.64 106	69.51 77	79.85 124	62.57 165	85.82 109	89.63 129	53.18 184	88.39 95	87.35 77	88.28 126	86.43 79
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
V42		79.59 120	83.59 123	74.93 129	69.61 193	77.05 139	86.59 107	55.84 183	78.42 132	77.29 94	89.84 63	95.08 63	74.12 78	83.05 140	80.11 148	86.12 147	81.59 122

FPMVS		81.56 102	84.04 117	78.66 100	82.92 115	75.96 147	86.48 108	65.66 117	84.67 77	71.47 128	77.78 154	83.22 162	77.57 50	91.24 61	90.21 52	87.84 129	85.21 87

EIA-MVS		78.57 129	77.90 150	79.35 97	87.24 69	80.71 106	86.16 109	64.03 133	62.63 201	73.49 115	73.60 185	76.12 189	73.83 82	88.49 93	84.93 104	91.36 81	78.78 144

FC-MVSNet-train		79.20 125	86.29 80	70.94 150	84.06 97	77.67 131	85.68 110	64.11 131	82.90 89	52.22 195	92.57 36	93.69 84	49.52 197	88.30 96	86.93 80	90.03 95	81.95 119

IS_MVSNet		81.72 101	85.01 96	77.90 105	86.19 76	82.64 90	85.56 111	70.02 74	80.11 122	63.52 161	87.28 94	81.18 169	67.26 122	91.08 67	89.33 63	94.82 31	83.42 103

EC-MVSNet		83.70 77	84.77 104	82.46 66	87.47 66	82.79 87	85.50 112	72.00 63	69.81 166	77.66 93	85.02 117	89.63 129	78.14 44	90.40 74	87.56 75	94.00 41	88.16 67

FA-MVS(training)		78.93 128	80.63 138	76.93 111	79.79 139	75.57 152	85.44 113	61.95 153	77.19 136	78.97 85	84.82 119	82.47 164	66.43 130	84.09 136	80.13 147	89.02 111	80.15 137

TinyColmap		83.79 76	86.12 82	81.07 78	83.42 109	81.44 99	85.42 114	68.55 90	88.71 43	89.46 8	87.60 88	92.72 96	70.34 108	89.29 86	81.94 131	89.20 108	81.12 125

EPP-MVSNet		82.76 92	86.47 78	78.45 102	86.00 80	84.47 74	85.39 115	68.42 91	84.17 80	62.97 163	89.26 71	76.84 185	72.13 94	92.56 48	90.40 51	95.76 20	87.56 74

Gipuma		86.47 55	89.25 54	83.23 55	83.88 103	78.78 124	85.35 116	68.42 91	92.69 10	89.03 11	91.94 39	96.32 32	81.80 21	94.45 26	86.86 82	90.91 88	83.69 100
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
FC-MVSNet-test		75.91 146	83.59 123	66.95 175	76.63 172	69.07 179	85.33 117	64.97 122	84.87 76	41.95 211	93.17 25	87.04 145	47.78 200	91.09 66	85.56 98	85.06 160	74.34 163

MSDG		81.39 106	84.23 113	78.09 104	82.40 122	82.47 92	85.31 118	60.91 162	79.73 125	80.26 75	86.30 103	88.27 141	69.67 110	87.20 105	84.98 103	89.97 96	80.67 128

thisisatest0515		81.18 109	84.32 110	77.52 110	76.73 170	74.84 158	85.06 119	61.37 158	81.05 114	73.95 111	88.79 79	89.25 134	75.49 68	85.98 115	84.78 106	92.53 68	85.56 86

Fast-Effi-MVS+-dtu		76.92 136	77.18 155	76.62 114	79.55 140	79.17 120	84.80 120	77.40 29	64.46 191	68.75 144	70.81 198	86.57 148	63.36 146	81.74 154	81.76 133	85.86 152	75.78 157

DELS-MVS		79.71 116	83.74 121	75.01 126	79.31 143	82.68 89	84.79 121	60.06 168	75.43 144	69.09 140	86.13 105	89.38 132	67.16 123	85.12 123	83.87 114	89.65 101	83.57 101
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
MIMVSNet1		73.40 158	81.85 134	63.55 188	72.90 183	64.37 193	84.58 122	53.60 193	90.84 21	53.92 187	87.75 87	96.10 33	45.31 203	85.37 122	79.32 152	70.98 197	69.18 182

ambc			88.38 60		91.62 17	87.97 52	84.48 123		88.64 44	87.93 15	87.38 92	94.82 69	74.53 76	89.14 88	83.86 115	85.94 151	86.84 76

pmmvs4		75.92 145	77.48 154	74.10 133	78.21 154	70.94 171	84.06 124	64.78 123	75.13 145	68.47 147	84.12 124	83.32 160	64.74 138	75.93 183	79.14 154	84.31 163	73.77 167

MDA-MVSNet-bldmvs		76.51 139	82.87 129	69.09 163	50.71 221	74.72 160	84.05 125	60.27 166	81.62 104	71.16 130	88.21 84	91.58 114	69.62 111	92.78 44	77.48 161	78.75 182	73.69 168

CANet_DTU		75.04 152	78.45 145	71.07 147	77.27 161	77.96 129	83.88 126	58.00 178	64.11 192	68.67 145	75.65 175	88.37 140	53.92 182	82.05 151	81.11 136	84.67 161	79.88 138

casdiffmvs_mvg		81.50 103	85.70 88	76.60 115	82.68 119	80.54 108	83.50 127	64.49 127	83.40 84	72.53 119	92.15 38	95.40 53	65.84 132	84.69 131	81.89 132	90.59 90	81.86 121
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
our_test_3					73.27 181	70.91 172	83.26 128

HyFIR lowres test		73.29 159	74.14 176	72.30 142	73.08 182	78.33 127	83.12 129	62.41 151	63.81 193	62.13 167	76.67 165	78.50 178	71.09 101	74.13 187	77.47 162	81.98 174	70.10 177

IB-MVS	71.28 17	75.21 151	77.00 157	73.12 141	76.76 164	77.45 133	83.05 130	58.92 174	63.01 197	64.31 160	59.99 216	87.57 144	68.64 115	86.26 114	82.34 129	87.05 138	82.36 116
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
CVMVSNet		75.65 148	77.62 153	73.35 140	71.95 186	69.89 176	83.04 131	60.84 163	69.12 171	68.76 143	79.92 143	78.93 177	73.64 85	81.02 159	81.01 138	81.86 175	83.43 102

casdiffmvs		79.93 114	84.11 116	75.05 124	81.41 130	78.99 122	82.95 132	62.90 147	81.53 105	68.60 146	91.94 39	96.03 36	65.84 132	82.89 142	77.07 164	88.59 120	80.34 134
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tttt0517		75.86 147	76.23 164	75.42 120	75.55 176	74.06 162	82.73 133	60.31 164	69.24 169	70.24 135	79.18 144	58.79 213	72.17 92	84.49 133	83.08 124	91.54 78	84.80 88

ET-MVSNet_ETH3D		74.71 154	74.19 175	75.31 122	79.22 145	75.29 153	82.70 134	64.05 132	65.45 186	70.96 132	77.15 161	57.70 215	65.89 131	84.40 134	81.65 134	89.03 110	77.67 150

USDC		81.39 106	83.07 126	79.43 96	81.48 128	78.95 123	82.62 135	66.17 109	87.45 53	90.73 4	82.40 134	93.65 85	66.57 127	83.63 139	77.97 156	89.00 112	77.45 151

EPNet_dtu		71.90 169	73.03 181	70.59 152	78.28 152	61.64 199	82.44 136	64.12 130	63.26 195	69.74 136	71.47 192	82.41 165	51.89 193	78.83 170	78.01 155	77.07 183	75.60 159
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MDTV_nov1_ep13_2view		72.96 164	75.59 169	69.88 157	71.15 190	64.86 192	82.31 137	54.45 189	76.30 138	78.32 91	86.52 101	91.58 114	61.35 150	76.80 176	66.83 196	71.70 190	66.26 186

thisisatest0530		75.54 149	75.95 168	75.05 124	75.08 177	73.56 164	82.15 138	60.31 164	69.17 170	69.32 138	79.02 145	58.78 214	72.17 92	83.88 137	83.08 124	91.30 83	84.20 95

v148		79.33 123	82.32 131	75.84 118	80.14 135	75.74 148	81.98 139	57.06 180	81.51 107	79.36 83	89.42 67	96.42 27	71.32 99	81.54 157	75.29 175	85.20 158	76.32 153

UniMVSNet_ETH3D		85.39 62	91.12 43	78.71 99	90.48 37	83.72 79	81.76 140	82.41 6	93.84 6	64.43 159	95.41 7	98.76 1	63.72 141	93.63 33	89.74 57	89.47 106	82.74 112

EU-MVSNet		76.48 140	80.53 139	71.75 145	67.62 200	70.30 174	81.74 141	54.06 191	75.47 143	71.01 131	80.10 140	93.17 93	73.67 83	83.73 138	77.85 157	82.40 172	83.07 105

Vis-MVSNet (Re-imp)		76.15 143	80.84 137	70.68 151	83.66 107	74.80 159	81.66 142	69.59 75	80.48 120	46.94 205	87.44 91	80.63 171	53.14 185	86.87 107	84.56 109	89.12 109	71.12 173

DI_MVS_plusplus_trai		77.64 133	79.64 141	75.31 122	79.87 138	76.89 140	81.55 143	63.64 138	76.21 139	72.03 124	85.59 111	82.97 163	66.63 126	79.27 169	77.78 158	88.14 127	78.76 145

test1111		79.67 117	84.40 108	74.16 132	85.29 84	79.56 118	81.16 144	73.13 59	84.65 78	56.08 178	88.38 82	86.14 150	60.49 152	89.78 82	85.59 97	88.79 115	76.68 152

testgi		68.20 183	76.05 166	59.04 196	79.99 137	67.32 186	81.16 144	51.78 199	84.91 75	39.36 216	73.42 186	95.19 58	32.79 216	76.54 180	70.40 188	69.14 201	64.55 190

PatchMatch-RL		76.05 144	76.64 160	75.36 121	77.84 160	69.87 177	81.09 146	63.43 141	71.66 160	68.34 148	71.70 190	81.76 168	74.98 73	84.83 130	83.44 118	86.45 144	73.22 170

IterMVS		73.62 157	76.53 161	70.23 155	71.83 187	77.18 138	80.69 147	53.22 195	72.23 157	66.62 155	85.21 113	78.96 176	69.54 112	76.28 182	71.63 185	79.45 179	74.25 165
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs		76.74 137	81.61 135	71.06 148	75.64 175	74.45 161	80.68 148	57.57 179	77.48 133	67.62 152	88.95 75	93.94 81	61.98 149	79.74 166	76.18 169	82.85 171	80.50 129
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DCV-MVSNet		80.04 113	85.67 90	73.48 137	82.91 116	81.11 104	80.44 149	66.06 110	85.01 74	62.53 166	78.84 148	94.43 77	58.51 161	88.66 90	85.91 93	90.41 91	85.73 84

canonicalmvs		81.22 108	86.04 85	75.60 119	83.17 113	83.18 85	80.29 150	65.82 116	85.97 66	67.98 149	77.74 155	91.51 116	65.17 135	88.62 91	86.15 91	91.17 86	89.09 58

GA-MVS		75.01 153	76.39 162	73.39 138	78.37 151	75.66 150	80.03 151	58.40 176	70.51 164	75.85 100	83.24 129	76.14 188	63.75 140	77.28 175	76.62 168	83.97 165	75.30 161

OpenMVS	75.38 16	78.44 130	81.39 136	74.99 127	80.46 133	79.85 114	79.99 152	58.31 177	77.34 135	73.85 112	77.19 160	82.33 167	68.60 116	84.67 132	81.95 130	88.72 117	86.40 80

MVS_Test		76.72 138	79.40 143	73.60 134	78.85 149	74.99 156	79.91 153	61.56 156	69.67 167	72.44 120	85.98 108	90.78 123	63.50 144	78.30 171	75.74 172	85.33 157	80.31 135

IterMVS-LS		79.79 115	82.56 130	76.56 116	81.83 126	77.85 130	79.90 154	69.42 80	78.93 130	71.21 129	90.47 55	85.20 156	70.86 105	80.54 163	80.57 141	86.15 146	84.36 92
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
QAPM		80.43 111	84.34 109	75.86 117	79.40 142	82.06 95	79.86 155	61.94 154	83.28 86	74.73 108	81.74 137	85.44 154	70.97 103	84.99 129	84.71 108	88.29 125	88.14 68

PVSNet_BlendedMVS		76.45 141	78.12 147	74.49 130	76.76 164	78.46 125	79.65 156	63.26 143	65.42 187	73.15 116	75.05 178	88.96 135	66.51 128	82.73 145	77.66 159	87.61 132	78.60 146

PVSNet_Blended		76.45 141	78.12 147	74.49 130	76.76 164	78.46 125	79.65 156	63.26 143	65.42 187	73.15 116	75.05 178	88.96 135	66.51 128	82.73 145	77.66 159	87.61 132	78.60 146

test2506		75.32 150	76.87 159	73.50 136	84.55 91	80.37 109	79.63 158	73.23 57	82.64 91	55.41 182	76.87 163	45.42 227	59.61 156	90.35 76	86.46 86	88.58 121	75.98 155

ECVR-MVS		79.31 124	84.20 114	73.60 134	84.55 91	80.37 109	79.63 158	73.23 57	82.64 91	55.98 179	87.50 89	86.85 147	59.61 156	90.35 76	86.46 86	88.58 121	75.26 162

CDS-MVSNet		73.07 163	77.02 156	68.46 166	81.62 127	72.89 166	79.56 160	70.78 71	69.56 168	52.52 192	77.37 159	81.12 170	42.60 205	84.20 135	83.93 112	83.65 166	70.07 178
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CostFormer		66.81 188	66.94 194	66.67 176	72.79 184	68.25 182	79.55 161	55.57 184	65.52 185	62.77 164	76.98 162	60.09 209	56.73 167	65.69 211	62.35 200	72.59 189	69.71 179

Anonymous202405211			84.68 105		83.92 101	79.45 119	79.03 162	67.79 98	82.01 99		88.77 80	92.58 98	55.93 171	86.68 109	84.26 110	88.92 113	78.98 142

CHOSEN 1792x2688		68.80 180	71.09 183	66.13 179	69.11 195	68.89 181	78.98 163	54.68 186	61.63 203	56.69 175	71.56 191	78.39 179	67.69 120	72.13 194	72.01 184	69.63 200	73.02 171

Anonymous20231211		79.37 121	85.78 87	71.89 144	82.87 118	79.66 117	78.77 164	63.93 137	83.36 85	59.39 170	90.54 54	94.66 71	56.46 168	87.38 101	84.12 111	89.92 97	80.74 127

thres600view7		74.34 156	78.43 146	69.56 160	80.47 132	76.28 144	78.65 165	62.56 149	77.39 134	52.53 191	74.03 182	76.78 186	55.90 172	85.06 124	85.19 101	87.25 136	74.29 164

FMVSNet1		78.20 132	84.83 102	70.46 154	78.62 150	79.03 121	77.90 166	67.53 101	83.02 88	55.10 184	87.19 96	93.18 92	55.65 173	85.57 117	83.39 119	87.98 128	82.40 115

pmmvs6		80.46 110	88.34 63	71.26 146	81.96 125	77.51 132	77.54 167	68.83 86	93.72 7	55.92 180	93.94 19	98.03 9	55.94 170	89.21 87	85.61 96	87.36 135	80.38 130

TransMVSNet (Re)		79.05 126	86.66 75	70.18 156	83.32 110	75.99 146	77.54 167	63.98 135	90.68 25	55.84 181	94.80 10	96.06 35	53.73 183	86.27 113	83.22 123	86.65 139	79.61 140

thres400		73.13 162	76.99 158	68.62 165	79.46 141	74.93 157	77.23 169	61.23 160	75.54 142	52.31 194	72.20 189	77.10 184	54.89 175	82.92 141	82.62 128	86.57 142	73.66 169

MS-PatchMatch		71.18 173	73.99 177	67.89 172	77.16 162	71.76 170	77.18 170	56.38 182	67.35 176	55.04 185	74.63 180	75.70 190	62.38 147	76.62 178	75.97 171	79.22 180	75.90 156

tfpn200view9		72.01 168	75.40 170	68.06 169	77.97 156	76.44 142	77.04 171	62.67 148	66.81 178	50.82 200	67.30 207	75.67 191	52.46 192	85.06 124	82.64 127	87.41 134	73.86 166

SCA		68.54 182	67.52 193	69.73 158	67.79 199	75.04 154	76.96 172	68.94 85	66.41 180	67.86 150	74.03 182	60.96 206	65.55 134	68.99 203	65.67 197	71.30 195	61.54 202

dmvs_re		68.11 184	70.60 185	65.21 185	77.91 158	63.73 196	76.72 173	59.65 170	55.93 213	47.79 204	59.79 217	79.91 173	49.72 196	82.48 148	76.98 166	79.48 178	75.41 160

baseline2		68.71 181	68.34 191	69.14 162	75.69 174	69.70 178	76.60 174	55.53 185	60.13 206	62.07 168	66.76 209	60.35 208	60.77 151	76.53 181	74.03 177	84.19 164	70.88 174

tfpnnormal		77.16 135	84.26 111	68.88 164	81.02 131	75.02 155	76.52 175	63.30 142	87.29 54	52.40 193	91.24 51	93.97 80	54.85 177	85.46 120	81.08 137	85.18 159	75.76 158

pm-mvs1		78.21 131	85.68 89	69.50 161	80.38 134	75.73 149	76.25 176	65.04 121	87.59 51	54.47 186	93.16 26	95.99 40	54.20 179	86.37 112	82.98 126	86.64 140	77.96 149

tpm cat1		64.79 193	62.74 207	67.17 173	74.61 179	65.91 190	76.18 177	59.32 171	64.88 190	66.41 156	71.21 195	53.56 223	59.17 158	61.53 215	58.16 209	67.33 205	63.95 191

RPMNet		67.02 187	63.99 202	70.56 153	71.55 188	67.63 183	75.81 178	69.44 79	59.93 207	63.24 162	64.32 211	47.51 226	59.68 154	70.37 200	69.64 191	83.64 167	68.49 183

MDTV_nov1_ep13		64.96 191	64.77 199	65.18 186	67.08 203	62.46 198	75.80 179	51.10 202	62.27 202	69.74 136	74.12 181	62.65 204	55.64 174	68.19 205	62.16 204	71.70 190	61.57 201

GBi-Net		73.17 160	77.64 151	67.95 170	76.76 164	77.36 134	75.77 180	64.57 124	62.99 198	51.83 196	76.05 169	77.76 181	52.73 189	85.57 117	83.39 119	86.04 148	80.37 131

test1		73.17 160	77.64 151	67.95 170	76.76 164	77.36 134	75.77 180	64.57 124	62.99 198	51.83 196	76.05 169	77.76 181	52.73 189	85.57 117	83.39 119	86.04 148	80.37 131

FMVSNet2		74.43 155	79.70 140	68.27 167	76.76 164	77.36 134	75.77 180	65.36 119	72.28 156	52.97 190	81.92 136	85.61 153	52.73 189	80.66 162	79.73 149	86.04 148	80.37 131

MVSTER		68.08 185	69.73 187	66.16 178	66.33 208	70.06 175	75.71 183	52.36 197	55.18 216	58.64 172	70.23 203	56.72 218	57.34 165	79.68 167	76.03 170	86.61 141	80.20 136

test20.03		69.91 174	76.20 165	62.58 189	84.01 100	67.34 185	75.67 184	65.88 115	79.98 123	40.28 215	82.65 131	89.31 133	39.63 210	77.41 174	73.28 179	69.98 198	63.40 194

IterMVS-SCA-FT		77.23 134	79.18 144	74.96 128	76.67 171	79.85 114	75.58 185	61.34 159	73.10 149	73.79 113	86.23 104	79.61 174	79.00 36	80.28 165	75.50 174	83.41 170	79.70 139

thres200		72.41 167	76.00 167	68.21 168	78.28 152	76.28 144	74.94 186	62.56 149	72.14 159	51.35 199	69.59 205	76.51 187	54.89 175	85.06 124	80.51 143	87.25 136	71.92 172

FMVSNet3		71.40 172	75.20 173	66.97 174	75.00 178	76.59 141	74.29 187	64.57 124	62.99 198	51.83 196	76.05 169	77.76 181	51.49 194	76.58 179	77.03 165	84.62 162	79.43 141

Anonymous20231206		67.28 186	73.41 180	60.12 195	76.45 173	63.61 197	74.21 188	56.52 181	76.35 137	42.23 210	75.81 174	90.47 126	41.51 208	74.52 184	69.97 190	69.83 199	63.17 195

baseline		69.33 178	75.37 171	62.28 191	66.54 206	66.67 188	73.95 189	48.07 204	66.10 181	59.26 171	82.45 132	86.30 149	54.44 178	74.42 186	73.25 180	71.42 193	78.43 148

WB-MVS		72.91 165	82.95 127	61.21 193	68.59 196	73.96 163	73.65 190	61.48 157	90.88 20	42.55 209	94.18 16	95.80 43	53.02 186	85.42 121	75.73 173	67.97 204	64.65 189

thres100view900		69.86 175	72.97 182	66.24 177	77.97 156	72.49 168	73.29 191	59.12 172	66.81 178	50.82 200	67.30 207	75.67 191	50.54 195	78.24 172	79.40 151	85.71 155	70.88 174

PatchmatchNet		64.81 192	63.74 203	66.06 181	69.21 194	58.62 203	73.16 192	60.01 169	65.92 182	66.19 157	76.27 167	59.09 210	60.45 153	66.58 208	61.47 206	67.33 205	58.24 208
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test-mter		59.39 205	61.59 209	56.82 200	53.21 217	54.82 207	73.12 193	26.57 219	53.19 217	56.31 176	64.71 210	60.47 207	56.36 169	68.69 204	64.27 199	75.38 185	65.00 187

pmmvs5		68.91 179	74.35 174	62.56 190	67.45 202	66.78 187	71.70 194	51.47 200	67.17 177	56.25 177	82.41 133	88.59 139	47.21 202	73.21 193	74.23 176	81.30 176	68.03 184

tpm		62.79 196	63.25 204	62.26 192	70.09 192	53.78 208	71.65 195	47.31 205	65.72 184	76.70 95	80.62 139	56.40 220	48.11 199	64.20 213	58.54 207	59.70 211	63.47 193

dps		65.14 190	64.50 200	65.89 182	71.41 189	65.81 191	71.44 196	61.59 155	58.56 210	61.43 169	75.45 176	52.70 224	58.06 163	69.57 202	64.65 198	71.39 194	64.77 188

baseline1		69.62 176	73.55 179	65.02 187	78.95 148	70.39 173	71.38 197	62.03 152	70.97 163	47.95 203	78.47 152	68.19 201	47.77 201	79.65 168	76.94 167	82.05 173	70.27 176

gg-mvs-nofinetune		72.68 166	75.21 172	69.73 158	81.48 128	69.04 180	70.48 198	76.67 35	86.92 58	67.80 151	88.06 85	64.67 203	42.12 207	77.60 173	73.65 178	79.81 177	66.57 185

PatchT		66.25 189	66.76 195	65.67 183	55.87 216	60.75 200	70.17 199	59.00 173	59.80 209	72.30 121	78.68 150	54.12 222	65.04 136	71.64 195	72.91 181	71.63 192	69.40 180

pmmvs3		62.72 197	68.71 190	55.74 202	50.74 220	57.10 204	70.05 200	28.82 217	61.57 205	57.39 174	71.19 196	85.73 151	53.96 181	73.36 192	69.43 192	73.47 188	62.55 197

MIMVSNet		63.02 194	69.02 189	56.01 201	68.20 197	59.26 202	70.01 201	53.79 192	71.56 161	41.26 214	71.38 193	82.38 166	36.38 212	71.43 197	67.32 195	66.45 207	59.83 205

TAMVS		63.02 194	69.30 188	55.70 203	70.12 191	56.89 205	69.63 202	45.13 207	70.23 165	38.00 217	77.79 153	75.15 193	42.60 205	74.48 185	72.81 183	68.70 202	57.75 210

PMMVS		61.98 201	65.61 197	57.74 198	45.03 222	51.76 213	69.54 203	35.05 214	55.49 215	55.32 183	68.23 206	78.39 179	58.09 162	70.21 201	71.56 186	83.42 169	63.66 192

test-LLR		62.15 200	59.46 216	65.29 184	79.07 146	52.66 211	69.46 204	62.93 145	50.76 219	53.81 188	63.11 213	58.91 211	52.87 187	66.54 209	62.34 201	73.59 186	61.87 199

TESTMET0.1,1		57.21 208	59.46 216	54.60 206	50.95 219	52.66 211	69.46 204	26.91 218	50.76 219	53.81 188	63.11 213	58.91 211	52.87 187	66.54 209	62.34 201	73.59 186	61.87 199

CHOSEN 280x420		56.32 212	58.85 218	53.36 207	51.63 218	39.91 222	69.12 206	38.61 213	56.29 212	36.79 218	48.84 219	62.59 205	63.39 145	73.61 191	67.66 194	60.61 209	63.07 196

test0.0.03 1		61.79 202	65.33 198	57.65 199	79.07 146	64.09 194	68.51 207	62.93 145	61.59 204	33.71 219	61.58 215	71.58 199	33.43 215	70.95 198	68.68 193	68.26 203	58.82 206

tpmrst		59.42 204	60.02 214	58.71 197	67.56 201	53.10 210	66.99 208	51.88 198	63.80 194	57.68 173	76.73 164	56.49 219	48.73 198	56.47 219	55.55 212	59.43 212	58.02 209

FMVSNet5		56.37 211	60.14 213	51.98 211	60.83 212	59.58 201	66.85 209	42.37 210	52.68 218	41.33 213	47.09 220	54.68 221	35.28 213	73.88 188	70.77 187	65.24 208	62.26 198

CR-MVSNet		69.56 177	68.34 191	70.99 149	72.78 185	67.63 183	64.47 210	67.74 99	59.93 207	72.30 121	80.10 140	56.77 217	65.04 136	71.64 195	72.91 181	83.61 168	69.40 180

Patchmtry						56.88 206	64.47 210	67.74 99		72.30 121

CMPMVS	55.74 18	71.56 170	76.26 163	66.08 180	68.11 198	63.91 195	63.17 212	50.52 203	68.79 174	75.49 101	70.78 199	85.67 152	63.54 143	81.58 155	77.20 163	75.63 184	85.86 82
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmnet_mix02		62.60 198	70.81 184	53.02 208	66.56 205	50.44 215	62.81 213	46.84 206	79.13 129	43.76 208	87.45 90	90.75 124	39.85 209	70.48 199	57.09 210	58.27 213	60.32 204

EMVS		58.97 207	62.63 208	54.70 205	66.26 209	48.71 216	61.74 214	42.71 209	72.80 153	46.00 206	73.01 188	71.66 197	57.91 164	80.41 164	50.68 219	53.55 218	41.11 220

EPMVS		56.62 210	59.77 215	52.94 209	62.41 211	50.55 214	60.66 215	52.83 196	65.15 189	41.80 212	77.46 158	57.28 216	42.68 204	59.81 217	54.82 213	57.23 215	53.35 213

E-PMN		59.07 206	62.79 206	54.72 204	67.01 204	47.81 218	60.44 216	43.40 208	72.95 151	44.63 207	70.42 201	73.17 196	58.73 160	80.97 160	51.98 217	54.14 217	42.26 219

ADS-MVSNet		56.89 209	61.09 210	52.00 210	59.48 213	48.10 217	58.02 217	54.37 190	72.82 152	49.19 202	75.32 177	65.97 202	37.96 211	59.34 218	54.66 214	52.99 219	51.42 215

N_pmnet		54.95 213	65.90 196	42.18 213	66.37 207	43.86 221	57.92 218	39.79 212	79.54 126	17.24 225	86.31 102	87.91 142	25.44 217	64.68 212	51.76 218	46.33 220	47.23 217

MVS-HIRNet		59.74 203	58.74 219	60.92 194	57.74 215	45.81 219	56.02 219	58.69 175	55.69 214	65.17 158	70.86 197	71.66 197	56.75 166	61.11 216	53.74 215	71.17 196	52.28 214

GG-mvs-BLEND		41.63 217	60.36 212	19.78 217	0.14 229	66.04 189	55.66 220	0.17 225	57.64 211	2.42 228	51.82 218	69.42 200	0.28 225	64.11 214	58.29 208	60.02 210	55.18 212

new-patchmatchnet		62.59 199	73.79 178	49.53 212	76.98 163	53.57 209	53.46 221	54.64 187	85.43 70	28.81 220	91.94 39	96.41 28	25.28 218	76.80 176	53.66 216	57.99 214	58.69 207

PMMVS2		48.13 216	64.06 201	29.55 216	44.06 223	36.69 223	51.95 222	29.97 216	74.75 147	8.90 227	76.02 172	91.24 120	7.53 221	73.78 189	55.91 211	34.87 222	40.01 221

new_pmnet		52.29 214	63.16 205	39.61 215	58.89 214	44.70 220	48.78 223	34.73 215	65.88 183	17.85 224	73.42 186	80.00 172	23.06 219	67.00 207	62.28 203	54.36 216	48.81 216

MVE	41.12 19	51.80 215	60.92 211	41.16 214	35.21 224	34.14 224	48.45 224	41.39 211	69.11 172	19.53 223	63.33 212	73.80 194	63.56 142	67.19 206	61.51 205	38.85 221	57.38 211
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		22.69 218	26.99 220	17.67 218	2.13 226	4.31 227	27.50 225	4.53 221	37.94 221	24.52 222	36.20 222	51.40 225	15.26 220	29.86 221	17.09 221	32.07 223	12.16 222

DeepMVS_CX						17.78 225	20.40 226	6.69 220	31.41 222	9.80 226	38.61 221	34.88 229	33.78 214	28.41 222		23.59 224	45.77 218

tmp_tt				13.54 219	16.73 225	6.42 226	8.49 227	2.36 222	28.69 223	27.44 221	18.40 223	13.51 230	3.70 222	33.23 220	36.26 220	22.54 225

Patchmatch-RL test							4.13 228

testmvs		0.93 220	1.37 222	0.41 221	0.36 228	0.36 229	0.62 229	0.39 223	1.48 224	0.18 230	2.41 224	1.31 232	0.41 224	1.25 224	1.08 223	0.48 226	1.68 223

test123		1.06 219	1.41 221	0.64 220	0.39 227	0.48 228	0.52 230	0.25 224	1.11 225	1.37 229	2.01 225	1.98 231	0.87 223	1.43 223	1.27 222	0.46 227	1.62 224

uanet_test		0.00 221	0.00 223	0.00 222	0.00 230	0.00 230	0.00 231	0.00 226	0.00 226	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet-low-res		0.00 221	0.00 223	0.00 222	0.00 230	0.00 230	0.00 231	0.00 226	0.00 226	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet		0.00 221	0.00 223	0.00 222	0.00 230	0.00 230	0.00 231	0.00 226	0.00 226	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

RE-MVS-def										87.10 28

9.14												89.43 131

SR-MVS					91.82 13			80.80 7				95.53 50

MTAPA										89.37 9		94.85 67

MTMP										90.54 5		95.16 60

mPP-MVS					93.05 3							95.77 44

NP-MVS									78.65 131

High-resolution multi-view benchmark