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 22	95.55 2	93.00 1	93.98 17	96.01 39	87.53 1	97.69 1	96.81 1	97.33 1	95.34 3

XVS					91.28 25	91.23 8	96.89 2			87.14 26		94.53 72				95.84 15

X-MVStestdata					91.28 25	91.23 8	96.89 2			87.14 26		94.53 72				95.84 15

X-MVS		89.36 28	90.73 47	87.77 17	91.50 20	91.23 8	96.76 4	78.88 18	87.29 55	87.14 26	78.98 141	94.53 72	76.47 55	95.25 19	94.28 12	95.85 14	93.55 15

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 14	89.54 65	95.57 48	84.25 7	95.24 20	94.27 13	95.97 11	93.85 7

MP-MVS		90.84 6	91.95 34	89.55 3	92.92 5	90.90 19	96.56 6	79.60 11	86.83 60	88.75 13	89.00 73	94.38 78	84.01 9	94.94 25	94.34 11	95.45 24	93.24 22
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PGM-MVS		90.42 10	91.58 37	89.05 6	91.77 14	91.06 13	96.51 7	78.94 17	85.41 72	87.67 19	87.02 94	95.26 56	83.62 12	95.01 24	93.94 16	95.79 19	93.40 19

SteuartSystems-ACMMP		90.00 17	91.73 35	87.97 13	91.21 29	90.29 28	96.51 7	78.00 24	86.33 63	85.32 41	88.23 81	94.67 70	82.08 21	95.13 22	93.88 17	94.72 36	93.59 12
Skip Steuart: Steuart Systems R&D Blog.
ACMMP		90.63 8	92.40 20	88.56 9	91.24 28	91.60 6	96.49 9	77.53 27	87.89 49	86.87 31	87.24 92	96.46 26	82.87 16	95.59 15	94.50 9	96.35 6	93.51 17
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 46	89.17 11	87.00 95	96.34 31	83.95 10	95.77 11	94.72 8	95.81 17	93.78 9

zzz-MVS		90.38 11	91.35 41	89.25 5	93.08 3	86.59 64	96.45 11	79.00 16	90.23 28	89.30 10	85.87 106	94.97 65	82.54 18	95.05 23	94.83 7	95.14 27	91.94 36

ACMM	80.67 7	90.67 7	92.46 19	88.57 8	91.35 22	89.93 31	96.34 12	77.36 31	90.17 29	86.88 30	87.32 90	96.63 24	83.32 13	95.79 10	94.49 10	96.19 9	92.91 25
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
anonymousdsp		85.62 61	90.53 48	79.88 92	64.64 203	76.35 139	96.28 13	53.53 188	85.63 69	81.59 70	92.81 30	97.71 14	86.88 2	94.56 26	92.83 25	96.35 6	93.84 8

TSAR-MVS + MP.		89.67 24	92.25 28	86.65 26	91.53 18	90.98 17	96.15 14	73.30 56	87.88 50	81.83 67	92.92 29	95.15 60	82.23 19	93.58 35	92.25 34	94.87 31	93.01 24
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 27	90.47 38	91.34 7	96.04 15	76.41 40	91.11 17	78.50 88	93.44 21	95.82 43	81.55 24	93.16 38	91.90 39	94.77 34	93.58 14

ACMMP_NAP		89.86 19	91.96 33	87.42 20	91.00 30	90.08 29	96.00 16	76.61 37	89.28 35	87.73 18	90.04 57	91.80 111	78.71 38	94.36 29	93.82 18	94.48 38	94.32 5

CPTT-MVS		89.63 25	90.52 49	88.59 7	90.95 31	90.74 21	95.71 17	79.13 15	87.70 51	85.68 39	80.05 136	95.74 46	84.77 6	94.28 30	92.68 27	95.28 26	92.45 31

HFP-MVS		90.32 13	92.37 22	87.94 14	91.46 21	90.91 18	95.69 18	79.49 12	89.94 34	83.50 51	89.06 72	94.44 76	81.68 23	94.17 31	94.19 14	95.81 17	93.87 6

DPE-MVS		89.81 22	92.34 24	86.86 24	89.69 44	91.00 16	95.53 19	76.91 34	88.18 47	83.43 54	93.48 20	95.19 57	81.07 27	92.75 46	92.07 37	94.55 37	93.74 10
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 12	88.98 51	92.86 2	95.51 20	72.17 59	94.95 5	91.27 3	94.11 16	97.77 12	84.22 8	96.49 4	95.27 5	96.79 2	93.60 11
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 44	86.67 25	91.73 15	91.02 15	95.50 21	77.74 25	84.04 83	79.47 83	91.48 44	94.85 67	81.14 26	92.94 41	92.20 36	94.47 39	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 10	90.88 32	91.15 11	95.35 22	77.65 26	86.26 65	87.23 24	90.45 54	97.35 18	83.20 14	95.44 16	93.41 21	96.28 8	92.63 26

MSP-MVS		88.51 42	91.36 40	85.19 39	90.63 36	92.01 4	95.29 23	77.52 28	90.48 26	80.21 78	90.21 56	96.08 35	76.38 57	88.30 93	91.42 42	91.12 87	91.01 45
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 18	91.68 16	90.44 26	95.22 24	77.34 33	90.79 22	87.80 17	90.42 55	92.05 108	79.05 35	93.89 33	93.59 19	94.77 34	94.62 4
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 36	95.11 25	75.98 42	90.73 23	80.15 79	94.21 15	94.51 75	76.59 54	92.94 41	91.17 45	93.46 49	93.37 21

HPM-MVS++		88.74 40	89.54 54	87.80 16	92.58 7	85.69 72	95.10 26	78.01 23	87.08 57	87.66 20	87.89 84	92.07 106	80.28 30	90.97 70	91.41 44	93.17 56	91.69 38

OPM-MVS		89.82 21	92.24 29	86.99 23	90.86 33	89.35 37	95.07 27	75.91 43	91.16 16	86.87 31	91.07 50	97.29 19	79.13 34	93.32 36	91.99 38	94.12 41	91.49 41

ACMP	80.00 8	90.12 16	92.30 26	87.58 19	90.83 34	91.10 12	94.96 28	76.06 41	87.47 53	85.33 40	88.91 76	97.65 16	82.13 20	95.31 17	93.44 20	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 33	94.76 29	77.45 29	85.41 72	74.79 104	88.83 77	88.90 135	78.67 40	96.06 7	95.45 4	96.66 3	95.58 1

DeepC-MVS	83.59 4	90.37 12	92.56 18	87.82 15	91.26 27	92.33 3	94.72 30	80.04 9	90.01 32	84.61 43	93.33 22	94.22 79	80.59 28	92.90 44	92.52 29	95.69 21	92.57 27
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 55	87.73 71	85.43 35	91.51 19	82.72 89	94.47 31	74.22 53	81.71 98	81.54 71	89.20 71	92.87 94	78.33 42	90.12 77	88.47 70	92.51 69	89.04 61

SD-MVS		89.91 18	92.23 30	87.19 22	91.31 24	89.79 34	94.31 32	75.34 47	89.26 38	81.79 68	92.68 31	95.08 62	83.88 11	93.10 39	92.69 26	96.54 4	93.02 23
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 52	85.94 29	86.82 72	91.06 13	94.26 33	75.39 46	88.85 42	85.76 38	85.74 108	86.92 144	78.02 43	93.03 40	92.21 35	95.39 25	92.21 34

DeepPCF-MVS	81.61 6	87.95 48	90.29 51	85.22 38	87.48 66	90.01 30	93.79 34	73.54 54	88.93 40	83.89 46	89.40 67	90.84 120	80.26 31	90.62 73	90.19 54	92.36 70	92.03 35

DVP-MVS		89.40 27	92.69 13	85.56 34	89.01 50	89.85 32	93.72 35	75.42 45	92.28 11	80.49 73	94.36 13	94.87 66	81.46 25	92.49 50	91.42 42	93.27 52	93.54 16
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 21	90.16 39	88.75 41	93.64 36	75.78 44	90.00 33	83.70 48	92.97 28	92.22 103	86.13 4	97.01 3	96.79 2	94.94 30	90.96 46
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 11	83.19 110	86.35 67	93.60 37	78.79 19	95.48 4	91.79 2	93.08 26	97.21 21	86.34 3	97.06 2	96.27 3	95.46 23	95.56 2
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
WR-MVS		89.79 23	93.66 4	85.27 37	91.32 23	88.27 45	93.49 38	79.86 10	92.75 9	75.37 100	96.86 1	98.38 6	75.10 69	95.93 8	94.07 15	96.46 5	89.39 58

NCCC		86.74 54	87.97 70	85.31 36	90.64 35	87.25 58	93.27 39	74.59 49	86.50 61	83.72 47	75.92 166	92.39 100	77.08 52	91.72 53	90.68 49	92.57 67	91.30 43

CNVR-MVS		86.93 53	88.98 58	84.54 44	90.11 40	87.41 57	93.23 40	73.47 55	86.31 64	82.25 62	82.96 124	92.15 104	76.04 60	91.69 54	90.69 48	92.17 73	91.64 40

OMC-MVS		88.16 43	91.34 42	84.46 46	86.85 71	90.63 23	93.01 41	67.00 100	90.35 27	87.40 22	86.86 97	96.35 30	77.66 48	92.63 48	90.84 47	94.84 32	91.68 39

CDPH-MVS		86.66 56	88.52 61	84.48 45	89.61 45	88.27 45	92.86 42	72.69 58	80.55 116	82.71 56	86.92 96	93.32 90	75.55 65	91.00 69	89.85 58	93.47 48	89.71 55

DeepC-MVS_fast	81.78 5	87.38 51	89.64 53	84.75 41	89.89 42	90.70 22	92.74 43	74.45 50	86.02 66	82.16 65	86.05 104	91.99 110	75.84 63	91.16 64	90.44 50	93.41 50	91.09 44
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 63	90.83 21	87.24 23	89.71 63	92.07 106	78.37 41	94.43 28	92.59 28	95.86 13	91.35 42

ACMH+	79.05 11	89.62 26	93.08 8	85.58 32	88.58 55	89.26 38	92.18 45	74.23 52	93.55 8	82.66 59	92.32 36	98.35 8	80.29 29	95.28 18	92.34 32	95.52 22	90.43 50

WR-MVS_H		88.99 35	93.28 5	83.99 54	91.92 11	89.13 39	91.95 46	83.23 1	90.14 30	71.92 123	95.85 5	98.01 11	71.83 96	95.82 9	93.19 23	93.07 58	90.83 48

MVS_0304		84.73 72	86.19 83	83.02 58	88.32 56	86.71 63	91.55 47	70.87 67	73.79 145	82.88 55	85.13 112	93.35 89	72.55 88	88.62 87	87.69 76	91.93 75	88.05 70

ACMH	78.40 12	88.94 38	92.62 16	84.65 42	86.45 75	87.16 59	91.47 48	68.79 85	95.49 3	89.74 6	93.55 19	98.50 3	77.96 44	94.14 32	89.57 63	93.49 47	89.94 54
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HQP-MVS		85.02 68	86.41 81	83.40 55	89.19 48	86.59 64	91.28 49	71.60 64	82.79 89	83.48 52	78.65 145	93.54 87	72.55 88	86.49 108	85.89 92	92.28 72	90.95 47

PCF-MVS	76.59 14	84.11 76	85.27 93	82.76 65	86.12 78	88.30 44	91.24 50	69.10 80	82.36 93	84.45 44	77.56 151	90.40 125	72.91 87	85.88 113	83.88 110	92.72 63	88.53 65
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 51	79.48 13	88.86 41	79.80 80	93.01 27	93.53 88	83.17 15	92.75 46	92.45 30	91.32 82	93.59 12

DTE-MVSNet		88.99 35	92.77 12	84.59 43	93.31 2	88.10 48	90.96 52	83.09 2	91.38 14	76.21 94	96.03 3	98.04 9	70.78 105	95.65 14	92.32 33	93.18 55	87.84 71

test_part1		87.86 49	93.26 6	81.56 74	87.23 70	86.76 62	90.91 53	70.06 71	96.50 1	76.74 92	96.63 2	98.62 2	69.45 113	92.93 43	90.92 46	94.98 29	90.46 49

CNLPA		85.50 63	88.58 59	81.91 69	84.55 92	87.52 56	90.89 54	63.56 136	88.18 47	84.06 45	83.85 121	91.34 117	76.46 56	91.27 61	89.00 68	91.96 74	88.88 63

PEN-MVS		88.86 39	92.92 9	84.11 53	92.92 5	88.05 50	90.83 55	82.67 5	91.04 18	74.83 103	95.97 4	98.47 4	70.38 106	95.70 13	92.43 31	93.05 59	88.78 64

xxxxxxxxxxxxxcwj		88.03 47	91.29 43	84.22 49	88.17 60	87.90 52	90.80 56	71.80 61	89.28 35	82.70 57	89.90 59	97.72 13	77.91 45	91.69 54	90.04 55	93.95 44	92.47 28

SF-MVS		87.85 50	90.95 46	84.22 49	88.17 60	87.90 52	90.80 56	71.80 61	89.28 35	82.70 57	89.90 59	95.37 54	77.91 45	91.69 54	90.04 55	93.95 44	92.47 28

PHI-MVS		86.37 58	88.14 67	84.30 47	86.65 74	87.56 55	90.76 58	70.16 70	82.55 90	89.65 7	84.89 115	92.40 99	75.97 61	90.88 71	89.70 60	92.58 65	89.03 62

TAPA-MVS	78.00 13	85.88 60	88.37 63	82.96 61	84.69 88	88.62 42	90.62 59	64.22 126	89.15 39	88.05 15	78.83 143	93.71 83	76.20 59	90.11 78	88.22 73	94.00 42	89.97 53
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Vis-MVSNet		83.32 83	88.12 68	77.71 107	77.91 153	83.44 86	90.58 60	69.49 76	81.11 110	67.10 151	89.85 61	91.48 115	71.71 97	91.34 60	89.37 64	89.48 104	90.26 51
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 62	90.59 25	90.57 61	68.60 87	91.37 15	83.45 53	89.94 58	95.14 61	78.71 38	91.45 59	88.21 74	95.96 12	93.44 18

AdaColmap		84.15 75	85.14 96	83.00 60	89.08 49	87.14 60	90.56 62	70.90 66	82.40 92	80.41 74	73.82 177	84.69 153	75.19 68	91.58 58	89.90 57	91.87 76	86.48 78

PS-CasMVS		89.07 32	93.23 7	84.21 51	92.44 8	88.23 47	90.54 63	82.95 3	90.50 25	75.31 101	95.80 6	98.37 7	71.16 99	96.30 5	93.32 22	92.88 60	90.11 52

SixPastTwentyTwo		89.14 29	92.19 31	85.58 32	84.62 90	82.56 92	90.53 64	71.93 60	91.95 12	85.89 36	94.22 14	97.25 20	85.42 5	95.73 12	91.71 41	95.08 28	91.89 37

MVS_111021_HR		83.95 77	86.10 85	81.44 75	84.62 90	80.29 107	90.51 65	68.05 94	84.07 82	80.38 76	84.74 116	91.37 116	74.23 75	90.37 75	87.25 78	90.86 89	84.59 90

TSAR-MVS + COLMAP		85.51 62	88.36 64	82.19 67	86.05 79	87.69 54	90.50 66	70.60 69	86.40 62	82.33 60	89.69 64	92.52 98	74.01 79	87.53 97	86.84 83	89.63 101	87.80 72

abl_6				79.30 98	84.98 87	85.78 70	90.50 66	66.88 101	77.08 133	74.02 109	73.29 181	89.34 130	68.94 115			90.49 90	85.98 81

CP-MVSNet		88.71 41	92.63 15	84.13 52	92.39 9	88.09 49	90.47 68	82.86 4	88.79 43	75.16 102	94.87 9	97.68 15	71.05 101	96.16 6	93.18 24	92.85 61	89.64 56

MCST-MVS		84.79 71	86.48 79	82.83 64	87.30 67	87.03 61	90.46 69	69.33 79	83.14 86	82.21 64	81.69 132	92.14 105	75.09 70	87.27 100	84.78 102	92.58 65	89.30 59

gm-plane-assit		71.56 164	69.99 179	73.39 134	84.43 94	73.21 159	90.42 70	51.36 195	84.08 81	76.00 96	91.30 47	37.09 221	59.01 154	73.65 183	70.24 182	79.09 175	60.37 196

CANet		82.84 89	84.60 104	80.78 81	87.30 67	85.20 75	90.23 71	69.00 81	72.16 153	78.73 87	84.49 118	90.70 123	69.54 111	87.65 96	86.17 87	89.87 98	85.84 83

CLD-MVS		82.75 92	87.22 76	77.54 110	88.01 63	85.76 71	90.23 71	54.52 182	82.28 94	82.11 66	88.48 80	95.27 55	63.95 138	89.41 81	88.29 72	86.45 139	81.01 125
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
DPM-MVS		81.42 102	82.11 127	80.62 86	87.54 65	85.30 74	90.18 73	68.96 82	81.00 112	79.15 85	70.45 194	83.29 156	67.67 122	82.81 138	83.46 114	90.19 93	88.48 66

RPSCF		88.05 46	92.61 17	82.73 66	84.24 95	88.40 43	90.04 74	66.29 105	91.46 13	82.29 61	88.93 75	96.01 39	79.38 32	95.15 21	94.90 6	94.15 40	93.40 19

v7n		87.11 52	90.46 50	83.19 57	85.22 85	83.69 83	90.03 75	68.20 93	91.01 19	86.71 34	94.80 10	98.46 5	77.69 47	91.10 66	85.98 89	91.30 83	88.19 67

GeoE		81.92 99	83.87 114	79.66 94	84.64 89	79.87 109	89.75 76	65.90 112	76.12 137	75.87 97	84.62 117	92.23 102	71.96 95	86.83 105	83.60 113	89.83 99	83.81 98

MVS_111021_LR		83.20 85	85.33 92	80.73 84	82.88 114	78.23 124	89.61 77	65.23 118	82.08 95	81.19 72	85.31 110	92.04 109	75.22 67	89.50 80	85.90 91	90.24 92	84.23 93

v1192		83.61 79	85.23 94	81.72 71	84.05 97	82.15 95	89.54 78	66.20 106	81.38 107	86.76 33	91.79 41	96.03 37	74.88 72	81.81 146	80.92 135	88.91 112	82.50 113

v1921920		83.49 81	84.94 100	81.80 70	83.78 103	81.20 103	89.50 79	65.91 111	81.64 100	87.18 25	91.70 42	95.39 53	75.85 62	81.56 149	80.27 141	88.60 116	82.80 109

v1240		83.57 80	84.94 100	81.97 68	84.05 97	81.27 101	89.46 80	66.06 108	81.31 108	87.50 21	91.88 40	95.46 52	76.25 58	81.16 151	80.51 139	88.52 119	82.98 107

v144192		83.43 82	84.97 99	81.63 73	83.43 106	81.23 102	89.42 81	66.04 110	81.45 106	86.40 35	91.46 45	95.70 47	75.76 64	82.14 142	80.23 142	88.74 113	82.57 112

MAR-MVS		81.98 98	82.92 123	80.88 80	85.18 86	85.85 69	89.13 82	69.52 74	71.21 157	82.25 62	71.28 188	88.89 136	69.69 108	88.71 85	86.96 79	89.52 103	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 66	87.41 75	82.89 63	90.07 41	85.69 72	89.07 83	72.99 57	82.45 91	74.52 107	85.09 113	87.67 141	79.24 33	91.11 65	90.41 51	91.45 79	89.45 57

v1144		83.22 84	85.01 97	81.14 77	83.76 104	81.60 98	88.95 84	65.58 116	81.89 97	85.80 37	91.68 43	95.84 42	74.04 78	82.12 143	80.56 138	88.70 115	81.41 121

PLC	76.06 15	85.38 65	87.46 73	82.95 62	85.79 81	88.84 40	88.86 85	68.70 86	87.06 58	83.60 49	79.02 139	90.05 126	77.37 51	90.88 71	89.66 61	93.37 51	86.74 77
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ETV-MVS		79.01 124	77.98 143	80.22 91	86.69 73	79.73 113	88.80 86	68.27 92	63.22 191	71.56 125	70.25 196	73.63 189	73.66 82	90.30 76	86.77 84	92.33 71	81.95 118

CS-MVS		79.35 120	77.74 145	81.22 76	85.59 83	79.85 110	88.78 87	66.61 102	67.63 170	80.41 74	67.82 200	75.07 187	73.27 86	88.31 92	84.36 106	92.63 64	81.18 122

v10		83.17 86	85.22 95	80.78 81	83.26 109	82.99 88	88.66 88	66.49 104	79.24 125	83.60 49	91.46 45	95.47 51	74.12 76	82.60 141	80.66 136	88.53 118	84.11 96

Effi-MVS+-dtu		82.04 97	83.39 121	80.48 89	85.48 84	86.57 66	88.40 89	68.28 91	69.04 167	73.13 117	76.26 161	91.11 119	74.74 73	88.40 90	87.76 75	92.84 62	84.57 91

EPNet		79.36 119	79.44 136	79.27 99	89.51 46	77.20 133	88.35 90	77.35 32	68.27 169	74.29 108	76.31 159	79.22 168	59.63 152	85.02 124	85.45 95	86.49 138	84.61 89
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
UniMVSNet (Re)		84.95 69	88.53 60	80.78 81	87.82 64	84.21 78	88.03 91	76.50 38	81.18 109	69.29 137	92.63 34	96.83 23	69.07 114	91.23 63	89.60 62	93.97 43	84.00 97

PVSNet_Blended_VisFu		83.00 87	84.16 111	81.65 72	82.17 120	86.01 68	88.03 91	71.23 65	76.05 138	79.54 82	83.88 120	83.44 154	77.49 50	87.38 98	84.93 100	91.41 80	87.40 75

Baseline_NR-MVSNet		82.79 90	86.51 78	78.44 104	88.30 57	75.62 147	87.81 93	74.97 48	81.53 102	66.84 152	94.71 12	96.46 26	66.90 126	91.79 51	83.37 119	85.83 148	82.09 116

Fast-Effi-MVS+		81.42 102	83.82 116	78.62 102	82.24 119	80.62 106	87.72 94	63.51 137	73.01 147	74.75 105	83.80 122	92.70 96	73.44 84	88.15 95	85.26 96	90.05 94	83.17 103

v2v482		82.20 95	84.26 108	79.81 93	82.67 116	80.18 108	87.67 95	63.96 133	81.69 99	84.73 42	91.27 48	96.33 32	72.05 94	81.94 145	79.56 145	87.79 125	78.84 141

Effi-MVS+		82.33 93	83.87 114	80.52 88	84.51 93	81.32 100	87.53 96	68.05 94	74.94 143	79.67 81	82.37 129	92.31 101	72.21 90	85.06 120	86.91 81	91.18 85	84.20 94

pmmvs-eth3d		79.64 115	82.06 128	76.83 112	80.05 132	72.64 161	87.47 97	66.59 103	80.83 113	73.50 113	89.32 69	93.20 91	67.78 120	80.78 154	81.64 131	85.58 151	76.01 151

TranMVSNet+NR-MVSNet		85.23 67	89.38 55	80.39 90	88.78 53	83.77 81	87.40 98	76.75 35	85.47 70	68.99 139	95.18 8	97.55 17	67.13 125	91.61 57	89.13 67	93.26 53	82.95 108

v8		82.20 95	84.56 105	79.45 95	82.42 117	81.65 97	87.26 99	64.27 125	79.36 124	81.70 69	91.04 51	95.75 45	73.30 85	82.82 137	79.18 148	87.74 126	82.09 116

3Dnovator	79.41 10	82.21 94	86.07 86	77.71 107	79.31 138	84.61 76	87.18 100	61.02 156	85.65 68	76.11 95	85.07 114	85.38 151	70.96 103	87.22 101	86.47 85	91.66 77	88.12 69

PM-MVS		80.42 110	83.63 118	76.67 113	78.04 150	72.37 163	87.14 101	60.18 162	80.13 118	71.75 124	86.12 103	93.92 82	77.08 52	86.56 107	85.12 98	85.83 148	81.18 122

NR-MVSNet		82.89 88	87.43 74	77.59 109	83.91 101	83.59 84	87.10 102	78.35 20	80.64 114	68.85 140	92.67 32	96.50 25	54.19 175	87.19 103	88.68 69	93.16 57	82.75 110

UniMVSNet_NR-MVSNet		84.62 73	88.00 69	80.68 85	88.18 59	83.83 80	87.06 103	76.47 39	81.46 105	70.49 131	93.24 23	95.56 49	68.13 118	90.43 74	88.47 70	93.78 46	83.02 105

DU-MVS		84.88 70	88.27 66	80.92 79	88.30 57	83.59 84	87.06 103	78.35 20	80.64 114	70.49 131	92.67 32	96.91 22	68.13 118	91.79 51	89.29 66	93.20 54	83.02 105

MSLP-MVS++		86.29 59	89.10 57	83.01 59	85.71 82	89.79 34	87.04 105	74.39 51	85.17 74	78.92 86	77.59 150	93.57 86	82.60 17	93.23 37	91.88 40	89.42 106	92.46 30

EG-PatchMatch MVS		84.35 74	87.55 72	80.62 86	86.38 76	82.24 94	86.75 106	64.02 131	84.24 79	78.17 90	89.38 68	95.03 64	78.78 37	89.95 79	86.33 86	89.59 102	85.65 85

UGNet		79.62 116	85.91 88	72.28 139	73.52 174	83.91 79	86.64 107	69.51 75	79.85 121	62.57 163	85.82 107	89.63 127	53.18 179	88.39 91	87.35 77	88.28 121	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		79.59 117	83.59 119	74.93 128	69.61 187	77.05 135	86.59 108	55.84 177	78.42 129	77.29 91	89.84 62	95.08 62	74.12 76	83.05 134	80.11 143	86.12 142	81.59 120

FPMVS		81.56 101	84.04 113	78.66 101	82.92 112	75.96 143	86.48 109	65.66 115	84.67 78	71.47 126	77.78 148	83.22 157	77.57 49	91.24 62	90.21 53	87.84 124	85.21 87

EIA-MVS		78.57 125	77.90 144	79.35 97	87.24 69	80.71 105	86.16 110	64.03 130	62.63 196	73.49 114	73.60 178	76.12 182	73.83 80	88.49 89	84.93 100	91.36 81	78.78 142

FC-MVSNet-train		79.20 122	86.29 82	70.94 146	84.06 96	77.67 127	85.68 111	64.11 128	82.90 88	52.22 190	92.57 35	93.69 84	49.52 190	88.30 93	86.93 80	90.03 95	81.95 118

IS_MVSNet		81.72 100	85.01 97	77.90 106	86.19 77	82.64 91	85.56 112	70.02 72	80.11 119	63.52 159	87.28 91	81.18 163	67.26 123	91.08 68	89.33 65	94.82 33	83.42 102

TinyColmap		83.79 78	86.12 84	81.07 78	83.42 107	81.44 99	85.42 113	68.55 88	88.71 44	89.46 8	87.60 86	92.72 95	70.34 107	89.29 82	81.94 128	89.20 107	81.12 124

EPP-MVSNet		82.76 91	86.47 80	78.45 103	86.00 80	84.47 77	85.39 114	68.42 89	84.17 80	62.97 161	89.26 70	76.84 178	72.13 93	92.56 49	90.40 52	95.76 20	87.56 74

Gipuma		86.47 57	89.25 56	83.23 56	83.88 102	78.78 120	85.35 115	68.42 89	92.69 10	89.03 12	91.94 37	96.32 33	81.80 22	94.45 27	86.86 82	90.91 88	83.69 99
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
FC-MVSNet-test		75.91 142	83.59 119	66.95 171	76.63 166	69.07 173	85.33 116	64.97 120	84.87 77	41.95 204	93.17 24	87.04 143	47.78 193	91.09 67	85.56 94	85.06 155	74.34 157

MSDG		81.39 104	84.23 110	78.09 105	82.40 118	82.47 93	85.31 117	60.91 157	79.73 122	80.26 77	86.30 100	88.27 139	69.67 109	87.20 102	84.98 99	89.97 96	80.67 127

thisisatest0515		81.18 107	84.32 107	77.52 111	76.73 164	74.84 153	85.06 118	61.37 153	81.05 111	73.95 110	88.79 78	89.25 132	75.49 66	85.98 112	84.78 102	92.53 68	85.56 86

Fast-Effi-MVS+-dtu		76.92 132	77.18 150	76.62 114	79.55 135	79.17 116	84.80 119	77.40 30	64.46 186	68.75 142	70.81 192	86.57 145	63.36 145	81.74 147	81.76 129	85.86 147	75.78 153

DELS-MVS		79.71 114	83.74 117	75.01 125	79.31 138	82.68 90	84.79 120	60.06 163	75.43 141	69.09 138	86.13 102	89.38 129	67.16 124	85.12 119	83.87 111	89.65 100	83.57 100
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		73.40 153	81.85 129	63.55 183	72.90 177	64.37 187	84.58 121	53.60 187	90.84 20	53.92 182	87.75 85	96.10 34	45.31 196	85.37 118	79.32 147	70.98 191	69.18 176

ambc			88.38 62		91.62 17	87.97 51	84.48 122		88.64 45	87.93 16	87.38 89	94.82 69	74.53 74	89.14 84	83.86 112	85.94 146	86.84 76

pmmvs4		75.92 141	77.48 149	74.10 131	78.21 149	70.94 165	84.06 123	64.78 121	75.13 142	68.47 145	84.12 119	83.32 155	64.74 137	75.93 176	79.14 149	84.31 158	73.77 161

MDA-MVSNet-bldmvs		76.51 135	82.87 124	69.09 159	50.71 214	74.72 155	84.05 124	60.27 161	81.62 101	71.16 128	88.21 82	91.58 112	69.62 110	92.78 45	77.48 156	78.75 176	73.69 162

CANet_DTU		75.04 147	78.45 139	71.07 143	77.27 155	77.96 125	83.88 125	58.00 172	64.11 187	68.67 143	75.65 168	88.37 138	53.92 177	82.05 144	81.11 132	84.67 156	79.88 136

our_test_3					73.27 175	70.91 166	83.26 126

HyFIR lowres test		73.29 154	74.14 170	72.30 138	73.08 176	78.33 123	83.12 127	62.41 148	63.81 188	62.13 165	76.67 158	78.50 171	71.09 100	74.13 180	77.47 157	81.98 169	70.10 171

IB-MVS	71.28 17	75.21 146	77.00 152	73.12 137	76.76 158	77.45 129	83.05 128	58.92 168	63.01 192	64.31 158	59.99 210	87.57 142	68.64 116	86.26 111	82.34 126	87.05 133	82.36 115
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		75.65 144	77.62 148	73.35 136	71.95 180	69.89 170	83.04 129	60.84 158	69.12 165	68.76 141	79.92 137	78.93 170	73.64 83	81.02 152	81.01 134	81.86 170	83.43 101

casdiffmvs		79.93 112	84.11 112	75.05 123	81.41 126	78.99 118	82.95 130	62.90 144	81.53 102	68.60 144	91.94 37	96.03 37	65.84 132	82.89 136	77.07 159	88.59 117	80.34 133

tttt0517		75.86 143	76.23 158	75.42 119	75.55 170	74.06 157	82.73 131	60.31 159	69.24 163	70.24 133	79.18 138	58.79 207	72.17 91	84.49 128	83.08 121	91.54 78	84.80 88

ET-MVSNet_ETH3D		74.71 149	74.19 169	75.31 121	79.22 140	75.29 148	82.70 132	64.05 129	65.45 181	70.96 130	77.15 155	57.70 209	65.89 131	84.40 129	81.65 130	89.03 109	77.67 148

USDC		81.39 104	83.07 122	79.43 96	81.48 124	78.95 119	82.62 133	66.17 107	87.45 54	90.73 4	82.40 128	93.65 85	66.57 128	83.63 133	77.97 151	89.00 110	77.45 149

EPNet_dtu		71.90 163	73.03 175	70.59 148	78.28 147	61.64 192	82.44 134	64.12 127	63.26 190	69.74 134	71.47 186	82.41 159	51.89 187	78.83 163	78.01 150	77.07 177	75.60 155
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MDTV_nov1_ep13_2view		72.96 159	75.59 163	69.88 153	71.15 184	64.86 186	82.31 135	54.45 183	76.30 135	78.32 89	86.52 98	91.58 112	61.35 148	76.80 169	66.83 189	71.70 184	66.26 180

thisisatest0530		75.54 145	75.95 162	75.05 123	75.08 171	73.56 158	82.15 136	60.31 159	69.17 164	69.32 136	79.02 139	58.78 208	72.17 91	83.88 131	83.08 121	91.30 83	84.20 94

v148		79.33 121	82.32 126	75.84 117	80.14 131	75.74 144	81.98 137	57.06 174	81.51 104	79.36 84	89.42 66	96.42 28	71.32 98	81.54 150	75.29 168	85.20 153	76.32 150

UniMVSNet_ETH3D		85.39 64	91.12 45	78.71 100	90.48 37	83.72 82	81.76 138	82.41 6	93.84 6	64.43 157	95.41 7	98.76 1	63.72 140	93.63 34	89.74 59	89.47 105	82.74 111

EU-MVSNet		76.48 136	80.53 133	71.75 141	67.62 193	70.30 168	81.74 139	54.06 185	75.47 140	71.01 129	80.10 134	93.17 93	73.67 81	83.73 132	77.85 152	82.40 167	83.07 104

Vis-MVSNet (Re-imp)		76.15 139	80.84 132	70.68 147	83.66 105	74.80 154	81.66 140	69.59 73	80.48 117	46.94 199	87.44 88	80.63 165	53.14 180	86.87 104	84.56 105	89.12 108	71.12 167

DI_MVS_plusplus_trai		77.64 129	79.64 135	75.31 121	79.87 134	76.89 136	81.55 141	63.64 135	76.21 136	72.03 122	85.59 109	82.97 158	66.63 127	79.27 162	77.78 153	88.14 122	78.76 143

testgi		68.20 177	76.05 160	59.04 190	79.99 133	67.32 180	81.16 142	51.78 193	84.91 76	39.36 209	73.42 179	95.19 57	32.79 209	76.54 173	70.40 181	69.14 195	64.55 183

PatchMatch-RL		76.05 140	76.64 154	75.36 120	77.84 154	69.87 171	81.09 143	63.43 138	71.66 155	68.34 146	71.70 184	81.76 162	74.98 71	84.83 126	83.44 115	86.45 139	73.22 164

IterMVS		73.62 152	76.53 155	70.23 151	71.83 181	77.18 134	80.69 144	53.22 189	72.23 152	66.62 153	85.21 111	78.96 169	69.54 111	76.28 175	71.63 178	79.45 173	74.25 159
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs		76.74 133	81.61 130	71.06 144	75.64 169	74.45 156	80.68 145	57.57 173	77.48 130	67.62 150	88.95 74	93.94 81	61.98 147	79.74 159	76.18 163	82.85 166	80.50 128

DCV-MVSNet		80.04 111	85.67 91	73.48 133	82.91 113	81.11 104	80.44 146	66.06 108	85.01 75	62.53 164	78.84 142	94.43 77	58.51 156	88.66 86	85.91 90	90.41 91	85.73 84

canonicalmvs		81.22 106	86.04 87	75.60 118	83.17 111	83.18 87	80.29 147	65.82 114	85.97 67	67.98 147	77.74 149	91.51 114	65.17 134	88.62 87	86.15 88	91.17 86	89.09 60

GA-MVS		75.01 148	76.39 156	73.39 134	78.37 146	75.66 146	80.03 148	58.40 170	70.51 159	75.85 98	83.24 123	76.14 181	63.75 139	77.28 168	76.62 162	83.97 160	75.30 156

OpenMVS	75.38 16	78.44 126	81.39 131	74.99 126	80.46 129	79.85 110	79.99 149	58.31 171	77.34 132	73.85 111	77.19 154	82.33 161	68.60 117	84.67 127	81.95 127	88.72 114	86.40 80

MVS_Test		76.72 134	79.40 137	73.60 132	78.85 144	74.99 151	79.91 150	61.56 152	69.67 161	72.44 118	85.98 105	90.78 121	63.50 143	78.30 164	75.74 166	85.33 152	80.31 134

IterMVS-LS		79.79 113	82.56 125	76.56 115	81.83 122	77.85 126	79.90 151	69.42 78	78.93 127	71.21 127	90.47 53	85.20 152	70.86 104	80.54 156	80.57 137	86.15 141	84.36 92
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
QAPM		80.43 109	84.34 106	75.86 116	79.40 137	82.06 96	79.86 152	61.94 150	83.28 85	74.73 106	81.74 131	85.44 150	70.97 102	84.99 125	84.71 104	88.29 120	88.14 68

PVSNet_BlendedMVS		76.45 137	78.12 141	74.49 129	76.76 158	78.46 121	79.65 153	63.26 140	65.42 182	73.15 115	75.05 171	88.96 133	66.51 129	82.73 139	77.66 154	87.61 127	78.60 144

PVSNet_Blended		76.45 137	78.12 141	74.49 129	76.76 158	78.46 121	79.65 153	63.26 140	65.42 182	73.15 115	75.05 171	88.96 133	66.51 129	82.73 139	77.66 154	87.61 127	78.60 144

CDS-MVSNet		73.07 158	77.02 151	68.46 162	81.62 123	72.89 160	79.56 155	70.78 68	69.56 162	52.52 187	77.37 153	81.12 164	42.60 198	84.20 130	83.93 109	83.65 161	70.07 172
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CostFormer		66.81 181	66.94 187	66.67 172	72.79 178	68.25 176	79.55 156	55.57 178	65.52 180	62.77 162	76.98 156	60.09 203	56.73 162	65.69 204	62.35 193	72.59 183	69.71 173

Anonymous202405211			84.68 103		83.92 100	79.45 115	79.03 157	67.79 96	82.01 96		88.77 79	92.58 97	55.93 166	86.68 106	84.26 107	88.92 111	78.98 140

CHOSEN 1792x2688		68.80 174	71.09 177	66.13 175	69.11 189	68.89 175	78.98 158	54.68 180	61.63 198	56.69 173	71.56 185	78.39 172	67.69 121	72.13 187	72.01 177	69.63 194	73.02 165

Anonymous20231211		79.37 118	85.78 89	71.89 140	82.87 115	79.66 114	78.77 159	63.93 134	83.36 84	59.39 168	90.54 52	94.66 71	56.46 163	87.38 98	84.12 108	89.92 97	80.74 126

thres600view7		74.34 151	78.43 140	69.56 156	80.47 128	76.28 140	78.65 160	62.56 146	77.39 131	52.53 186	74.03 175	76.78 179	55.90 167	85.06 120	85.19 97	87.25 131	74.29 158

FMVSNet1		78.20 128	84.83 102	70.46 150	78.62 145	79.03 117	77.90 161	67.53 99	83.02 87	55.10 179	87.19 93	93.18 92	55.65 168	85.57 114	83.39 116	87.98 123	82.40 114

pmmvs6		80.46 108	88.34 65	71.26 142	81.96 121	77.51 128	77.54 162	68.83 84	93.72 7	55.92 176	93.94 18	98.03 10	55.94 165	89.21 83	85.61 93	87.36 130	80.38 129

TransMVSNet (Re)		79.05 123	86.66 77	70.18 152	83.32 108	75.99 142	77.54 162	63.98 132	90.68 24	55.84 177	94.80 10	96.06 36	53.73 178	86.27 110	83.22 120	86.65 134	79.61 138

thres400		73.13 157	76.99 153	68.62 161	79.46 136	74.93 152	77.23 164	61.23 155	75.54 139	52.31 189	72.20 183	77.10 177	54.89 170	82.92 135	82.62 125	86.57 137	73.66 163

MS-PatchMatch		71.18 167	73.99 171	67.89 168	77.16 156	71.76 164	77.18 165	56.38 176	67.35 171	55.04 180	74.63 173	75.70 183	62.38 146	76.62 171	75.97 165	79.22 174	75.90 152

tfpn200view9		72.01 162	75.40 164	68.06 165	77.97 151	76.44 138	77.04 166	62.67 145	66.81 173	50.82 195	67.30 201	75.67 184	52.46 186	85.06 120	82.64 124	87.41 129	73.86 160

SCA		68.54 176	67.52 186	69.73 154	67.79 192	75.04 149	76.96 167	68.94 83	66.41 175	67.86 148	74.03 175	60.96 200	65.55 133	68.99 196	65.67 190	71.30 189	61.54 195

baseline2		68.71 175	68.34 184	69.14 158	75.69 168	69.70 172	76.60 168	55.53 179	60.13 201	62.07 166	66.76 203	60.35 202	60.77 149	76.53 174	74.03 170	84.19 159	70.88 168

tfpnnormal		77.16 131	84.26 108	68.88 160	81.02 127	75.02 150	76.52 169	63.30 139	87.29 55	52.40 188	91.24 49	93.97 80	54.85 172	85.46 117	81.08 133	85.18 154	75.76 154

pm-mvs1		78.21 127	85.68 90	69.50 157	80.38 130	75.73 145	76.25 170	65.04 119	87.59 52	54.47 181	93.16 25	95.99 41	54.20 174	86.37 109	82.98 123	86.64 135	77.96 147

tpm cat1		64.79 186	62.74 200	67.17 169	74.61 173	65.91 184	76.18 171	59.32 165	64.88 185	66.41 154	71.21 189	53.56 217	59.17 153	61.53 208	58.16 202	67.33 198	63.95 184

RPMNet		67.02 180	63.99 195	70.56 149	71.55 182	67.63 177	75.81 172	69.44 77	59.93 202	63.24 160	64.32 205	47.51 220	59.68 151	70.37 193	69.64 184	83.64 162	68.49 177

MDTV_nov1_ep13		64.96 184	64.77 192	65.18 181	67.08 196	62.46 191	75.80 173	51.10 196	62.27 197	69.74 134	74.12 174	62.65 198	55.64 169	68.19 198	62.16 197	71.70 184	61.57 194

GBi-Net		73.17 155	77.64 146	67.95 166	76.76 158	77.36 130	75.77 174	64.57 122	62.99 193	51.83 191	76.05 162	77.76 174	52.73 183	85.57 114	83.39 116	86.04 143	80.37 130

test1		73.17 155	77.64 146	67.95 166	76.76 158	77.36 130	75.77 174	64.57 122	62.99 193	51.83 191	76.05 162	77.76 174	52.73 183	85.57 114	83.39 116	86.04 143	80.37 130

FMVSNet2		74.43 150	79.70 134	68.27 163	76.76 158	77.36 130	75.77 174	65.36 117	72.28 151	52.97 185	81.92 130	85.61 149	52.73 183	80.66 155	79.73 144	86.04 143	80.37 130

MVSTER		68.08 178	69.73 180	66.16 174	66.33 201	70.06 169	75.71 177	52.36 191	55.18 210	58.64 170	70.23 197	56.72 212	57.34 160	79.68 160	76.03 164	86.61 136	80.20 135

test20.03		69.91 168	76.20 159	62.58 184	84.01 99	67.34 179	75.67 178	65.88 113	79.98 120	40.28 208	82.65 125	89.31 131	39.63 203	77.41 167	73.28 172	69.98 192	63.40 187

IterMVS-SCA-FT		77.23 130	79.18 138	74.96 127	76.67 165	79.85 110	75.58 179	61.34 154	73.10 146	73.79 112	86.23 101	79.61 167	79.00 36	80.28 158	75.50 167	83.41 165	79.70 137

thres200		72.41 161	76.00 161	68.21 164	78.28 147	76.28 140	74.94 180	62.56 146	72.14 154	51.35 194	69.59 198	76.51 180	54.89 170	85.06 120	80.51 139	87.25 131	71.92 166

FMVSNet3		71.40 166	75.20 167	66.97 170	75.00 172	76.59 137	74.29 181	64.57 122	62.99 193	51.83 191	76.05 162	77.76 174	51.49 188	76.58 172	77.03 160	84.62 157	79.43 139

Anonymous20231206		67.28 179	73.41 174	60.12 189	76.45 167	63.61 190	74.21 182	56.52 175	76.35 134	42.23 203	75.81 167	90.47 124	41.51 201	74.52 177	69.97 183	69.83 193	63.17 188

baseline		69.33 172	75.37 165	62.28 186	66.54 199	66.67 182	73.95 183	48.07 198	66.10 176	59.26 169	82.45 126	86.30 146	54.44 173	74.42 179	73.25 173	71.42 187	78.43 146

thres100view900		69.86 169	72.97 176	66.24 173	77.97 151	72.49 162	73.29 184	59.12 166	66.81 173	50.82 195	67.30 201	75.67 184	50.54 189	78.24 165	79.40 146	85.71 150	70.88 168

PatchmatchNet		64.81 185	63.74 196	66.06 177	69.21 188	58.62 196	73.16 185	60.01 164	65.92 177	66.19 155	76.27 160	59.09 204	60.45 150	66.58 201	61.47 199	67.33 198	58.24 201
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test-mter		59.39 198	61.59 202	56.82 194	53.21 210	54.82 200	73.12 186	26.57 213	53.19 211	56.31 174	64.71 204	60.47 201	56.36 164	68.69 197	64.27 192	75.38 179	65.00 181

pmmvs5		68.91 173	74.35 168	62.56 185	67.45 195	66.78 181	71.70 187	51.47 194	67.17 172	56.25 175	82.41 127	88.59 137	47.21 195	73.21 186	74.23 169	81.30 171	68.03 178

tpm		62.79 189	63.25 197	62.26 187	70.09 186	53.78 201	71.65 188	47.31 199	65.72 179	76.70 93	80.62 133	56.40 214	48.11 192	64.20 206	58.54 200	59.70 204	63.47 186

dps		65.14 183	64.50 193	65.89 178	71.41 183	65.81 185	71.44 189	61.59 151	58.56 205	61.43 167	75.45 169	52.70 218	58.06 158	69.57 195	64.65 191	71.39 188	64.77 182

baseline1		69.62 170	73.55 173	65.02 182	78.95 143	70.39 167	71.38 190	62.03 149	70.97 158	47.95 198	78.47 146	68.19 195	47.77 194	79.65 161	76.94 161	82.05 168	70.27 170

gg-mvs-nofinetune		72.68 160	75.21 166	69.73 154	81.48 124	69.04 174	70.48 191	76.67 36	86.92 59	67.80 149	88.06 83	64.67 197	42.12 200	77.60 166	73.65 171	79.81 172	66.57 179

PatchT		66.25 182	66.76 188	65.67 179	55.87 209	60.75 193	70.17 192	59.00 167	59.80 204	72.30 119	78.68 144	54.12 216	65.04 135	71.64 188	72.91 174	71.63 186	69.40 174

pmmvs3		62.72 190	68.71 183	55.74 196	50.74 213	57.10 197	70.05 193	28.82 211	61.57 200	57.39 172	71.19 190	85.73 147	53.96 176	73.36 185	69.43 185	73.47 182	62.55 190

MIMVSNet		63.02 187	69.02 182	56.01 195	68.20 190	59.26 195	70.01 194	53.79 186	71.56 156	41.26 207	71.38 187	82.38 160	36.38 205	71.43 190	67.32 188	66.45 200	59.83 198

TAMVS		63.02 187	69.30 181	55.70 197	70.12 185	56.89 198	69.63 195	45.13 201	70.23 160	38.00 210	77.79 147	75.15 186	42.60 198	74.48 178	72.81 176	68.70 196	57.75 203

PMMVS		61.98 194	65.61 190	57.74 192	45.03 215	51.76 206	69.54 196	35.05 208	55.49 209	55.32 178	68.23 199	78.39 172	58.09 157	70.21 194	71.56 179	83.42 164	63.66 185

test-LLR		62.15 193	59.46 209	65.29 180	79.07 141	52.66 204	69.46 197	62.93 142	50.76 213	53.81 183	63.11 207	58.91 205	52.87 181	66.54 202	62.34 194	73.59 180	61.87 192

TESTMET0.1,1		57.21 201	59.46 209	54.60 200	50.95 212	52.66 204	69.46 197	26.91 212	50.76 213	53.81 183	63.11 207	58.91 205	52.87 181	66.54 202	62.34 194	73.59 180	61.87 192

CHOSEN 280x420		56.32 205	58.85 211	53.36 201	51.63 211	39.91 215	69.12 199	38.61 207	56.29 207	36.79 211	48.84 212	62.59 199	63.39 144	73.61 184	67.66 187	60.61 202	63.07 189

test0.0.03 1		61.79 195	65.33 191	57.65 193	79.07 141	64.09 188	68.51 200	62.93 142	61.59 199	33.71 212	61.58 209	71.58 193	33.43 208	70.95 191	68.68 186	68.26 197	58.82 199

tpmrst		59.42 197	60.02 207	58.71 191	67.56 194	53.10 203	66.99 201	51.88 192	63.80 189	57.68 171	76.73 157	56.49 213	48.73 191	56.47 212	55.55 205	59.43 205	58.02 202

FMVSNet5		56.37 204	60.14 206	51.98 205	60.83 205	59.58 194	66.85 202	42.37 204	52.68 212	41.33 206	47.09 213	54.68 215	35.28 206	73.88 181	70.77 180	65.24 201	62.26 191

CR-MVSNet		69.56 171	68.34 184	70.99 145	72.78 179	67.63 177	64.47 203	67.74 97	59.93 202	72.30 119	80.10 134	56.77 211	65.04 135	71.64 188	72.91 174	83.61 163	69.40 174

Patchmtry						56.88 199	64.47 203	67.74 97		72.30 119

CMPMVS	55.74 18	71.56 164	76.26 157	66.08 176	68.11 191	63.91 189	63.17 205	50.52 197	68.79 168	75.49 99	70.78 193	85.67 148	63.54 142	81.58 148	77.20 158	75.63 178	85.86 82
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmnet_mix02		62.60 191	70.81 178	53.02 202	66.56 198	50.44 208	62.81 206	46.84 200	79.13 126	43.76 202	87.45 87	90.75 122	39.85 202	70.48 192	57.09 203	58.27 206	60.32 197

EMVS		58.97 200	62.63 201	54.70 199	66.26 202	48.71 209	61.74 207	42.71 203	72.80 150	46.00 200	73.01 182	71.66 191	57.91 159	80.41 157	50.68 212	53.55 211	41.11 213

EPMVS		56.62 203	59.77 208	52.94 203	62.41 204	50.55 207	60.66 208	52.83 190	65.15 184	41.80 205	77.46 152	57.28 210	42.68 197	59.81 210	54.82 206	57.23 208	53.35 206

E-PMN		59.07 199	62.79 199	54.72 198	67.01 197	47.81 211	60.44 209	43.40 202	72.95 148	44.63 201	70.42 195	73.17 190	58.73 155	80.97 153	51.98 210	54.14 210	42.26 212

ADS-MVSNet		56.89 202	61.09 203	52.00 204	59.48 206	48.10 210	58.02 210	54.37 184	72.82 149	49.19 197	75.32 170	65.97 196	37.96 204	59.34 211	54.66 207	52.99 212	51.42 208

N_pmnet		54.95 206	65.90 189	42.18 207	66.37 200	43.86 214	57.92 211	39.79 206	79.54 123	17.24 218	86.31 99	87.91 140	25.44 210	64.68 205	51.76 211	46.33 213	47.23 210

MVS-HIRNet		59.74 196	58.74 212	60.92 188	57.74 208	45.81 212	56.02 212	58.69 169	55.69 208	65.17 156	70.86 191	71.66 191	56.75 161	61.11 209	53.74 208	71.17 190	52.28 207

GG-mvs-BLEND		41.63 210	60.36 205	19.78 211	0.14 222	66.04 183	55.66 213	0.17 219	57.64 206	2.42 221	51.82 211	69.42 194	0.28 218	64.11 207	58.29 201	60.02 203	55.18 205

new-patchmatchnet		62.59 192	73.79 172	49.53 206	76.98 157	53.57 202	53.46 214	54.64 181	85.43 71	28.81 213	91.94 37	96.41 29	25.28 211	76.80 169	53.66 209	57.99 207	58.69 200

PMMVS2		48.13 209	64.06 194	29.55 210	44.06 216	36.69 216	51.95 215	29.97 210	74.75 144	8.90 220	76.02 165	91.24 118	7.53 214	73.78 182	55.91 204	34.87 215	40.01 214

new_pmnet		52.29 207	63.16 198	39.61 209	58.89 207	44.70 213	48.78 216	34.73 209	65.88 178	17.85 217	73.42 179	80.00 166	23.06 212	67.00 200	62.28 196	54.36 209	48.81 209

MVE	41.12 19	51.80 208	60.92 204	41.16 208	35.21 217	34.14 217	48.45 217	41.39 205	69.11 166	19.53 216	63.33 206	73.80 188	63.56 141	67.19 199	61.51 198	38.85 214	57.38 204
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		22.69 211	26.99 213	17.67 212	2.13 219	4.31 220	27.50 218	4.53 215	37.94 215	24.52 215	36.20 215	51.40 219	15.26 213	29.86 214	17.09 214	32.07 216	12.16 215

DeepMVS_CX						17.78 218	20.40 219	6.69 214	31.41 216	9.80 219	38.61 214	34.88 222	33.78 207	28.41 215		23.59 217	45.77 211

tmp_tt				13.54 213	16.73 218	6.42 219	8.49 220	2.36 216	28.69 217	27.44 214	18.40 216	13.51 223	3.70 215	33.23 213	36.26 213	22.54 218

Patchmatch-RL test							4.13 221

testmvs		0.93 213	1.37 215	0.41 215	0.36 221	0.36 222	0.62 222	0.39 217	1.48 218	0.18 223	2.41 217	1.31 225	0.41 217	1.25 217	1.08 216	0.48 219	1.68 216

test123		1.06 212	1.41 214	0.64 214	0.39 220	0.48 221	0.52 223	0.25 218	1.11 219	1.37 222	2.01 218	1.98 224	0.87 216	1.43 216	1.27 215	0.46 220	1.62 217

uanet_test		0.00 214	0.00 216	0.00 216	0.00 223	0.00 223	0.00 224	0.00 220	0.00 220	0.00 224	0.00 219	0.00 226	0.00 219	0.00 218	0.00 217	0.00 221	0.00 218

sosnet-low-res		0.00 214	0.00 216	0.00 216	0.00 223	0.00 223	0.00 224	0.00 220	0.00 220	0.00 224	0.00 219	0.00 226	0.00 219	0.00 218	0.00 217	0.00 221	0.00 218

sosnet		0.00 214	0.00 216	0.00 216	0.00 223	0.00 223	0.00 224	0.00 220	0.00 220	0.00 224	0.00 219	0.00 226	0.00 219	0.00 218	0.00 217	0.00 221	0.00 218

RE-MVS-def										87.10 29

9.14												89.43 128

SR-MVS					91.82 13			80.80 7				95.53 50

MTAPA										89.37 9		94.85 67

MTMP										90.54 5		95.16 59

mPP-MVS					93.05 4							95.77 44

NP-MVS									78.65 128

High-resolution multi-view benchmark