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		86.29 1	90.77 1	81.06 1	75.10 55	83.76 2	93.79 1	61.08 18	89.57 1	86.19 1	90.06 10	93.01 24	76.72 2	94.71 1	92.72 1	93.47 1	91.56 2

COLMAP_ROB	75.87 2	84.34 2	89.80 2	77.97 11	75.52 52	82.76 4	90.39 19	54.21 55	89.37 2	83.18 2	89.90 12	95.58 11	72.34 10	92.31 4	90.04 5	92.17 5	88.61 18
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CP-MVS		84.06 3	86.79 10	80.86 2	81.81 8	79.66 29	92.67 6	64.48 1	83.13 32	82.32 3	80.89 91	92.97 25	72.51 9	91.74 6	90.02 6	91.40 17	89.14 8

ACMMPR		83.94 4	87.20 4	80.14 4	81.04 13	81.92 8	92.57 8	63.14 5	84.35 20	79.45 11	83.37 55	92.04 38	72.82 8	90.66 12	88.96 11	91.80 6	89.13 9

MP-MVS		83.50 5	86.11 19	80.45 3	82.58 4	80.60 24	92.68 5	63.48 3	81.43 46	80.21 9	81.95 77	90.76 62	72.86 6	90.14 19	89.30 10	90.92 19	88.59 19
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ACMMP		83.17 6	86.75 11	79.01 7	80.11 25	82.01 7	92.29 10	60.35 25	82.20 40	78.32 15	80.59 92	93.14 22	70.67 15	91.30 8	89.36 9	92.30 4	88.62 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
PGM-MVS		83.03 7	85.67 26	79.95 5	80.69 17	81.09 15	92.40 9	63.06 6	79.38 61	80.21 9	80.31 96	91.44 43	71.75 12	90.46 15	88.53 14	91.57 9	88.50 20

LGP-MVS_train		82.91 8	86.50 13	78.72 8	78.72 34	81.03 16	89.78 23	61.16 17	80.15 56	80.44 6	84.83 41	94.19 14	70.52 17	90.70 11	87.19 22	91.71 8	87.37 31

ACMM	71.24 7	82.85 9	86.59 12	78.50 9	80.10 26	78.59 34	91.77 11	60.76 22	84.43 18	76.49 24	81.58 85	93.50 17	70.45 18	91.38 7	89.42 8	91.42 16	87.22 33
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HFP-MVS		82.37 10	86.28 15	77.81 14	79.94 27	80.96 18	91.13 14	63.30 4	84.04 22	71.81 39	82.39 69	89.59 85	69.16 23	89.08 25	88.83 13	91.49 13	89.10 10

DeepC-MVS	73.80 3	82.34 11	86.87 8	77.06 18	78.62 35	84.34 1	90.30 21	63.54 2	83.10 33	71.30 44	86.91 24	90.54 68	67.12 31	87.81 34	87.05 23	91.46 15	88.37 21
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CPTT-MVS		82.32 12	85.00 34	79.19 6	80.73 16	80.86 21	91.68 12	62.59 10	82.55 37	75.53 28	73.88 148	92.28 32	73.74 5	90.07 20	87.65 18	90.87 20	87.74 25

ACMP	70.35 9	82.17 13	86.45 14	77.18 17	79.33 28	81.00 17	89.27 27	58.63 31	81.35 48	75.46 29	82.97 62	95.08 12	68.90 24	90.49 14	87.43 21	91.48 14	86.84 35
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SteuartSystems-ACMMP		82.16 14	85.55 28	78.21 10	80.48 19	79.28 30	92.65 7	61.03 19	80.55 54	77.00 22	81.80 80	90.71 63	68.73 25	90.25 17	87.94 17	89.36 27	88.30 22
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		82.15 15	85.93 21	77.74 15	80.13 24	80.25 26	91.01 15	60.61 23	85.54 12	78.61 14	83.21 58	86.96 124	65.95 36	88.10 31	87.59 19	90.11 21	89.83 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
SD-MVS		82.13 16	86.80 9	76.67 19	80.36 22	80.66 22	89.48 25	56.93 35	82.50 38	67.55 68	87.05 22	91.40 45	72.84 7	88.66 27	88.32 15	92.85 2	89.04 11
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
LTVRE_ROB	75.99 1	82.04 17	87.16 5	76.07 22	63.57 142	70.27 77	86.48 45	62.99 7	89.00 5	80.32 7	86.25 28	91.04 54	74.66 4	92.58 3	90.29 4	88.42 34	90.72 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
DVP-MVS++		82.03 18	88.03 3	75.05 27	82.08 6	78.96 32	88.98 31	56.44 40	89.29 3	72.39 37	93.25 1	93.86 16	63.42 51	85.46 45	81.36 57	86.96 47	94.00 1

PMVS	70.37 8	81.82 19	87.08 6	75.68 24	77.06 44	77.23 42	87.77 41	56.25 43	83.33 31	67.18 75	89.48 15	87.94 108	77.70 1	93.02 2	92.57 2	88.13 37	86.00 40
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ACMMP_NAP		81.79 20	85.72 24	77.21 16	79.15 32	79.68 28	91.62 13	59.66 27	83.55 28	77.74 18	83.72 52	87.34 116	65.36 37	88.61 28	87.56 20	89.73 26	89.58 6

X-MVS		81.61 21	84.73 37	77.97 11	80.31 23	81.29 12	93.53 2	62.50 11	81.41 47	77.45 19	72.04 160	90.19 77	62.50 58	90.57 13	88.87 12	91.54 10	88.73 15

OPM-MVS		81.44 22	85.68 25	76.49 20	79.27 29	78.21 37	89.84 22	58.67 30	85.25 13	76.26 25	85.28 38	92.88 26	66.03 35	87.20 37	85.40 27	88.86 31	85.58 44
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
TSAR-MVS + MP.		81.23 23	86.13 17	75.52 25	80.74 15	83.22 3	90.55 16	55.12 50	80.87 51	67.62 67	88.01 17	92.38 31	70.61 16	86.64 39	83.10 42	88.51 32	88.67 16
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
TSAR-MVS + ACMM		81.20 24	86.92 7	74.52 29	77.60 40	82.29 5	84.41 51	62.95 8	82.99 34	64.03 92	87.71 18	89.17 91	71.98 11	88.19 30	88.10 16	86.18 56	89.95 4

APDe-MVS		81.08 25	86.12 18	75.20 26	79.25 30	80.91 19	90.38 20	57.05 34	85.83 10	66.07 80	87.34 21	91.27 47	69.45 19	85.99 43	82.55 44	88.98 30	88.95 13
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DPE-MVS		81.01 26	85.18 30	76.15 21	78.58 36	80.64 23	89.77 24	57.92 32	81.66 45	73.45 32	86.84 25	89.80 83	69.33 21	85.40 46	82.91 43	87.87 39	89.01 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APD-MVS		80.60 27	84.63 38	75.91 23	81.22 11	81.48 10	90.49 17	58.81 29	77.54 70	67.49 70	85.90 30	89.82 82	69.43 20	86.08 42	83.80 37	88.01 38	87.77 24
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HPM-MVS++		80.44 28	82.57 51	77.96 13	81.99 7	72.76 63	90.48 18	61.31 14	80.85 52	77.90 17	81.93 78	87.01 121	68.20 27	84.15 58	85.27 29	87.85 40	86.00 40

DVP-MVS		80.31 29	85.60 27	74.15 33	76.23 48	78.39 35	86.62 43	55.79 46	86.47 9	71.32 43	90.96 7	89.02 94	69.28 22	84.62 56	81.64 54	85.66 61	88.09 23
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
ACMH+	67.97 10	80.15 30	86.16 16	73.14 41	73.82 62	76.41 45	83.59 55	54.82 53	87.35 6	70.86 48	86.98 23	96.27 4	66.50 32	89.17 24	83.39 39	89.26 28	83.56 50

OMC-MVS		79.95 31	85.28 29	73.74 37	72.95 65	80.10 27	87.87 38	48.13 87	84.62 17	79.42 12	80.27 97	92.49 29	64.14 45	87.25 36	85.11 30	89.92 24	87.10 34

MED-MVS		79.80 32	84.79 36	73.98 34	78.58 36	78.68 33	87.97 36	57.27 33	85.66 11	64.22 90	85.63 35	90.11 80	67.50 29	84.90 53	81.13 59	88.32 35	87.45 29

SED-MVS		79.70 33	85.16 31	73.34 39	75.83 51	78.11 38	88.77 33	56.45 39	84.85 15	69.45 59	90.70 9	88.38 101	63.16 53	85.12 51	81.28 58	86.40 53	87.63 26

MSP-MVS		79.65 34	84.28 42	74.25 31	78.92 33	81.86 9	89.07 28	60.49 24	83.85 25	70.05 54	85.12 39	90.92 60	62.99 55	81.15 78	81.64 54	83.99 71	85.42 46
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
DeepPCF-MVS	71.57 5	79.49 35	84.05 43	74.17 32	74.14 59	80.88 20	89.33 26	56.24 44	82.41 39	71.58 41	82.27 71	86.47 129	66.47 33	84.80 54	84.16 35	87.26 45	87.34 32

LS3D		79.33 36	84.03 44	73.84 35	75.37 53	78.09 39	83.30 57	52.94 64	84.42 19	76.01 26	84.16 47	87.44 115	65.34 38	86.30 40	82.08 51	90.09 22	85.70 42

aaEdge-Enhanced		78.93 37	84.62 39	72.30 45	77.98 39	79.20 31	87.82 39	53.22 61	83.71 27	62.73 94	85.63 35	91.37 46	67.58 28	84.40 57	80.56 60	84.46 66	87.45 29

3Dnovator+	72.94 4	78.78 38	83.05 48	73.80 36	70.70 78	81.34 11	88.33 34	56.01 45	81.33 49	72.87 36	78.06 116	81.15 162	63.83 48	87.39 35	85.82 25	91.06 18	86.28 39

UA-Net		78.65 39	83.96 45	72.46 43	84.87 1	76.15 46	89.06 29	55.70 47	77.25 71	53.14 139	79.73 102	82.09 160	59.69 74	92.21 5	90.93 3	92.32 3	89.36 7

DeepC-MVS_fast	71.40 6	78.48 40	82.92 49	73.31 40	76.44 47	82.23 6	87.59 42	56.56 38	77.79 68	68.91 64	77.00 123	87.32 117	61.90 60	85.40 46	84.37 32	88.46 33	86.33 38
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SF-MVS		78.36 41	83.47 47	72.41 44	76.04 50	75.72 49	83.86 53	51.81 68	84.00 24	70.65 51	81.27 87	92.22 33	64.64 43	83.28 68	80.28 62	87.44 44	87.49 28

WR-MVS		78.32 42	86.09 20	69.25 62	76.22 49	72.33 70	85.71 48	59.02 28	86.66 7	51.41 145	92.91 2	96.76 1	53.09 113	90.21 18	85.30 28	90.05 23	78.46 78

ACMH	66.19 11	78.12 43	84.55 40	70.63 53	69.62 85	72.40 69	80.77 72	46.43 100	89.24 4	77.99 16	87.42 20	95.83 9	62.95 56	86.27 41	78.24 72	86.00 59	82.46 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
train_agg		77.83 44	80.47 61	74.77 28	80.92 14	69.60 78	88.87 32	56.32 42	74.03 97	71.03 46	83.67 53	87.68 111	64.75 42	83.70 60	81.85 53	86.71 49	82.73 51

NCCC		77.82 45	80.72 60	74.43 30	79.24 31	75.72 49	88.06 35	56.36 41	79.61 58	73.22 34	67.75 175	87.05 120	63.09 54	85.62 44	84.00 36	86.62 50	85.30 47

CNVR-MVS		77.79 46	81.57 55	73.38 38	78.37 38	75.91 47	87.97 36	55.11 51	79.41 60	70.98 47	74.70 142	86.43 130	61.77 61	85.10 52	83.73 38	86.10 58	85.68 43

WR-MVS_H		77.56 47	85.88 22	67.86 66	80.54 18	74.32 58	83.23 58	61.78 12	83.47 29	47.46 171	91.81 6	95.84 8	50.50 138	90.44 16	84.37 32	83.63 76	80.89 65

RPSCF		77.56 47	84.51 41	69.46 61	65.17 120	74.36 57	79.74 79	47.45 90	84.01 23	72.89 35	77.89 117	90.67 64	65.14 40	88.25 29	89.74 7	86.38 54	86.64 37

PS-CasMVS		77.46 49	85.80 23	67.73 68	81.24 10	72.88 62	80.63 73	61.28 15	84.14 21	50.53 155	92.13 4	96.76 1	50.12 141	91.02 9	84.46 31	82.60 88	79.19 71

DTE-MVSNet		77.28 50	84.87 35	68.42 64	82.94 3	72.70 65	81.60 67	61.78 12	85.03 14	51.40 146	92.11 5	96.00 6	49.42 145	89.73 22	82.52 46	83.39 81	75.98 91

SixPastTwentyTwo		77.24 51	83.65 46	69.78 58	65.14 121	64.85 104	77.44 89	47.74 89	82.76 36	68.52 65	87.65 19	93.31 19	71.68 13	89.49 23	82.41 47	88.14 36	85.05 48

CDPH-MVS		77.22 52	81.05 59	72.75 42	77.29 42	77.46 41	86.36 46	54.02 57	73.00 106	69.75 57	77.78 119	88.90 96	61.31 65	84.09 59	82.54 45	87.79 41	83.57 49

PEN-MVS		77.06 53	85.05 32	67.74 67	82.29 5	72.59 66	80.86 71	61.03 19	84.66 16	50.08 159	92.19 3	96.59 3	49.12 147	89.83 21	82.35 48	83.06 82	77.14 84

CP-MVSNet		77.01 54	85.04 33	67.65 69	81.16 12	72.72 64	80.54 74	61.18 16	82.09 41	50.41 156	90.81 8	95.89 7	50.03 142	90.86 10	84.30 34	82.56 90	78.65 77

CSCG		76.95 55	82.08 53	70.97 49	73.32 64	78.35 36	81.08 70	47.19 91	83.47 29	69.82 56	80.44 93	87.19 118	64.59 44	81.01 81	77.26 79	89.83 25	86.84 35

CNLPA		76.67 56	81.72 54	70.77 52	70.75 76	76.68 44	86.14 47	46.11 103	81.82 43	74.68 30	76.37 125	86.23 135	62.92 57	85.28 49	83.29 40	84.02 70	82.40 53

MSLP-MVS++		76.66 57	82.32 52	70.06 55	70.51 79	80.27 25	79.77 78	55.58 48	77.79 68	63.09 93	67.25 182	89.50 86	71.01 14	88.10 31	85.74 26	80.39 105	87.56 27

TSAR-MVS + COLMAP		75.85 58	81.06 57	69.77 59	71.15 72	76.90 43	82.93 60	52.43 66	79.25 62	70.13 52	82.78 63	87.00 122	60.02 70	80.30 85	79.61 66	81.95 95	81.61 61

HQP-MVS		75.81 59	78.91 68	72.18 46	77.41 41	75.38 52	84.75 49	53.35 59	76.12 81	73.32 33	69.48 165	88.07 105	57.76 82	79.42 91	78.44 69	86.48 51	85.50 45

PLC	64.88 15	75.76 60	80.22 62	70.57 54	70.46 80	77.75 40	82.01 65	48.84 81	80.74 53	70.85 49	71.32 162	84.82 147	63.69 49	84.73 55	82.35 48	87.54 42	79.80 68
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TAPA-MVS	66.11 12	75.37 61	79.24 66	70.86 50	67.63 93	74.09 59	83.17 59	44.75 119	81.82 43	80.83 5	65.61 199	88.04 106	61.58 62	83.21 69	80.12 63	87.17 46	81.82 57
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PHI-MVS		75.17 62	78.37 69	71.43 47	71.13 73	72.46 68	82.28 64	50.55 74	73.39 103	79.05 13	73.65 150	87.50 114	61.98 59	81.10 79	78.48 68	83.60 77	81.99 55

MGCNet		74.91 63	79.25 65	69.85 57	75.01 56	74.95 54	86.61 44	48.67 82	68.87 144	67.51 69	80.13 99	83.78 154	55.77 92	83.37 66	81.89 52	85.55 63	81.75 58

anonymousdsp		74.76 64	82.59 50	65.63 86	45.61 253	61.13 135	89.06 29	32.58 236	74.11 96	59.55 107	84.06 48	94.12 15	75.24 3	88.94 26	86.95 24	91.74 7	88.81 14

AdaColmap		74.73 65	77.57 74	71.40 48	76.90 45	75.76 48	84.54 50	53.08 63	76.20 79	66.64 78	66.06 195	78.16 188	61.32 64	85.37 48	82.20 50	85.95 60	79.27 70

v7n		74.47 66	81.06 57	66.77 75	66.98 99	67.10 81	76.76 93	45.88 105	81.98 42	67.43 71	88.38 16	95.67 10	61.38 63	80.76 83	73.49 101	82.21 93	80.06 66

PCF-MVS	65.25 14	73.99 67	76.74 79	70.79 51	71.61 71	75.33 53	83.76 54	50.40 75	74.88 85	74.50 31	67.60 176	85.36 144	58.30 80	78.61 97	74.25 96	86.15 57	81.13 64
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MCST-MVS		73.84 68	77.44 75	69.63 60	73.75 63	74.73 56	81.38 69	48.58 83	74.77 86	69.16 61	71.97 161	86.20 136	59.50 75	78.51 98	74.06 98	85.42 64	81.85 56

TSAR-MVS + GP.		73.42 69	76.31 80	70.05 56	77.15 43	71.13 73	81.59 68	54.11 56	69.84 136	58.65 111	66.20 193	78.77 182	65.29 39	83.65 61	83.14 41	83.54 78	81.47 62

Gipuma		73.40 70	79.27 64	66.55 80	63.64 141	59.35 154	70.28 147	45.92 104	83.79 26	71.78 40	84.04 49	93.07 23	68.69 26	87.90 33	76.76 81	78.98 120	69.96 138
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVS_111021_HR		72.37 71	76.12 83	68.00 65	68.55 89	64.30 112	82.93 60	48.98 80	74.25 94	65.39 84	73.59 151	84.11 152	59.48 76	82.61 72	78.38 70	82.66 87	75.59 93

TinyColmap		71.85 72	76.11 84	66.87 74	66.07 109	65.34 98	74.35 109	49.30 79	79.93 57	75.93 27	75.66 132	87.74 110	54.72 101	80.66 84	70.42 125	80.85 103	73.02 111

UniMVSNet_ETH3D		71.84 73	81.36 56	60.74 123	76.46 46	66.01 92	66.49 174	60.24 26	86.58 8	41.87 199	90.04 11	96.02 5	43.72 183	85.14 50	77.30 78	75.64 153	68.40 162

TranMVSNet+NR-MVSNet		71.66 74	79.23 67	62.83 108	72.54 68	65.64 94	74.77 107	55.27 49	75.91 83	45.50 184	89.55 13	94.25 13	45.96 172	82.74 71	77.03 80	82.96 84	69.48 146

MVS_111021_LR		71.60 75	75.21 89	67.38 70	67.42 94	62.44 123	81.73 66	46.24 101	70.89 120	66.80 77	73.19 154	84.98 145	60.09 69	81.94 75	77.77 76	82.00 94	75.29 94

EG-PatchMatch MVS		71.50 76	76.82 78	65.30 87	70.74 77	66.50 87	74.23 111	43.25 129	72.02 111	59.11 108	79.85 101	86.88 126	63.95 47	80.29 86	75.25 92	80.51 104	76.98 85

DPM-MVS		71.35 77	73.50 114	68.84 63	74.93 57	73.35 60	84.07 52	50.56 73	71.91 112	67.06 76	61.21 222	77.02 195	52.64 118	74.15 125	75.14 93	83.79 74	81.74 59

UniMVSNet (Re)		71.29 78	78.14 70	63.30 99	70.29 81	66.57 84	75.98 97	54.74 54	70.20 128	46.20 182	85.08 40	93.21 20	48.19 156	82.50 73	78.33 71	84.40 68	71.08 126

CLD-MVS		71.24 79	78.12 71	63.20 101	74.03 60	71.60 71	82.82 62	32.91 232	74.23 95	69.32 60	79.65 103	91.54 41	47.02 165	81.22 77	79.01 67	73.09 176	69.63 142
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Casviewmamba		71.14 80	77.09 77	64.20 93	69.71 84	66.51 86	76.15 96	46.24 101	75.99 82	57.72 117	86.62 27	91.14 49	54.30 103	76.97 105	68.87 133	81.07 100	73.52 105

CANet		71.07 81	75.09 91	66.39 81	72.57 67	71.53 72	82.38 63	47.10 92	59.81 193	59.81 106	74.97 137	84.37 151	54.25 106	79.89 89	77.64 77	82.25 92	77.40 82

v1192		71.06 82	74.87 93	66.61 77	66.38 103	65.80 93	78.27 83	45.28 110	70.19 129	70.79 50	83.37 55	91.79 39	58.76 79	70.86 173	69.02 132	80.16 109	73.08 109

DU-MVS		71.03 83	77.92 72	62.98 104	70.81 74	65.48 96	73.93 115	56.76 36	69.95 134	46.77 178	85.70 33	93.49 18	46.91 166	83.47 62	77.82 75	82.72 86	69.54 143

v1240		70.94 84	74.52 97	66.76 76	66.54 102	64.40 108	77.76 86	45.29 109	70.05 132	71.45 42	83.36 57	90.96 56	60.37 67	70.50 178	68.68 135	79.14 117	73.68 104

v1921920		70.82 85	74.46 101	66.58 79	66.33 104	64.35 111	77.72 87	45.07 112	70.39 125	71.18 45	83.15 59	90.62 66	59.97 71	70.90 171	68.43 142	79.19 116	73.39 106

UniMVSNet_NR-MVSNet		70.82 85	77.44 75	63.11 103	71.75 70	66.02 91	73.93 115	55.00 52	70.90 119	46.77 178	86.68 26	91.54 41	46.91 166	81.07 80	76.32 86	84.28 69	69.54 143

PVSNet_Blended_VisFu		70.70 87	73.62 112	67.28 72	63.53 143	72.96 61	77.97 84	52.10 67	63.65 169	62.66 95	71.14 163	73.46 208	63.55 50	79.35 95	75.34 91	83.90 72	79.43 69

v144192		70.68 88	74.40 103	66.34 82	65.94 111	64.38 109	77.63 88	45.18 111	69.97 133	70.11 53	82.70 65	90.77 61	59.84 73	71.43 166	68.46 138	79.31 115	73.08 109

EC-MVSNet		70.50 89	73.32 119	67.20 73	72.07 69	66.21 89	70.86 142	50.10 76	57.66 207	60.49 105	74.97 137	79.42 176	63.32 52	79.65 90	75.46 90	86.35 55	79.87 67

FPMVS		70.46 90	74.89 92	65.28 88	69.09 87	61.42 129	77.07 91	46.92 95	76.73 76	53.53 134	67.33 179	75.07 203	67.23 30	83.41 64	81.54 56	77.86 129	78.73 75

v1144		70.45 91	74.50 100	65.73 85	65.74 114	64.88 103	77.33 90	44.16 121	70.59 124	69.63 58	83.15 59	91.42 44	57.79 81	71.29 168	68.53 137	79.72 113	71.63 122

v10		70.25 92	74.59 96	65.19 89	65.32 118	66.46 88	76.60 95	44.84 116	67.38 151	67.21 74	82.75 64	90.56 67	57.70 83	71.69 161	68.63 136	79.44 114	74.67 97

Effi-MVS+-dtu		70.10 93	73.76 111	65.82 84	70.23 82	74.92 55	79.47 80	44.49 120	56.98 212	54.34 128	64.26 204	84.78 148	59.97 71	80.96 82	80.38 61	86.44 52	74.05 102

viewdifsd2359ckpt09		70.05 94	75.98 85	63.14 102	63.10 146	66.55 85	76.63 94	46.51 98	69.53 139	56.89 120	77.65 120	89.44 89	55.48 94	77.98 103	76.58 84	80.24 107	74.13 100

SPE-MVS-test		70.00 95	72.92 122	66.59 78	66.71 101	64.06 114	80.28 76	44.82 117	58.41 199	58.08 115	73.57 152	80.94 165	63.98 46	83.29 67	75.93 88	85.65 62	74.23 98

MAR-MVS		70.00 95	72.28 135	67.34 71	69.89 83	72.57 67	80.09 77	49.49 78	60.28 186	69.03 62	59.29 231	80.79 167	54.68 102	78.39 100	76.00 87	80.87 102	78.67 76
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
casdiffseed414692147		69.96 97	75.50 88	63.50 97	67.73 92	63.35 118	72.92 127	44.85 115	73.46 101	62.21 96	82.98 61	92.85 27	54.29 104	74.81 120	68.84 134	79.00 119	72.21 117

Vis-MVSNet		69.95 98	77.69 73	60.91 121	60.67 164	66.71 82	77.94 85	48.58 83	69.10 142	45.78 183	80.21 98	83.58 156	53.41 112	82.92 70	80.11 64	79.08 118	81.21 63
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS		69.56 99	72.49 131	66.14 83	66.85 100	64.10 113	72.55 128	42.91 131	58.90 196	60.78 101	72.93 157	83.21 158	66.32 34	78.77 96	72.84 108	87.45 43	76.72 86

EPP-MVSNet		69.51 100	76.17 81	61.74 117	68.38 91	66.60 83	71.77 132	46.98 93	73.60 100	41.79 200	82.06 74	69.65 219	52.51 119	83.41 64	79.94 65	89.02 29	77.94 79

3Dnovator	65.69 13	69.43 101	75.74 87	62.06 114	60.78 162	70.50 76	75.85 99	39.57 181	74.44 89	57.41 118	75.91 128	77.73 192	55.34 97	76.86 106	75.61 89	83.44 79	79.14 72

E6new		69.19 102	74.52 97	62.96 105	64.65 125	60.53 142	74.96 103	41.17 153	78.08 65	67.31 72	84.59 45	92.19 34	53.04 115	72.20 154	65.00 174	76.67 136	69.09 153

E6		69.19 102	74.52 97	62.96 105	64.65 125	60.53 142	74.96 103	41.17 153	78.08 65	67.31 72	84.59 45	92.19 34	53.04 115	72.20 154	65.00 174	76.67 136	69.09 153

Effi-MVS+		69.04 104	73.01 121	64.40 92	67.20 97	64.83 105	74.87 106	43.97 123	63.33 171	60.90 100	73.06 155	85.79 141	55.61 93	73.58 134	76.41 85	83.84 73	74.09 101

v2v482		69.01 105	73.39 118	63.89 95	63.86 135	62.99 120	75.26 102	42.05 142	70.22 127	68.46 66	82.64 66	91.61 40	55.38 95	70.89 172	66.93 160	78.30 125	68.48 161

MSDG		68.98 106	73.31 120	63.92 94	67.08 98	68.27 79	75.41 101	40.77 162	67.61 149	64.89 87	75.75 131	78.96 178	53.70 109	76.72 109	73.95 99	81.71 98	71.93 120

v8		68.77 107	73.50 114	63.26 100	63.74 139	64.47 107	74.22 112	42.07 141	67.30 153	64.89 87	82.08 73	90.23 75	56.50 90	71.85 160	66.57 163	78.14 126	72.02 118

NR-MVSNet		68.66 108	76.15 82	59.93 129	65.49 115	65.48 96	74.42 108	56.76 36	69.95 134	45.38 185	85.70 33	91.13 51	34.68 233	74.52 123	76.75 82	82.83 85	69.49 145

E4		68.56 109	73.87 108	62.38 109	64.56 127	60.30 144	74.15 113	40.68 164	77.12 73	65.86 81	83.44 54	91.14 49	52.51 119	71.34 167	64.56 177	76.49 141	69.19 151

USDC		68.53 110	71.82 144	64.68 90	63.53 143	61.87 128	70.12 149	46.98 93	77.89 67	76.58 23	68.55 171	86.88 126	50.50 138	73.73 130	65.62 166	80.39 105	68.21 165

IS_MVSNet		68.20 111	74.41 102	60.96 120	68.55 89	64.36 110	71.47 137	48.33 85	70.11 131	43.30 191	80.90 90	74.54 205	47.19 164	81.25 76	77.97 74	86.94 48	71.76 121

E5new		68.19 112	73.41 116	62.09 111	64.54 128	60.26 145	73.68 121	40.53 167	76.37 77	65.41 82	82.61 67	90.32 72	52.09 122	70.81 174	64.16 181	76.33 143	69.36 147

E5		68.19 112	73.41 116	62.09 111	64.54 128	60.26 145	73.68 121	40.53 167	76.37 77	65.41 82	82.61 67	90.32 72	52.09 122	70.81 174	64.16 181	76.33 143	69.36 147

Baseline_NR-MVSNet		68.15 114	75.12 90	60.02 128	70.81 74	55.67 182	75.88 98	53.40 58	71.25 116	43.96 189	85.88 31	92.68 28	45.76 173	83.47 62	68.34 143	70.34 208	68.58 159

GeoE		68.11 115	72.10 140	63.47 98	67.32 95	62.42 124	78.32 82	43.22 130	64.06 168	55.72 124	73.97 146	84.58 149	55.35 96	76.09 114	70.41 126	80.89 101	73.14 108

casdiffmvs_mvg		68.01 116	74.22 106	60.78 122	63.75 138	62.08 127	70.21 148	42.58 133	72.11 110	58.53 112	84.80 43	88.98 95	49.37 146	73.25 138	67.54 155	80.24 107	70.75 129
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E3		67.77 117	72.78 125	61.92 115	64.26 130	60.09 150	73.72 120	40.40 172	74.39 91	65.10 85	81.79 81	90.27 74	51.99 124	70.42 181	63.76 189	76.04 145	68.75 157

E3new		67.76 118	72.77 126	61.92 115	64.26 130	60.10 149	73.73 119	40.41 171	74.39 91	65.08 86	81.78 82	90.23 75	51.98 125	70.43 180	63.75 190	76.04 145	68.75 157

Fast-Effi-MVS+		67.71 119	72.54 130	62.07 113	63.83 136	63.68 116	75.74 100	39.94 175	60.89 185	54.29 129	73.00 156	86.19 137	56.85 87	78.46 99	73.23 104	81.74 97	72.36 115

viewmacassd2359aftdt		67.58 120	74.22 106	59.84 131	61.60 156	59.46 153	72.40 129	35.74 211	76.19 80	62.14 97	83.74 51	90.96 56	51.94 126	73.07 139	65.37 171	75.17 158	70.72 130

MVSMamba_PlusPlus		67.34 121	71.15 152	62.89 107	66.08 108	66.04 90	73.24 125	43.69 127	59.94 192	58.73 110	67.34 178	81.03 164	53.68 110	74.26 124	71.91 113	81.93 96	77.53 81

hybridcas		67.20 122	73.79 110	59.52 133	64.79 122	61.42 129	71.75 134	39.04 182	74.57 88	53.34 136	85.47 37	89.06 93	50.57 137	72.84 146	64.11 184	77.64 132	69.05 155

viewcassd2359sk11		67.13 123	71.88 143	61.59 118	64.04 133	59.95 151	73.40 124	40.24 173	72.16 109	64.55 89	80.41 94	89.49 87	51.60 127	69.66 190	63.11 196	75.72 149	68.40 162

thisisatest0515		66.95 124	72.29 134	60.72 124	56.37 196	56.05 180	71.08 138	38.81 187	67.59 150	53.26 138	78.21 113	79.79 175	60.11 68	75.69 117	73.02 106	84.69 65	75.66 92

EPNet		66.87 125	68.89 167	64.53 91	73.97 61	61.13 135	78.46 81	61.03 19	56.78 214	53.41 135	66.91 187	70.91 214	43.49 184	76.08 115	76.68 83	76.81 134	73.73 103
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
viewdifsd2359ckpt13		66.73 126	72.00 142	60.58 125	62.91 148	61.21 134	72.39 131	39.64 179	68.65 145	60.54 104	78.08 115	88.54 100	52.11 121	71.52 163	65.24 173	75.88 148	70.78 128

E2		66.57 127	71.07 153	61.32 119	63.87 134	59.84 152	73.12 126	40.09 174	70.14 130	64.12 91	79.09 109	88.79 97	51.25 129	68.97 195	62.58 200	75.46 154	68.09 166

sasdasda		66.37 128	74.37 104	57.04 151	65.89 112	65.06 99	62.58 195	42.55 134	76.82 74	46.87 176	67.33 179	86.38 131	45.49 175	76.77 107	71.85 114	78.87 122	76.35 87

canonicalmvs		66.37 128	74.37 104	57.04 151	65.89 112	65.06 99	62.58 195	42.55 134	76.82 74	46.87 176	67.33 179	86.38 131	45.49 175	76.77 107	71.85 114	78.87 122	76.35 87

QAPM		66.36 130	72.76 127	58.90 137	59.57 171	65.01 101	64.05 189	41.17 153	73.09 105	56.82 121	69.42 166	77.78 191	55.07 99	73.00 142	72.07 111	76.71 135	78.96 73

viewmanbaseed2359cas		66.24 131	72.42 132	59.03 135	61.13 159	59.13 156	71.64 135	35.37 212	71.67 113	60.68 102	80.93 89	89.48 88	50.83 133	71.60 162	64.04 186	74.50 164	70.09 136

casdiffmvs		66.19 132	72.34 133	59.02 136	62.75 149	60.61 141	69.06 156	41.38 150	69.49 140	54.11 130	84.00 50	89.74 84	49.12 147	70.74 177	62.70 198	77.70 131	69.14 152
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
V42		65.79 133	72.11 138	58.42 141	51.89 228	58.69 157	73.80 117	34.50 221	65.40 162	57.10 119	79.54 105	89.09 92	57.51 84	71.98 158	67.83 151	75.70 151	72.26 116

IterMVS-LS		65.76 134	70.85 157	59.81 132	65.33 117	57.78 164	64.63 186	48.02 88	65.65 161	51.05 150	81.31 86	77.47 193	54.94 100	69.46 191	69.36 131	74.90 162	74.95 95
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PM-MVS		65.66 135	71.25 151	59.14 134	58.92 182	54.88 197	73.66 123	38.55 190	66.12 158	49.91 161	69.87 164	86.97 123	60.61 66	76.30 112	74.75 94	73.19 174	69.83 139

UGNet		65.61 136	74.79 94	54.91 167	54.54 221	68.20 80	70.97 141	48.21 86	67.14 155	41.67 201	74.15 145	80.65 169	36.10 224	79.39 92	77.99 73	77.95 128	76.01 90
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
DELS-MVS		65.54 137	71.79 145	58.24 144	59.68 170	65.55 95	70.99 139	38.69 189	62.29 175	49.27 165	75.03 136	81.42 161	50.93 132	73.71 132	71.35 117	79.90 111	73.20 107
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
pmmvs-eth3d		65.36 138	70.09 161	59.85 130	63.05 147	53.61 203	74.29 110	46.45 99	68.14 147	51.45 144	78.83 111	85.78 142	49.87 144	70.44 179	70.45 124	74.00 167	63.38 190

FA-MVS(training)		65.22 139	69.19 165	60.58 125	60.91 160	57.60 168	71.57 136	38.82 186	65.84 160	61.18 99	75.95 127	74.52 206	51.18 131	73.32 136	67.41 157	79.80 112	69.70 141

onestephybrid01		64.95 140	71.07 153	57.81 149	60.74 163	57.96 162	70.47 145	41.03 156	61.12 184	54.46 127	77.87 118	88.01 107	47.42 161	73.62 133	67.51 156	72.74 177	71.42 125

v148		64.92 141	70.58 160	58.32 142	59.89 168	57.09 171	66.04 178	35.27 213	69.11 141	60.66 103	79.57 104	90.93 59	53.91 108	69.81 189	62.22 202	74.14 165	65.31 181

FC-MVSNet-train		64.87 142	74.76 95	53.33 176	65.24 119	58.05 160	69.69 153	41.92 145	70.99 118	32.62 238	85.75 32	88.23 102	32.10 244	77.61 104	74.41 95	78.43 124	68.25 164

pmmvs6		64.78 143	75.82 86	51.89 184	62.41 151	57.13 170	60.24 205	45.59 107	82.90 35	34.69 223	84.83 41	93.18 21	36.22 223	76.43 111	71.13 120	72.21 184	65.12 182

viewmamba		64.77 144	71.33 149	57.11 150	59.34 176	56.66 174	69.98 150	39.86 176	64.70 164	54.75 126	80.33 95	88.09 104	46.49 169	72.71 149	66.26 165	72.23 183	70.56 132

viewdifsd2359ckpt07		64.71 145	72.11 138	56.08 159	62.59 150	56.76 173	70.41 146	32.26 239	73.93 98	51.19 147	82.32 70	90.96 56	49.92 143	69.24 193	61.27 207	70.10 210	70.27 133

OpenMVS	60.79 16	64.42 146	69.72 162	58.23 145	61.63 155	62.17 125	64.11 188	37.54 202	67.17 154	55.71 125	65.89 196	74.89 204	52.67 117	72.20 154	68.29 145	77.73 130	77.39 83

MGCFI-Net		64.40 147	73.52 113	53.76 174	65.41 116	63.86 115	58.32 216	42.38 137	77.23 72	37.76 211	68.03 173	86.11 139	39.76 204	75.70 116	67.69 154	78.96 121	76.03 89

test1111		64.34 148	71.57 146	55.90 160	67.25 96	60.24 148	66.66 171	51.63 71	73.36 104	34.69 223	75.63 133	80.67 168	39.43 207	78.17 101	71.69 116	75.71 150	61.23 200

DCV-MVSNet		64.34 148	72.84 124	54.42 170	63.79 137	62.09 126	62.50 197	42.72 132	74.32 93	41.34 206	66.96 184	88.57 99	39.18 208	75.20 119	70.35 127	77.01 133	72.37 114

ETV-MVS		64.30 150	64.76 186	63.77 96	68.59 88	62.49 122	77.02 92	45.31 108	49.27 240	50.88 151	56.23 243	59.91 243	57.12 86	80.19 88	74.23 97	83.68 75	71.03 127

viewdifsd2359ckpt11		64.18 151	72.66 128	54.28 173	59.33 177	55.48 188	68.20 160	34.30 224	69.68 137	42.09 197	82.03 75	90.43 71	48.52 151	73.95 127	65.57 167	73.27 172	71.49 123

viewmsd2359difaftdt		64.18 151	72.66 128	54.29 172	59.33 177	55.49 187	68.20 160	34.31 223	69.68 137	42.10 196	82.03 75	90.45 70	48.51 152	73.94 128	65.57 167	73.27 172	71.48 124

ECVR-MVS		63.93 153	71.52 147	55.08 165	66.19 105	61.34 131	63.84 190	51.79 69	70.75 122	34.77 221	74.70 142	81.10 163	38.92 209	79.39 92	73.43 102	75.00 160	59.92 212

Anonymous20231211		63.69 154	72.86 123	53.00 180	63.72 140	60.25 147	60.33 204	40.96 158	72.49 107	38.91 209	81.77 83	88.17 103	37.60 217	73.30 137	68.01 148	76.47 142	66.06 178

diffmvs_AUTHOR		63.60 155	71.07 153	54.90 168	56.75 194	55.35 190	67.91 165	37.08 205	66.87 156	50.84 152	81.64 84	88.73 98	45.49 175	70.02 188	64.15 183	71.31 197	70.70 131

TransMVSNet (Re)		63.49 156	73.86 109	51.39 190	64.26 130	56.07 179	61.17 200	42.23 139	78.81 64	34.80 220	85.94 29	90.63 65	34.35 237	72.73 148	67.98 149	71.50 194	64.84 183

DI_MVS_pp		63.43 157	67.54 174	58.63 138	62.34 152	58.06 159	65.75 182	42.15 140	63.05 172	53.28 137	75.88 130	75.92 200	50.18 140	68.04 198	64.20 180	78.07 127	67.65 168

EIA-MVS		63.24 158	64.16 190	62.16 110	69.30 86	63.20 119	72.40 129	40.82 161	48.31 247	51.50 143	59.63 229	62.23 235	57.33 85	78.00 102	71.94 112	81.59 99	65.82 179

Fast-Effi-MVS+-dtu		63.22 159	65.55 180	60.49 127	61.24 158	64.70 106	74.15 113	53.24 60	51.46 225	49.67 163	58.03 238	78.42 184	48.05 158	72.03 157	71.14 119	76.60 140	63.09 191

IterMVS-SCA-FT		62.67 160	68.00 171	56.45 158	56.92 193	64.92 102	57.51 222	38.12 193	59.44 195	53.62 133	74.74 141	71.60 211	64.84 41	70.24 183	65.27 172	67.70 219	69.83 139

diffmvs		62.64 161	69.66 163	54.46 169	56.19 199	55.06 193	67.36 168	36.74 208	64.18 166	50.58 154	79.54 105	87.55 113	45.13 179	68.04 198	63.20 192	70.78 203	70.02 137
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		62.58 162	67.46 175	56.89 154	59.52 172	55.90 181	64.94 184	38.83 185	57.08 211	56.55 122	76.53 124	84.49 150	47.45 160	66.95 202	62.01 203	74.04 166	69.27 149

MDA-MVSNet-bldmvs		62.46 163	72.13 137	51.19 192	34.32 267	56.10 178	68.65 158	38.85 184	69.05 143	49.50 164	78.17 114	85.43 143	51.32 128	86.67 38	67.40 158	64.46 227	62.08 194

FE-MVSNET2		62.31 164	70.75 159	52.46 181	57.40 192	55.60 184	60.43 203	40.97 157	73.41 102	42.12 195	74.36 144	91.26 48	38.76 211	71.29 168	66.83 161	75.11 159	62.50 193

dtuplus		62.30 165	68.17 170	55.45 163	59.26 179	54.38 198	66.94 170	38.05 196	62.56 173	50.39 157	76.24 126	86.29 133	46.42 170	68.97 195	61.35 206	71.64 190	67.44 169

pm-mvs1		61.97 166	72.01 141	50.25 201	60.64 165	55.23 191	58.67 214	42.44 136	74.40 90	33.63 235	81.03 88	89.86 81	34.87 232	72.93 145	67.95 150	71.28 198	62.65 192

FMVSNet1		61.92 167	71.36 148	50.90 195	57.67 191	59.29 155	59.48 211	44.14 122	70.24 126	34.72 222	75.45 135	84.94 146	36.75 220	72.33 151	68.45 139	72.66 178	68.83 156

viewmambaseed2359dif		61.91 168	67.70 173	55.15 164	58.68 185	54.97 194	66.48 175	38.16 192	61.22 183	49.79 162	75.90 129	85.95 140	46.19 171	67.70 200	60.19 211	71.60 191	67.93 167

hybridnocas07		61.87 169	69.09 166	53.44 175	55.06 217	53.58 204	66.51 172	34.96 214	61.85 178	51.08 149	78.89 110	86.78 128	42.89 187	70.11 185	63.19 193	70.14 209	69.23 150

PVSNet_BlendedMVS		61.75 170	65.07 184	57.87 147	56.27 197	60.99 138	65.81 180	43.75 125	51.27 229	54.08 131	62.12 216	78.84 180	50.67 134	71.49 164	63.91 187	76.64 138	66.86 172

PVSNet_Blended		61.75 170	65.07 184	57.87 147	56.27 197	60.99 138	65.81 180	43.75 125	51.27 229	54.08 131	62.12 216	78.84 180	50.67 134	71.49 164	63.91 187	76.64 138	66.86 172

tttt0517		61.44 172	63.85 192	58.62 139	55.20 212	55.61 183	68.80 157	38.02 197	55.70 216	50.01 160	66.93 186	48.90 254	56.69 88	73.84 129	71.10 121	82.99 83	74.89 96

tfpnnormal		61.41 173	71.33 149	49.83 204	61.73 154	54.90 196	58.52 215	41.24 151	75.20 84	32.00 243	82.13 72	87.87 109	35.63 228	72.75 147	66.30 164	69.87 211	60.14 208

IB-MVS	57.02 17	61.37 174	65.39 181	56.69 155	56.65 195	60.85 140	70.70 143	37.90 199	49.37 239	45.37 186	48.75 255	79.14 177	53.55 111	76.26 113	70.85 123	75.97 147	72.50 113
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
hybrid		61.34 175	68.38 169	53.12 178	54.36 222	53.13 211	66.37 176	34.35 222	61.60 181	50.79 153	77.15 122	86.26 134	43.00 186	69.33 192	62.68 199	69.85 212	68.51 160

CANet_DTU		61.22 176	67.07 177	54.40 171	59.89 168	63.62 117	70.98 140	36.77 207	50.49 232	47.15 172	62.45 213	80.81 166	37.90 216	71.87 159	70.09 129	73.69 168	70.19 135

pmmvs4		61.12 177	64.61 187	57.04 151	60.88 161	52.15 217	70.59 144	44.82 117	61.35 182	46.91 175	72.08 159	73.27 209	46.79 168	65.06 206	67.76 152	72.28 181	60.58 204

thisisatest0530		61.02 178	63.44 199	58.19 146	54.75 219	55.09 192	68.03 164	38.02 197	55.45 217	49.06 166	66.58 190	48.69 255	56.69 88	73.07 139	71.10 121	82.60 88	74.14 99

Vis-MVSNet (Re-imp)		60.99 179	67.78 172	53.06 179	64.66 124	53.49 205	67.40 166	49.52 77	68.55 146	28.00 253	79.53 107	71.41 213	33.08 241	75.30 118	71.28 118	75.69 152	54.91 225

PatchMatch-RL		60.96 180	63.00 205	58.57 140	59.16 180	52.18 216	67.38 167	41.99 143	57.85 205	48.16 167	53.55 251	69.77 218	59.47 77	73.73 130	72.49 110	75.27 157	61.44 196

GA-MVS		60.73 181	64.24 189	56.64 156	59.38 175	57.45 169	65.07 183	36.65 209	57.39 209	58.17 114	73.43 153	69.10 222	47.38 162	64.47 212	63.63 191	73.19 174	64.22 187

CVMVSNet		60.45 182	63.72 195	56.63 157	54.82 218	53.75 199	68.41 159	41.95 144	55.07 218	48.03 168	58.08 237	68.67 223	55.09 98	69.14 194	68.34 143	71.51 193	72.97 112

ET-MVSNet_ETH3D		60.33 183	62.10 210	58.27 143	58.61 186	58.05 160	68.06 162	41.20 152	51.40 226	51.10 148	64.06 205	49.42 253	50.61 136	74.72 121	70.29 128	80.05 110	66.74 174

FC-MVSNet-test		60.28 184	70.83 158	47.96 217	54.69 220	47.12 236	68.06 162	41.68 149	71.42 114	23.73 262	84.70 44	77.41 194	28.92 249	82.33 74	73.08 105	70.68 204	59.77 213

test2506		59.86 185	64.01 191	55.02 166	66.19 105	61.34 131	63.84 190	51.79 69	70.75 122	34.39 228	62.65 212	39.92 275	38.92 209	79.39 92	73.43 102	75.00 160	60.56 205

EU-MVSNet		59.77 186	66.07 178	52.42 182	47.81 239	51.86 219	62.98 194	32.28 238	62.08 176	47.10 173	59.94 227	83.42 157	53.08 114	70.06 187	63.19 193	71.26 200	71.96 119

IterMVS		59.24 187	64.45 188	53.16 177	50.98 230	61.29 133	66.51 172	32.85 233	58.17 201	46.31 181	72.58 158	70.23 216	54.26 105	64.81 209	60.24 210	68.04 218	63.81 189
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		59.15 188	62.28 207	55.49 162	52.42 226	62.59 121	71.76 133	39.74 177	50.25 234	41.92 198	62.88 210	69.16 221	55.85 91	62.77 219	67.18 159	71.27 199	61.11 201

thres600view7		58.87 189	65.91 179	50.66 197	61.27 157	56.32 176	59.88 209	40.63 165	64.88 163	32.10 242	64.82 201	69.83 217	36.72 221	72.99 143	72.55 109	73.34 170	59.97 211

FE-MVSNET		58.15 190	67.14 176	47.65 221	49.53 235	50.47 221	57.09 230	37.15 204	67.85 148	35.64 219	67.57 177	87.16 119	35.36 229	71.23 170	65.57 167	71.17 202	60.12 209

CMPMVS	45.32 18	58.10 191	65.24 183	49.76 205	47.88 238	46.86 239	48.16 258	32.82 234	58.06 202	61.35 98	59.64 228	80.00 172	47.27 163	70.15 184	64.10 185	61.08 232	77.85 80
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDTV_nov1_ep13_2view		58.09 192	63.54 198	51.74 186	50.13 232	46.56 240	66.95 169	33.41 230	63.52 170	58.77 109	74.84 139	84.10 153	43.12 185	65.95 205	54.69 236	58.04 239	55.13 224

dtuonlycased		58.01 193	69.36 164	44.76 232	44.25 257	58.11 158	69.81 152	22.59 259	67.34 152	16.28 269	68.81 168	80.61 170	53.94 107	76.65 110	66.59 162	61.71 231	67.42 170

CDS-MVSNet		57.90 194	63.57 197	51.28 191	62.30 153	53.17 210	64.70 185	51.61 72	57.41 208	32.75 237	63.73 206	70.53 215	27.12 252	72.49 150	73.02 106	69.22 215	54.68 226
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gbinet_0.2-2-1-0.02		57.89 195	63.71 196	51.09 194	55.89 200	55.60 184	59.23 212	36.08 210	59.64 194	42.40 193	66.53 191	76.89 196	40.76 196	64.76 210	57.84 218	72.19 185	64.74 184

FMVSNet2		57.80 196	65.39 181	48.94 212	55.88 201	57.61 165	57.26 223	42.37 138	58.21 200	33.19 236	68.36 172	75.55 202	34.58 234	66.91 203	64.55 178	70.38 205	66.56 175

blended_shiyan6		57.28 197	63.20 203	50.37 199	55.61 206	53.68 201	57.83 220	34.81 215	61.78 180	41.66 202	66.96 184	78.89 179	39.92 202	62.76 220	56.95 223	72.40 180	61.36 197

blended_shiyan8		57.27 198	63.19 204	50.37 199	55.60 207	53.69 200	57.78 221	34.81 215	61.83 179	41.63 203	67.00 183	78.75 183	39.97 201	62.78 218	56.97 222	72.41 179	61.29 199

thres400		57.25 199	63.73 194	49.70 206	60.19 167	54.95 195	58.16 217	39.60 180	62.42 174	31.98 245	62.33 214	69.20 220	35.96 225	70.07 186	68.03 147	72.28 181	59.12 215

WB-MVS		57.14 200	71.03 156	40.93 243	47.97 237	53.10 212	52.35 245	39.66 178	79.59 59	23.31 263	89.49 14	89.23 90	32.94 242	74.68 122	61.41 205	49.32 255	49.74 239

usedtu_dtu_shiyan1		56.93 201	63.39 200	49.39 208	55.48 208	53.03 213	56.77 231	38.34 191	60.26 187	37.42 213	64.85 200	80.06 171	36.94 219	63.97 214	62.55 201	71.36 196	58.99 216

gm-plane-assit		56.76 202	57.64 224	55.73 161	66.01 110	55.45 189	74.96 103	30.54 244	73.71 99	56.04 123	81.81 79	30.91 278	43.83 181	58.77 237	54.71 235	63.02 229	48.13 246

MIMVSNet1		56.72 203	68.69 168	42.76 239	46.70 246	42.81 247	69.13 154	30.52 245	81.01 50	32.00 243	74.82 140	91.10 53	26.83 254	73.98 126	64.72 176	51.40 251	52.38 234

EPNet_dtu		56.63 204	60.77 216	51.80 185	55.47 209	44.63 241	69.83 151	38.74 188	50.27 233	47.64 169	58.01 239	72.27 210	33.71 239	68.60 197	67.72 153	65.39 223	63.86 188
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
wanda-best-256-512		56.57 205	62.27 208	49.92 202	55.08 213	53.36 206	57.15 227	34.52 217	60.20 188	41.40 204	65.86 197	78.11 189	39.54 205	61.94 224	55.90 228	71.82 186	60.53 206

FE-blended-shiyan7		56.57 205	62.27 208	49.92 202	55.08 213	53.36 206	57.15 227	34.52 217	60.20 188	41.40 204	65.86 197	78.11 189	39.54 205	61.94 224	55.90 228	71.82 186	60.53 206

GBi-Net		56.54 207	63.26 201	48.70 214	55.88 201	57.61 165	57.26 223	41.75 146	49.06 241	32.37 239	61.81 218	67.02 226	34.58 234	72.33 151	68.45 139	70.38 205	66.56 175

test1		56.54 207	63.26 201	48.70 214	55.88 201	57.61 165	57.26 223	41.75 146	49.06 241	32.37 239	61.81 218	67.02 226	34.58 234	72.33 151	68.45 139	70.38 205	66.56 175

gg-mvs-nofinetune		56.45 209	61.04 214	51.10 193	63.42 145	49.40 229	53.71 240	52.52 65	74.77 86	46.93 174	77.31 121	53.88 247	26.42 256	62.51 222	57.81 219	63.60 228	51.57 237

thres200		56.35 210	62.36 206	49.34 209	58.87 183	56.32 176	55.91 232	40.63 165	58.51 198	31.34 246	58.81 235	67.31 225	35.96 225	72.99 143	65.51 170	73.34 170	57.07 219

MS-PatchMatch		56.31 211	60.22 219	51.73 187	60.53 166	55.53 186	63.41 192	37.18 203	51.34 228	37.44 212	60.53 225	62.19 236	45.52 174	64.25 213	63.17 195	66.33 220	64.56 185

tfpn200view9		56.07 212	61.85 211	49.34 209	58.57 187	56.48 175	58.01 219	40.72 163	53.23 219	31.01 247	56.41 241	66.40 231	34.18 238	73.02 141	68.06 146	73.53 169	59.35 214

usedtu_dtu_shiyan2		55.91 213	63.79 193	46.72 227	59.06 181	49.07 230	60.88 202	43.83 124	79.17 63	29.73 250	66.13 194	86.96 124	27.91 250	62.70 221	57.21 220	58.91 235	45.28 252

FMVSNet3		54.77 214	60.73 217	47.81 218	54.29 223	56.88 172	55.89 233	41.75 146	49.06 241	32.37 239	61.81 218	67.02 226	33.67 240	62.88 217	61.96 204	68.88 216	65.53 180

thres100view900		53.88 215	59.19 220	47.68 220	58.57 187	52.74 215	54.45 237	38.07 195	53.23 219	31.01 247	56.41 241	66.40 231	32.80 243	65.03 208	64.43 179	71.18 201	56.10 222

CR-MVSNet		53.82 216	55.40 228	51.98 183	51.57 229	50.23 223	45.00 261	44.97 113	46.90 249	52.60 140	67.91 174	46.99 268	48.37 153	59.15 235	59.53 214	69.38 214	57.07 219

baseline2		53.55 217	55.19 229	51.62 188	55.27 211	51.95 218	60.89 201	34.23 225	46.69 251	42.47 192	53.56 250	50.01 250	45.33 178	64.63 211	61.22 208	71.56 192	58.28 218

test20.03		53.49 218	60.95 215	44.78 231	64.73 123	47.25 235	61.58 199	43.30 128	65.86 159	22.85 264	66.87 189	79.85 173	22.99 258	62.38 223	56.95 223	53.25 248	47.46 248

baseline		53.46 219	61.55 212	44.01 234	45.83 251	48.77 231	57.26 223	28.75 251	49.99 235	38.85 210	68.78 169	75.65 201	38.30 213	60.80 228	59.78 213	55.10 246	67.07 171

MVSTER		53.08 220	56.39 226	49.21 211	47.19 242	51.08 220	60.14 207	31.74 241	40.63 261	38.97 208	55.78 244	46.74 269	42.47 190	67.29 201	62.99 197	74.73 163	70.23 134

CHOSEN 1792x2688		52.99 221	56.91 225	48.42 216	47.32 240	50.10 225	64.18 187	33.85 227	45.46 254	36.95 215	55.20 247	66.49 230	51.20 130	59.28 233	59.81 212	57.01 241	61.99 195

baseline1		52.90 222	58.38 221	46.51 228	58.87 183	50.01 226	54.17 238	40.45 170	56.81 213	29.25 251	62.72 211	58.99 244	30.25 247	65.05 207	60.57 209	66.07 221	54.54 227

CostFormer		52.59 223	55.14 230	49.61 207	52.72 224	50.40 222	66.28 177	33.78 228	52.85 221	43.43 190	66.30 192	51.37 249	41.78 193	54.92 247	51.18 243	59.68 234	58.98 217

SCA		52.47 224	53.97 236	50.71 196	46.95 245	57.79 163	60.18 206	46.89 96	51.92 224	46.71 180	60.73 223	49.97 251	47.69 159	56.39 244	52.98 240	55.82 243	48.03 247

testgi		51.94 225	61.37 213	40.94 242	58.38 189	47.03 237	65.88 179	30.49 246	70.87 121	22.64 265	57.53 240	87.59 112	18.30 265	63.01 216	54.32 237	49.93 254	49.27 241

FE-MVSNET3		51.86 226	54.48 233	48.80 213	55.08 213	53.36 206	57.15 227	34.52 217	60.20 188	34.24 229	41.26 265	47.37 261	40.03 198	61.94 224	55.90 228	71.82 186	61.36 197

usedtu_blend_shiyan5		51.33 227	54.39 234	47.77 219	55.08 213	53.36 206	50.91 251	34.52 217	60.20 188	34.24 229	41.26 265	47.37 261	40.03 198	61.94 224	55.90 228	71.82 186	60.71 202

dmvs_re		51.01 228	54.88 232	46.49 229	58.06 190	44.35 244	60.08 208	37.67 200	42.11 258	28.68 252	45.12 261	66.70 229	31.90 246	66.62 204	59.18 216	62.59 230	60.11 210

tpm cat1		50.98 229	51.28 242	50.62 198	55.74 204	49.92 227	63.13 193	38.12 193	52.38 223	47.61 170	60.11 226	44.51 272	44.86 180	51.31 256	47.49 253	54.25 247	53.24 231

RPMNet		50.92 230	50.32 245	51.62 188	50.25 231	50.23 223	59.16 213	46.70 97	46.90 249	42.39 194	48.97 254	37.23 276	41.78 193	57.30 242	56.18 226	69.44 213	55.43 223

pmmvs5		50.64 231	58.01 222	42.05 240	47.01 244	43.67 245	49.27 256	29.43 250	50.77 231	33.83 234	68.69 170	76.16 199	27.82 251	57.53 241	57.07 221	64.95 225	52.18 235

PatchT		50.55 232	53.55 238	47.05 225	37.59 265	42.26 248	50.55 253	37.56 201	46.37 252	52.60 140	66.91 187	43.54 274	48.37 153	59.15 235	59.53 214	55.62 244	57.07 219

Anonymous20231206		50.28 233	57.94 223	41.35 241	55.45 210	43.65 246	58.06 218	34.12 226	62.02 177	24.25 261	59.33 230	79.80 174	24.49 257	59.55 230	54.28 238	51.74 250	46.94 250

dps		49.71 234	51.97 240	47.07 224	52.37 227	47.00 238	53.02 243	40.52 169	44.91 255	41.23 207	64.55 202	44.27 273	40.12 197	57.71 240	51.97 242	55.14 245	53.41 230

MDTV_nov1_ep13		49.60 235	51.57 241	47.31 222	46.28 248	44.61 242	59.82 210	30.96 242	48.80 246	50.20 158	59.26 232	52.38 248	38.56 212	56.20 245	49.70 247	58.04 239	50.01 238

PatchmatchNet		48.67 236	50.10 246	46.99 226	48.29 236	41.00 249	55.54 234	38.94 183	51.38 227	45.15 187	63.22 208	48.45 257	42.83 188	53.80 252	48.50 252	51.19 253	44.37 253
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
blend_shiyan4		47.96 237	50.55 244	44.94 230	43.47 258	52.81 214	47.71 260	32.72 235	36.60 267	34.24 229	41.26 265	47.37 261	40.03 198	59.51 231	55.57 232	71.48 195	60.71 202

new-patchmatchnet		47.33 238	60.49 218	31.99 260	55.69 205	33.86 262	36.84 272	33.31 231	72.36 108	14.33 271	80.09 100	92.14 36	13.27 268	63.54 215	40.09 261	38.51 265	41.32 261

dtuonly		47.04 239	55.08 231	37.67 251	36.58 266	38.07 254	54.74 236	20.55 262	48.83 245	27.31 254	62.23 215	67.56 224	39.92 202	60.00 229	55.14 234	46.90 257	53.71 229

0.4-1-1-0.1		46.90 240	49.04 252	44.40 233	47.28 241	49.55 228	52.48 244	30.44 247	40.85 260	34.58 225	47.16 257	48.13 258	35.64 227	52.90 253	50.70 246	65.97 222	53.98 228

tpm		46.67 241	49.20 251	43.72 235	49.60 233	36.60 259	53.93 239	26.84 253	52.70 222	58.05 116	69.04 167	47.96 259	30.06 248	48.33 262	42.76 256	43.88 259	47.01 249

pmmvs3		46.64 242	54.13 235	37.90 250	31.23 271	40.68 250	49.83 255	15.34 266	46.31 253	36.34 217	53.15 252	74.40 207	36.36 222	58.43 238	56.64 225	58.32 238	49.29 240

TAMVS		46.64 242	53.62 237	38.49 248	49.56 234	36.87 256	53.16 242	25.76 255	56.33 215	22.55 266	60.72 224	61.80 238	27.12 252	59.50 232	58.33 217	52.79 249	41.82 260

test-LLR		46.01 244	45.06 263	47.11 223	59.39 173	36.72 257	51.28 248	40.95 159	36.41 268	34.45 226	46.14 258	47.02 266	38.00 214	51.78 254	48.53 250	58.60 236	48.84 243

MIMVSNet		45.83 245	53.46 239	36.94 252	45.38 255	39.50 252	52.20 246	30.68 243	57.09 210	24.53 260	55.22 246	71.54 212	21.74 261	55.81 246	51.08 244	47.11 256	43.96 254

0.3-1-1-0.015		45.78 246	47.55 255	43.71 236	46.29 247	48.64 233	51.52 247	29.70 248	39.03 265	34.24 229	44.15 263	47.37 261	35.28 230	51.31 256	49.52 248	65.23 224	52.80 232

pmnet_mix02		45.67 247	55.99 227	33.63 259	45.77 252	31.22 266	42.04 266	27.60 252	64.14 167	24.89 257	75.50 134	82.30 159	21.88 260	54.53 250	41.22 258	39.62 263	43.05 256

0.4-1-1-0.2		45.53 248	47.38 256	43.38 238	46.00 250	48.29 234	50.94 250	29.49 249	38.16 266	34.06 233	45.06 262	47.50 260	34.99 231	51.04 258	49.00 249	64.81 226	52.58 233

test0.0.03 1		45.40 249	49.55 249	40.57 245	59.39 173	44.36 243	53.37 241	40.95 159	47.14 248	19.23 267	45.49 260	60.24 241	19.24 263	54.82 248	51.98 241	51.21 252	42.82 257

PMMVS		45.37 250	49.29 250	40.79 244	27.75 272	35.07 261	50.88 252	19.88 263	39.27 263	35.78 218	50.11 253	61.29 239	42.04 191	54.13 251	55.95 227	68.43 217	49.19 242

MVS-HIRNet		44.56 251	45.52 261	43.44 237	40.98 261	31.03 267	39.52 270	36.96 206	42.80 257	44.37 188	53.80 249	60.04 242	41.85 192	47.97 264	41.08 259	56.99 242	41.95 259

test-mter		44.18 252	47.60 254	40.18 246	33.20 268	39.03 253	55.28 235	13.91 268	39.07 264	36.63 216	48.09 256	49.52 252	41.12 195	54.55 249	50.91 245	60.97 233	52.03 236

EMVS		43.85 253	49.91 247	36.77 254	45.46 254	32.70 263	44.09 263	25.33 256	57.88 204	26.62 255	58.99 234	61.14 240	42.77 189	70.26 182	38.52 265	36.38 267	29.87 267

E-PMN		43.83 254	49.81 248	36.84 253	46.09 249	31.86 265	42.77 265	25.85 254	57.76 206	25.53 256	55.50 245	62.47 234	43.77 182	70.78 176	39.51 262	37.04 266	30.79 266

tpmrst		43.31 255	46.14 259	40.02 247	47.05 243	36.48 260	48.01 259	32.17 240	49.50 238	37.26 214	63.66 207	47.04 265	31.98 245	42.00 268	40.55 260	43.64 260	43.75 255

TESTMET0.1,1		41.79 256	45.06 263	37.97 249	31.32 270	36.72 257	51.28 248	14.17 267	36.41 268	34.45 226	46.14 258	47.02 266	38.00 214	51.78 254	48.53 250	58.60 236	48.84 243

ADS-MVSNet		40.61 257	46.31 257	33.96 257	40.70 262	30.42 268	40.42 268	33.44 229	58.01 203	30.87 249	63.05 209	54.48 246	22.67 259	44.35 267	39.23 264	35.64 268	34.64 264

CHOSEN 280x420		40.24 258	44.14 266	35.69 255	32.36 269	23.58 272	50.30 254	21.21 261	40.94 259	18.84 268	32.75 270	48.65 256	48.13 157	59.16 234	55.31 233	43.28 261	48.62 245

EPMVS		40.11 259	44.96 265	34.44 256	41.55 260	32.65 264	41.74 267	32.39 237	49.89 237	24.83 258	64.44 203	46.38 270	26.57 255	44.75 266	39.47 263	39.59 264	37.16 263

FMVSNet5		39.83 260	45.08 262	33.71 258	39.24 263	39.56 251	48.77 257	23.55 258	39.45 262	24.55 259	33.73 269	44.57 271	20.97 262	58.27 239	54.23 239	45.16 258	45.77 251

N_pmnet		39.50 261	51.01 243	26.09 262	44.48 256	25.59 270	40.20 269	21.49 260	64.20 165	7.98 276	73.86 149	76.67 198	13.66 266	50.17 259	36.69 268	28.71 271	29.86 268

MVE	28.01 19	35.86 262	43.56 267	26.88 261	22.33 274	19.75 274	30.85 275	23.88 257	49.90 236	10.48 273	43.64 264	61.87 237	48.99 149	47.26 265	42.15 257	24.76 272	40.37 262
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
new_pmnet		35.76 263	45.64 260	24.22 263	38.59 264	25.83 269	31.87 274	19.24 264	49.06 241	9.01 274	54.34 248	64.73 233	12.46 269	49.21 261	44.91 254	34.17 269	31.41 265

PMMVS2		34.11 264	48.55 253	17.26 264	25.45 273	20.72 273	35.08 273	16.26 265	58.71 197	4.16 278	59.22 233	78.40 185	3.65 273	57.24 243	38.31 266	18.94 274	27.28 270

GG-mvs-BLEND		31.54 265	46.27 258	14.37 265	0.07 283	48.65 232	42.97 264	0.08 277	44.04 256	1.21 281	39.77 268	57.94 245	0.15 279	48.19 263	42.82 255	41.70 262	42.46 258

test_method		13.28 266	15.83 268	10.30 266	1.05 279	2.18 279	15.40 276	2.23 271	22.43 270	13.84 272	22.00 272	33.14 277	9.78 270	17.80 270	9.93 270	19.50 273	3.31 276

VLMVS_CLIP		8.71 267	10.25 270	6.90 268	18.57 275	7.95 276	1.73 280	7.14 269	8.77 274	2.23 279	11.00 274	9.82 281	9.03 271	10.51 272	8.62 272	2.71 277	15.09 272

MVS_clip		7.23 268	11.04 269	2.78 269	4.95 277	4.38 277	1.40 281	1.30 272	10.87 273	0.37 283	15.29 273	13.65 280	7.24 272	9.55 273	8.87 271	1.43 278	14.65 273

MVS_baseline		1.95 269	3.24 271	0.46 271	0.58 280	0.23 282	0.08 285	0.00 278	2.89 275	0.00 285	3.70 276	4.08 283	2.06 274	1.11 275	1.26 273	0.01 282	9.40 274

VLMVS		1.29 270	1.82 272	0.66 270	1.29 278	0.84 280	0.36 282	0.35 274	2.02 276	0.44 282	1.69 277	2.68 284	1.15 276	1.12 274	0.90 274	0.39 279	3.51 275

test123		0.53 271	0.60 274	0.46 271	0.22 281	0.25 281	0.33 284	0.13 276	0.66 277	1.37 280	1.10 278	0.00 286	0.43 277	0.68 276	0.61 275	0.26 280	0.88 277

testmvs		0.47 272	0.69 273	0.21 273	0.17 282	0.17 283	0.35 283	0.16 275	0.66 277	0.18 284	1.05 279	0.99 285	0.27 278	0.62 277	0.54 276	0.15 281	0.77 278

uanet_test		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 286	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet-low-res		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 286	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 286	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

ACM-MVS					75.22 54	70.53 75	83.32 56		66.82 157	69.00 63	61.79 221	78.25 186	48.80 150			82.49 91	82.38 54

PatchmatchNet2					42.50 259	24.33 271	39.02 271
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												76.75 197	13.63 267	49.76 260	36.71 267	28.75 270	29.80 269
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										8.05 275	73.92 147
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							87.82 39	53.22 61		58.49 113						84.46 66

TPM-MVS					72.72 66	70.92 74	80.38 75			66.22 79	58.35 236	78.23 187	48.26 155			83.40 80	81.74 59
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										70.04 55

9.14												83.64 155

SR-MVS					81.31 9			62.63 9				91.11 52

Anonymous202405211			72.22 136		66.19 105	61.09 137	62.23 198	45.87 106	71.25 116		79.33 108	86.16 138	37.36 218	73.54 135	69.84 130	75.45 155	64.32 186

our_test_3					52.72 224	53.66 202	69.11 155

ambc			79.96 63		74.57 58	75.48 51	73.75 118		80.32 55	72.34 38	78.46 112	92.41 30	59.05 78	80.24 87	73.95 99	75.41 156	78.85 74

MTAPA										80.26 8		90.53 69

MTMP										82.07 4		91.00 55

Patchmatch-RL test							2.05 279

tmp_tt				7.47 267	8.89 276	3.32 278	4.35 278	1.14 273	15.58 272	15.76 270	8.50 275	5.90 282	2.00 275	20.02 269	21.51 269	12.70 275

XVS					80.47 20	81.29 12	93.33 3			77.45 19		90.19 77				91.52 11

X-MVStestdata					80.47 20	81.29 12	93.33 3			77.45 19		90.19 77				91.52 11

mPP-MVS					82.97 2							92.12 37

NP-MVS									71.39 115

Patchmtry						37.73 255	45.00 261	44.97 113		52.60 140

DeepMVS_CX						8.52 275	9.75 277	3.19 270	16.70 271	5.02 277	23.06 271	19.33 279	18.69 264	13.75 271		11.34 276	25.07 271

High-resolution multi-view benchmark