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 52	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 50	82.76 4	90.39 19	54.21 54	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 30	82.32 3	80.89 72	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 19	79.45 11	83.37 46	92.04 35	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 44	80.21 9	81.95 62	90.76 53	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 38	78.32 15	80.59 73	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 58	80.21 9	80.31 75	91.44 40	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 54	80.44 6	84.83 36	94.19 14	70.52 17	90.70 11	87.19 22	91.71 8	87.37 29

ACMM	71.24 7	82.85 9	86.59 12	78.50 9	80.10 26	78.59 32	91.77 11	60.76 22	84.43 17	76.49 24	81.58 67	93.50 17	70.45 18	91.38 7	89.42 8	91.42 16	87.22 31
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 21	71.81 39	82.39 57	89.59 69	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 31	71.30 44	86.91 23	90.54 59	67.12 29	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 35	75.53 28	73.88 117	92.28 31	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 46	75.46 29	82.97 52	95.08 12	68.90 24	90.49 14	87.43 21	91.48 14	86.84 33
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 52	77.00 22	81.80 65	90.71 54	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 11	78.61 14	83.21 49	86.96 98	65.95 34	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 34	82.50 36	67.55 67	87.05 21	91.40 42	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	63.57 123	70.27 73	86.48 41	62.99 7	89.00 5	80.32 7	86.25 26	91.04 47	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 31	88.98 31	56.44 39	89.29 3	72.39 37	93.25 1	93.86 16	63.42 49	85.46 45	81.36 56	86.96 46	94.00 1

PMVS	70.37 8	81.82 19	87.08 6	75.68 24	77.06 42	77.23 40	87.77 38	56.25 42	83.33 29	67.18 72	89.48 14	87.94 82	77.70 1	93.02 2	92.57 2	88.13 36	86.00 38
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 26	77.74 18	83.72 44	87.34 91	65.36 35	88.61 28	87.56 20	89.73 26	89.58 6

X-MVS		81.61 21	84.73 36	77.97 11	80.31 23	81.29 12	93.53 2	62.50 11	81.41 45	77.45 19	72.04 129	90.19 62	62.50 56	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 35	89.84 22	58.67 30	85.25 12	76.26 25	85.28 33	92.88 26	66.03 33	87.20 37	85.40 27	88.86 31	85.58 42
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 49	80.87 49	67.62 66	88.01 16	92.38 30	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 38	82.29 5	84.41 48	62.95 8	82.99 32	64.03 80	87.71 17	89.17 71	71.98 11	88.19 30	88.10 16	86.18 55	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 33	85.83 10	66.07 76	87.34 20	91.27 43	69.45 19	85.99 43	82.55 44	88.98 30	88.95 13

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 43	73.45 32	86.84 24	89.80 67	69.33 21	85.40 46	82.91 43	87.87 38	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 37	75.91 23	81.22 11	81.48 10	90.49 17	58.81 29	77.54 64	67.49 68	85.90 28	89.82 66	69.43 20	86.08 42	83.80 37	88.01 37	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 49	77.96 13	81.99 7	72.76 61	90.48 18	61.31 14	80.85 50	77.90 17	81.93 63	87.01 95	68.20 27	84.15 56	85.27 29	87.85 39	86.00 38

DVP-MVS		80.31 29	85.60 27	74.15 33	76.23 46	78.39 33	86.62 40	55.79 45	86.47 9	71.32 43	90.96 7	89.02 73	69.28 22	84.62 55	81.64 53	85.66 60	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 40	73.82 59	76.41 43	83.59 52	54.82 52	87.35 6	70.86 48	86.98 22	96.27 4	66.50 30	89.17 24	83.39 39	89.26 28	83.56 48

OMC-MVS		79.95 31	85.28 29	73.74 36	72.95 62	80.10 27	87.87 37	48.13 84	84.62 16	79.42 12	80.27 76	92.49 28	64.14 43	87.25 36	85.11 30	89.92 24	87.10 32

SED-MVS		79.70 32	85.16 31	73.34 38	75.83 49	78.11 36	88.77 33	56.45 38	84.85 14	69.45 59	90.70 9	88.38 77	63.16 51	85.12 51	81.28 57	86.40 52	87.63 26

MSP-MVS		79.65 33	84.28 40	74.25 31	78.92 33	81.86 9	89.07 28	60.49 24	83.85 24	70.05 54	85.12 34	90.92 51	62.99 53	81.15 76	81.64 53	83.99 68	85.42 44
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DeepPCF-MVS	71.57 5	79.49 34	84.05 41	74.17 32	74.14 56	80.88 20	89.33 26	56.24 43	82.41 37	71.58 41	82.27 58	86.47 101	66.47 31	84.80 53	84.16 35	87.26 44	87.34 30

LS3D		79.33 35	84.03 42	73.84 34	75.37 51	78.09 37	83.30 53	52.94 61	84.42 18	76.01 26	84.16 40	87.44 90	65.34 36	86.30 40	82.08 51	90.09 22	85.70 40

3Dnovator+	72.94 4	78.78 36	83.05 46	73.80 35	70.70 74	81.34 11	88.33 34	56.01 44	81.33 47	72.87 36	78.06 91	81.15 128	63.83 46	87.39 35	85.82 25	91.06 18	86.28 37

UA-Net		78.65 37	83.96 43	72.46 42	84.87 1	76.15 44	89.06 29	55.70 46	77.25 65	53.14 115	79.73 80	82.09 126	59.69 72	92.21 5	90.93 3	92.32 3	89.36 7

DeepC-MVS_fast	71.40 6	78.48 38	82.92 47	73.31 39	76.44 45	82.23 6	87.59 39	56.56 37	77.79 62	68.91 63	77.00 95	87.32 92	61.90 58	85.40 46	84.37 32	88.46 33	86.33 36
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 39	83.47 45	72.41 43	76.04 48	75.72 47	83.86 50	51.81 65	84.00 23	70.65 51	81.27 69	92.22 32	64.64 41	83.28 65	80.28 59	87.44 43	87.49 28

WR-MVS		78.32 40	86.09 20	69.25 60	76.22 47	72.33 68	85.71 44	59.02 28	86.66 7	51.41 121	92.91 2	96.76 1	53.09 106	90.21 18	85.30 28	90.05 23	78.46 74

ACMH	66.19 11	78.12 41	84.55 38	70.63 51	69.62 80	72.40 67	80.77 68	46.43 96	89.24 4	77.99 16	87.42 19	95.83 9	62.95 54	86.27 41	78.24 70	86.00 58	82.46 50
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
train_agg		77.83 42	80.47 59	74.77 28	80.92 14	69.60 74	88.87 32	56.32 41	74.03 81	71.03 46	83.67 45	87.68 85	64.75 40	83.70 58	81.85 52	86.71 48	82.73 49

NCCC		77.82 43	80.72 58	74.43 30	79.24 31	75.72 47	88.06 35	56.36 40	79.61 56	73.22 34	67.75 142	87.05 94	63.09 52	85.62 44	84.00 36	86.62 49	85.30 45

CNVR-MVS		77.79 44	81.57 53	73.38 37	78.37 37	75.91 45	87.97 36	55.11 50	79.41 57	70.98 47	74.70 113	86.43 102	61.77 59	85.10 52	83.73 38	86.10 57	85.68 41

WR-MVS_H		77.56 45	85.88 22	67.86 64	80.54 18	74.32 55	83.23 54	61.78 12	83.47 27	47.46 141	91.81 6	95.84 8	50.50 118	90.44 16	84.37 32	83.63 73	80.89 60

RPSCF		77.56 45	84.51 39	69.46 59	65.17 111	74.36 54	79.74 74	47.45 87	84.01 22	72.89 35	77.89 92	90.67 55	65.14 38	88.25 29	89.74 7	86.38 53	86.64 35

PS-CasMVS		77.46 47	85.80 23	67.73 66	81.24 10	72.88 60	80.63 69	61.28 15	84.14 20	50.53 127	92.13 4	96.76 1	50.12 121	91.02 9	84.46 31	82.60 84	79.19 67

DTE-MVSNet		77.28 48	84.87 35	68.42 62	82.94 3	72.70 63	81.60 63	61.78 12	85.03 13	51.40 122	92.11 5	96.00 6	49.42 124	89.73 22	82.52 46	83.39 77	75.98 84

SixPastTwentyTwo		77.24 49	83.65 44	69.78 55	65.14 112	64.85 96	77.44 84	47.74 86	82.76 34	68.52 64	87.65 18	93.31 19	71.68 13	89.49 23	82.41 47	88.14 35	85.05 46

CDPH-MVS		77.22 50	81.05 57	72.75 41	77.29 40	77.46 39	86.36 42	54.02 56	73.00 87	69.75 57	77.78 93	88.90 75	61.31 63	84.09 57	82.54 45	87.79 40	83.57 47

PEN-MVS		77.06 51	85.05 32	67.74 65	82.29 5	72.59 64	80.86 67	61.03 19	84.66 15	50.08 130	92.19 3	96.59 3	49.12 126	89.83 21	82.35 48	83.06 78	77.14 79

CP-MVSNet		77.01 52	85.04 33	67.65 67	81.16 12	72.72 62	80.54 70	61.18 16	82.09 39	50.41 128	90.81 8	95.89 7	50.03 122	90.86 10	84.30 34	82.56 86	78.65 73

CSCG		76.95 53	82.08 51	70.97 47	73.32 61	78.35 34	81.08 66	47.19 88	83.47 27	69.82 56	80.44 74	87.19 93	64.59 42	81.01 79	77.26 77	89.83 25	86.84 33

CNLPA		76.67 54	81.72 52	70.77 50	70.75 72	76.68 42	86.14 43	46.11 98	81.82 41	74.68 30	76.37 97	86.23 104	62.92 55	85.28 49	83.29 40	84.02 67	82.40 51

MSLP-MVS++		76.66 55	82.32 50	70.06 53	70.51 75	80.27 25	79.77 73	55.58 47	77.79 62	63.09 81	67.25 146	89.50 70	71.01 14	88.10 31	85.74 26	80.39 98	87.56 27

TSAR-MVS + COLMAP		75.85 56	81.06 55	69.77 56	71.15 68	76.90 41	82.93 56	52.43 63	79.25 59	70.13 52	82.78 53	87.00 96	60.02 68	80.30 83	79.61 63	81.95 90	81.61 56

HQP-MVS		75.81 57	78.91 65	72.18 44	77.41 39	75.38 50	84.75 45	53.35 58	76.12 69	73.32 33	69.48 134	88.07 80	57.76 80	79.42 89	78.44 67	86.48 50	85.50 43

PLC	64.88 15	75.76 58	80.22 60	70.57 52	70.46 76	77.75 38	82.01 61	48.84 79	80.74 51	70.85 49	71.32 131	84.82 114	63.69 47	84.73 54	82.35 48	87.54 41	79.80 64
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 59	79.24 63	70.86 48	67.63 87	74.09 56	83.17 55	44.75 113	81.82 41	80.83 5	65.61 157	88.04 81	61.58 60	83.21 66	80.12 60	87.17 45	81.82 54
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PHI-MVS		75.17 60	78.37 66	71.43 45	71.13 69	72.46 66	82.28 60	50.55 71	73.39 84	79.05 13	73.65 119	87.50 89	61.98 57	81.10 77	78.48 66	83.60 74	81.99 52

anonymousdsp		74.76 61	82.59 48	65.63 84	45.61 204	61.13 123	89.06 29	32.58 191	74.11 80	59.55 90	84.06 41	94.12 15	75.24 3	88.94 26	86.95 24	91.74 7	88.81 14

AdaColmap		74.73 62	77.57 71	71.40 46	76.90 43	75.76 46	84.54 47	53.08 60	76.20 68	66.64 75	66.06 155	78.16 147	61.32 62	85.37 48	82.20 50	85.95 59	79.27 66

v7n		74.47 63	81.06 55	66.77 73	66.98 93	67.10 77	76.76 88	45.88 100	81.98 40	67.43 69	88.38 15	95.67 10	61.38 61	80.76 81	73.49 98	82.21 88	80.06 62

PCF-MVS	65.25 14	73.99 64	76.74 76	70.79 49	71.61 67	75.33 51	83.76 51	50.40 72	74.88 72	74.50 31	67.60 143	85.36 111	58.30 78	78.61 95	74.25 93	86.15 56	81.13 59
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MCST-MVS		73.84 65	77.44 72	69.63 58	73.75 60	74.73 53	81.38 65	48.58 80	74.77 73	69.16 61	71.97 130	86.20 105	59.50 73	78.51 96	74.06 95	85.42 62	81.85 53

MVS_0304		73.74 66	77.16 74	69.74 57	74.24 55	73.47 57	84.70 46	49.62 74	62.26 143	67.27 70	75.87 101	87.57 87	57.49 83	81.20 75	79.50 64	85.10 63	80.27 61

TSAR-MVS + GP.		73.42 67	76.31 77	70.05 54	77.15 41	71.13 71	81.59 64	54.11 55	69.84 114	58.65 93	66.20 154	78.77 144	65.29 37	83.65 59	83.14 41	83.54 75	81.47 57

Gipuma		73.40 68	79.27 62	66.55 78	63.64 122	59.35 132	70.28 123	45.92 99	83.79 25	71.78 40	84.04 42	93.07 23	68.69 26	87.90 33	76.76 79	78.98 111	69.96 119
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVS_111021_HR		72.37 69	76.12 80	68.00 63	68.55 84	64.30 104	82.93 56	48.98 78	74.25 78	65.39 77	73.59 120	84.11 119	59.48 74	82.61 69	78.38 68	82.66 83	75.59 86

TinyColmap		71.85 70	76.11 81	66.87 72	66.07 102	65.34 91	74.35 100	49.30 77	79.93 55	75.93 27	75.66 103	87.74 84	54.72 98	80.66 82	70.42 120	80.85 96	73.02 102

UniMVSNet_ETH3D		71.84 71	81.36 54	60.74 108	76.46 44	66.01 85	66.49 143	60.24 26	86.58 8	41.87 164	90.04 11	96.02 5	43.72 152	85.14 50	77.30 76	75.64 132	68.40 133

TranMVSNet+NR-MVSNet		71.66 72	79.23 64	62.83 100	72.54 64	65.64 87	74.77 98	55.27 48	75.91 70	45.50 153	89.55 13	94.25 13	45.96 143	82.74 68	77.03 78	82.96 80	69.48 127

MVS_111021_LR		71.60 73	75.21 84	67.38 68	67.42 88	62.44 113	81.73 62	46.24 97	70.89 99	66.80 74	73.19 123	84.98 112	60.09 67	81.94 72	77.77 74	82.00 89	75.29 87

EG-PatchMatch MVS		71.50 74	76.82 75	65.30 85	70.74 73	66.50 81	74.23 102	43.25 121	72.02 91	59.11 91	79.85 79	86.88 99	63.95 45	80.29 84	75.25 89	80.51 97	76.98 80

DPM-MVS		71.35 75	73.50 102	68.84 61	74.93 53	73.35 58	84.07 49	50.56 70	71.91 92	67.06 73	61.21 177	77.02 152	52.64 109	74.15 115	75.14 90	83.79 71	81.74 55

UniMVSNet (Re)		71.29 76	78.14 67	63.30 95	70.29 77	66.57 80	75.98 90	54.74 53	70.20 107	46.20 151	85.08 35	93.21 20	48.19 131	82.50 70	78.33 69	84.40 65	71.08 113

CLD-MVS		71.24 77	78.12 68	63.20 97	74.03 57	71.60 69	82.82 58	32.91 188	74.23 79	69.32 60	79.65 81	91.54 38	47.02 139	81.22 74	79.01 65	73.09 149	69.63 123
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CANet		71.07 78	75.09 86	66.39 79	72.57 63	71.53 70	82.38 59	47.10 89	59.81 149	59.81 89	74.97 108	84.37 118	54.25 101	79.89 87	77.64 75	82.25 87	77.40 77

v1192		71.06 79	74.87 88	66.61 75	66.38 97	65.80 86	78.27 78	45.28 105	70.19 108	70.79 50	83.37 46	91.79 36	58.76 77	70.86 150	69.02 127	80.16 101	73.08 100

DU-MVS		71.03 80	77.92 69	62.98 99	70.81 70	65.48 89	73.93 105	56.76 35	69.95 112	46.77 147	85.70 31	93.49 18	46.91 140	83.47 60	77.82 73	82.72 82	69.54 124

v1240		70.94 81	74.52 92	66.76 74	66.54 96	64.40 100	77.76 81	45.29 104	70.05 110	71.45 42	83.36 48	90.96 49	60.37 65	70.50 153	68.68 128	79.14 109	73.68 96

v1921920		70.82 82	74.46 94	66.58 77	66.33 98	64.35 103	77.72 82	45.07 107	70.39 104	71.18 45	83.15 50	90.62 57	59.97 69	70.90 148	68.43 135	79.19 108	73.39 97

UniMVSNet_NR-MVSNet		70.82 82	77.44 72	63.11 98	71.75 66	66.02 84	73.93 105	55.00 51	70.90 98	46.77 147	86.68 25	91.54 38	46.91 140	81.07 78	76.32 83	84.28 66	69.54 124

PVSNet_Blended_VisFu		70.70 84	73.62 101	67.28 70	63.53 124	72.96 59	77.97 79	52.10 64	63.65 137	62.66 82	71.14 132	73.46 163	63.55 48	79.35 93	75.34 88	83.90 69	79.43 65

v144192		70.68 85	74.40 96	66.34 80	65.94 104	64.38 101	77.63 83	45.18 106	69.97 111	70.11 53	82.70 55	90.77 52	59.84 71	71.43 146	68.46 131	79.31 107	73.08 100

DROMVSNet		70.50 86	73.32 105	67.20 71	72.07 65	66.21 83	70.86 120	50.10 73	57.66 162	60.49 88	74.97 108	79.42 139	63.32 50	79.65 88	75.46 87	86.35 54	79.87 63

FPMVS		70.46 87	74.89 87	65.28 86	69.09 82	61.42 119	77.07 86	46.92 92	76.73 67	53.53 111	67.33 144	75.07 158	67.23 28	83.41 62	81.54 55	77.86 118	78.73 71

v1144		70.45 88	74.50 93	65.73 83	65.74 106	64.88 95	77.33 85	44.16 115	70.59 103	69.63 58	83.15 50	91.42 41	57.79 79	71.29 147	68.53 130	79.72 105	71.63 112

v10		70.25 89	74.59 91	65.19 87	65.32 109	66.46 82	76.60 89	44.84 110	67.38 123	67.21 71	82.75 54	90.56 58	57.70 81	71.69 143	68.63 129	79.44 106	74.67 90

Effi-MVS+-dtu		70.10 90	73.76 100	65.82 82	70.23 78	74.92 52	79.47 75	44.49 114	56.98 167	54.34 105	64.26 161	84.78 115	59.97 69	80.96 80	80.38 58	86.44 51	74.05 94

CS-MVS-test		70.00 91	72.92 108	66.59 76	66.71 95	64.06 106	80.28 71	44.82 111	58.41 154	58.08 96	73.57 121	80.94 130	63.98 44	83.29 64	75.93 85	85.65 61	74.23 91

MAR-MVS		70.00 91	72.28 116	67.34 69	69.89 79	72.57 65	80.09 72	49.49 76	60.28 148	69.03 62	59.29 186	80.79 132	54.68 99	78.39 98	76.00 84	80.87 95	78.67 72
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
Vis-MVSNet		69.95 93	77.69 70	60.91 106	60.67 139	66.71 78	77.94 80	48.58 80	69.10 117	45.78 152	80.21 77	83.58 122	53.41 105	82.92 67	80.11 61	79.08 110	81.21 58
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS		69.56 94	72.49 113	66.14 81	66.85 94	64.10 105	72.55 110	42.91 123	58.90 151	60.78 86	72.93 126	83.21 124	66.32 32	78.77 94	72.84 105	87.45 42	76.72 81

EPP-MVSNet		69.51 95	76.17 78	61.74 104	68.38 86	66.60 79	71.77 112	46.98 90	73.60 83	41.79 165	82.06 61	69.65 174	52.51 110	83.41 62	79.94 62	89.02 29	77.94 75

3Dnovator	65.69 13	69.43 96	75.74 83	62.06 103	60.78 138	70.50 72	75.85 92	39.57 157	74.44 75	57.41 98	75.91 99	77.73 149	55.34 94	76.86 102	75.61 86	83.44 76	79.14 68

Effi-MVS+		69.04 97	73.01 107	64.40 90	67.20 91	64.83 97	74.87 97	43.97 117	63.33 139	60.90 85	73.06 124	85.79 108	55.61 91	73.58 121	76.41 82	83.84 70	74.09 93

v2v482		69.01 98	73.39 104	63.89 92	63.86 116	62.99 110	75.26 95	42.05 132	70.22 106	68.46 65	82.64 56	91.61 37	55.38 92	70.89 149	66.93 151	78.30 114	68.48 132

MSDG		68.98 99	73.31 106	63.92 91	67.08 92	68.27 75	75.41 94	40.77 148	67.61 121	64.89 78	75.75 102	78.96 141	53.70 103	76.72 104	73.95 96	81.71 92	71.93 110

v8		68.77 100	73.50 102	63.26 96	63.74 120	64.47 99	74.22 103	42.07 131	67.30 124	64.89 78	82.08 60	90.23 61	56.50 89	71.85 142	66.57 152	78.14 115	72.02 108

NR-MVSNet		68.66 101	76.15 79	59.93 113	65.49 107	65.48 89	74.42 99	56.76 35	69.95 112	45.38 154	85.70 31	91.13 44	34.68 184	74.52 114	76.75 80	82.83 81	69.49 126

USDC		68.53 102	71.82 122	64.68 88	63.53 124	61.87 118	70.12 125	46.98 90	77.89 61	76.58 23	68.55 139	86.88 99	50.50 118	73.73 118	65.62 154	80.39 98	68.21 135

IS_MVSNet		68.20 103	74.41 95	60.96 105	68.55 84	64.36 102	71.47 115	48.33 82	70.11 109	43.30 160	80.90 71	74.54 160	47.19 138	81.25 73	77.97 72	86.94 47	71.76 111

Baseline_NR-MVSNet		68.15 104	75.12 85	60.02 112	70.81 70	55.67 155	75.88 91	53.40 57	71.25 95	43.96 158	85.88 29	92.68 27	45.76 144	83.47 60	68.34 136	70.34 166	68.58 131

GeoE		68.11 105	72.10 120	63.47 94	67.32 89	62.42 114	78.32 77	43.22 122	64.06 136	55.72 103	73.97 116	84.58 116	55.35 93	76.09 108	70.41 121	80.89 94	73.14 99

casdiffmvs_mvg		68.01 106	74.22 98	60.78 107	63.75 119	62.08 117	70.21 124	42.58 125	72.11 90	58.53 94	84.80 38	88.98 74	49.37 125	73.25 125	67.54 147	80.24 100	70.75 115
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Fast-Effi-MVS+		67.71 107	72.54 112	62.07 102	63.83 117	63.68 107	75.74 93	39.94 154	60.89 147	54.29 106	73.00 125	86.19 106	56.85 86	78.46 97	73.23 101	81.74 91	72.36 106

thisisatest0515		66.95 108	72.29 115	60.72 109	56.37 162	56.05 153	71.08 116	38.81 162	67.59 122	53.26 114	78.21 89	79.79 138	60.11 66	75.69 110	73.02 103	84.69 64	75.66 85

EPNet		66.87 109	68.89 136	64.53 89	73.97 58	61.13 123	78.46 76	61.03 19	56.78 169	53.41 112	66.91 149	70.91 169	43.49 153	76.08 109	76.68 81	76.81 122	73.73 95
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
canonicalmvs		66.37 110	74.37 97	57.04 130	65.89 105	65.06 92	62.58 162	42.55 126	76.82 66	46.87 146	67.33 144	86.38 103	45.49 146	76.77 103	71.85 110	78.87 112	76.35 82

QAPM		66.36 111	72.76 111	58.90 118	59.57 146	65.01 93	64.05 156	41.17 143	73.09 86	56.82 100	69.42 135	77.78 148	55.07 96	73.00 128	72.07 108	76.71 123	78.96 69

casdiffmvs		66.19 112	72.34 114	59.02 117	62.75 128	60.61 129	69.06 130	41.38 140	69.49 115	54.11 107	84.00 43	89.74 68	49.12 126	70.74 152	62.70 169	77.70 120	69.14 129
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
V42		65.79 113	72.11 119	58.42 122	51.89 184	58.69 134	73.80 107	34.50 180	65.40 131	57.10 99	79.54 83	89.09 72	57.51 82	71.98 140	67.83 144	75.70 130	72.26 107

IterMVS-LS		65.76 114	70.85 129	59.81 115	65.33 108	57.78 139	64.63 153	48.02 85	65.65 130	51.05 124	81.31 68	77.47 150	54.94 97	69.46 161	69.36 126	74.90 138	74.95 88
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PM-MVS		65.66 115	71.25 128	59.14 116	58.92 152	54.88 164	73.66 109	38.55 165	66.12 127	49.91 132	69.87 133	86.97 97	60.61 64	76.30 106	74.75 91	73.19 147	69.83 120

UGNet		65.61 116	74.79 89	54.91 142	54.54 178	68.20 76	70.97 119	48.21 83	67.14 126	41.67 166	74.15 115	80.65 134	36.10 179	79.39 90	77.99 71	77.95 117	76.01 83
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		65.54 117	71.79 123	58.24 125	59.68 145	65.55 88	70.99 117	38.69 164	62.29 142	49.27 135	75.03 107	81.42 127	50.93 114	73.71 120	71.35 112	79.90 103	73.20 98
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		65.36 118	70.09 132	59.85 114	63.05 127	53.61 167	74.29 101	46.45 95	68.14 120	51.45 120	78.83 87	85.78 109	49.87 123	70.44 154	70.45 119	74.00 142	63.38 155

FA-MVS(training)		65.22 119	69.19 135	60.58 110	60.91 136	57.60 143	71.57 114	38.82 161	65.84 129	61.18 84	75.95 98	74.52 161	51.18 113	73.32 123	67.41 148	79.80 104	69.70 122

v148		64.92 120	70.58 131	58.32 123	59.89 143	57.09 146	66.04 145	35.27 179	69.11 116	60.66 87	79.57 82	90.93 50	53.91 102	69.81 160	62.22 170	74.14 140	65.31 147

FC-MVSNet-train		64.87 121	74.76 90	53.33 146	65.24 110	58.05 136	69.69 127	41.92 135	70.99 97	32.62 190	85.75 30	88.23 78	32.10 194	77.61 101	74.41 92	78.43 113	68.25 134

pmmvs6		64.78 122	75.82 82	51.89 152	62.41 129	57.13 145	60.24 169	45.59 102	82.90 33	34.69 181	84.83 36	93.18 21	36.22 178	76.43 105	71.13 115	72.21 153	65.12 148

OpenMVS	60.79 16	64.42 123	69.72 133	58.23 126	61.63 133	62.17 115	64.11 155	37.54 173	67.17 125	55.71 104	65.89 156	74.89 159	52.67 108	72.20 138	68.29 138	77.73 119	77.39 78

test1111		64.34 124	71.57 124	55.90 137	67.25 90	60.24 131	66.66 141	51.63 68	73.36 85	34.69 181	75.63 104	80.67 133	39.43 164	78.17 99	71.69 111	75.71 129	61.23 161

DCV-MVSNet		64.34 124	72.84 110	54.42 144	63.79 118	62.09 116	62.50 163	42.72 124	74.32 77	41.34 167	66.96 147	88.57 76	39.18 165	75.20 112	70.35 122	77.01 121	72.37 105

ETV-MVS		64.30 126	64.76 151	63.77 93	68.59 83	62.49 112	77.02 87	45.31 103	49.27 195	50.88 125	56.23 197	59.91 196	57.12 85	80.19 86	74.23 94	83.68 72	71.03 114

ECVR-MVS		63.93 127	71.52 125	55.08 140	66.19 99	61.34 120	63.84 157	51.79 66	70.75 101	34.77 179	74.70 113	81.10 129	38.92 166	79.39 90	73.43 99	75.00 136	59.92 167

Anonymous20231211		63.69 128	72.86 109	53.00 149	63.72 121	60.25 130	60.33 168	40.96 144	72.49 88	38.91 170	81.77 66	88.17 79	37.60 173	73.30 124	68.01 141	76.47 127	66.06 144

TransMVSNet (Re)		63.49 129	73.86 99	51.39 158	64.26 115	56.07 152	61.17 166	42.23 129	78.81 60	34.80 178	85.94 27	90.63 56	34.35 188	72.73 133	67.98 142	71.50 156	64.84 149

DI_MVS_plusplus_trai		63.43 130	67.54 140	58.63 119	62.34 130	58.06 135	65.75 149	42.15 130	63.05 140	53.28 113	75.88 100	75.92 155	50.18 120	68.04 164	64.20 160	78.07 116	67.65 136

EIA-MVS		63.24 131	64.16 155	62.16 101	69.30 81	63.20 109	72.40 111	40.82 147	48.31 201	51.50 119	59.63 184	62.23 188	57.33 84	78.00 100	71.94 109	81.59 93	65.82 145

Fast-Effi-MVS+-dtu		63.22 132	65.55 145	60.49 111	61.24 135	64.70 98	74.15 104	53.24 59	51.46 180	49.67 133	58.03 192	78.42 145	48.05 133	72.03 139	71.14 114	76.60 126	63.09 156

IterMVS-SCA-FT		62.67 133	68.00 138	56.45 136	56.92 160	64.92 94	57.51 181	38.12 166	59.44 150	53.62 110	74.74 112	71.60 166	64.84 39	70.24 156	65.27 156	67.70 174	69.83 120

diffmvs		62.64 134	69.66 134	54.46 143	56.19 165	55.06 161	67.36 139	36.74 177	64.18 134	50.58 126	79.54 83	87.55 88	45.13 148	68.04 164	63.20 165	70.78 161	70.02 118
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		62.58 135	67.46 141	56.89 132	59.52 147	55.90 154	64.94 151	38.83 160	57.08 166	56.55 101	76.53 96	84.49 117	47.45 135	66.95 167	62.01 171	74.04 141	69.27 128

MDA-MVSNet-bldmvs		62.46 136	72.13 118	51.19 160	34.32 214	56.10 151	68.65 132	38.85 159	69.05 118	49.50 134	78.17 90	85.43 110	51.32 111	86.67 38	67.40 149	64.46 179	62.08 158

pm-mvs1		61.97 137	72.01 121	50.25 166	60.64 140	55.23 159	58.67 176	42.44 127	74.40 76	33.63 187	81.03 70	89.86 65	34.87 183	72.93 131	67.95 143	71.28 157	62.65 157

FMVSNet1		61.92 138	71.36 126	50.90 162	57.67 159	59.29 133	59.48 174	44.14 116	70.24 105	34.72 180	75.45 106	84.94 113	36.75 175	72.33 135	68.45 132	72.66 150	68.83 130

PVSNet_BlendedMVS		61.75 139	65.07 149	57.87 128	56.27 163	60.99 126	65.81 147	43.75 118	51.27 184	54.08 108	62.12 172	78.84 142	50.67 115	71.49 144	63.91 162	76.64 124	66.86 138

PVSNet_Blended		61.75 139	65.07 149	57.87 128	56.27 163	60.99 126	65.81 147	43.75 118	51.27 184	54.08 108	62.12 172	78.84 142	50.67 115	71.49 144	63.91 162	76.64 124	66.86 138

tttt0517		61.44 141	63.85 157	58.62 120	55.20 174	55.61 156	68.80 131	38.02 169	55.70 171	50.01 131	66.93 148	48.90 207	56.69 87	73.84 117	71.10 116	82.99 79	74.89 89

tfpnnormal		61.41 142	71.33 127	49.83 167	61.73 132	54.90 163	58.52 177	41.24 141	75.20 71	32.00 195	82.13 59	87.87 83	35.63 182	72.75 132	66.30 153	69.87 167	60.14 165

IB-MVS	57.02 17	61.37 143	65.39 146	56.69 133	56.65 161	60.85 128	70.70 121	37.90 171	49.37 194	45.37 155	48.75 209	79.14 140	53.55 104	76.26 107	70.85 118	75.97 128	72.50 104
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
CANet_DTU		61.22 144	67.07 142	54.40 145	59.89 143	63.62 108	70.98 118	36.77 176	50.49 187	47.15 142	62.45 170	80.81 131	37.90 172	71.87 141	70.09 124	73.69 143	70.19 117

pmmvs4		61.12 145	64.61 152	57.04 130	60.88 137	52.15 172	70.59 122	44.82 111	61.35 146	46.91 145	72.08 128	73.27 164	46.79 142	65.06 170	67.76 145	72.28 151	60.58 163

thisisatest0530		61.02 146	63.44 162	58.19 127	54.75 176	55.09 160	68.03 136	38.02 169	55.45 172	49.06 136	66.58 152	48.69 208	56.69 87	73.07 126	71.10 116	82.60 84	74.14 92

Vis-MVSNet (Re-imp)		60.99 147	67.78 139	53.06 148	64.66 114	53.49 168	67.40 137	49.52 75	68.55 119	28.00 203	79.53 85	71.41 168	33.08 192	75.30 111	71.28 113	75.69 131	54.91 179

PatchMatch-RL		60.96 148	63.00 165	58.57 121	59.16 151	52.18 171	67.38 138	41.99 133	57.85 160	48.16 137	53.55 205	69.77 173	59.47 75	73.73 118	72.49 107	75.27 135	61.44 160

GA-MVS		60.73 149	64.24 154	56.64 134	59.38 150	57.45 144	65.07 150	36.65 178	57.39 164	58.17 95	73.43 122	69.10 177	47.38 136	64.47 175	63.63 164	73.19 147	64.22 152

CVMVSNet		60.45 150	63.72 159	56.63 135	54.82 175	53.75 165	68.41 133	41.95 134	55.07 173	48.03 138	58.08 191	68.67 178	55.09 95	69.14 162	68.34 136	71.51 155	72.97 103

ET-MVSNet_ETH3D		60.33 151	62.10 168	58.27 124	58.61 155	58.05 136	68.06 134	41.20 142	51.40 181	51.10 123	64.06 162	49.42 206	50.61 117	74.72 113	70.29 123	80.05 102	66.74 140

FC-MVSNet-test		60.28 152	70.83 130	47.96 178	54.69 177	47.12 186	68.06 134	41.68 139	71.42 93	23.73 211	84.70 39	77.41 151	28.92 198	82.33 71	73.08 102	70.68 162	59.77 168

test2506		59.86 153	64.01 156	55.02 141	66.19 99	61.34 120	63.84 157	51.79 66	70.75 101	34.39 185	62.65 169	39.92 222	38.92 166	79.39 90	73.43 99	75.00 136	60.56 164

EU-MVSNet		59.77 154	66.07 143	52.42 150	47.81 193	51.86 174	62.98 161	32.28 193	62.08 144	47.10 143	59.94 182	83.42 123	53.08 107	70.06 159	63.19 166	71.26 159	71.96 109

IterMVS		59.24 155	64.45 153	53.16 147	50.98 186	61.29 122	66.51 142	32.85 189	58.17 156	46.31 150	72.58 127	70.23 171	54.26 100	64.81 173	60.24 175	68.04 173	63.81 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		59.15 156	62.28 167	55.49 139	52.42 182	62.59 111	71.76 113	39.74 155	50.25 189	41.92 163	62.88 167	69.16 176	55.85 90	62.77 180	67.18 150	71.27 158	61.11 162

thres600view7		58.87 157	65.91 144	50.66 164	61.27 134	56.32 149	59.88 172	40.63 150	64.88 132	32.10 194	64.82 158	69.83 172	36.72 176	72.99 129	72.55 106	73.34 145	59.97 166

CMPMVS	45.32 18	58.10 158	65.24 148	49.76 168	47.88 192	46.86 189	48.16 206	32.82 190	58.06 157	61.35 83	59.64 183	80.00 135	47.27 137	70.15 157	64.10 161	61.08 182	77.85 76
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDTV_nov1_ep13_2view		58.09 159	63.54 161	51.74 154	50.13 188	46.56 190	66.95 140	33.41 186	63.52 138	58.77 92	74.84 110	84.10 120	43.12 154	65.95 169	54.69 189	58.04 188	55.13 178

CDS-MVSNet		57.90 160	63.57 160	51.28 159	62.30 131	53.17 169	64.70 152	51.61 69	57.41 163	32.75 189	63.73 163	70.53 170	27.12 200	72.49 134	73.02 103	69.22 170	54.68 180
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
FMVSNet2		57.80 161	65.39 146	48.94 174	55.88 166	57.61 140	57.26 182	42.37 128	58.21 155	33.19 188	68.36 140	75.55 157	34.58 185	66.91 168	64.55 158	70.38 163	66.56 141

thres400		57.25 162	63.73 158	49.70 169	60.19 142	54.95 162	58.16 178	39.60 156	62.42 141	31.98 197	62.33 171	69.20 175	35.96 180	70.07 158	68.03 140	72.28 151	59.12 170

gm-plane-assit		56.76 163	57.64 182	55.73 138	66.01 103	55.45 158	74.96 96	30.54 198	73.71 82	56.04 102	81.81 64	30.91 225	43.83 150	58.77 190	54.71 188	63.02 181	48.13 195

MIMVSNet1		56.72 164	68.69 137	42.76 191	46.70 199	42.81 196	69.13 128	30.52 199	81.01 48	32.00 195	74.82 111	91.10 46	26.83 202	73.98 116	64.72 157	51.40 200	52.38 184

EPNet_dtu		56.63 165	60.77 174	51.80 153	55.47 171	44.63 191	69.83 126	38.74 163	50.27 188	47.64 139	58.01 193	72.27 165	33.71 190	68.60 163	67.72 146	65.39 177	63.86 153
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GBi-Net		56.54 166	63.26 163	48.70 175	55.88 166	57.61 140	57.26 182	41.75 136	49.06 196	32.37 191	61.81 174	67.02 180	34.58 185	72.33 135	68.45 132	70.38 163	66.56 141

test1		56.54 166	63.26 163	48.70 175	55.88 166	57.61 140	57.26 182	41.75 136	49.06 196	32.37 191	61.81 174	67.02 180	34.58 185	72.33 135	68.45 132	70.38 163	66.56 141

gg-mvs-nofinetune		56.45 168	61.04 172	51.10 161	63.42 126	49.40 182	53.71 193	52.52 62	74.77 73	46.93 144	77.31 94	53.88 200	26.42 204	62.51 181	57.81 181	63.60 180	51.57 187

thres200		56.35 169	62.36 166	49.34 171	58.87 153	56.32 149	55.91 186	40.63 150	58.51 153	31.34 198	58.81 190	67.31 179	35.96 180	72.99 129	65.51 155	73.34 145	57.07 173

MS-PatchMatch		56.31 170	60.22 177	51.73 155	60.53 141	55.53 157	63.41 159	37.18 174	51.34 183	37.44 172	60.53 180	62.19 189	45.52 145	64.25 176	63.17 167	66.33 175	64.56 150

tfpn200view9		56.07 171	61.85 169	49.34 171	58.57 156	56.48 148	58.01 180	40.72 149	53.23 174	31.01 199	56.41 195	66.40 184	34.18 189	73.02 127	68.06 139	73.53 144	59.35 169

FMVSNet3		54.77 172	60.73 175	47.81 179	54.29 179	56.88 147	55.89 187	41.75 136	49.06 196	32.37 191	61.81 174	67.02 180	33.67 191	62.88 179	61.96 172	68.88 171	65.53 146

thres100view900		53.88 173	59.19 178	47.68 180	58.57 156	52.74 170	54.45 190	38.07 168	53.23 174	31.01 199	56.41 195	66.40 184	32.80 193	65.03 172	64.43 159	71.18 160	56.10 176

CR-MVSNet		53.82 174	55.40 186	51.98 151	51.57 185	50.23 177	45.00 208	44.97 108	46.90 203	52.60 116	67.91 141	46.99 215	48.37 129	59.15 188	59.53 178	69.38 169	57.07 173

baseline2		53.55 175	55.19 187	51.62 156	55.27 173	51.95 173	60.89 167	34.23 181	46.69 205	42.47 161	53.56 204	50.01 203	45.33 147	64.63 174	61.22 173	71.56 154	58.28 172

test20.03		53.49 176	60.95 173	44.78 187	64.73 113	47.25 185	61.58 165	43.30 120	65.86 128	22.85 212	66.87 151	79.85 136	22.99 206	62.38 182	56.95 183	53.25 197	47.46 197

baseline		53.46 177	61.55 170	44.01 188	45.83 202	48.77 183	57.26 182	28.75 202	49.99 190	38.85 171	68.78 137	75.65 156	38.30 169	60.80 183	59.78 177	55.10 195	67.07 137

MVSTER		53.08 178	56.39 184	49.21 173	47.19 195	51.08 175	60.14 171	31.74 195	40.63 213	38.97 169	55.78 198	46.74 216	42.47 157	67.29 166	62.99 168	74.73 139	70.23 116

CHOSEN 1792x2688		52.99 179	56.91 183	48.42 177	47.32 194	50.10 179	64.18 154	33.85 183	45.46 208	36.95 174	55.20 201	66.49 183	51.20 112	59.28 186	59.81 176	57.01 190	61.99 159

baseline1		52.90 180	58.38 179	46.51 186	58.87 153	50.01 180	54.17 191	40.45 153	56.81 168	29.25 202	62.72 168	58.99 197	30.25 196	65.05 171	60.57 174	66.07 176	54.54 181

CostFormer		52.59 181	55.14 188	49.61 170	52.72 180	50.40 176	66.28 144	33.78 184	52.85 176	43.43 159	66.30 153	51.37 202	41.78 160	54.92 200	51.18 196	59.68 184	58.98 171

SCA		52.47 182	53.97 190	50.71 163	46.95 198	57.79 138	60.18 170	46.89 93	51.92 179	46.71 149	60.73 178	49.97 204	47.69 134	56.39 197	52.98 193	55.82 192	48.03 196

testgi		51.94 183	61.37 171	40.94 194	58.38 158	47.03 187	65.88 146	30.49 200	70.87 100	22.64 213	57.53 194	87.59 86	18.30 213	63.01 178	54.32 190	49.93 203	49.27 190

tpm cat1		50.98 184	51.28 196	50.62 165	55.74 169	49.92 181	63.13 160	38.12 166	52.38 178	47.61 140	60.11 181	44.51 219	44.86 149	51.31 208	47.49 203	54.25 196	53.24 183

RPMNet		50.92 185	50.32 198	51.62 156	50.25 187	50.23 177	59.16 175	46.70 94	46.90 203	42.39 162	48.97 208	37.23 223	41.78 160	57.30 195	56.18 185	69.44 168	55.43 177

pmmvs5		50.64 186	58.01 180	42.05 192	47.01 197	43.67 194	49.27 204	29.43 201	50.77 186	33.83 186	68.69 138	76.16 154	27.82 199	57.53 194	57.07 182	64.95 178	52.18 185

PatchT		50.55 187	53.55 192	47.05 184	37.59 213	42.26 197	50.55 201	37.56 172	46.37 206	52.60 116	66.91 149	43.54 221	48.37 129	59.15 188	59.53 178	55.62 193	57.07 173

Anonymous20231206		50.28 188	57.94 181	41.35 193	55.45 172	43.65 195	58.06 179	34.12 182	62.02 145	24.25 210	59.33 185	79.80 137	24.49 205	59.55 184	54.28 191	51.74 199	46.94 199

dps		49.71 189	51.97 194	47.07 183	52.37 183	47.00 188	53.02 196	40.52 152	44.91 209	41.23 168	64.55 159	44.27 220	40.12 163	57.71 193	51.97 195	55.14 194	53.41 182

MDTV_nov1_ep13		49.60 190	51.57 195	47.31 181	46.28 200	44.61 192	59.82 173	30.96 196	48.80 200	50.20 129	59.26 187	52.38 201	38.56 168	56.20 198	49.70 199	58.04 188	50.01 188

PatchmatchNet		48.67 191	50.10 199	46.99 185	48.29 191	41.00 198	55.54 188	38.94 158	51.38 182	45.15 156	63.22 165	48.45 210	42.83 155	53.80 205	48.50 202	51.19 202	44.37 201
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
new-patchmatchnet		47.33 192	60.49 176	31.99 210	55.69 170	33.86 210	36.84 218	33.31 187	72.36 89	14.33 218	80.09 78	92.14 33	13.27 215	63.54 177	40.09 211	38.51 212	41.32 209

tpm		46.67 193	49.20 204	43.72 189	49.60 189	36.60 207	53.93 192	26.84 204	52.70 177	58.05 97	69.04 136	47.96 211	30.06 197	48.33 211	42.76 206	43.88 206	47.01 198

pmmvs3		46.64 194	54.13 189	37.90 201	31.23 218	40.68 199	49.83 203	15.34 215	46.31 207	36.34 176	53.15 206	74.40 162	36.36 177	58.43 191	56.64 184	58.32 187	49.29 189

TAMVS		46.64 194	53.62 191	38.49 199	49.56 190	36.87 204	53.16 195	25.76 206	56.33 170	22.55 214	60.72 179	61.80 191	27.12 200	59.50 185	58.33 180	52.79 198	41.82 208

test-LLR		46.01 196	45.06 213	47.11 182	59.39 148	36.72 205	51.28 198	40.95 145	36.41 217	34.45 183	46.14 211	47.02 213	38.00 170	51.78 206	48.53 200	58.60 185	48.84 192

MIMVSNet		45.83 197	53.46 193	36.94 202	45.38 206	39.50 201	52.20 197	30.68 197	57.09 165	24.53 209	55.22 200	71.54 167	21.74 209	55.81 199	51.08 197	47.11 204	43.96 202

pmnet_mix02		45.67 198	55.99 185	33.63 209	45.77 203	31.22 214	42.04 213	27.60 203	64.14 135	24.89 206	75.50 105	82.30 125	21.88 208	54.53 203	41.22 208	39.62 210	43.05 204

test0.0.03 1		45.40 199	49.55 202	40.57 196	59.39 148	44.36 193	53.37 194	40.95 145	47.14 202	19.23 215	45.49 213	60.24 194	19.24 211	54.82 201	51.98 194	51.21 201	42.82 205

PMMVS		45.37 200	49.29 203	40.79 195	27.75 219	35.07 209	50.88 200	19.88 212	39.27 215	35.78 177	50.11 207	61.29 192	42.04 158	54.13 204	55.95 186	68.43 172	49.19 191

MVS-HIRNet		44.56 201	45.52 211	43.44 190	40.98 209	31.03 215	39.52 217	36.96 175	42.80 211	44.37 157	53.80 203	60.04 195	41.85 159	47.97 213	41.08 209	56.99 191	41.95 207

test-mter		44.18 202	47.60 206	40.18 197	33.20 215	39.03 202	55.28 189	13.91 217	39.07 216	36.63 175	48.09 210	49.52 205	41.12 162	54.55 202	50.91 198	60.97 183	52.03 186

EMVS		43.85 203	49.91 200	36.77 204	45.46 205	32.70 211	44.09 210	25.33 207	57.88 159	26.62 204	58.99 189	61.14 193	42.77 156	70.26 155	38.52 215	36.38 214	29.87 215

E-PMN		43.83 204	49.81 201	36.84 203	46.09 201	31.86 213	42.77 212	25.85 205	57.76 161	25.53 205	55.50 199	62.47 187	43.77 151	70.78 151	39.51 212	37.04 213	30.79 214

tpmrst		43.31 205	46.14 209	40.02 198	47.05 196	36.48 208	48.01 207	32.17 194	49.50 193	37.26 173	63.66 164	47.04 212	31.98 195	42.00 217	40.55 210	43.64 207	43.75 203

TESTMET0.1,1		41.79 206	45.06 213	37.97 200	31.32 217	36.72 205	51.28 198	14.17 216	36.41 217	34.45 183	46.14 211	47.02 213	38.00 170	51.78 206	48.53 200	58.60 185	48.84 192

ADS-MVSNet		40.61 207	46.31 207	33.96 207	40.70 210	30.42 216	40.42 215	33.44 185	58.01 158	30.87 201	63.05 166	54.48 199	22.67 207	44.35 216	39.23 214	35.64 215	34.64 212

CHOSEN 280x420		40.24 208	44.14 216	35.69 205	32.36 216	23.58 219	50.30 202	21.21 211	40.94 212	18.84 216	32.75 217	48.65 209	48.13 132	59.16 187	55.31 187	43.28 208	48.62 194

EPMVS		40.11 209	44.96 215	34.44 206	41.55 208	32.65 212	41.74 214	32.39 192	49.89 192	24.83 207	64.44 160	46.38 217	26.57 203	44.75 215	39.47 213	39.59 211	37.16 211

FMVSNet5		39.83 210	45.08 212	33.71 208	39.24 211	39.56 200	48.77 205	23.55 209	39.45 214	24.55 208	33.73 216	44.57 218	20.97 210	58.27 192	54.23 192	45.16 205	45.77 200

N_pmnet		39.50 211	51.01 197	26.09 212	44.48 207	25.59 218	40.20 216	21.49 210	64.20 133	7.98 222	73.86 118	76.67 153	13.66 214	50.17 209	36.69 217	28.71 217	29.86 216

MVE	28.01 19	35.86 212	43.56 217	26.88 211	22.33 221	19.75 221	30.85 221	23.88 208	49.90 191	10.48 220	43.64 214	61.87 190	48.99 128	47.26 214	42.15 207	24.76 218	40.37 210
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
new_pmnet		35.76 213	45.64 210	24.22 213	38.59 212	25.83 217	31.87 220	19.24 213	49.06 196	9.01 221	54.34 202	64.73 186	12.46 216	49.21 210	44.91 204	34.17 216	31.41 213

PMMVS2		34.11 214	48.55 205	17.26 214	25.45 220	20.72 220	35.08 219	16.26 214	58.71 152	4.16 224	59.22 188	78.40 146	3.65 218	57.24 196	38.31 216	18.94 220	27.28 217

GG-mvs-BLEND		31.54 215	46.27 208	14.37 215	0.07 226	48.65 184	42.97 211	0.08 223	44.04 210	1.21 226	39.77 215	57.94 198	0.15 222	48.19 212	42.82 205	41.70 209	42.46 206

test_method		13.28 216	15.83 218	10.30 216	1.05 223	2.18 224	15.40 222	2.23 219	22.43 219	13.84 219	22.00 219	33.14 224	9.78 217	17.80 219	9.93 219	19.50 219	3.31 219

test123		0.53 217	0.60 220	0.46 218	0.22 224	0.25 225	0.33 227	0.13 222	0.66 222	1.37 225	1.10 221	0.00 229	0.43 220	0.68 221	0.61 220	0.26 223	0.88 220

testmvs		0.47 218	0.69 219	0.21 219	0.17 225	0.17 226	0.35 226	0.16 221	0.66 222	0.18 227	1.05 222	0.99 228	0.27 221	0.62 222	0.54 221	0.15 224	0.77 221

uanet_test		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 229	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

sosnet-low-res		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 229	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

sosnet		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 229	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

RE-MVS-def										70.04 55

9.14												83.64 121

SR-MVS					81.31 9			62.63 9				91.11 45

Anonymous202405211			72.22 117		66.19 99	61.09 125	62.23 164	45.87 101	71.25 95		79.33 86	86.16 107	37.36 174	73.54 122	69.84 125	75.45 133	64.32 151

our_test_3					52.72 180	53.66 166	69.11 129

ambc			79.96 61		74.57 54	75.48 49	73.75 108		80.32 53	72.34 38	78.46 88	92.41 29	59.05 76	80.24 85	73.95 96	75.41 134	78.85 70

MTAPA										80.26 8		90.53 60

MTMP										82.07 4		91.00 48

Patchmatch-RL test							2.05 225

tmp_tt				7.47 217	8.89 222	3.32 223	4.35 224	1.14 220	15.58 221	15.76 217	8.50 220	5.90 227	2.00 219	20.02 218	21.51 218	12.70 221

XVS					80.47 20	81.29 12	93.33 3			77.45 19		90.19 62				91.52 11

X-MVStestdata					80.47 20	81.29 12	93.33 3			77.45 19		90.19 62				91.52 11

mPP-MVS					82.97 2							92.12 34

NP-MVS									71.39 94

Patchmtry						37.73 203	45.00 208	44.97 108		52.60 116

DeepMVS_CX						8.52 222	9.75 223	3.19 218	16.70 220	5.02 223	23.06 218	19.33 226	18.69 212	13.75 220		11.34 222	25.07 218

High-resolution multi-view benchmark