Learning descriptor, confidence, and depth estimation in multi-view stereo

Sungil Choi; Seungryong Kim; Kihong Park; Kwanghoon Sohn

doi:10.1109/CVPRW.2018.00065

Learning descriptor, confidence, and depth estimation in multi-view stereo

Sungil Choi, Seungryong Kim, Kihong Park, Kwanghoon Sohn

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

10 Citations (Scopus)

Abstract

Depth estimation from multi-view stereo images is one of the most fundamental and essential tasks in understanding a scene imaginary. In this paper, we propose a machine learning technique based on deep convolutional neural networks (CNNs) for multi-view stereo matching. The proposed method measures the matching cost to extract depth values between two-view stereo images among multi-view stereo images using a deep architecture. Moreover, we present the confidence estimation network for incorporating the cost volumes along the depth hypothesis in multiview stereo. Experiments show that our estimated depth map from multiple views shows the better performance than the other matching similarity measure on DTU dataset.

Original language	English
Title of host publication	Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
Publisher	IEEE Computer Society
Pages	389-395
Number of pages	7
ISBN (Electronic)	9781538661000
DOIs	https://doi.org/10.1109/CVPRW.2018.00065
Publication status	Published - 2018 Dec 13
Event	31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 - Salt Lake City, United States Duration: 2018 Jun 18 → 2018 Jun 22

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2018-June
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Other

Other	31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
Country/Territory	United States
City	Salt Lake City
Period	18/6/18 → 18/6/22

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1109/CVPRW.2018.00065

Cite this

Choi, S., Kim, S., Park, K., & Sohn, K. (2018). Learning descriptor, confidence, and depth estimation in multi-view stereo. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 (pp. 389-395). [8575527] (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2018-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2018.00065

@inproceedings{0867ff0c1ff643e2a6bef82e3c710915,

title = "Learning descriptor, confidence, and depth estimation in multi-view stereo",

abstract = "Depth estimation from multi-view stereo images is one of the most fundamental and essential tasks in understanding a scene imaginary. In this paper, we propose a machine learning technique based on deep convolutional neural networks (CNNs) for multi-view stereo matching. The proposed method measures the matching cost to extract depth values between two-view stereo images among multi-view stereo images using a deep architecture. Moreover, we present the confidence estimation network for incorporating the cost volumes along the depth hypothesis in multiview stereo. Experiments show that our estimated depth map from multiple views shows the better performance than the other matching similarity measure on DTU dataset.",

author = "Sungil Choi and Seungryong Kim and Kihong Park and Kwanghoon Sohn",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 ; Conference date: 18-06-2018 Through 22-06-2018",

year = "2018",

month = dec,

day = "13",

doi = "10.1109/CVPRW.2018.00065",

language = "English",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "389--395",

booktitle = "Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018",

address = "United States",

}

Choi, S, Kim, S, Park, K & Sohn, K 2018, Learning descriptor, confidence, and depth estimation in multi-view stereo. in Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018., 8575527, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2018-June, IEEE Computer Society, pp. 389-395, 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018, Salt Lake City, United States, 18/6/18. https://doi.org/10.1109/CVPRW.2018.00065

Learning descriptor, confidence, and depth estimation in multi-view stereo. / Choi, Sungil; Kim, Seungryong; Park, Kihong et al.
Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society, 2018. p. 389-395 8575527 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2018-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Learning descriptor, confidence, and depth estimation in multi-view stereo

AU - Choi, Sungil

AU - Kim, Seungryong

AU - Park, Kihong

AU - Sohn, Kwanghoon

PY - 2018/12/13

Y1 - 2018/12/13

N2 - Depth estimation from multi-view stereo images is one of the most fundamental and essential tasks in understanding a scene imaginary. In this paper, we propose a machine learning technique based on deep convolutional neural networks (CNNs) for multi-view stereo matching. The proposed method measures the matching cost to extract depth values between two-view stereo images among multi-view stereo images using a deep architecture. Moreover, we present the confidence estimation network for incorporating the cost volumes along the depth hypothesis in multiview stereo. Experiments show that our estimated depth map from multiple views shows the better performance than the other matching similarity measure on DTU dataset.

AB - Depth estimation from multi-view stereo images is one of the most fundamental and essential tasks in understanding a scene imaginary. In this paper, we propose a machine learning technique based on deep convolutional neural networks (CNNs) for multi-view stereo matching. The proposed method measures the matching cost to extract depth values between two-view stereo images among multi-view stereo images using a deep architecture. Moreover, we present the confidence estimation network for incorporating the cost volumes along the depth hypothesis in multiview stereo. Experiments show that our estimated depth map from multiple views shows the better performance than the other matching similarity measure on DTU dataset.

UR - http://www.scopus.com/inward/record.url?scp=85060856639&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060856639&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2018.00065

DO - 10.1109/CVPRW.2018.00065

M3 - Conference contribution

AN - SCOPUS:85060856639

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 389

EP - 395

BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018

PB - IEEE Computer Society

T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018

Y2 - 18 June 2018 through 22 June 2018

ER -

Choi S, Kim S, Park K, Sohn K. Learning descriptor, confidence, and depth estimation in multi-view stereo. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society. 2018. p. 389-395. 8575527. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW.2018.00065

Learning descriptor, confidence, and depth estimation in multi-view stereo

Abstract

Publication series

Other

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this