Monocular depth estimation using relative depth maps

Jae Han Lee; Chang Su Kim

doi:10.1109/CVPR.2019.00996

Monocular depth estimation using relative depth maps

Jae Han Lee
, Chang Su Kim

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

142 Citations (Scopus)

Abstract

We propose a novel algorithm for monocular depth estimation using relative depth maps. First, using a convolutional neural network, we estimate relative depths between pairs of regions, as well as ordinary depths, at various scales. Second, we restore relative depth maps from selectively estimated data based on the rank-1 property of pairwise comparison matrices. Third, we decompose ordinary and relative depth maps into components and recombine them optimally to reconstruct a final depth map. Experimental results show that the proposed algorithm provides the state-of-art depth estimation performance.

Original language	English
Title of host publication	Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Publisher	IEEE Computer Society
Pages	9721-9730
Number of pages	10
ISBN (Electronic)	9781728132938
DOIs	https://doi.org/10.1109/CVPR.2019.00996
Publication status	Published - 2019 Jun
Event	32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, United States Duration: 2019 Jun 16 → 2019 Jun 20

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2019-June
ISSN (Print)	1063-6919

Conference

Conference	32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Country/Territory	United States
City	Long Beach
Period	19/6/16 → 19/6/20

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

3D from Single Image
Low-level Vision

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2019.00996

Cite this

Lee, J. H., & Kim, C. S. (2019). Monocular depth estimation using relative depth maps. In Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 (pp. 9721-9730). Article 8954450 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2019-June). IEEE Computer Society. https://doi.org/10.1109/CVPR.2019.00996

Monocular depth estimation using relative depth maps. / Lee, Jae Han; Kim, Chang Su.
Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019. IEEE Computer Society, 2019. p. 9721-9730 8954450 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2019-June).

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

Lee, JH & Kim, CS 2019, Monocular depth estimation using relative depth maps. in Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019., 8954450, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2019-June, IEEE Computer Society, pp. 9721-9730, 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, United States, 19/6/16. https://doi.org/10.1109/CVPR.2019.00996

@inproceedings{c1a216c4f78f45f889b522fa21738607,

title = "Monocular depth estimation using relative depth maps",

abstract = "We propose a novel algorithm for monocular depth estimation using relative depth maps. First, using a convolutional neural network, we estimate relative depths between pairs of regions, as well as ordinary depths, at various scales. Second, we restore relative depth maps from selectively estimated data based on the rank-1 property of pairwise comparison matrices. Third, we decompose ordinary and relative depth maps into components and recombine them optimally to reconstruct a final depth map. Experimental results show that the proposed algorithm provides the state-of-art depth estimation performance.",

keywords = "3D from Single Image, Low-level Vision",

author = "Lee, \{Jae Han\} and Kim, \{Chang Su\}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 ; Conference date: 16-06-2019 Through 20-06-2019",

year = "2019",

month = jun,

doi = "10.1109/CVPR.2019.00996",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "9721--9730",

booktitle = "Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019",

}

TY - GEN

T1 - Monocular depth estimation using relative depth maps

AU - Lee, Jae Han

AU - Kim, Chang Su

PY - 2019/6

Y1 - 2019/6

N2 - We propose a novel algorithm for monocular depth estimation using relative depth maps. First, using a convolutional neural network, we estimate relative depths between pairs of regions, as well as ordinary depths, at various scales. Second, we restore relative depth maps from selectively estimated data based on the rank-1 property of pairwise comparison matrices. Third, we decompose ordinary and relative depth maps into components and recombine them optimally to reconstruct a final depth map. Experimental results show that the proposed algorithm provides the state-of-art depth estimation performance.

AB - We propose a novel algorithm for monocular depth estimation using relative depth maps. First, using a convolutional neural network, we estimate relative depths between pairs of regions, as well as ordinary depths, at various scales. Second, we restore relative depth maps from selectively estimated data based on the rank-1 property of pairwise comparison matrices. Third, we decompose ordinary and relative depth maps into components and recombine them optimally to reconstruct a final depth map. Experimental results show that the proposed algorithm provides the state-of-art depth estimation performance.

KW - 3D from Single Image

KW - Low-level Vision

UR - https://www.scopus.com/pages/publications/85078792242

U2 - 10.1109/CVPR.2019.00996

DO - 10.1109/CVPR.2019.00996

M3 - Conference contribution

AN - SCOPUS:85078792242

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 9721

EP - 9730

BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019

PB - IEEE Computer Society

T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019

Y2 - 16 June 2019 through 20 June 2019

ER -

Monocular depth estimation using relative depth maps

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this