Single-image depth perception in the wild

Weifeng Chen; Zhao Fu; Dawei Yang; Jia Deng

Single-image depth perception in the wild

Weifeng Chen, Zhao Fu, Dawei Yang, Jia Deng

Research output: Contribution to journal › Conference article › peer-review

Abstract

This paper studies single-image depth perception in the wild, i.e., recovering depth from a single image taken in unconstrained settings. We introduce a new dataset "Depth in the Wild" consisting of images in the wild annotated with relative depth between pairs of random points. We also propose a new algorithm that learns to estimate metric depth using annotations of relative depth. Compared to the state of the art, our algorithm is simpler and performs better. Experiments show that our algorithm, combined with existing RGB-D data and our new relative depth annotations, significantly improves single-image depth perception in the wild.

Original language	English (US)
Pages (from-to)	730-738
Number of pages	9
Journal	Advances in Neural Information Processing Systems
State	Published - 2016
Externally published	Yes
Event	30th Annual Conference on Neural Information Processing Systems, NIPS 2016 - Barcelona, Spain Duration: Dec 5 2016 → Dec 10 2016

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

@article{bf8c515faecf4e14bea894ef781438aa,

title = "Single-image depth perception in the wild",

abstract = "This paper studies single-image depth perception in the wild, i.e., recovering depth from a single image taken in unconstrained settings. We introduce a new dataset {"}Depth in the Wild{"} consisting of images in the wild annotated with relative depth between pairs of random points. We also propose a new algorithm that learns to estimate metric depth using annotations of relative depth. Compared to the state of the art, our algorithm is simpler and performs better. Experiments show that our algorithm, combined with existing RGB-D data and our new relative depth annotations, significantly improves single-image depth perception in the wild.",

author = "Weifeng Chen and Zhao Fu and Dawei Yang and Jia Deng",

note = "Publisher Copyright: {\textcopyright} 2016 NIPS Foundation - All Rights Reserved.; 30th Annual Conference on Neural Information Processing Systems, NIPS 2016 ; Conference date: 05-12-2016 Through 10-12-2016",

year = "2016",

language = "English (US)",

pages = "730--738",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

publisher = "Neural information processing systems foundation",

}

TY - JOUR

T1 - Single-image depth perception in the wild

AU - Chen, Weifeng

AU - Fu, Zhao

AU - Yang, Dawei

AU - Deng, Jia

PY - 2016

Y1 - 2016

N2 - This paper studies single-image depth perception in the wild, i.e., recovering depth from a single image taken in unconstrained settings. We introduce a new dataset "Depth in the Wild" consisting of images in the wild annotated with relative depth between pairs of random points. We also propose a new algorithm that learns to estimate metric depth using annotations of relative depth. Compared to the state of the art, our algorithm is simpler and performs better. Experiments show that our algorithm, combined with existing RGB-D data and our new relative depth annotations, significantly improves single-image depth perception in the wild.

AB - This paper studies single-image depth perception in the wild, i.e., recovering depth from a single image taken in unconstrained settings. We introduce a new dataset "Depth in the Wild" consisting of images in the wild annotated with relative depth between pairs of random points. We also propose a new algorithm that learns to estimate metric depth using annotations of relative depth. Compared to the state of the art, our algorithm is simpler and performs better. Experiments show that our algorithm, combined with existing RGB-D data and our new relative depth annotations, significantly improves single-image depth perception in the wild.

UR - http://www.scopus.com/inward/record.url?scp=85019262625&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019262625&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85019262625

SN - 1049-5258

SP - 730

EP - 738

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

T2 - 30th Annual Conference on Neural Information Processing Systems, NIPS 2016

Y2 - 5 December 2016 through 10 December 2016

ER -

Single-image depth perception in the wild

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this