Shadow removal from single RGB-D images

Yao Xiao; Efstratios Tsougenis; Chi Keung Tang

doi:10.1109/CVPR.2014.385

Shadow removal from single RGB-D images

Yao Xiao^*, Efstratios Tsougenis, Chi Keung Tang

^*Corresponding author for this work

Department of Computer Science and Engineering

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

27 Citations (Scopus)

Abstract

We present the first automatic method to remove shadows from single RGB-D images. Using normal cues directly derived from depth, we can remove hard and soft shadows while preserving surface texture and shading. Our key assumption is: pixels with similar normals, spatial locations and chromaticity should have similar colors. A modified nonlocal matching is used to compute a shadow confidence map that localizes well hard shadow boundary, thus handling hard and soft shadows within the same framework. We compare our results produced using state-of-the-art shadow removal on single RGB images, and intrinsic image decomposition on standard RGB-D datasets.

Original language	English
Title of host publication	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher	IEEE Computer Society
Pages	3011-3018
Number of pages	8
ISBN (Electronic)	9781479951178, 9781479951178
DOIs	https://doi.org/10.1109/CVPR.2014.385
Publication status	Published - 24 Sept 2014
Event	27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States Duration: 23 Jun 2014 → 28 Jun 2014

Publication series

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

Conference

Conference	27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Country/Territory	United States
City	Columbus
Period	23/06/14 → 28/06/14

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Access to Document

10.1109/CVPR.2014.385

Cite this

Xiao, Y., Tsougenis, E., & Tang, C. K. (2014). Shadow removal from single RGB-D images. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 3011-3018). Article 6909781 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE Computer Society. https://doi.org/10.1109/CVPR.2014.385

@inproceedings{c911230f95c34e288a7d19509f8b9bc2,

title = "Shadow removal from single RGB-D images",

abstract = "We present the first automatic method to remove shadows from single RGB-D images. Using normal cues directly derived from depth, we can remove hard and soft shadows while preserving surface texture and shading. Our key assumption is: pixels with similar normals, spatial locations and chromaticity should have similar colors. A modified nonlocal matching is used to compute a shadow confidence map that localizes well hard shadow boundary, thus handling hard and soft shadows within the same framework. We compare our results produced using state-of-the-art shadow removal on single RGB images, and intrinsic image decomposition on standard RGB-D datasets.",

author = "Yao Xiao and Efstratios Tsougenis and Tang, \{Chi Keung\}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 ; Conference date: 23-06-2014 Through 28-06-2014",

year = "2014",

month = sep,

day = "24",

doi = "10.1109/CVPR.2014.385",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "3011--3018",

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

}

Xiao, Y, Tsougenis, E & Tang, CK 2014, Shadow removal from single RGB-D images. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 6909781, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, pp. 3011-3018, 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, United States, 23/06/14. https://doi.org/10.1109/CVPR.2014.385

Shadow removal from single RGB-D images. / Xiao, Yao; Tsougenis, Efstratios; Tang, Chi Keung.
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2014. p. 3011-3018 6909781 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - Shadow removal from single RGB-D images

AU - Xiao, Yao

AU - Tsougenis, Efstratios

AU - Tang, Chi Keung

PY - 2014/9/24

Y1 - 2014/9/24

N2 - We present the first automatic method to remove shadows from single RGB-D images. Using normal cues directly derived from depth, we can remove hard and soft shadows while preserving surface texture and shading. Our key assumption is: pixels with similar normals, spatial locations and chromaticity should have similar colors. A modified nonlocal matching is used to compute a shadow confidence map that localizes well hard shadow boundary, thus handling hard and soft shadows within the same framework. We compare our results produced using state-of-the-art shadow removal on single RGB images, and intrinsic image decomposition on standard RGB-D datasets.

AB - We present the first automatic method to remove shadows from single RGB-D images. Using normal cues directly derived from depth, we can remove hard and soft shadows while preserving surface texture and shading. Our key assumption is: pixels with similar normals, spatial locations and chromaticity should have similar colors. A modified nonlocal matching is used to compute a shadow confidence map that localizes well hard shadow boundary, thus handling hard and soft shadows within the same framework. We compare our results produced using state-of-the-art shadow removal on single RGB images, and intrinsic image decomposition on standard RGB-D datasets.

UR - https://www.webofscience.com/wos/woscc/full-record/WOS:000361555603009

UR - https://openalex.org/W2038174692

UR - https://www.scopus.com/pages/publications/84911412704

U2 - 10.1109/CVPR.2014.385

DO - 10.1109/CVPR.2014.385

M3 - Conference Paper published in a book

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

SP - 3011

EP - 3018

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

PB - IEEE Computer Society

T2 - 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014

Y2 - 23 June 2014 through 28 June 2014

ER -

Shadow removal from single RGB-D images

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this