Gradient domain color restoration of clipped highlights

Mushfiqur Rouf*, Cheryl Lau, Wolfgang Heidrich

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

Sensor clipping destroys the hue of colored highlight regions by misrepresenting the relative magnitude of the color channels. This becomes particularly noticeable in regions with brightly colored light sources or specularities. We present a simple yet effective gradient-space color restoration algorithm for recovering the hue in such image regions. First, we estimate a smooth distribution of the hue of the affected region from information at its boundary. We combine this hue estimate with gradient information from channels unaffected by clipping to restore clipped color channels.

Original languageEnglish (US)
Title of host publication2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012
Pages7-14
Number of pages8
DOIs
StatePublished - Aug 20 2012
Event2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012 - Providence, RI, United States
Duration: Jun 16 2012Jun 21 2012

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Other

Other2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012
CountryUnited States
CityProvidence, RI
Period06/16/1206/21/12

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Gradient domain color restoration of clipped highlights'. Together they form a unique fingerprint.

Cite this