DocumentCode
2172976
Title
Highlight removal by illumination-constrained inpainting
Author
Tan, Ping ; Lin, Stephen ; Quan, Long ; Shum, HeungYeung
fYear
2003
fDate
13-16 Oct. 2003
Firstpage
164
Abstract
We present a single-image highlight removal method that incorporates illumination-based constraints into image inpainting. Unlike occluded image regions filled by traditional inpainting, highlight pixels contain some useful information for guiding the inpainting process. Constraints provided by observed pixel colors, highlight color analysis and illumination color uniformity are employed in our method to improve estimation of the underlying diffuse color. The inclusion of these illumination constraints allows for better recovery of shading and textures by inpainting. Experimental results are given to demonstrate the performance of our method.
Keywords
computer vision; image colour analysis; image texture; highlight color analysis; illumination color uniformity; illumination-based constraints; image inpainting; image shading; image texture; inpainting process; occluded image regions; pixel colors; single image highlight removal method; Colored noise; Histograms; Image color analysis; Lighting; Optical polarization; Optical reflection; Rough surfaces; Shape measurement; Surface fitting; Surface roughness;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on
Conference_Location
Nice, France
Print_ISBN
0-7695-1950-4
Type
conf
DOI
10.1109/ICCV.2003.1238333
Filename
1238333
Link To Document