Direct Analytical Methods for Solving Poisson Equations in Computer Vision Problems
IEEE Transactions on Pattern Analysis and Machine Intelligence
Recovering Shading from Color Images
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Separating Reflection Components of Textured Surfaces using a Single Image
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Illumination chromaticity estimation using inverse-intensity chromaticity space
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Hi-index | 0.00 |
Given a standard RGB color image, an approach to recoveringthe shading image, an intrinsic image that dependsonly on the geometry of the viewing situation, ispresented. The approach is formulated for scenes that exhibitboth diffuse and specular properties. It is discriminativein the sense that variations in intensity caused by materialchanges are .rst detected and then removed. Materialchanges are detected using a method based on colorinformation alone. The method stems from a scheme proposedhere to handle specularities under known scene illuminationchromaticity. This scheme is also used to producean image that is free of specular re.ections. Any materialchanges are then removed from this specular-free imageby using an inpainting technique. The performance ofthe proposed approach has been tested on synthetic images.