Specular Reflection Separation Using Dark Channel Prior

Hyeongwoo Kim, Hailin Jin, Sunil Hadap, Inso Kweon; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 1460-1467

Abstract


We present a novel method to separate specular reflection from a single image. Separating an image into diffuse and specular components is an ill-posed problem due to lack of observations. Existing methods rely on a specularfree image to detect and estimate specularity, which however may confuse diffuse pixels with the same hue but a different saturation value as specular pixels. Our method is based on a novel observation that for most natural images the dark channel can provide an approximate specular-free image. We also propose a maximum a posteriori formulation which robustly recovers the specular reflection and chromaticity despite of the hue-saturation ambiguity. We demonstrate the effectiveness of the proposed algorithm on real and synthetic examples. Experimental results show that our method significantly outperforms the state-of-theart methods in separating specular reflection.

Related Material


[pdf]
[bibtex]
@InProceedings{Kim_2013_CVPR,
author = {Kim, Hyeongwoo and Jin, Hailin and Hadap, Sunil and Kweon, Inso},
title = {Specular Reflection Separation Using Dark Channel Prior},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}
}