DANIEL FREEDMAN

In this paper, we present a unified approach for the problem of computing color transforms, applications of which include shadow removal and object recoloring. We propose two algorithms for transforming colors. In the first algorithm, the detection of source and target regions is performed using a Bayesian classifier. Given these regions, the computed transform alters the color properties of the target region so as to closely resemble those of the source region. The proposed probabilistic formulation leads to a linear program (similar to the classic Transportation Problem), which computes the desired transformation between the target and source distributions. In the second algorithm, the detection and transformation steps are united into a single unified approach; furthermore, the continuity of the transformation arises more intrinsically within this algorithm. Both formulations allow the target region to acquire the properties of the source region, while at the same time retaining its own look and feel. Promising results are shown for a variety of applications.