Color Transforms for Creative Image Editing

摘要

In this paper, we present a unified approach for the prob-lem of computing color transforms, applications of which include shadow removal, object recoloring, and scene relighting. The de-tection 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 resem-ble those of the source region. The proposed probabilistic for-mulation leads to a linear program (similar to the classic Trans-portation Problem), which computes the desired transformation between the target and source distributions. This formulation allows 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.