Color-aware Regularization for Gradient Domain Image Manipulation

Abstract

We propose a color-aware regularization for use with gradient domain image manipulation to avoid color shift artifacts. Our work is motivated by the observation that colors of objects in natural images typically follow distinct distributions in the color space. Conventional regularization methods ignore these distributions which can lead to undesirable colors appearing in the nal output. Our approach uses an anisotropic Mahalanobis distance to control output colors to better toriginal distributions. Our color-aware regularization is simple, easy to implement, and does not introduce signicant computational overhead. To demonstrate the eectiveness of our method, we show the results with and without our color-aware regularization on three gradient domain tasks: gradient transfer, gradient boosting, and saliency sharpening.