Abstract

This paper introduces a new color transfer method whichis a process of transferring color of an image to match thecolor of another image of the same scene. The color ofa scene may vary from image to image because the photographs are taken at different times, with different cam-eras, and under different camera settings. To solve for afull nonlinear and nonparametric color mapping in the 3DRGB color space, we propose a scattered point interpola-tion scheme using moving least squares and strengthen it with a probabilistic modeling of the color transfer in the 3Dcolor space to deal with mis-alignments and noise. Exper-iments show the effectiveness of our method over previouscolor transfer methods both quantitatively and qualitatively.In addition, our framework can be applied for various instances of color transfer such as transferring color betweendifferent camera models, camera settings, and illuminationconditions, as well as for video color transfers.