User‐Controllable Color Transfer

Abstract

This paper presents an image editing framework where users use reference images to indicate desired color edits. In our approach, users specify pairs of strokes to indicate corresponding regions in both the original and the reference image that should have the same color "style". Within each stroke pair, a nonlinear constrained parametric transfer model is used to transfer the reference colors to the original. We estimate the model parameters by matching color distributions, under constraints that ensure no visual artifacts are present in the transfer result. To perform transfer on the whole image, we employ optimization methods to propagate the model parameters defined at each stroke location to spatially-close regions of similar appearance. This stroke-based formulation requires minimal user effort while retaining the high degree of user control necessary to allow artistic interpretations. We demonstrate our approach by performing color transfer on a number of image pairs varying in content and style, and show that our algorithm outperforms state-of-the-art color transfer methods on both user-controllability and visual qualities of the transfer results.

Style transfer for headshot portraits

“…All these methods aim for a different application than ours. Joshi et al [2010] and An and Pellacini [2010] successfully transfer color balance and overall exposure. Tong et al [2007] and Guo et al [2009] transfer make-up.…”

Tonal stabilization of video

“…Indeed, a variety of color transfer methods have been proposed over the years [An and Pellacini 2010]. Following Reinhard et al [2001], several researchers tried to match various global color statistics of two images, such as mean and variance in some color space.…”

“…An and Pellacini [2010] employ this interface in a system specifically designed for user-controlled color transfer between images, using a powerful nonlinear parametric transfer model. We show that it is possible to achieve tonal stabilization using a simpler transfer model, and without requiring user interaction.…”

Tonal stabilization of video

“…A richer model, which interleaves the channels and has more parameters, such as the one proposed by An and Pellacini [2010], can better account for the variations in the data. This is demonstrated in the second row of Figure 2, where we used an affine transformation with 12 degrees of freedom.…”