Example-based Color Transfer with Gaussian Mixture Modeling

TL;DR

This paper introduces a probabilistic framework for color transfer in images using Gaussian Mixture Models and EM optimization, improving results over existing methods.

Contribution

It models color transfer as a GMM parameter estimation problem and incorporates Laplacian regularization for better gradient preservation.

Findings

Outperforms other color transfer methods visually and quantitatively

Produces continuous color transfer results with iterative EM optimization

Effectively preserves image gradients during color transfer

Abstract

Color transfer, which plays a key role in image editing, has attracted noticeable attention recently. It has remained a challenge to date due to various issues such as time-consuming manual adjustments and prior segmentation issues. In this paper, we propose to model color transfer under a probability framework and cast it as a parameter estimation problem. In particular, we relate the transferred image with the example image under the Gaussian Mixture Model (GMM) and regard the transferred image color as the GMM centroids. We employ the Expectation-Maximization (EM) algorithm (E-step and M-step) for optimization. To better preserve gradient information, we introduce a Laplacian based regularization term to the objective function at the M-step which is solved by deriving a gradient descent algorithm. Given the input of a source image and an example image, our method is able to generate continuous color transfer results with increasing EM iterations. Various experiments show that our approach generally outperforms other competitive color transfer methods, both visually and quantitatively.