Example-based color transfer with Gaussian mixture modeling. (September 2022)

• Record Type: Journal Article
• Authors: Gu, Chunzhi; Lu, Xuequan; Zhang, Chao
• Is Part Of: Pattern recognition. Volume 129(2022)
• Publication Date: 2022-09
• Subjects: Color transfer -- Gaussian mixture model -- EM optimization; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.108716
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose a novel color transfer approach under GMM framework by taking an example image and a source image as input. We introduce a regularization term to better preserve the gradient information in color transfer. We conduct extensive experiments and demonstrate that our method generally outperforms other competitive techniques. Graphical abstract: 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 multiple color transfer results with increasing EM iterations. Extensive experiments show that our approach generally outperforms other competitive color transfer methods, both visually and quantitatively.