Mixed l(0)/l(1) Norm Minimization Approach to Image Colorization

作者：Uruma Kazunori^*; Konishi Katsumi; Takahashi Tomohiro; Furukawa Toshihiro

来源：IEICE Transactions on Information and Systems, 2012, E95D(8): 2150-2153.

DOI：10.1587/transinf.E95.D.2150

• image colorization
• image restoration
• sparse optimization
• matrix completion

This letter proposes a new image colorization algorithm based on the sparse optimization. Introducing some assumptions, a problem of recovering a color image from a grayscale image with the small number of known color pixels is formulated as a mixed l(0)/l(1) norm minimization, and an iterative reweighted least squares (IRLS) algorithm is proposed. Numerical examples show that the proposed algorithm colorizes the grayscale image efficiently.

• 出版日期2012-8