A Colorization Algorithm Based on Local MAP Estimation

This paper presents a colorization algorithm which adds color to monochrome im-ages. In this paper, the colorization problem is formulated as the maximum a poste-riori (MAP) estimation of a color image given a monochrome image. Markov random field (MRF) is used for modeling a color image which is utilized as a prior for the MAP estimation. The MAP estimation problem for a whole image is decomposed into local MAP estimation problems for each pixel. Using 0.6 % of whole pixels as references, the proposed method produced pretty high quality color images with 25.7 dB to 32.6 dB PSNR values for eight images