Recently, the study of colorization algorithm for monochrome still images has prospered. Considering actual application, an extension to moving images becomes important. As the first step, this paper proposes two colorization algorithms for monochrome image sequences which are defined as continuous frames without scene changing. In our approach, key frames in the image sequence are colorized by a conventional colorization technique for still images or human interactive painting. Then, each color in the colorized frame propagates to the next monochrome frame by extracting displacement vector for each pixel between two frames. In this paper, the displacement vector is calculated by an optical flow algorithm, and color propagation to temporary direction is performed. Experimental results suggest a success of colorization for image sequences by the proposed techniques.
Takahiko Horiuchi, Hiroaki Kotera, "Colorization Algorithm for Monochrome Image Sequences Using Optical Flow" in Proc. IS&T 12th Color and Imaging Conf., 2004, pp 140 - 143, https://doi.org/10.2352/CIC.2004.12.1.art00026