Natural Image Colorization

In this paper, we present an interactive system for users to easily colorize the natural images of complex scenes. In our system, colorization procedure is explicitly separated into two stages: Color labeling and Color mapping. Pixels that should roughly share similar colors are grouped into coherent regions in the color labeling stage, and the color mapping stage is then introduced to further fine-tune the colors in each coherent region. To handle textures commonly seen in natural images, we propose a new color labeling scheme that groups not only neighboring pixels with similar intensity but also remote pixels with similar texture. Motivated by the insight into the complementary nature possessed by the highly contrastive locations and the smooth locations, we employ a smoothness map to guide the incorporation of intensity-continuity and texture-similarity constraints in the design of our labeling algorithm. Within each coherent region obtained from the color labeling stage, the color mapping is applied to generate vivid colorization effect by assigning colors to a few pixels in the region. A set of intuitive interface tools is designed for labeling, coloring and modifying the result. We demonstrate compelling results of colorizing natural images using our system, with only a modest amount of user input.