Examplar-Based Face Colorization Using Image Morphing

Colorization of gray-scale images relies on prior color information. Examplar-based methods use a color image as source of such information. Then the colors of the source image are transferred to the gray-scale image. In the literature, this transfer is mainly guided by texture descriptors. Face images usually contain few texture so that the common approaches frequently fail. In this paper we propose a new method based on image morphing. This technique is able to compute a correspondence map between images with similar shapes. It is based on the geometric structure of the images rather than textures which is more reliable for faces. Our numerical experiments show that our morphing based approach clearly outperforms state-of-the-art methods.
Comment: 13 pages, 6 figures, preprint