Image-based facial sketch-to-photo synthesis via online coupled dictionary learning

Image-based sketch-to-photo synthesis has received intense attention in recent years because of its potential applications in digital entertainment and law enforcement. In order to achieve successful hallucinating synthesis of a realistic face photo, a coupled dictionary is first learned from a set of training photo-sketch pairs for modeling the relationship between patches from sketches and photos. Then, a series of overlapped photo patches can be synthesized on the basis of the learned coupled dictionary. Afterwards, these overlapped photo patches are further selected by the proposed global energy minimization framework based on a Markov network. Finally, a multi-band blending process is carried out to synthesize a realistic face photo. The experimental results convincingly validate the effectiveness of the proposed approach in comparison with the existing techniques.