Inverse Halftone Colorization: Making Halftone Prints Color Photos

We propose to tackle the joint problem of inverse halftone and colorization in this paper, where the former generates continuous-tone images from halftone prints while the latter translates gray-scale images into colorful pictures. Such joint problem is named as Inverse Halftone Colorization, which tries to recover colorful images from black and white halftone prints. Although the inverse halftone colorization seems to be achievable via applying inverse halftone followed by colorization, our proposed method advances from two perspectives: (1) we empirically discover that the orders of cascading inverse halftone and colorization (i.e first inverse halftone then colorization versus the reverse order) would lead to results with different properties, hence a fusion scheme is proposed to integrate the results produced by these two orders of cascade; (2) we introduce several novel losses to encourage the realness, diversity, and the structural coherence of the colorization. Moreover, our model is flexible to support both exemplar-based and random colorization. Extensive experiments not only demonstrate the efficacy of our method on inverse halftone colorization, but also well verify the contributions of our design choices.