Qiu, HaonanWang, ChuanZhu, Hangzhu, xiangyuGu, JinjinHan, XiaoguangLee, Jehee and Theobalt, Christian and Wetzstein, Gordon2019-10-142019-10-1420191467-8659https://doi.org/10.1111/cgf.13847https://diglib.eg.org:443/handle/10.1111/cgf13847Generating plausible hair image given limited guidance, such as sparse sketches or low-resolution image, has been made possible with the rise of Generative Adversarial Networks (GANs). Traditional image-to-image translation networks can generate recognizable results, but finer textures are usually lost and blur artifacts commonly exist. In this paper, we propose a two-phase generative model for high-quality hair image synthesis. The two-phase pipeline first generates a coarse image by an existing image translation model, then applies a re-generating network with self-enhancing capability to the coarse image. The selfenhancing capability is achieved by a proposed differentiable layer, which extracts the structural texture and orientation maps from a hair image. Extensive experiments on two tasks, Sketch2Hair and Hair Super-Resolution, demonstrate that our approach is able to synthesize plausible hair image with finer details, and reaches the state-of-the-art.10.1111/cgf.13847403-412