LAUSR

Face portrait line drawing is a unique style of art which is highly abstract and expressive. However, due to its high semantic constraints, many existing methods learn to generate portrait drawings using paired training data. In this paper, we propose a novel method to automatically transform face photos to portrait drawings using unpaired training data. Our method can (1) learn to generate high quality portrait drawings in multiple styles using a single network and (2) generate portrait drawings in a '`new style'' unseen in the training data. We observe that existing unpaired translation methods (such as CycleGAN) tend to embed invisible reconstruction information indiscriminately in the whole drawings due to significant information imbalance between the photo and portrait drawing domains, which leads to important facial features missing. To address this problem, we propose a novel asymmetric cycle mapping that enforces the reconstruction information to be visible and only embedded in selective facial regions. Along with localized discriminators for important facial regions, our method well preserves all important facial features. Generator dissection further explains that our model learns to incorporate face semantic information during drawing generation. Extensive experiments including a user study show that our model outperforms state-of-the-art methods.