High-Quality Face Sketch Synthesis via Geometric Normalization and Regularization

Xiang Li, Fei Gao, Fei Huang

Abstract: In this work, we propose a novel Generative Adversarial Network for generating a structure-consistent and texture-realistic sketch, conditioned on a face photo. To this end, we propose to boost the capacity of the generator via geometric normalization and regularization. Specially, we first propose an enhanced spatially-adaptive normalization module to modulate the activation, based on the semantic layout and encoding features of the input face. Besides, we use two regularization loss functions to minimize the structural divergence between a generated sketch and the corresponding face photo. Experimental results show that our proposed techniques significantly improve the quality of synthesized sketches, in terms of both structure and texture. Besides, our full model can generate high-quality sketches and significantly outperform previous state-of-the-arts, over a wide range of challenging data. We have made our code and results publicly available: http://aiart.live/genre/.