Abstract

This paper proposes a simple yet effective face sketch synthesis method. Similar to existing exemplar-based methods, a training dataset contain- ing photo-sketch pairs is required, and a K -NN photo patch search is performed between a test photo and every training exemplar for sketch patch selection. In- stead of using the Markov Random Field to optimize global sketch patch selec- tion, this paper formulates face sketch synthesis as an image denoising problem which can be solved efficiently using the proposed method. Real-time perfor- mance can be obtained on a state-of-the-art GPU. Meanwhile quantitative evalu- ations on face sketch recognition and user study demonstrate the effectiveness of the proposed method. In addition, the proposed method can be directly extended to the temporal domain for consistent video sketch synthesis, which is of great importance in digital entertainment.