Toward Identity Preserving Face Synthesis Between Sketches and Photos Using Deep Feature Injection

Identity preservation is crucial for the practical application of face sketch and photo synthesis, such as law enforcement and entertainment. However, existing methods mainly focus on generating faces with good visual quality, leading the evaluation of identity preservation is partial and insufficient. Besides, it is difficult to simultaneously synthesize photos and sketches that have good visual quality and identity preservation. In this article, we propose to utilize auxiliary deep features extracted by an off-the-shelf face classifier to inject into the synthesis processes, so that the synthesized faces have more identity information. Furthermore, we propose a light interpolated convolutional neural network that has a shared encoder and two face-specialized decoders to simultaneously complete the transformations between sketches and photos. Evaluations on identity preservation and visual quality show our method is superior to existing methods in synthesizing both sketches and photos, and is qualified in practical application.