Facial Synthesis from Visual Attributes via Sketch using Multi-Scale Generators
This work addresses face synthesis for applications in law enforcement and entertainment, but it is incremental as it builds on existing GAN-based approaches with a stage-wise formulation.
The paper tackles the problem of synthesizing faces from visual attributes by proposing a two-stage method that first generates a facial sketch from attributes and then synthesizes the face image from the sketch, achieving competitive results as verified through extensive experiments.
Automatic synthesis of faces from visual attributes is an important problem in computer vision and has wide applications in law enforcement and entertainment. With the advent of deep generative convolutional neural networks (CNNs), attempts have been made to synthesize face images from attributes and text descriptions. In this paper, we take a different approach, where we formulate the original problem as a stage-wise learning problem. We first synthesize the facial sketch corresponding to the visual attributes and then we generate the face image based on the synthesized sketch. The proposed framework, is based on a combination of two different Generative Adversarial Networks (GANs) - (1) a sketch generator network which synthesizes realistic sketch from the input attributes, and (2) a face generator network which synthesizes facial images from the synthesized sketch images with the help of facial attributes. Extensive experiments and comparison with recent methods are performed to verify the effectiveness of the proposed attribute-based two-stage face synthesis method.