High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks

Synthesizing face sketches from real photos and its inverse are well studied problems and they have many applications in digital forensics and entertainment. However, photo/sketch synthesis remains a challenging problem due to the fact that photo and sketch have different characteristics. In this work, we consider this task as an image-to-image translation problem and explore the recently popular generative models (GANs) to generate high-quality realistic photos from sketches and sketches from photos. Recent methods such as Pix2Pix, CycleGAN and DualGAN have shown promising results on imageto-image translation problems and photo-to-sketch synthesis in particular, however, they are known to have limited abilities in generating high-resolution realistic images. To this end, we propose a novel synthesis framework called Photo-Sketch Synthesis using Multi-Adversarial Networks, (PS2-MAN) that iteratively generates low resolution to high resolution images in an adversarial way. The hidden layers of the generator are supervised to first generate lower resolution images followed by implicit refinement in the network to generate higher resolution images. Furthermore, since photo-sketch synthesis is a coupled/paired translation problem where photo-sketch and sketch-photo are equally important, we leverage the pair information in the CycleGAN framework. Evaluation of the proposed method is performed on two datasets: CUHK and CUFSF. Both Image Quality Assessment (IQA) and PhotoSketch Matching experiments are conducted to demonstrate the superior performance of our framework in comparison to existing state-of-the-art solutions. Additionally, ablation studies are conducted to verify the effectiveness iterative synthesis and various loss functions.