A Multi-Scale Conditional Generative Adversarial Network for Face Sketch Synthesis

We investigate conditional generative adversarial network (cGAN) as a solution to realize the face-to-sketch translation problems. These networks not only learn the mapping relationships between the face and responding sketch, but also generate a loss function to train the mapping relationships automatically. This makes it possible to regard the transformation problems as minimizing the loss function. In previous works, cGAN employs a single scale to resolve the above problems and lacks multi-scale information. In this work, considering that image multi-scale representation can capture image texture, structure and other important features more effectively, and we construct a three-layer pyramid model to obtain multi-scale information, and employ the proposed multiscale cGAN to train the mapping relationships. With respects to four metrics, our method outperforms previous models.