MW-GAN: Multi-Warping GAN for Caricature Generation with Multi-Style Geometric Exaggeration
This addresses the challenge of creating diverse and identity-preserving caricatures for applications in entertainment or art, but it is incremental as it builds on prior GAN-based approaches.
The paper tackles the problem of generating caricatures from face photos by simultaneously transferring style and exaggerating shape while preserving identity, proposing MW-GAN which achieves better quality than existing methods.
Given an input face photo, the goal of caricature generation is to produce stylized, exaggerated caricatures that share the same identity as the photo. It requires simultaneous style transfer and shape exaggeration with rich diversity, and meanwhile preserving the identity of the input. To address this challenging problem, we propose a novel framework called Multi-Warping GAN (MW-GAN), including a style network and a geometric network that are designed to conduct style transfer and geometric exaggeration respectively. We bridge the gap between the style and landmarks of an image with corresponding latent code spaces by a dual way design, so as to generate caricatures with arbitrary styles and geometric exaggeration, which can be specified either through random sampling of latent code or from a given caricature sample. Besides, we apply identity preserving loss to both image space and landmark space, leading to a great improvement in quality of generated caricatures. Experiments show that caricatures generated by MW-GAN have better quality than existing methods.