WarpGAN: Automatic Caricature Generation
This work addresses the need for efficient and customizable caricature creation for artists and users, though it is incremental as it builds on existing GAN-based image generation methods.
The authors tackled the problem of automatic caricature generation from face photos by proposing WarpGAN, which learns to predict control points for warping and transfers texture styles while preserving identity, resulting in caricatures that experts rated as visually similar to hand-drawn ones with exaggerated prominent features.
We propose, WarpGAN, a fully automatic network that can generate caricatures given an input face photo. Besides transferring rich texture styles, WarpGAN learns to automatically predict a set of control points that can warp the photo into a caricature, while preserving identity. We introduce an identity-preserving adversarial loss that aids the discriminator to distinguish between different subjects. Moreover, WarpGAN allows customization of the generated caricatures by controlling the exaggeration extent and the visual styles. Experimental results on a public domain dataset, WebCaricature, show that WarpGAN is capable of generating a diverse set of caricatures while preserving the identities. Five caricature experts suggest that caricatures generated by WarpGAN are visually similar to hand-drawn ones and only prominent facial features are exaggerated.