WarpGAN: Automatic Caricature Generation

TL;DR

WarpGAN is an automatic neural network that generates diverse, identity-preserving caricatures from face photos, allowing style and exaggeration control, and producing results comparable to hand-drawn caricatures.

Contribution

It introduces WarpGAN, a novel network that automatically predicts control points for warping faces into caricatures while maintaining identity and enabling customization.

Findings

Capable of generating diverse caricatures

Preserves identity effectively

Produces caricatures similar to hand-drawn ones

Abstract

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.