Unpaired Photo-to-Caricature Translation on Faces in the Wild

TL;DR

This paper introduces a novel unpaired image translation method for converting wild face photos into caricatures, capturing high-level artistic features using a dual discriminator model and perceptual loss, outperforming existing methods.

Contribution

The proposed approach combines dual discriminators and perceptual loss for high-level face caricature translation, addressing challenges of unpaired data and artistic exaggeration.

Findings

Significant improvement over state-of-the-art methods.

Effective translation of wild face photos into caricatures.

Potential for real-world artistic applications.

Abstract

Recently, image-to-image translation has been made much progress owing to the success of conditional Generative Adversarial Networks (cGANs). And some unpaired methods based on cycle consistency loss such as DualGAN, CycleGAN and DiscoGAN are really popular. However, it's still very challenging for translation tasks with the requirement of high-level visual information conversion, such as photo-to-caricature translation that requires satire, exaggeration, lifelikeness and artistry. We present an approach for learning to translate faces in the wild from the source photo domain to the target caricature domain with different styles, which can also be used for other high-level image-to-image translation tasks. In order to capture global structure with local statistics while translation, we design a dual pathway model with one coarse discriminator and one fine discriminator. For generator, we provide one extra perceptual loss in association with adversarial loss and cycle consistency loss to achieve representation learning for two different domains. Also the style can be learned by the auxiliary noise input. Experiments on photo-to-caricature translation of faces in the wild show considerable performance gain of our proposed method over state-of-the-art translation methods as well as its potential real applications.