Landmark Assisted CycleGAN for Cartoon Face Generation

TL;DR

This paper introduces a landmark assisted CycleGAN that leverages face landmarks to improve the quality and structural accuracy of cartoon face generation from real face images using unpaired data.

Contribution

It proposes a novel landmark guided training method for CycleGAN, enhancing structural consistency and quality in cartoon face synthesis from unpaired datasets.

Findings

Produces high-quality cartoon faces indistinguishable from artist-drawn images.

Significantly improves over previous state-of-the-art methods.

Ensures structural facial features are preserved in generated cartoons.

Abstract

In this paper, we are interested in generating an cartoon face of a person by using unpaired training data between real faces and cartoon ones. A major challenge of this task is that the structures of real and cartoon faces are in two different domains, whose appearance differs greatly from each other. Without explicit correspondence, it is difficult to generate a high quality cartoon face that captures the essential facial features of a person. In order to solve this problem, we propose landmark assisted CycleGAN, which utilizes face landmarks to define landmark consistency loss and to guide the training of local discriminator in CycleGAN. To enforce structural consistency in landmarks, we utilize the conditional generator and discriminator. Our approach is capable to generate high-quality cartoon faces even indistinguishable from those drawn by artists and largely improves state-of-the-art.