Face Cartoonisation For Various Poses Using StyleGAN

TL;DR

This paper introduces a novel face cartoonisation method that uses StyleGAN's latent space and an encoder to preserve identity across various poses without requiring retraining of StyleGAN.

Contribution

It presents a new approach leveraging an encoder with pre-trained StyleGAN to achieve pose-invariant face cartoonisation, avoiding dataset and pose training challenges.

Findings

Effective preservation of identity in cartoonised faces across poses

Utilizes pre-trained StyleGAN without fine-tuning for cartoonisation

Extensive experiments demonstrate improved quality and pose robustness

Abstract

This paper presents an innovative approach to achieve face cartoonisation while preserving the original identity and accommodating various poses. Unlike previous methods in this field that relied on conditional-GANs, which posed challenges related to dataset requirements and pose training, our approach leverages the expressive latent space of StyleGAN. We achieve this by introducing an encoder that captures both pose and identity information from images and generates a corresponding embedding within the StyleGAN latent space. By subsequently passing this embedding through a pre-trained generator, we obtain the desired cartoonised output. While many other approaches based on StyleGAN necessitate a dedicated and fine-tuned StyleGAN model, our method stands out by utilizing an already-trained StyleGAN designed to produce realistic facial images. We show by extensive experimentation how our encoder adapts the StyleGAN output to better preserve identity when the objective is cartoonisation.