Neutral Face Game Character Auto-Creation via PokerFace-GAN

TL;DR

This paper introduces PokerFace-GAN, a novel neural network approach for automatically creating neutral face game characters from a single photo, effectively disentangling identity and expression parameters for multi-view rendering.

Contribution

The paper presents a differentiable renderer and adversarial training to disentangle facial features, enabling more flexible and accurate neutral face character generation from photos.

Findings

Generates highly similar neutral face characters to input photos.

Effective disentanglement of identity and expression parameters.

Improved multi-view rendering capability.

Abstract

Game character customization is one of the core features of many recent Role-Playing Games (RPGs), where players can edit the appearance of their in-game characters with their preferences. This paper studies the problem of automatically creating in-game characters with a single photo. In recent literature on this topic, neural networks are introduced to make game engine differentiable and the self-supervised learning is used to predict facial customization parameters. However, in previous methods, the expression parameters and facial identity parameters are highly coupled with each other, making it difficult to model the intrinsic facial features of the character. Besides, the neural network based renderer used in previous methods is also difficult to be extended to multi-view rendering cases. In this paper, considering the above problems, we propose a novel method named "PokerFace-GAN" for neutral face game character auto-creation. We first build a differentiable character renderer which is more flexible than the previous methods in multi-view rendering cases. We then take advantage of the adversarial training to effectively disentangle the expression parameters from the identity parameters and thus generate player-preferred neutral face (expression-less) characters. Since all components of our method are differentiable, our method can be easily trained under a multi-task self-supervised learning paradigm. Experiment results show that our method can generate vivid neutral face game characters that are highly similar to the input photos. The effectiveness of our method is verified by comparison results and ablation studies.