Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation

TL;DR

This paper introduces a fast, robust, and interactive framework for generating game characters from face photos by predicting facial parameters with a single, efficient neural network, significantly outperforming previous methods in speed and robustness.

Contribution

The paper presents a novel facial parameter translator that enables rapid, one-pass character creation from face images, improving speed and robustness over prior iterative or style transfer methods.

Findings

Achieves 1000x faster creation speed than previous methods.

Demonstrates improved robustness to head-pose variations.

Effective across multiple face verification datasets.

Abstract

With the rapid development of Role-Playing Games (RPGs), players are now allowed to edit the facial appearance of their in-game characters with their preferences rather than using default templates. This paper proposes a game character auto-creation framework that generates in-game characters according to a player's input face photo. Different from the previous methods that are designed based on neural style transfer or monocular 3D face reconstruction, we re-formulate the character auto-creation process in a different point of view: by predicting a large set of physically meaningful facial parameters under a self-supervised learning paradigm. Instead of updating facial parameters iteratively at the input end of the renderer as suggested by previous methods, which are time-consuming, we introduce a facial parameter translator so that the creation can be done efficiently through a single forward propagation from the face embeddings to parameters, with a considerable 1000x computational speedup. Despite its high efficiency, the interactivity is preserved in our method where users are allowed to optionally fine-tune the facial parameters on our creation according to their needs. Our approach also shows better robustness than previous methods, especially for those photos with head-pose variance. Comparison results and ablation analysis on seven public face verification datasets suggest the effectiveness of our method.