SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines

TL;DR

SwiftAvatar is a novel framework that efficiently auto-creates parameterized stylized characters by synthesizing paired realistic face and avatar data using dual-domain generators and training a lightweight estimator, outperforming previous methods.

Contribution

It introduces dual-domain generators and semantic augmentation to generate high-quality paired data, enabling efficient avatar auto-creation across different engines.

Findings

Outperforms previous avatar vector estimation methods.

Generates high-quality paired data for training.

Demonstrates effectiveness and flexibility in experiments.

Abstract

The creation of a parameterized stylized character involves careful selection of numerous parameters, also known as the "avatar vectors" that can be interpreted by the avatar engine. Existing unsupervised avatar vector estimation methods that auto-create avatars for users, however, often fail to work because of the domain gap between realistic faces and stylized avatar images. To this end, we propose SwiftAvatar, a novel avatar auto-creation framework that is evidently superior to previous works. SwiftAvatar introduces dual-domain generators to create pairs of realistic faces and avatar images using shared latent codes. The latent codes can then be bridged with the avatar vectors as pairs, by performing GAN inversion on the avatar images rendered from the engine using avatar vectors. Through this way, we are able to synthesize paired data in high-quality as many as possible, consisting of avatar vectors and their corresponding realistic faces. We also propose semantic augmentation to improve the diversity of synthesis. Finally, a light-weight avatar vector estimator is trained on the synthetic pairs to implement efficient auto-creation. Our experiments demonstrate the effectiveness and efficiency of SwiftAvatar on two different avatar engines. The superiority and advantageous flexibility of SwiftAvatar are also verified in both subjective and objective evaluations.