ToonifyGB: StyleGAN-based Gaussian Blendshapes for 3D Stylized Head Avatars
This work addresses the need for real-time, animatable stylized head avatars in applications like gaming or virtual reality, but it is incremental as it builds on existing StyleGAN and Gaussian blendshape methods.
The paper tackled the problem of synthesizing diverse stylized 3D head avatars from monocular video by proposing ToonifyGB, a two-stage framework that combines StyleGAN-based stylization with Gaussian blendshapes, resulting in efficient rendering of stylized avatars with arbitrary expressions validated on benchmark datasets like Arcane and Pixar.
The introduction of 3D Gaussian blendshapes has enabled the real-time reconstruction of animatable head avatars from monocular video. Toonify, a StyleGAN-based method, has become widely used for facial image stylization. To extend Toonify for synthesizing diverse stylized 3D head avatars using Gaussian blendshapes, we propose an efficient two-stage framework, ToonifyGB. In Stage 1 (stylized video generation), we adopt an improved StyleGAN to generate the stylized video from the input video frames, which overcomes the limitation of cropping aligned faces at a fixed resolution as preprocessing for normal StyleGAN. This process provides a more stable stylized video, which enables Gaussian blendshapes to better capture the high-frequency details of the video frames, facilitating the synthesis of high-quality animations in the next stage. In Stage 2 (Gaussian blendshapes synthesis), our method learns a stylized neutral head model and a set of expression blendshapes from the generated stylized video. By combining the neutral head model with expression blendshapes, ToonifyGB can efficiently render stylized avatars with arbitrary expressions. We validate the effectiveness of ToonifyGB on benchmark datasets using two representative styles: Arcane and Pixar.