SelfieAvatar: Real-time Head Avatar reenactment from a Selfie Video
Wei Liang, Hui Yu, Derui Ding, Rachael E. Jack, Philippe G. Schyns

TL;DR
This paper presents a real-time head avatar reenactment method from a single selfie video, combining 3D morphable models with StyleGAN to produce detailed, high-fidelity avatars with fine textures and background details.
Contribution
It introduces a novel approach integrating 3DMMs with StyleGAN and a detailed reconstruction model for high-quality head avatar reenactment from minimal input.
Findings
Achieves superior head avatar reconstruction with rich textures
Demonstrates effective real-time performance
Outperforms existing methods in detail preservation
Abstract
Head avatar reenactment focuses on creating animatable personal avatars from monocular videos, serving as a foundational element for applications like social signal understanding, gaming, human-machine interaction, and computer vision. Recent advances in 3D Morphable Model (3DMM)-based facial reconstruction methods have achieved remarkable high-fidelity face estimation. However, on the one hand, they struggle to capture the entire head, including non-facial regions and background details in real time, which is an essential aspect for producing realistic, high-fidelity head avatars. On the other hand, recent approaches leveraging generative adversarial networks (GANs) for head avatar generation from videos can achieve high-quality reenactments but encounter limitations in reproducing fine-grained head details, such as wrinkles and hair textures. In addition, existing methods generally…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Face recognition and analysis · Face Recognition and Perception
