Towards Practical Capture of High-Fidelity Relightable Avatars
This work addresses the challenge of creating practical and efficient relightable avatars for applications in virtual reality, gaming, and film, representing a novel method for a known bottleneck.
The paper tackles the problem of capturing and reconstructing high-fidelity 3D avatars by proposing TRAvatar, a framework that enables realistic relighting and real-time animation without needing accurate surface tracking, achieving superior performance in photorealistic avatar animation and relighting.
In this paper, we propose a novel framework, Tracking-free Relightable Avatar (TRAvatar), for capturing and reconstructing high-fidelity 3D avatars. Compared to previous methods, TRAvatar works in a more practical and efficient setting. Specifically, TRAvatar is trained with dynamic image sequences captured in a Light Stage under varying lighting conditions, enabling realistic relighting and real-time animation for avatars in diverse scenes. Additionally, TRAvatar allows for tracking-free avatar capture and obviates the need for accurate surface tracking under varying illumination conditions. Our contributions are two-fold: First, we propose a novel network architecture that explicitly builds on and ensures the satisfaction of the linear nature of lighting. Trained on simple group light captures, TRAvatar can predict the appearance in real-time with a single forward pass, achieving high-quality relighting effects under illuminations of arbitrary environment maps. Second, we jointly optimize the facial geometry and relightable appearance from scratch based on image sequences, where the tracking is implicitly learned. This tracking-free approach brings robustness for establishing temporal correspondences between frames under different lighting conditions. Extensive qualitative and quantitative experiments demonstrate that our framework achieves superior performance for photorealistic avatar animation and relighting.