Relightable and Animatable Neural Avatars from Videos
This enables lightweight creation of realistic human avatars for applications like VR/AR and entertainment, representing a strong specific gain in a domain-specific area.
The paper tackles the problem of creating 3D digital avatars from sparse videos under unknown illumination, achieving relightable and animatable neural avatars that synthesize photorealistic images under novel viewpoints, poses, and lighting, with results showing high-quality geometry and realistic shadows in experiments.
Lightweight creation of 3D digital avatars is a highly desirable but challenging task. With only sparse videos of a person under unknown illumination, we propose a method to create relightable and animatable neural avatars, which can be used to synthesize photorealistic images of humans under novel viewpoints, body poses, and lighting. The key challenge here is to disentangle the geometry, material of the clothed body, and lighting, which becomes more difficult due to the complex geometry and shadow changes caused by body motions. To solve this ill-posed problem, we propose novel techniques to better model the geometry and shadow changes. For geometry change modeling, we propose an invertible deformation field, which helps to solve the inverse skinning problem and leads to better geometry quality. To model the spatial and temporal varying shading cues, we propose a pose-aware part-wise light visibility network to estimate light occlusion. Extensive experiments on synthetic and real datasets show that our approach reconstructs high-quality geometry and generates realistic shadows under different body poses. Code and data are available at \url{https://wenbin-lin.github.io/RelightableAvatar-page/}.