Relightable and Animatable Neural Avatars from Videos

TL;DR

This paper introduces a novel method for creating relightable and animatable 3D neural avatars from sparse videos, effectively disentangling geometry, material, and lighting to produce photorealistic human images under new viewpoints, poses, and lighting conditions.

Contribution

It presents innovative techniques including an invertible deformation field and a pose-aware light visibility network to improve geometry quality and shadow modeling in neural avatars.

Findings

High-quality geometry reconstruction demonstrated

Realistic shadow generation under various poses

Effective disentanglement of geometry, material, and lighting

Abstract

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/}.