ARS-Avatar: Animatable and Relightable Surfel Avatars with Learnable Ambient Occlusion

2026-09-23

AI Summary

本文提出ARS-Avatar方法，通过surfels表示从多视角图像生成高质量可动画和可重照明的人体虚拟形象，解决了姿态依赖变形、材质与光照可见性耦合的问题。

Abstract

Creating animatable and relightable human avatars from multi-view images remains challenging, as pose-dependent deformation, materials, and light visibility are intrinsically coupled in images. In this paper, we present ARS-Avatar, a novel method using surfel representation for high-quality, animatable, and relightable human avatars from multi-view images captured under unknown illumination. We first extract deformation priors from the template mesh and leverage as additional details beyond driving poses to facilitate faithful estimation of surfel attributes and reconstruction of animatable avatar. To support relighting, the deferred shading is employed to estimate BRDF materials. We further introduce a differentiable screen-space ambient occlusion formulation that enables gradient-based optimization of body-part specific occlusion radii through finite differences, providing an efficient approximation of light visibility that can be jointly optimized with the avatar. Extensive experiments demonstrate that ARS-Avatar achieves high-fidelity appearance reconstruction and physically-based material estimation, while enabling realistic animation and relighting under novel poses and illuminations.

Problem

• animatable avatars
• relightable avatars
• multi-view images
• pose-dependent deformation
• light visibility

Innovation

• surfel representation
• learnable ambient occlusion
• deferred shading
• deformation priors