ARAH: Animatable Volume Rendering of Articulated Human SDFs

TL;DR

This paper introduces a novel method for creating detailed, animatable clothed human avatars from sparse multi-view RGB videos, addressing geometric detail and pose generalization issues in existing neural radiance field approaches.

Contribution

It combines articulated implicit surface modeling with a new joint root-finding algorithm to improve geometry detail and pose generalization in avatar creation.

Findings

Achieves state-of-the-art geometry and appearance reconstruction.

Generates high-quality, pose-dependent avatars from limited views.

Generalizes well to unseen poses beyond training data.

Abstract

Combining human body models with differentiable rendering has recently enabled animatable avatars of clothed humans from sparse sets of multi-view RGB videos. While state-of-the-art approaches achieve realistic appearance with neural radiance fields (NeRF), the inferred geometry often lacks detail due to missing geometric constraints. Further, animating avatars in out-of-distribution poses is not yet possible because the mapping from observation space to canonical space does not generalize faithfully to unseen poses. In this work, we address these shortcomings and propose a model to create animatable clothed human avatars with detailed geometry that generalize well to out-of-distribution poses. To achieve detailed geometry, we combine an articulated implicit surface representation with volume rendering. For generalization, we propose a novel joint root-finding algorithm for simultaneous ray-surface intersection search and correspondence search. Our algorithm enables efficient point sampling and accurate point canonicalization while generalizing well to unseen poses. We demonstrate that our proposed pipeline can generate clothed avatars with high-quality pose-dependent geometry and appearance from a sparse set of multi-view RGB videos. Our method achieves state-of-the-art performance on geometry and appearance reconstruction while creating animatable avatars that generalize well to out-of-distribution poses beyond the small number of training poses.