Relightable and Animatable Neural Avatar from Sparse-View Video

TL;DR

This paper introduces a novel method for creating relightable and animatable neural avatars from sparse-view or monocular videos, using a hierarchical distance query algorithm to efficiently approximate surface distances for dynamic humans under unknown lighting.

Contribution

It proposes the first system capable of recovering relightable and animatable neural avatars from sparse or monocular videos, leveraging a hierarchical distance query for efficient inverse rendering.

Findings

Outperforms state-of-the-art methods in relighting and animation quality

Successfully reconstructs dynamic human avatars from minimal viewpoints

Efficiently estimates surface and lighting for realistic rendering

Abstract

This paper tackles the challenge of creating relightable and animatable neural avatars from sparse-view (or even monocular) videos of dynamic humans under unknown illumination. Compared to studio environments, this setting is more practical and accessible but poses an extremely challenging ill-posed problem. Previous neural human reconstruction methods are able to reconstruct animatable avatars from sparse views using deformed Signed Distance Fields (SDF) but cannot recover material parameters for relighting. While differentiable inverse rendering-based methods have succeeded in material recovery of static objects, it is not straightforward to extend them to dynamic humans as it is computationally intensive to compute pixel-surface intersection and light visibility on deformed SDFs for inverse rendering. To solve this challenge, we propose a Hierarchical Distance Query (HDQ) algorithm to approximate the world space distances under arbitrary human poses. Specifically, we estimate coarse distances based on a parametric human model and compute fine distances by exploiting the local deformation invariance of SDF. Based on the HDQ algorithm, we leverage sphere tracing to efficiently estimate the surface intersection and light visibility. This allows us to develop the first system to recover animatable and relightable neural avatars from sparse view (or monocular) inputs. Experiments demonstrate that our approach is able to produce superior results compared to state-of-the-art methods. Our code will be released for reproducibility.