Expressive Whole-Body 3D Gaussian Avatar

TL;DR

This paper introduces ExAvatar, an expressive 3D human avatar combining SMPL-X and 3D Gaussian Splatting, capable of animating novel facial expressions and poses from short monocular videos despite limited data diversity.

Contribution

The work presents a hybrid mesh and 3D Gaussian representation enabling expressive, animatable avatars with reduced artifacts, addressing data limitations in facial expressions and poses.

Findings

Successfully animates novel facial expressions and poses.

Reduces artifacts in unseen expressions and poses.

Achieves expressive 3D avatars from minimal video data.

Abstract

Facial expression and hand motions are necessary to express our emotions and interact with the world. Nevertheless, most of the 3D human avatars modeled from a casually captured video only support body motions without facial expressions and hand motions.In this work, we present ExAvatar, an expressive whole-body 3D human avatar learned from a short monocular video. We design ExAvatar as a combination of the whole-body parametric mesh model (SMPL-X) and 3D Gaussian Splatting (3DGS). The main challenges are 1) a limited diversity of facial expressions and poses in the video and 2) the absence of 3D observations, such as 3D scans and RGBD images. The limited diversity in the video makes animations with novel facial expressions and poses non-trivial. In addition, the absence of 3D observations could cause significant ambiguity in human parts that are not observed in the video, which can result in noticeable artifacts under novel motions. To address them, we introduce our hybrid representation of the mesh and 3D Gaussians. Our hybrid representation treats each 3D Gaussian as a vertex on the surface with pre-defined connectivity information (i.e., triangle faces) between them following the mesh topology of SMPL-X. It makes our ExAvatar animatable with novel facial expressions by driven by the facial expression space of SMPL-X. In addition, by using connectivity-based regularizers, we significantly reduce artifacts in novel facial expressions and poses.