GUAVA: Generalizable Upper Body 3D Gaussian Avatar

TL;DR

GUAVA is a novel framework that reconstructs high-quality, animatable 3D upper-body avatars from a single image quickly, surpassing previous methods in speed and quality, and enabling real-time animation.

Contribution

It introduces an expressive human model and a fast reconstruction framework for animatable upper-body 3D Gaussian avatars from a single image, with significant speed and quality improvements.

Findings

Reconstruction time is reduced to 0.1 seconds.

Outperforms previous methods in rendering quality.

Supports real-time animation and rendering.

Abstract

Reconstructing a high-quality, animatable 3D human avatar with expressive facial and hand motions from a single image has gained significant attention due to its broad application potential. 3D human avatar reconstruction typically requires multi-view or monocular videos and training on individual IDs, which is both complex and time-consuming. Furthermore, limited by SMPLX's expressiveness, these methods often focus on body motion but struggle with facial expressions. To address these challenges, we first introduce an expressive human model (EHM) to enhance facial expression capabilities and develop an accurate tracking method. Based on this template model, we propose GUAVA, the first framework for fast animatable upper-body 3D Gaussian avatar reconstruction. We leverage inverse texture mapping and projection sampling techniques to infer Ubody (upper-body) Gaussians from a single image. The rendered images are refined through a neural refiner. Experimental results demonstrate that GUAVA significantly outperforms previous methods in rendering quality and offers significant speed improvements, with reconstruction times in the sub-second range (0.1s), and supports real-time animation and rendering.