GGAvatar: Reconstructing Garment-Separated 3D Gaussian Splatting Avatars from Monocular Video

TL;DR

GGAvatar introduces a novel method for reconstructing detailed, garment-separated 3D human avatars from monocular videos, enabling realistic, editable models with superior quality and efficiency compared to existing approaches.

Contribution

This work presents a new monocular video-based approach for decoupled, editable 3D human avatar reconstruction with garment separation, advancing the realism and flexibility of avatar modeling.

Findings

Outperforms existing models in quality and efficiency

Enables realistic clothing editing and disentanglement

Achieves effective garment separation from body in 3D reconstructions

Abstract

Avatar modelling has broad applications in human animation and virtual try-ons. Recent advancements in this field have focused on high-quality and comprehensive human reconstruction but often overlook the separation of clothing from the body. To bridge this gap, this paper introduces GGAvatar (Garment-separated 3D Gaussian Splatting Avatar), which relies on monocular videos. Through advanced parameterized templates and unique phased training, this model effectively achieves decoupled, editable, and realistic reconstruction of clothed humans. Comparative evaluations with other costly models confirm GGAvatar's superior quality and efficiency in modelling both clothed humans and separable garments. The paper also showcases applications in clothing editing, as illustrated in Figure 1, highlighting the model's benefits and the advantages of effective disentanglement. The code is available at https://github.com/J-X-Chen/GGAvatar/.