GGAvatar: Reconstructing Garment-Separated 3D Gaussian Splatting Avatars from Monocular Video
This addresses the need for detailed, editable avatars in applications like human animation and virtual try-ons, offering an incremental improvement by focusing on garment separation.
The paper tackles the problem of reconstructing clothed human avatars from monocular video by separating garments from the body, achieving decoupled, editable, and realistic results with superior quality and efficiency compared to other models.
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/.