Abstract
We propose a novel framework for decomposing arbitrarily posed humans into animatable multi-layered 3D human avatars, separating the body and garments. Conventional single-layer reconstruction methods lock clothing to one identity, while prior multi-layer approaches struggle with occluded regions. We overcome both limitations by encoding each layer as a set of 2D Gaussians for accurate geometry and photorealistic rendering, and inpainting hidden regions with a pretrained 2D diffusion model via score-distillation sampling (SDS). Our three-stage training strategy first reconstructs the coarse canonical garment via single-layer reconstruction, followed by multi-layer training to jointly recover the inner-layer body and outer-layer garment details. Experiments on two 3D human benchmark datasets (4D-Dress, Thuman2.0) show that our approach achieves better rendering quality and layer decomposition and recomposition than the previous state-of-the-art, enabling realistic virtual try-on under novel viewpoints and poses, and advancing practical creation of high-fidelity 3D human assets for immersive applications.
Decomposition Results
From left to right: Recomposed inner layer and outer layer, decomposed inner layer, and decomposed outer layer.
Qualitative Comparisons
Comparison between GALA and our method: The top row shows results from GALA trained with a 3D scan, and the bottom row from our approach, which does not require a 3D scan.
Comparison between VTON360 and our method
Custom Monocular Video Decomposition
Virtual Try-On
Video Presentation
BibTeX
@misc{xu2026layergsdecompositioninpaintinglayered,
title={LayerGS: Decomposition and Inpainting of Layered 3D Human Avatars via 2D Gaussian Splatting},
author={Yinghan Xu and John Dingliana},
year={2026},
eprint={2601.05853},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2601.05853},
}