LayerGS: Decomposition and Inpainting of Layered 3D Human Avatars via 2D Gaussian Splatting

• URL: http://arxiv.org/abs/2601.05853v1
• Date: Fri, 09 Jan 2026 15:30:12 GMT
• Title: LayerGS: Decomposition and Inpainting of Layered 3D Human Avatars via 2D Gaussian Splatting
• Authors: Yinghan Xu, John Dingliana,
• Abstract summary: We propose a novel framework for decomposing arbitrarily posed humans into animatable multi-layered 3D human avatars.<n>Our approach achieves better rendering quality and layer decomposition and recomposition than the previous state-of-the-art.
• Score: 0.7176107039687231
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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. Our code is available at https://github.com/RockyXu66/LayerGS

Related papers

• PFAvatar: Pose-Fusion 3D Personalized Avatar Reconstruction from Real-World Outfit-of-the-Day Photos [24.8968050268664]
  PFAvatar is a new method that reconstructs high-quality 3D avatars from Outfit of the Day (OOTD) photos.<n>Our method completes personalization in just 5 minutes, achieving a 48x speed-up compared to previous approaches.
  arXiv  Detail & Related papers  (2025-11-17T03:40:43Z)
• ReMu: Reconstructing Multi-layer 3D Clothed Human from Image Layers [3.046315755726937]
  We introduce ReMu for reconstructing multi-layer clothed humans in a new setup, Image Layers.<n>We first reconstruct and align each garment layer in a shared coordinate system defined by the canonical body pose.<n>It is worth noting that our method is template-free and category-agnostic, which enables the reconstruction of 3D garments in diverse clothing styles.
  arXiv  Detail & Related papers  (2025-08-02T14:24:47Z)
• AdaHuman: Animatable Detailed 3D Human Generation with Compositional Multiview Diffusion [56.12859795754579]
  AdaHuman is a novel framework that generates high-fidelity animatable 3D avatars from a single in-the-wild image.<n>AdaHuman incorporates two key innovations: a pose-conditioned 3D joint diffusion model and a compositional 3DGS refinement module.
  arXiv  Detail & Related papers  (2025-05-30T17:59:54Z)
• Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance [69.9745497000557]
  We introduce Arc2Avatar, the first SDS-based method utilizing a human face foundation model as guidance with just a single image as input.<n>Our avatars maintain a dense correspondence with a human face mesh template, allowing blendshape-based expression generation.
  arXiv  Detail & Related papers  (2025-01-09T17:04:33Z)
• 3D$^2$-Actor: Learning Pose-Conditioned 3D-Aware Denoiser for Realistic Gaussian Avatar Modeling [37.11454674584874]
  We introduce 3D$2$-Actor, a pose-conditioned 3D-aware human modeling pipeline that integrates 2D denoising and 3D rectifying steps.<n> Experimental results demonstrate that 3D$2$-Actor excels in high-fidelity avatar modeling and robustly generalizes to novel poses.
  arXiv  Detail & Related papers  (2024-12-16T09:37:52Z)
• DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses [57.17501809717155]
  We present DreamDance, a novel method for animating human images using only skeleton pose sequences as conditional inputs.<n>Our key insight is that human images naturally exhibit multiple levels of correlation.<n>We construct the TikTok-Dance5K dataset, comprising 5K high-quality dance videos with detailed frame annotations.
  arXiv  Detail & Related papers  (2024-11-30T08:42:13Z)
• FAMOUS: High-Fidelity Monocular 3D Human Digitization Using View Synthesis [51.193297565630886]
  The challenge of accurately inferring texture remains, particularly in obscured areas such as the back of a person in frontal-view images. This limitation in texture prediction largely stems from the scarcity of large-scale and diverse 3D datasets. We propose leveraging extensive 2D fashion datasets to enhance both texture and shape prediction in 3D human digitization.
  arXiv  Detail & Related papers  (2024-10-13T01:25:05Z)
• GALA: Generating Animatable Layered Assets from a Single Scan [20.310367593475508]
  We present GALA, a framework that takes as input a single-layer clothed 3D human mesh and decomposes it into complete multi-layered 3D assets. The outputs can then be combined with other assets to create novel clothed human avatars with any pose.
  arXiv  Detail & Related papers  (2024-01-23T18:59:59Z)
• GETAvatar: Generative Textured Meshes for Animatable Human Avatars [69.56959932421057]
  We study the problem of 3D-aware full-body human generation, aiming at creating animatable human avatars with high-quality geometries and textures. We propose GETAvatar, a Generative model that directly generates Explicit Textured 3D rendering for animatable human Avatar.
  arXiv  Detail & Related papers  (2023-10-04T10:30:24Z)
• AG3D: Learning to Generate 3D Avatars from 2D Image Collections [96.28021214088746]
  We propose a new adversarial generative model of realistic 3D people from 2D images. Our method captures shape and deformation of the body and loose clothing by adopting a holistic 3D generator. We experimentally find that our method outperforms previous 3D- and articulation-aware methods in terms of geometry and appearance.
  arXiv  Detail & Related papers  (2023-05-03T17:56:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.