OASIS: Occlusion-aware Single-image Hand Avatar Reconstruction via 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2607.29633v1
• Date: Fri, 31 Jul 2026 17:09:46 GMT
• Title: OASIS: Occlusion-aware Single-image Hand Avatar Reconstruction via 3D Gaussian Splatting
• Abstract summary: Single-image 3D hand avatar reconstruction is fundamentally ill-posed due to limited visual evidence under severe self-occlusion.<n>We present a tailored 3D Gaussian Splatting framework for single-image hand avatar reconstruction.
• Score: 21.50893911212589
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Single-image 3D hand avatar reconstruction is fundamentally ill-posed and particularly challenging due to limited visual evidence under severe self-occlusion and the complex pose-dependent deformation of highly articulated hands. Existing methods predominantly rely on implicit NeRF-style representations, whose volumetric fitting is computationally expensive and often struggles to preserve fine-grained hand details. In this work, we present OASIS, a tailored 3D Gaussian Splatting framework for single-image hand avatar reconstruction. To faithfully encode sparse image-specific appearance cues in single-view reconstruction, we construct geometry-aligned visual evidence tokens by explicitly aligning input image observations with 3D hand geometry and context-adaptively tokenizing the resulting visual evidence. Since severe self-occlusion makes the reliability of image evidence inherently visibility-dependent, we introduce a visibility-conditioned point-image attention to reliably transfer visual evidence to geometric tokens, yielding occlusion-aware Gaussian features for faithful and robust reconstruction. To further capture non-rigid deformation of articulated hands, we introduce a Feature-on-Mesh representation to enable Gaussian deformation to be guided by local surface stretching. Under this framework, we adopt a one-shot adaptation scheme that learns a shared hand prior from multi-identity training data and then fits it to a target image for target-specific reconstruction. Extensive experiments show that OASIS outperforms existing baselines in both visual fidelity and efficiency across challenging poses and in-the-wild scenarios, and further demonstrates strong versatility in downstream applications such as text-to-avatar generation and texture editing.

Related papers

• WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images [22.89871818686434]
  We introduce WildSplat, the first feedforward 3D Gaussian Splatting framework capable of appearance-conditioned novel-view synthesis for unposed in-the-wild images.<n>We show that WildSplat surpasses existing optimization-based and feedforward methods, achieving state-of-the-art performance in in-the-wild novel view synthesis and appearance editing from sparse inputs in a single forward pass.
  arXiv  Detail & Related papers  (2026-07-06T17:29:44Z)
• VEPHand: View-Efficient Photometric Hand Performance Capture at Scale [27.713586141581498]
  This paper presents an end-to-end pipeline for dynamic hand performance capture and registration.<n>Our method achieves state-of-the-art reconstruction fidelity in view-efficient, unmasked scenarios and highly accurate registration.
  arXiv  Detail & Related papers  (2026-06-14T18:47:44Z)
• HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images [81.42866295265443]
  High-fidelity 3D hand geometry is a critical task in computer vision.<n> scalable applications demand both accuracy and deployment flexibility.<n>We propose a feed-forward architecture that infers 3D hand meshes and camera poses from uncalibrated views.
  arXiv  Detail & Related papers  (2026-03-25T06:54:34Z)
• InpaintHuman: Reconstructing Occluded Humans with Multi-Scale UV Mapping and Identity-Preserving Diffusion Inpainting [64.42884719282323]
  InpaintHuman is a novel method for generating high-fidelity, complete, and animatable avatars from occluded monocular videos.<n>Our approach employs direct pixel-level supervision to ensure identity fidelity.
  arXiv  Detail & Related papers  (2026-01-05T13:26:02Z)
• Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand Avatars [47.61442517627826]
  We propose to create animatable avatars for interacting hands with 3D Gaussian Splatting (GS) and single-image inputs. Our proposed method is validated via extensive experiments on the large-scale InterHand2.6M dataset.
  arXiv  Detail & Related papers  (2024-10-11T14:14:51Z)
• DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image [98.29284902879652]
  We present DICE, the first end-to-end method for Deformation-aware hand-face Interaction reCovEry from a single image.<n>It features disentangling the regression of local deformation fields and global mesh locations into two network branches.<n>It achieves state-of-the-art performance on a standard benchmark and in-the-wild data in terms of accuracy and physical plausibility.
  arXiv  Detail & Related papers  (2024-06-26T00:08:29Z)
• DiffFAE: Advancing High-fidelity One-shot Facial Appearance Editing with Space-sensitive Customization and Semantic Preservation [84.0586749616249]
  This paper presents DiffFAE, a one-stage and highly-efficient diffusion-based framework tailored for high-fidelity Facial Appearance Editing. For high-fidelity query attributes transfer, we adopt Space-sensitive Physical Customization (SPC), which ensures the fidelity and generalization ability. In order to preserve source attributes, we introduce the Region-responsive Semantic Composition (RSC) This module is guided to learn decoupled source-regarding features, thereby better preserving the identity and alleviating artifacts from non-facial attributes such as hair, clothes, and background.
  arXiv  Detail & Related papers  (2024-03-26T12:53:10Z)
• SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation [90.59734612754222]
  Estimating 3D hand mesh from RGB images is one of the most challenging problems. Existing attempts towards this task often fail when the occlusion dominates the image space. We propose SiMA-Hand, aiming to boost the mesh reconstruction performance by Single-to-Multi-view Adaptation.
  arXiv  Detail & Related papers  (2024-02-02T13:14:20Z)
• Generalizable One-shot Neural Head Avatar [90.50492165284724]
  We present a method that reconstructs and animates a 3D head avatar from a single-view portrait image. We propose a framework that not only generalizes to unseen identities based on a single-view image, but also captures characteristic details within and beyond the face area.
  arXiv  Detail & Related papers  (2023-06-14T22:33:09Z)

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.