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

arXiv: https://arxiv.org/abs/2607.29633 · HTML: https://mlsanity.com/paper/2607.29633/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video](https://mlsanity.com/paper/2201.04127/) (2022)
- [InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.09309/) (2020)
- [SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting](https://mlsanity.com/paper/2403.05087/) (2024)
- [WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild](https://mlsanity.com/paper/2409.12259/) (2024)
- [LISA: Learning Implicit Shape and Appearance of Hands](https://mlsanity.com/paper/2204.01695/) (2022)
- [Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba](https://mlsanity.com/paper/2407.09646/) (2024)
- [LAM: Large Avatar Model for One-shot Animatable Gaussian Head](https://mlsanity.com/paper/2502.17796/) (2025)
- [Hand Avatar: Free-Pose Hand Animation and Rendering from Monocular Video](https://mlsanity.com/paper/2211.12782/) (2022)
- [AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction](https://mlsanity.com/paper/2412.02684/) (2024)
- [Contrastive Representation Learning for Hand Shape Estimation](https://mlsanity.com/paper/2106.04324/) (2021)
- [HARP: Personalized Hand Reconstruction from a Monocular RGB Video](https://mlsanity.com/paper/2212.09530/) (2022)
- [LiveHand: Real-time and Photorealistic Neural Hand Rendering](https://mlsanity.com/paper/2302.07672/) (2023)
- [GUAVA: Generalizable Upper Body 3D Gaussian Avatar](https://mlsanity.com/paper/2505.03351/) (2025)
- [Contextual Attention for Hand Detection in the Wild](https://mlsanity.com/paper/1904.04882/) (2019)
- [Authentic Hand Avatar from a Phone Scan via Universal Hand Model](https://mlsanity.com/paper/2405.07933/) (2024)
- [GST: Precise 3D Human Body from a Single Image with Gaussian Splatting Transformers](https://mlsanity.com/paper/2409.04196/) (2024)
- [SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction](https://mlsanity.com/paper/2510.07723/) (2025)
- [BiTT: Bi-directional Texture Reconstruction of Interacting Two Hands from a Single Image](https://mlsanity.com/paper/2403.08262/) (2024)

## Abstract (arXiv)

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.