Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.18912 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914409286205440 |
|---|---|
| author | Aboukhadra, Ahmed Tawfik Rogge, Marcel Robertini, Nadia Arafa, Abdalla Malik, Jameel Elhayek, Ahmed Stricker, Didier |
| author_facet | Aboukhadra, Ahmed Tawfik Rogge, Marcel Robertini, Nadia Arafa, Abdalla Malik, Jameel Elhayek, Ahmed Stricker, Didier |
| contents | Understanding realistic hand-object interactions from monocular RGB videos is essential for AR/VR, robotics, and embodied AI. Existing methods rely on category-specific templates or heavy computation, yet still produce physically inconsistent hand-object alignment in 3D. We introduce GHOST (Gaussian Hand-Object Splatting), a fast, category-agnostic framework for reconstructing dynamic hand-object interactions using 2D Gaussian Splatting. GHOST represents both hands and objects as dense, view-consistent Gaussian discs and introduces three key innovations: (1) a geometric-prior retrieval and consistency loss that completes occluded object regions, (2) a grasp-aware alignment that refines hand translations and object scale to ensure realistic contact, and (3) a hand-aware background loss that prevents penalizing hand-occluded object regions. GHOST achieves complete, physically consistent, and animatable reconstructions from a single RGB video while running an order of magnitude faster than prior category-agnostic methods. Extensive experiments on ARCTIC, HO3D, and in-the-wild datasets demonstrate state-of-the-art accuracy in 3D reconstruction and 2D rendering quality, establishing GHOST as an efficient and robust solution for realistic hand-object interaction modeling. Code is available at https://github.com/ATAboukhadra/GHOST. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_18912 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GHOST: Fast Category-agnostic Hand-Object Interaction Reconstruction from RGB Videos using Gaussian Splatting Aboukhadra, Ahmed Tawfik Rogge, Marcel Robertini, Nadia Arafa, Abdalla Malik, Jameel Elhayek, Ahmed Stricker, Didier Computer Vision and Pattern Recognition Understanding realistic hand-object interactions from monocular RGB videos is essential for AR/VR, robotics, and embodied AI. Existing methods rely on category-specific templates or heavy computation, yet still produce physically inconsistent hand-object alignment in 3D. We introduce GHOST (Gaussian Hand-Object Splatting), a fast, category-agnostic framework for reconstructing dynamic hand-object interactions using 2D Gaussian Splatting. GHOST represents both hands and objects as dense, view-consistent Gaussian discs and introduces three key innovations: (1) a geometric-prior retrieval and consistency loss that completes occluded object regions, (2) a grasp-aware alignment that refines hand translations and object scale to ensure realistic contact, and (3) a hand-aware background loss that prevents penalizing hand-occluded object regions. GHOST achieves complete, physically consistent, and animatable reconstructions from a single RGB video while running an order of magnitude faster than prior category-agnostic methods. Extensive experiments on ARCTIC, HO3D, and in-the-wild datasets demonstrate state-of-the-art accuracy in 3D reconstruction and 2D rendering quality, establishing GHOST as an efficient and robust solution for realistic hand-object interaction modeling. Code is available at https://github.com/ATAboukhadra/GHOST. |
| title | GHOST: Fast Category-agnostic Hand-Object Interaction Reconstruction from RGB Videos using Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.18912 |