HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910075133624320 |
|---|---|
| author | Liu, Yumeng Long, Xiao-Xiao Habermann, Marc Yang, Xuanze Lin, Cheng Liu, Yuan Ma, Yuexin Wang, Wenping Liu, Ligang |
| author_facet | Liu, Yumeng Long, Xiao-Xiao Habermann, Marc Yang, Xuanze Lin, Cheng Liu, Yuan Ma, Yuexin Wang, Wenping Liu, Ligang |
| contents | Recovering high-fidelity 3D hand geometry from images is a critical task in computer vision, holding significant value for domains such as robotics, animation and VR/AR. Crucially, scalable applications demand both accuracy and deployment flexibility, requiring the ability to leverage massive amounts of unstructured image data from the internet or enable deployment on consumer-grade RGB cameras without complex calibration. However, current methods face a dilemma. While single-view approaches are easy to deploy, they suffer from depth ambiguity and occlusion. Conversely, multi-view systems resolve these uncertainties but typically demand fixed, calibrated setups, limiting their real-world utility. To bridge this gap, we draw inspiration from 3D foundation models that learn explicit geometry directly from visual data. By reformulating hand reconstruction from arbitrary views as a visual-geometry grounded task, we propose a feed-forward architecture that, for the first time in literature, jointly infers 3D hand meshes and camera poses from uncalibrated views. Extensive evaluations show that our approach outperforms state-of-the-art benchmarks and demonstrates strong generalization to uncalibrated, in-the-wild scenarios. Here is the link of our project page: https://lym29.github.io/HGGT/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_23997 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images Liu, Yumeng Long, Xiao-Xiao Habermann, Marc Yang, Xuanze Lin, Cheng Liu, Yuan Ma, Yuexin Wang, Wenping Liu, Ligang Computer Vision and Pattern Recognition Recovering high-fidelity 3D hand geometry from images is a critical task in computer vision, holding significant value for domains such as robotics, animation and VR/AR. Crucially, scalable applications demand both accuracy and deployment flexibility, requiring the ability to leverage massive amounts of unstructured image data from the internet or enable deployment on consumer-grade RGB cameras without complex calibration. However, current methods face a dilemma. While single-view approaches are easy to deploy, they suffer from depth ambiguity and occlusion. Conversely, multi-view systems resolve these uncertainties but typically demand fixed, calibrated setups, limiting their real-world utility. To bridge this gap, we draw inspiration from 3D foundation models that learn explicit geometry directly from visual data. By reformulating hand reconstruction from arbitrary views as a visual-geometry grounded task, we propose a feed-forward architecture that, for the first time in literature, jointly infers 3D hand meshes and camera poses from uncalibrated views. Extensive evaluations show that our approach outperforms state-of-the-art benchmarks and demonstrates strong generalization to uncalibrated, in-the-wild scenarios. Here is the link of our project page: https://lym29.github.io/HGGT/. |
| title | HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.23997 |