Skip to content

Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba

License

Notifications You must be signed in to change notification settings

humansensinglab/Hamba

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 

Repository files navigation

Hamba: Single-view 3D Hand Reconstruction with
Graph-guided Bi-Scanning Mamba

Carnegie Mellon University 
*Equal Contribution
NeurIPS 2024

arXiv Webpage GitHub Stars






Our method Hamba can achieve an accurate and robust reconstruction of 3D Hands.
📖 For more visual results, go checkout our project page


🚀 Updates

  • More Coming Soon
  • 🔲 Coming Soon!: Hamba Hugging Face and Codes. Test Hamba with a single click!
  • Jul. 16, 2024: We released the Hamba project page. Check it out!
  • Jul. 12, 2024: We released the Hamba Paper on arXiv.

📖 Abstract

3D Hand reconstruction from a single RGB image is challenging due to the articulated motion, self-occlusion, and interaction with objects. Existing SOTA methods employ attention-based transformers to learn the 3D hand pose and shape, but they fail to achieve robust and accurate performance due to insufficient modeling of joint spatial relations. To address this problem, we propose a novel graph-guided Mamba framework, named Hamba, which bridges graph learning and state space modeling. Our core idea is to reformulate Mamba’s scanning into graph-guided bidirectional scanning for 3D reconstruction using a few effective tokens. This enables us to learn the joint relations and spatial sequences for enhancing the reconstruction performance. Specifically, we design a novel Graph-guided State Space (GSS) block that learns the graph-structured relations and spatial sequences of joints and uses 88.5% fewer tokens than attention-based methods. Additionally, we integrate the state space features and the global features using a fusion module. By utilizing the GSS block and the fusion module, Hamba effectively leverages the graph-guided state space modeling features and jointly considers global and local features to improve performance. Extensive experiments on several benchmarks and in-the-wild tests demonstrate that Hamba significantly outperforms existing SOTAs, achieving the PA-MPVPE of 5.3mm and F@15mm of 0.992 on FreiHAND. Hamba is currently Rank 1 in two challenging competition leaderboards on 3D hand reconstruction. The code will be available upon acceptance.

📑 Citation

If you find our work useful for your project, please consider adding a star to this repo and citing the paper:

    @misc{dong2024hambasingleview3dhand,
        title={Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba}, 
        author={Haoye Dong and Aviral Chharia and Wenbo Gou and Francisco Vicente Carrasco and Fernando De la Torre},
        year={2024},
        eprint={2407.09646},
        archivePrefix={arXiv},
        primaryClass={cs.CV},
        url={https://arxiv.org/abs/2407.09646}, 
    }