Saved in:
Bibliographic Details
Main Authors: Bi, Han, Yu, Ge, He, Yu, Liu, Wenzhuo, Zheng, Zijie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.14618
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909586080923648
author Bi, Han
Yu, Ge
He, Yu
Liu, Wenzhuo
Zheng, Zijie
author_facet Bi, Han
Yu, Ge
He, Yu
Liu, Wenzhuo
Zheng, Zijie
contents Understanding bimanual hand interactions is essential for realistic 3D pose and shape reconstruction. However, existing methods struggle with occlusions, ambiguous appearances, and computational inefficiencies. To address these challenges, we propose Vision Mamba Bimanual Hand Interaction Network (VM-BHINet), introducing state space models (SSMs) into hand reconstruction to enhance interaction modeling while improving computational efficiency. The core component, Vision Mamba Interaction Feature Extraction Block (VM-IFEBlock), combines SSMs with local and global feature operations, enabling deep understanding of hand interactions. Experiments on the InterHand2.6M dataset show that VM-BHINet reduces Mean per-joint position error (MPJPE) and Mean per-vertex position error (MPVPE) by 2-3%, significantly surpassing state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14618
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VM-BHINet:Vision Mamba Bimanual Hand Interaction Network for 3D Interacting Hand Mesh Recovery From a Single RGB Image
Bi, Han
Yu, Ge
He, Yu
Liu, Wenzhuo
Zheng, Zijie
Computer Vision and Pattern Recognition
Artificial Intelligence
Understanding bimanual hand interactions is essential for realistic 3D pose and shape reconstruction. However, existing methods struggle with occlusions, ambiguous appearances, and computational inefficiencies. To address these challenges, we propose Vision Mamba Bimanual Hand Interaction Network (VM-BHINet), introducing state space models (SSMs) into hand reconstruction to enhance interaction modeling while improving computational efficiency. The core component, Vision Mamba Interaction Feature Extraction Block (VM-IFEBlock), combines SSMs with local and global feature operations, enabling deep understanding of hand interactions. Experiments on the InterHand2.6M dataset show that VM-BHINet reduces Mean per-joint position error (MPJPE) and Mean per-vertex position error (MPVPE) by 2-3%, significantly surpassing state-of-the-art methods.
title VM-BHINet:Vision Mamba Bimanual Hand Interaction Network for 3D Interacting Hand Mesh Recovery From a Single RGB Image
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2504.14618