VM-BHINet:Vision Mamba Bimanual Hand Interaction Network for 3D Interacting Hand Mesh Recovery From a Single RGB Image
This work addresses the problem of realistic 3D hand reconstruction for applications like VR/AR, but it is incremental as it builds on existing methods with specific improvements.
The paper tackled 3D interacting hand mesh recovery from a single RGB image by proposing VM-BHINet, which uses state space models to address occlusions and inefficiencies, resulting in a 2-3% reduction in MPJPE and MPVPE on the InterHand2.6M dataset.
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.