Tutorials
HandMvNet: Real-Time 3D Hand Pose Estimation Using Multi-View Cross-Attention Fusion
arXiv:2608.20093v1 Announce Type: new Abstract: In this work, we present HandMvNet, one of the first real-time method designed to estimate 3D hand motion and shape from multi-view camera images. Unlik
arXiv:2608.20093v1 Announce Type: new Abstract: In this work, we present HandMvNet, one of the first real-time method designed to estimate 3D hand motion and shape from multi-view camera images. Unlike previous monocular approaches, which suffer from scale-depth ambiguities, our method ensures consistent and accurate absolute hand poses and shapes. This is achieved through a multi-view attention-fusion mechanism that effectively integrates features from multiple viewpoints. In contrast to previous multi-view methods, our approach eliminates the need for camera parameters as input to learn 3D geometry. HandMvNet also achieves a substantial reduction in inference time while delivering competitive results compared to the state-of-the-art methods, making it suitable for real-time applications. Evaluated on publicly available datasets, HandMvNet qualitatively and quantitatively outperforms previous methods under identical settings. Code is available at github.com/pyxploiter/handmvnet.
Related
- Physically Grounded 3D Generative Reconstruction under Hand Occlusion using Proprioception and Multi-Contact Touch
- 2D Pre-Training for 3D Pose Estimation
- Neural Surface Reconstruction from Sparse Views Using Epipolar Geometry
- ExMesh: EXplicit Mesh Reconstruction with Topology Adaptation
Source: arXiv cs.CV | 2026-08-21