# HandMvNet: Real-Time 3D Hand Pose Estimation Using Multi-View Cross-Attention Fusion

arXiv: https://arxiv.org/abs/2608.20093 · HTML: https://mlsanity.com/paper/2608.20093/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 42 references that are in the map.
- First posted on arXiv 20 Aug 2026.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [End-to-End Human Pose and Mesh Reconstruction with Transformers](https://mlsanity.com/paper/2012.09760/) (2020)
- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.03713/) (2020)
- [Integral Human Pose Regression](https://mlsanity.com/paper/1711.08229/) (2017)
- [3D Hand Shape and Pose from Images in the Wild](https://mlsanity.com/paper/1902.03451/) (2019)
- [3D Hand Shape and Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/1903.00812/) (2019)
- [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019)
- [MediaPipe Hands: On-device Real-time Hand Tracking](https://mlsanity.com/paper/2006.10214/) (2020)
- [OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction](https://mlsanity.com/paper/2203.15709/) (2022)
- [Epipolar Transformers](https://mlsanity.com/paper/2005.04551/) (2020)
- [Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data](https://mlsanity.com/paper/2003.09572/) (2020)
- [HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network](https://mlsanity.com/paper/2203.14564/) (2022)
- [Direct Multi-view Multi-person 3D Pose Estimation](https://mlsanity.com/paper/2111.04076/) (2021)
- [Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration](https://mlsanity.com/paper/2103.02845/) (2021)
- [Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation](https://mlsanity.com/paper/2004.02186/) (2020)
- [I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modeling](https://mlsanity.com/paper/2102.03725/) (2021)
- [UmeTrack: Unified multi-view end-to-end hand tracking for VR](https://mlsanity.com/paper/2211.00099/) (2022)
- [AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild](https://mlsanity.com/paper/2010.13302/) (2020)
- [Robust 3D Hand Pose Estimation in Single Depth Images: from Single-View CNN to Multi-View CNNs](https://mlsanity.com/paper/1606.07253/) (2016)
- [PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation](https://mlsanity.com/paper/2209.08194/) (2022)
- [Generalizable Human Pose Triangulation](https://mlsanity.com/paper/2110.00280/) (2021)
- [HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation from a Single Depth Map](https://mlsanity.com/paper/2004.01588/) (2020)
- [Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2110.05092/) (2021)
- [HandVoxNet++: 3D Hand Shape and Pose Estimation using Voxel-Based Neural Networks](https://mlsanity.com/paper/2107.01205/) (2021)
- [POEM: Reconstructing Hand in a Point Embedded Multi-view Stereo](https://mlsanity.com/paper/2304.04038/) (2023)

## Abstract (arXiv)

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.