# M3DHMR: Monocular 3D Hand Mesh Recovery

arXiv: https://arxiv.org/abs/2505.20058 · HTML: https://mlsanity.com/paper/2505.20058/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 27 of 27)

- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [End-to-End Human Pose and Mesh Reconstruction with Transformers](https://mlsanity.com/paper/2012.09760/) (2020)
- [Learning joint reconstruction of hands and manipulated objects](https://mlsanity.com/paper/1904.05767/) (2019)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [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)
- [FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images](https://mlsanity.com/paper/1909.04349/) (2019)
- [Mesh Graphormer](https://mlsanity.com/paper/2104.00272/) (2021)
- [Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose](https://mlsanity.com/paper/2008.09047/) (2020)
- [3D Hand Shape and Pose from Images in the Wild](https://mlsanity.com/paper/1902.03451/) (2019)
- [Embodied Hands: Modeling and Capturing Hands and Bodies Together](https://mlsanity.com/paper/2201.02610/) (2022)
- [3D Hand Shape and Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/1903.00812/) (2019)
- [FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization](https://mlsanity.com/paper/2303.14189/) (2023)
- [Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild](https://mlsanity.com/paper/2004.01946/) (2020)
- [Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data](https://mlsanity.com/paper/2003.09572/) (2020)
- [SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator](https://mlsanity.com/paper/1911.05856/) (2019)
- [MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image](https://mlsanity.com/paper/2112.02753/) (2021)
- [Model-based 3D Hand Reconstruction via Self-Supervised Learning](https://mlsanity.com/paper/2103.11703/) (2021)
- [Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration](https://mlsanity.com/paper/2103.02845/) (2021)
- [I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modeling](https://mlsanity.com/paper/2102.03725/) (2021)
- [Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstruction](https://mlsanity.com/paper/2109.01723/) (2021)
- [A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshes](https://mlsanity.com/paper/1809.06664/) (2018)
- [Hand Image Understanding via Deep Multi-Task Learning](https://mlsanity.com/paper/2107.11646/) (2021)
- [Sampling is Matter: Point-guided 3D Human Mesh Reconstruction](https://mlsanity.com/paper/2304.09502/) (2023)
- [Stacked Dense U-Nets with Dual Transformers for Robust Face Alignment](https://mlsanity.com/paper/1812.01936/) (2018)
- [RealisticHands: A Hybrid Model for 3D Hand Reconstruction](https://mlsanity.com/paper/2108.13995/) (2021)
- [CLIP-Hand3D: Exploiting 3D Hand Pose Estimation via Context-Aware Prompting](https://mlsanity.com/paper/2309.16140/) (2023)

## Abstract (arXiv)

Monocular 3D hand mesh recovery is challenging due to high degrees of freedom of hands, 2D-to-3D ambiguity and self-occlusion. Most existing methods are either inefficient or less straightforward for predicting the position of 3D mesh vertices. Thus, we propose a new pipeline called Monocular 3D Hand Mesh Recovery (M3DHMR) to directly estimate the positions of hand mesh vertices. M3DHMR provides 2D cues for 3D tasks from a single image and uses a new spiral decoder consist of several Dynamic Spiral Convolution (DSC) Layers and a Region of Interest (ROI) Layer. On the one hand, DSC Layers adaptively adjust the weights based on the vertex positions and extract the vertex features in both spatial and channel dimensions. On the other hand, ROI Layer utilizes the physical information and refines mesh vertices in each predefined hand region separately. Extensive experiments on popular dataset FreiHAND demonstrate that M3DHMR significantly outperforms state-of-the-art real-time methods.