# Single Image 3D Hand Reconstruction with Mesh Convolutions

arXiv: https://arxiv.org/abs/1905.01326 · HTML: https://mlsanity.com/paper/1905.01326/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2019.

## Built on by (most cited first, 30 of 32)

- [PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images](https://mlsanity.com/paper/2207.06400/) (2022)
- [Collaborative Regression of Expressive Bodies using Moderation](https://mlsanity.com/paper/2105.05301/) (2021)
- [WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild](https://mlsanity.com/paper/2409.12259/) (2024)
- [Recovering 3D Human Mesh from Monocular Images: A Survey](https://mlsanity.com/paper/2203.01923/) (2022)
- [Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications](https://mlsanity.com/paper/2208.03826/) (2022)
- [HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos](https://mlsanity.com/paper/2501.02973/) (2025)
- [Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration](https://mlsanity.com/paper/2103.02845/) (2021)
- [AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction](https://mlsanity.com/paper/2207.12909/) (2022)
- [gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction](https://mlsanity.com/paper/2304.11970/) (2023)
- [HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery](https://mlsanity.com/paper/2304.05690/) (2023)
- [Consistent 3D Hand Reconstruction in Video via self-supervised Learning](https://mlsanity.com/paper/2201.09548/) (2022)
- [SUPR: A Sparse Unified Part-Based Human Representation](https://mlsanity.com/paper/2210.13861/) (2022)
- [HandTailor: Towards High-Precision Monocular 3D Hand Recovery](https://mlsanity.com/paper/2102.09244/) (2021)
- [Deep Structural Causal Shape Models](https://mlsanity.com/paper/2208.10950/) (2022)
- [HORT: Monocular Hand-held Objects Reconstruction with Transformers](https://mlsanity.com/paper/2503.21313/) (2025)
- [Stability-driven Contact Reconstruction From Monocular Color Images](https://mlsanity.com/paper/2205.00848/) (2022)
- [Im2Mesh GAN: Accurate 3D Hand Mesh Recovery from a Single RGB Image](https://mlsanity.com/paper/2101.11239/) (2021)
- [MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild](https://mlsanity.com/paper/2412.13393/) (2024)
- [Overcoming the Trade-off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction](https://mlsanity.com/paper/2305.00646/) (2023)
- [EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learning](https://mlsanity.com/paper/2601.19850/) (2026)
- [A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer](https://mlsanity.com/paper/2109.11719/) (2021)
- [Identity-Disentangled Neural Deformation Model for Dynamic Meshes](https://mlsanity.com/paper/2109.15299/) (2021)
- [UniHand: A Unified Model for Diverse Controlled 4D Hand Motion Modeling](https://mlsanity.com/paper/2602.21631/) (2026)
- [AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimation](https://mlsanity.com/paper/2603.25726/) (2026)
- [Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation](https://mlsanity.com/paper/2606.30598/) (2026)
- [Semi-Supervised 3D Hand Shape and Pose Estimation with Label Propagation](https://mlsanity.com/paper/2111.15199/) (2021)
- [Monocular Human Shape and Pose with Dense Mesh-borne Local Image Features](https://mlsanity.com/paper/2111.05319/) (2021)
- [Rotation Equivariant 3D Hand Mesh Generation from a Single RGB Image](https://mlsanity.com/paper/2111.13023/) (2021)
- [DIREG3D: DIrectly REGress 3D Hands from Multiple Cameras](https://mlsanity.com/paper/2201.11187/) (2022)
- [Pixel-Aligned Non-parametric Hand Mesh Reconstruction](https://mlsanity.com/paper/2210.09198/) (2022)

## Abstract (arXiv)

Monocular 3D reconstruction of deformable objects, such as human body parts, has been typically approached by predicting parameters of heavyweight linear models. In this paper, we demonstrate an alternative solution that is based on the idea of encoding images into a latent non-linear representation of meshes. The prior on 3D hand shapes is learned by training an autoencoder with intrinsic graph convolutions performed in the spectral domain. The pre-trained decoder acts as a non-linear statistical deformable model. The latent parameters that reconstruct the shape and articulated pose of hands in the image are predicted using an image encoder. We show that our system reconstructs plausible meshes and operates in real-time. We evaluate the quality of the mesh reconstructions produced by the decoder on a new dataset and show latent space interpolation results. Our code, data, and models will be made publicly available.