mlsanityData to 14 Oct 2026

M3DHMR: Monocular 3D Hand Mesh Recovery

arXiv 2505.20058 ↗First posted 26 May 2025cs.CVcited by 0

Not on the map. Why?

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.

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

27 of 35 references.

References · 27

  1. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  2. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  3. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  4. 2019Learning joint reconstruction of hands and manipulated objectscited by 378
  5. 2023Reconstructing Hands in 3D with Transformerscited by 306
  6. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  7. 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
  8. 2021Mesh Graphormercited by 265
  9. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  10. 20193D Hand Shape and Pose from Images in the Wildcited by 190
  11. 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 181
  12. 20193D Hand Shape and Pose Estimation from a Single RGB Imagecited by 174
15 more
  1. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 162
  2. 2020Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wildcited by 146
  3. 2020Monocular Real-time Hand Shape and Motion Capture using Multi-modal Datacited by 106
  4. 2019SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operatorcited by 89
  5. 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
  6. 2021Model-based 3D Hand Reconstruction via Self-Supervised Learningcited by 65
  7. 2021Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registrationcited by 59
  8. 2021I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modelingcited by 52
  9. 2021Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstructioncited by 44
  10. 2018A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshescited by 39
  11. 2021Hand Image Understanding via Deep Multi-Task Learningcited by 31
  12. 2023Sampling is Matter: Point-guided 3D Human Mesh Reconstructioncited by 24
  13. 2018Stacked Dense U-Nets with Dual Transformers for Robust Face Alignmentcited by 17
  14. 2021RealisticHands: A Hybrid Model for 3D Hand Reconstructioncited by 5
  15. 2023CLIP-Hand3D: Exploiting 3D Hand Pose Estimation via Context-Aware Promptingcited by 5

Built on by

Not cited yet.