mlsanityData to 7 Oct 2026

HandTailor: Towards High-Precision Monocular 3D Hand Recovery

arXiv 2102.09244 ↗First posted 18 Feb 2021cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

3D hand pose estimation and shape recovery are challenging tasks in computer vision. We introduce a novel framework HandTailor, which combines a learning-based hand module and an optimization-based tailor module to achieve high-precision hand mesh recovery from a monocular RGB image. The proposed hand module unifies perspective projection and weak perspective projection in a single network towards accuracy-oriented and in-the-wild scenarios. The proposed tailor module then utilizes the coarsely reconstructed mesh model provided by the hand module as initialization, and iteratively optimizes an energy function to obtain better results. The tailor module is time-efficient, costs only 8ms per frame on a modern CPU. We demonstrate that HandTailor can get state-of-the-art performance on several public benchmarks, with impressive qualitative results on in-the-wild experiments. Code and video are available on our project webpage https://sites.google.com/view/handtailor.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 30 of its 46 references that are in the map. First posted on arXiv 18 Feb 2021.

Builds on

30 of 46 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  3. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  4. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  5. 2017Neural 3D Mesh Renderercited by 437
  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. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  9. 2017Learning to Estimate 3D Hand Pose from Single RGB Imagescited by 234
  10. 20193D Hand Shape and Pose from Images in the Wildcited by 190
  11. 20193D Hand Shape and Pose Estimation from a Single RGB Imagecited by 174
  12. 2017GANerated Hands for Real-time 3D Hand Tracking from Monocular RGBcited by 147
18 more
  1. 2020Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wildcited by 146
  2. 2019End-to-end Hand Mesh Recovery from a Monocular RGB Imagecited by 124
  3. 2019Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Renderingcited by 115
  4. 2018Hand Pose Estimation via Latent 2.5D Heatmap Regressioncited by 111
  5. 2020Monocular Real-time Hand Shape and Motion Capture using Multi-modal Datacited by 106
  6. 2020Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraintscited by 97
  7. 2018Cross-modal Deep Variational Hand Pose Estimationcited by 89
  8. 2017Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensorcited by 84
  9. 2018Disentangling Latent Hands for Image Synthesis and Pose Estimationcited by 44
  10. 2017Using a single RGB frame for real time 3D hand pose estimation in the wildcited by 39
  11. 2020Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledgecited by 35
  12. 2019Single Image 3D Hand Reconstruction with Mesh Convolutionscited by 32
  13. 2016Robust 3D Hand Pose Estimation in Single Depth Images: from Single-View CNN to Multi-View CNNscited by 29
  14. 2020HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation from a Single Depth Mapcited by 23
  15. 2020BiHand: Recovering Hand Mesh with Multi-stage Bisected Hourglass Networkscited by 23
  16. 2017Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goalscited by 21
  17. 2015Depth-based hand pose estimation: methods, data, and challengescited by 16
  18. 2019Dual Grid Net: hand mesh vertex regression from single depth mapscited by 10

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 6; 2024: 4; 2025: 2.

15 papers.

Sort:

  1. 2022OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interactioncited by 129
  2. 2024OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completioncited by 78
  3. 2021ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesiscited by 76
  4. 2023gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstructioncited by 49
  5. 2023ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstructioncited by 37
  6. 2025HORT: Monocular Hand-held Objects Reconstruction with Transformerscited by 11
  7. 2024Human-Agent Joint Learning for Efficient Robot Manipulation Skill Acquisitioncited by 10
  8. 2024MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraintscited by 9
  9. 2023DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulationcited by 8
  10. 2022End-to-end Weakly-supervised Single-stage Multiple 3D Hand Mesh Reconstruction from a Single RGB Imagecited by 6
  11. 2023In-Hand 3D Object Reconstruction from a Monocular RGB Videocited by 4
  12. 2023Semi-supervised Hand Appearance Recovery via Structure Disentanglement and Dual Adversarial Discriminationcited by 2
3 more
  1. 2023Lightweight Estimation of Hand Mesh and Biomechanically Feasible Kinematic Parameterscited by 0
  2. 2024HandS3C: 3D Hand Mesh Reconstruction with State Space Spatial Channel Attention from RGB imagescited by 0
  3. 2025EHPE: A Segmented Architecture for Enhanced Hand Pose Estimationcited by 0