mlsanityData to 7 Oct 2026

Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild

arXiv 2004.01946 ↗First posted 4 Apr 2020cs.CVcited by 146

Not on the map. Why?

Abstract (arXiv)

We introduce a simple and effective network architecture for monocular 3D hand pose estimation consisting of an image encoder followed by a mesh convolutional decoder that is trained through a direct 3D hand mesh reconstruction loss. We train our network by gathering a large-scale dataset of hand action in YouTube videos and use it as a source of weak supervision. Our weakly-supervised mesh convolutions-based system largely outperforms state-of-the-art methods, even halving the errors on the in the wild benchmark. The dataset and additional resources are available at https://arielai.com/mesh_hands.

Key facts. Cited by 146 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 37; 2022: 30; 2023: 36; 2024: 20; 2025: 12; 2026: 11.

146 papers.

Sort:

By area:

  1. 2023Reconstructing Hands in 3D with Transformerscited by 298
  2. 2021DexMV: Imitation Learning for Dexterous Manipulation from Human Videoscited by 194
  3. 2021FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integrationcited by 168
  4. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 161
  5. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  6. 2021Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Timecited by 140
  7. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  8. 2021Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimationcited by 122
  9. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 117
  10. 2024Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulationcited by 116
  11. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  12. 2022HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Networkcited by 95
38 more
  1. 2022Interacting Attention Graph for Single Image Two-Hand Reconstructioncited by 87
  2. 2022Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applicationscited by 78
  3. 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
  4. 2021Model-based 3D Hand Reconstruction via Self-Supervised Learningcited by 65
  5. 2022LISA: Learning Implicit Shape and Appearance of Handscited by 63
  6. 2021Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registrationcited by 59
  7. 2022AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstructioncited by 58
  8. 2021Towards unconstrained joint hand-object reconstruction from RGB videoscited by 57
  9. 2022Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolutioncited by 54
  10. 2021I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modelingcited by 52
  11. 2023Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Planscited by 51
  12. 2021A Skeleton-Driven Neural Occupancy Representation for Articulated Handscited by 50
  13. 2023Zero-Shot Robot Manipulation from Passive Human Videoscited by 49
  14. 2023gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstructioncited by 49
  15. 2022UmeTrack: Unified multi-view end-to-end hand tracking for VRcited by 48
  16. 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 48
  17. 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mambacited by 45
  18. 2021Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstructioncited by 44
  19. 2021Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentationcited by 40
  20. 2023ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstructioncited by 37
  21. 20223D Interacting Hand Pose Estimation by Hand De-occlusion and Removalcited by 36
  22. 2022Reconstructing Hand-Held Objects from Monocular Videocited by 35
  23. 2023A Dataset of Relighted 3D Interacting Handscited by 35
  24. 2021Contrastive Representation Learning for Hand Shape Estimationcited by 34
  25. 2021Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Camerascited by 32
  26. 2022Learning to Imitate Object Interactions from Internet Videoscited by 32
  27. 2023A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Imagecited by 32
  28. 2021Hand Image Understanding via Deep Multi-Task Learningcited by 31
  29. 2022Consistent 3D Hand Reconstruction in Video via self-supervised Learningcited by 28
  30. 2022HARP: Personalized Hand Reconstruction from a Monocular RGB Videocited by 28
  31. 2021Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinementscited by 27
  32. 2023Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapescited by 26
  33. 2022DART: Articulated Hand Model with Diverse Accessories and Rich Texturescited by 25
  34. 2022H3WB: Human3.6M 3D WholeBody Dataset and Benchmarkcited by 23
  35. 2022Interacting Hand-Object Pose Estimation via Dense Mutual Attentioncited by 22
  36. 2021To The Point: Correspondence-driven monocular 3D category reconstructioncited by 21
  37. 2021Learning monocular 3D reconstruction of articulated categories from motioncited by 18
  38. 2023High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decompositioncited by 18

50 most cited of 146 All 146 (JSON)