mlsanityData to 7 Oct 2026

Hand Pose Estimation via Latent 2.5D Heatmap Regression

arXiv 1804.09534 ↗First posted 25 Apr 2018cs.CV cs.LGcited by 111

Not on the map. Why?

Abstract (arXiv)

Estimating the 3D pose of a hand is an essential part of human-computer interaction. Estimating 3D pose using depth or multi-view sensors has become easier with recent advances in computer vision, however, regressing pose from a single RGB image is much less straightforward. The main difficulty arises from the fact that 3D pose requires some form of depth estimates, which are ambiguous given only an RGB image. In this paper we propose a new method for 3D hand pose estimation from a monocular image through a novel 2.5D pose representation. Our new representation estimates pose up to a scaling factor, which can be estimated additionally if a prior of the hand size is given. We implicitly learn depth maps and heatmap distributions with a novel CNN architecture. Our system achieves the state-of-the-art estimation of 2D and 3D hand pose on several challenging datasets in presence of severe occlusions.

Key facts. Cited by 111 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 18; 2023: 24; 2024: 10; 2025: 14; 2026: 9.

111 papers.

Sort:

By area:

  1. 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 320
  2. 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 306
  3. 2021DexMV: Imitation Learning for Dexterous Manipulation from Human Videoscited by 194
  4. 2021FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integrationcited by 168
  5. 2021Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Timecited by 140
  6. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  7. 2021Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimationcited by 122
  8. 2024Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulationcited by 116
  9. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  10. 2022What's in your hands? 3D Reconstruction of Generic Objects in Handscited by 90
  11. 2023HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Videocited by 76
  12. 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
38 more
  1. 2021Model-based 3D Hand Reconstruction via Self-Supervised Learningcited by 65
  2. 2023AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimationcited by 64
  3. 2021Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registrationcited by 59
  4. 2022AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstructioncited by 58
  5. 2021Towards unconstrained joint hand-object reconstruction from RGB videoscited by 57
  6. 2021I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modelingcited by 52
  7. 2023Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Planscited by 51
  8. 2021A Skeleton-Driven Neural Occupancy Representation for Articulated Handscited by 50
  9. 2023Zero-Shot Robot Manipulation from Passive Human Videoscited by 49
  10. 2023gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstructioncited by 49
  11. 2022UmeTrack: Unified multi-view end-to-end hand tracking for VRcited by 48
  12. 2021Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstructioncited by 44
  13. 2021Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentationcited by 40
  14. 20223D Interacting Hand Pose Estimation by Hand De-occlusion and Removalcited by 36
  15. 2022Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videoscited by 35
  16. 2024Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objectscited by 35
  17. 2024EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wildcited by 33
  18. 2021Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Camerascited by 32
  19. 2021Hand Image Understanding via Deep Multi-Task Learningcited by 31
  20. 2022Consistent 3D Hand Reconstruction in Video via self-supervised Learningcited by 28
  21. 2022HARP: Personalized Hand Reconstruction from a Monocular RGB Videocited by 28
  22. 2023Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapescited by 26
  23. 2021RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Videocited by 23
  24. 2022H3WB: Human3.6M 3D WholeBody Dataset and Benchmarkcited by 23
  25. 2022Interacting Hand-Object Pose Estimation via Dense Mutual Attentioncited by 22
  26. 2021Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimationcited by 20
  27. 2023Reconstructing Interacting Hands with Interaction Prior from Monocular Imagescited by 18
  28. 2022Efficient Annotation and Learning for 3D Hand Pose Estimation: A Surveycited by 17
  29. 2022TempCLR: Reconstructing Hands via Time-Coherent Contrastive Learningcited by 17
  30. 2023EvHandPose: Event-based 3D Hand Pose Estimation with Sparse Supervisioncited by 17
  31. 20233D Pose Estimation of Two Interacting Hands from a Monocular Event Cameracited by 17
  32. 2023DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Fieldcited by 16
  33. 2021HandTailor: Towards High-Precision Monocular 3D Hand Recoverycited by 15
  34. 2025MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clipscited by 15
  35. 2024HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactionscited by 13
  36. 2023MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervisioncited by 12
  37. 2025HORT: Monocular Hand-held Objects Reconstruction with Transformerscited by 11
  38. 2022On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimationcited by 10

50 most cited of 111 All 111 (JSON)