mlsanityData to 7 Oct 2026

CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction

arXiv 2012.00924 ↗First posted 2 Dec 2020cs.CVcited by 127

Not on the map. Why?

Abstract (arXiv)

Modeling the hand-object (HO) interaction not only requires estimation of the HO pose, but also pays attention to the contact due to their interaction. Significant progress has been made in estimating hand and object separately with deep learning methods, simultaneous HO pose estimation and contact modeling has not yet been fully explored. In this paper, we present an explicit contact representation namely Contact Potential Field (CPF), and a learning-fitting hybrid framework namely MIHO to Modeling the Interaction of Hand and Object. In CPF, we treat each contacting HO vertex pair as a spring-mass system. Hence the whole system forms a potential field with minimal elastic energy at the grasp position. Extensive experiments on the two commonly used benchmarks have demonstrated that our method can achieve state-of-the-art in several reconstruction metrics, and allow us to produce more physically plausible HO pose even when the ground-truth exhibits severe interpenetration or disjointedness. Our code is available at https://github.com/lixiny/CPF.

Key facts. Cited by 127 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 16; 2023: 28; 2024: 33; 2025: 23; 2026: 19.

127 papers.

Sort:

By area:

  1. 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 306
  2. 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 246
  3. 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 144
  4. 2022OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interactioncited by 129
  5. 2022DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulationcited by 129
  6. 2025EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videoscited by 116
  7. 2021D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactionscited by 109
  8. 2022CHORE: Contact, Human and Object REconstruction from a single RGB imagecited by 95
  9. 2024TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understandingcited by 85
  10. 2021VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objectscited by 78
  11. 2024OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completioncited by 78
  12. 2021ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesiscited by 76
38 more
  1. 2023HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Videocited by 76
  2. 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
  3. 2022TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinementcited by 69
  4. 2024GraspXL: Generating Grasping Motions for Diverse Objects at Scalecited by 59
  5. 2022AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstructioncited by 58
  6. 2023Visibility Aware Human-Object Interaction Tracking from Single RGB Cameracited by 58
  7. 2021AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactionscited by 56
  8. 2022Human-Aware Object Placement for Visual Environment Reconstructioncited by 56
  9. 2025ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learningcited by 56
  10. 2022Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolutioncited by 54
  11. 2024ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactionscited by 54
  12. 2023ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulationcited by 53
  13. 2023ContactGen: Generative Contact Modeling for Grasp Generationcited by 52
  14. 2023gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstructioncited by 49
  15. 2023LEMON: Learning 3D Human-Object Interaction Relation from 2D Imagescited by 49
  16. 2021O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learningcited by 46
  17. 2024CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangementcited by 40
  18. 2023Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generationcited by 37
  19. 2023Object pop-up: Can we infer 3D objects and their poses from human interactions alone?cited by 36
  20. 2024Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objectscited by 35
  21. 2022Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrationscited by 34
  22. 2024GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusioncited by 33
  23. 2024Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Modelscited by 32
  24. 2024EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Viewscited by 26
  25. 2022DART: Articulated Hand Model with Diverse Accessories and Rich Texturescited by 25
  26. 2025Dex1B: Learning with 1B Demonstrations for Dexterous Manipulationcited by 23
  27. 2022Interacting Hand-Object Pose Estimation via Dense Mutual Attentioncited by 22
  28. 2024EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splattingcited by 22
  29. 2025PICO: Reconstructing 3D People In Contact with Objectscited by 22
  30. 2024GEARS: Local Geometry-aware Hand-object Interaction Synthesiscited by 20
  31. 2023CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Imagescited by 19
  32. 2022Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wildcited by 17
  33. 2024MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videoscited by 17
  34. 2021H2O: A Benchmark for Visual Human-human Object Handover Analysiscited by 16
  35. 2023Novel-view Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Viewscited by 16
  36. 2023RenderIH: A Large-scale Synthetic Dataset for 3D Interacting Hand Pose Estimationcited by 16
  37. 2024Dense Hand-Object(HO) GraspNet with Full Grasping Taxonomy and Dynamicscited by 15
  38. 2025MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clipscited by 15

50 most cited of 127 All 127 (JSON)