mlsanityData to 14 Oct 2026

Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos

arXiv 2312.15719 ↗First posted 25 Dec 2023cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

We propose the task of Hand-Object Stable Grasp Reconstruction (HO-SGR), the reconstruction of frames during which the hand is stably holding the object. We first develop the stable grasp definition based on the intuition that the in-contact area between the hand and object should remain stable. By analysing the 3D ARCTIC dataset, we identify stable grasp durations and showcase that objects in stable grasps move within a single degree of freedom (1-DoF). We thereby propose a method to jointly optimise all frames within a stable grasp, minimising object motions to a latent 1-DoF. Finally, we extend the knowledge to in-the-wild videos by labelling 2.4K clips of stable grasps. Our proposed EPIC-Grasps dataset includes 390 object instances of 9 categories, featuring stable grasps from videos of daily interactions in 141 environments. Without 3D ground truth, we use stable contact areas and 2D projection masks to assess the HO-SGR task in the wild. We evaluate relevant methods and our approach preserves significantly higher stable contact area, on both EPIC-Grasps and stable grasp sub-sequences from the ARCTIC dataset.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 51 of its 65 references that are in the map. First posted on arXiv 25 Dec 2023.

Builds on

51 of 65 references.

References · 51

  1. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 795
  2. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  3. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  4. 2020Rescaling Egocentric Visioncited by 540
  5. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  6. 2017Neural 3D Mesh Renderercited by 437
  7. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  8. 2020GRAB: A Dataset of Whole-Body Human Grasping of Objectscited by 405
  9. 2019Learning joint reconstruction of hands and manipulated objectscited by 378
  10. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 327
  11. 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 325
  12. 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 312
38 more
  1. 2023Reconstructing Hands in 3D with Transformerscited by 306
  2. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 289
  3. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  4. 2022Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activitiescited by 287
  5. 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 254
  6. 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 230
  7. 2020ContactPose: A Dataset of Grasps with Object Contact and Hand Posecited by 183
  8. 2020Grasping Field: Learning Implicit Representations for Human Graspscited by 179
  9. 2021FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integrationcited by 169
  10. 2020Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wildcited by 152
  11. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 148
  12. 2020Reconstructing Hand-Object Interactions in the Wildcited by 144
  13. 2019H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactionscited by 141
  14. 2021Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Timecited by 141
  15. 2022EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relationscited by 140
  16. 2020Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstructioncited by 139
  17. 2021ContactOpt: Optimizing Contact to Improve Graspscited by 139
  18. 2022OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interactioncited by 131
  19. 2020CPF: Learning a Contact Potential Field to Model the Hand-Object Interactioncited by 128
  20. 2022What's in your hands? 3D Reconstruction of Generic Objects in Handscited by 90
  21. 2023HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Videocited by 78
  22. 2021ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesiscited by 76
  23. 2023Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clipscited by 74
  24. 2022TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinementcited by 70
  25. 2020NodeSLAM: Neural Object Descriptors for Multi-View Shape Reconstructioncited by 61
  26. 2022AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstructioncited by 59
  27. 2021Towards unconstrained joint hand-object reconstruction from RGB videoscited by 58
  28. 2022Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolutioncited by 54
  29. 2022Reconstructing Hand-Held Objects from Monocular Videocited by 35
  30. 2022Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimationcited by 34
  31. 2022Learning to Imitate Object Interactions from Internet Videoscited by 34
  32. 20233D Hand Pose Estimation in Everyday Egocentric Imagescited by 34
  33. 2015Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Imagescited by 29
  34. 2022CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinementcited by 29
  35. 2022In-Hand 3D Object Scanning from an RGB Sequencecited by 27
  36. 2022Interacting Hand-Object Pose Estimation via Dense Mutual Attentioncited by 22
  37. 2022THOR-Net: End-to-end Graformer-based Realistic Two Hands and Object Reconstruction with Self-supervisioncited by 16
  38. 2023SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstructioncited by 16

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 5; 2026: 2.

10 papers.

  1. 2025ZeroMimic: Distilling Robotic Manipulation Skills from Web Videoscited by 32
  2. 2024EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splattingcited by 23
  3. 2024Diff-IP2D: Diffusion-Based Hand-Object Interaction Prediction on Egocentric Videoscited by 21
  4. 2024MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videoscited by 18
  5. 2025HORT: Monocular Hand-held Objects Reconstruction with Transformerscited by 11
  6. 2025Novel Diffusion Models for Multimodal 3D Hand Trajectory Predictioncited by 8
  7. 2025Diffusion-based 3D Hand Motion Recovery with Intuitive Physicscited by 5
  8. 2025Uni-Hand: Universal Hand Motion Forecasting in Egocentric Viewscited by 5
  9. 2026Towards in-the-wild Egocentric 3D Hand-Object Pose Estimationcited by 2
  10. 2026DP-DeGauss: Dynamic Probabilistic Gaussian Decomposition for Egocentric 4D Scene Reconstructioncited by 1