mlsanityData to 7 Oct 2026

DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation

arXiv 2210.02697 ↗First posted 6 Oct 2022cs.RO cs.CVcited by 129

Not on the map. Why?

Abstract (arXiv)

Robotic dexterous grasping is the first step to enable human-like dexterous object manipulation and thus a crucial robotic technology. However, dexterous grasping is much more under-explored than object grasping with parallel grippers, partially due to the lack of a large-scale dataset. In this work, we present a large-scale robotic dexterous grasp dataset, DexGraspNet, generated by our proposed highly efficient synthesis method that can be generally applied to any dexterous hand. Our method leverages a deeply accelerated differentiable force closure estimator and thus can efficiently and robustly synthesize stable and diverse grasps on a large scale. We choose ShadowHand and generate 1.32 million grasps for 5355 objects, covering more than 133 object categories and containing more than 200 diverse grasps for each object instance, with all grasps having been validated by the Isaac Gym simulator. Compared to the previous dataset from Liu et al. generated by GraspIt!, our dataset has not only more objects and grasps, but also higher diversity and quality. Via performing cross-dataset experiments, we show that training several algorithms of dexterous grasp synthesis on our dataset significantly outperforms training on the previous one. To access our data and code, including code for human and Allegro grasp synthesis, please visit our project page: https://pku-epic.github.io/DexGraspNet/.

Key facts. Cited by 129 papers in the map (data through 7 Oct 2026). Builds on 35 of its 65 references that are in the map. First posted on arXiv 6 Oct 2022.

Builds on

35 of 65 references.

References · 35

  1. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  3. 2019Solving Rubik's Cube with a Robot Handcited by 699
  4. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  5. 2020GRAB: A Dataset of Whole-Body Human Grasping of Objectscited by 397
  6. 2019Learning joint reconstruction of hands and manipulated objectscited by 377
  7. 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 320
  8. 2021Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenescited by 213
  9. 2020ContactPose: A Dataset of Grasps with Object Contact and Hand Posecited by 180
  10. 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 179
  11. 2020Grasping Field: Learning Implicit Representations for Human Graspscited by 178
  12. 2021Hand-Object Contact Consistency Reasoning for Human Grasps Generationcited by 160
23 more
  1. 2019ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imagingcited by 145
  2. 2021GOAL: Generating 4D Whole-Body Motion for Hand-Object Graspingcited by 142
  3. 2020CPF: Learning a Contact Potential Field to Model the Hand-Object Interactioncited by 127
  4. 2021Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimationcited by 122
  5. 2020ACRONYM: A Large-Scale Grasp Dataset Based on Simulationcited by 115
  6. 2019Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Researchcited by 98
  7. 2021Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Cluttercited by 94
  8. 2019ContactGrasp: Functional Multi-finger Grasp Synthesis from Contactcited by 87
  9. 2020Learning Dexterous Grasping with Object-Centric Visual Affordancescited by 80
  10. 2022From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperationcited by 79
  11. 2018GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learningcited by 77
  12. 2021Synthesizing Diverse and Physically Stable Grasps with Arbitrary Hand Structures using Differentiable Force Closure Estimatorcited by 70
  13. 2022Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Searchcited by 61
  14. 2022TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baselinecited by 55
  15. 2022Grasp'D: Differentiable Contact-rich Grasp Synthesis for Multi-fingered Handscited by 49
  16. 2020Deep Differentiable Grasp Planner for High-DOF Gripperscited by 39
  17. 2020ManifoldPlus: A Robust and Scalable Watertight Manifold Surface Generation Method for Triangle Soupscited by 38
  18. 2021RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Imagescited by 38
  19. 2022Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrationscited by 34
  20. 2021DDGC: Generative Deep Dexterous Grasping in Cluttercited by 28
  21. 2020Multi-FinGAN: Generative Coarse-To-Fine Sampling of Multi-Finger Graspscited by 20
  22. 2022Learning Diverse and Physically Feasible Dexterous Grasps with Generative Model and Bilevel Optimizationcited by 20
  23. 2022EfficientGrasp: A Unified Data-Efficient Learning to Grasp Method for Multi-fingered Robot Handscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 11; 2024: 27; 2025: 40; 2026: 51.

129 papers.

Sort:

By area:

  1. 2023UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policycited by 117
  2. 2025Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videoscited by 94
  3. 2025DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Graspingcited by 87
  4. 2024Human-Object Interaction from Human-Level Instructionscited by 62
  5. 2025ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learningcited by 56
  6. 2023ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulationcited by 53
  7. 2023AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Posecited by 47
  8. 2024DexDiffuser: Generating Dexterous Grasps with Diffusion Modelscited by 46
  9. 2024DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenescited by 41
  10. 2025Diffusion Models for Robotic Manipulation: A Surveycited by 39
  11. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Reviewcited by 38
  12. 2023Dexterous Functional Graspingcited by 36
38 more
  1. 2024RealDex: Towards Human-like Grasping for Robotic Dexterous Handcited by 33
  2. 2025GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Trainingcited by 32
  3. 2023UGG: Unified Generative Graspingcited by 30
  4. 2025HUMOTO: A 4D Dataset of Mocap Human Object Interactionscited by 30
  5. 2024BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objectscited by 29
  6. 2025DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awarenesscited by 25
  7. 2024Cross-Embodiment Dexterous Grasping with Reinforcement Learningcited by 24
  8. 2024An Economic Framework for 6-DoF Grasp Detectioncited by 23
  9. 2025Dex1B: Learning with 1B Demonstrations for Dexterous Manipulationcited by 23
  10. 2023SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulationcited by 22
  11. 2025DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulationcited by 21
  12. 2025Dexonomy: Synthesizing All Dexterous Grasp Types in a Grasp Taxonomycited by 19
  13. 2025DexVLG: Dexterous Vision-Language-Grasp Model at Scalecited by 19
  14. 2023Grasp Multiple Objects with One Handcited by 18
  15. 2024TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactionscited by 18
  16. 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 18
  17. 2025CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-Worldcited by 16
  18. 2023Exploiting Multimodal Synthetic Data for Egocentric Human-Object Interaction Detection in an Industrial Scenariocited by 14
  19. 2024GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation, Demonstration, and Imitationcited by 14
  20. 2025AnyDexGrasp: General Dexterous Grasping for Different Hands with Human-level Learning Efficiencycited by 14
  21. 2023SynH2R: Synthesizing Hand-Object Motions for Learning Human-to-Robot Handoverscited by 13
  22. 2024HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactionscited by 13
  23. 2024Multi-GraspLLM: A Multimodal LLM for Multi-Hand Semantic Guided Grasp Generationcited by 12
  24. 2025MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulationcited by 12
  25. 2025MAPLE: Encoding Dexterous Robotic Manipulation Priors Learned From Egocentric Videoscited by 12
  26. 2023Learning a Universal Human Prior for Dexterous Manipulation from Human Preferencecited by 10
  27. 2023Are Synthetic Data Useful for Egocentric Hand-Object Interaction Detection?cited by 10
  28. 2025Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactionscited by 10
  29. 2026HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videoscited by 10
  30. 2026Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulationcited by 10
  31. 2026T-Rex: Tactile-Reactive Dexterous Manipulationcited by 10
  32. 2024HandOS: 3D Hand Reconstruction in One Stagecited by 9
  33. 2025CEDex: Cross-Embodiment Dexterous Grasp Generation at Scale from Human-like Contact Representationscited by 9
  34. 2025METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Modelcited by 9
  35. 2024CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objectscited by 8
  36. 2024ContactDexNet: Multi-fingered Robotic Hand Grasping in Cluttered Environments through Hand-object Contact Semantic Mappingcited by 8
  37. 2024Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Graspingcited by 8
  38. 2024FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generationcited by 8

50 most cited of 129 All 129 (JSON)