mlsanityData to 7 Oct 2026

Target Pose Guided Whole-body Grasping Motion Generation for Digital Humans

arXiv 2410.01840 ↗First posted 26 Sep 2024cs.RO cs.AI cs.GRcited by 0

Not on the map. Why?

Abstract (arXiv)

Grasping manipulation is a fundamental mode for human interaction with daily life objects. The synthesis of grasping motion is also greatly demanded in many applications such as animation and robotics. In objects grasping research field, most works focus on generating the last static grasping pose with a parallel gripper or dexterous hand. Grasping motion generation for the full arm especially for the full humanlike intelligent agent is still under-explored. In this work, we propose a grasping motion generation framework for digital human which is an anthropomorphic intelligent agent with high degrees of freedom in virtual world. Given an object known initial pose in 3D space, we first generate a target pose for whole-body digital human based on off-the-shelf target grasping pose generation methods. With an initial pose and this generated target pose, a transformer-based neural network is used to generate the whole grasping trajectory, which connects initial pose and target pose smoothly and naturally. Additionally, two post optimization components are designed to mitigates foot-skating issue and hand-object interpenetration separately. Experiments are conducted on GRAB dataset to demonstrate effectiveness of this proposed method for whole-body grasping motion generation with randomly placed unknown objects.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 26 Sep 2024.

Builds on

31 of 45 references.

References · 31

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  3. 2016Generative Adversarial Imitation Learningcited by 1,576
  4. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  5. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  6. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  7. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 438
  8. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 406
  9. 2020GRAB: A Dataset of Whole-Body Human Grasping of Objectscited by 397
  10. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 294
  11. 2021Stochastic Scene-Aware Motion Predictioncited by 203
  12. 2021DexMV: Imitation Learning for Dexterous Manipulation from Human Videoscited by 194
19 more
  1. 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 179
  2. 2022HUMANISE: Language-conditioned Human Motion Generation in 3D Scenescited by 156
  3. 2021GOAL: Generating 4D Whole-Body Motion for Hand-Object Graspingcited by 142
  4. 2020Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenescited by 135
  5. 2022COUCH: Towards Controllable Human-Chair Interactionscited by 134
  6. 2022IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactionscited by 121
  7. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  8. 2021D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactionscited by 109
  9. 2023Human Motion Generation: A Surveycited by 95
  10. 2021SAGA: Stochastic Whole-Body Grasping with Contactcited by 89
  11. 2019ContactGrasp: Functional Multi-finger Grasp Synthesis from Contactcited by 87
  12. 2020Learning Dexterous Grasping with Object-Centric Visual Affordancescited by 80
  13. 2023CIRCLE: Capture In Rich Contextual Environmentscited by 79
  14. 2021Synthesizing Diverse and Physically Stable Grasps with Arbitrary Hand Structures using Differentiable Force Closure Estimatorcited by 70
  15. 2022TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinementcited by 69
  16. 2021The Wanderings of Odysseus in 3D Scenescited by 59
  17. 2023Generating Continual Human Motion in Diverse 3D Scenescited by 39
  18. 2020Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learningcited by 37
  19. 2022Learning Diverse and Physically Feasible Dexterous Grasps with Generative Model and Bilevel Optimizationcited by 20

Built on by

Not cited yet.