Learning Generalizable Hand-Object Tracking from Synthetic Demonstrations

• URL: http://arxiv.org/abs/2512.19583v1
• Date: Mon, 22 Dec 2025 17:08:54 GMT
• Title: Learning Generalizable Hand-Object Tracking from Synthetic Demonstrations
• Abstract summary: We present a system for learning generalizable hand-object tracking controllers purely from synthetic data, without requiring any human demonstrations.<n>Our approach makes two key contributions: (1) HOP, a Hand-Object Planner, which can synthesize diverse hand-object trajectories; and (2) HOT, a Hand-Object Tracker, that bridges synthetic-to-physical transfer through reinforcement learning and interaction imitation learning.
• Score: 71.15185260689928
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We present a system for learning generalizable hand-object tracking controllers purely from synthetic data, without requiring any human demonstrations. Our approach makes two key contributions: (1) HOP, a Hand-Object Planner, which can synthesize diverse hand-object trajectories; and (2) HOT, a Hand-Object Tracker that bridges synthetic-to-physical transfer through reinforcement learning and interaction imitation learning, delivering a generalizable controller conditioned on target hand-object states. Our method extends to diverse object shapes and hand morphologies. Through extensive evaluations, we show that our approach enables dexterous hands to track challenging, long-horizon sequences including object re-arrangement and agile in-hand reorientation. These results represent a significant step toward scalable foundation controllers for manipulation that can learn entirely from synthetic data, breaking the data bottleneck that has long constrained progress in dexterous manipulation.

Related papers

• CosmoH2G: A Hand-to-Gripper Transfer Dataset and Baseline Method for Object Manipulation with Complex Spatial Movements [63.40365657068892]
  Transferring human hand demonstrations to robotic grippers has recently emerged as a cost-effective solution for robot learning.<n>Motivated by this gap, we adopt an implicit, data-driven approach guided by fine-grained hand-pose motions.<n>In both simulation and real-robot experiments, our framework enables stable and precise hand-to-gripper transfer of complex spatial manipulations.
  arXiv  Detail & Related papers  (2026-09-07T13:47:22Z)
• Real-World Cooperative Bimanual Dexterous Grasp of Large Objects from Single-View Observations [18.70687400045831]
  Bimanual dexterous grasping of large objects is a critical challenge in robotic manipulation.<n>We propose a real-world bimanual grasping framework that includes a multimodal dataset capturing joint angles, visual observations and force signals.<n>Our approach enables the synthesis of executable bimanual grasps from single-view inputs, reducing dependence on complete 3D object models.
  arXiv  Detail & Related papers  (2026-08-11T02:24:27Z)
• GIRAF: Towards Generalizable Human Interactions with Articulated Objects [50.52795413484619]
  We present a text-conditioned diffusion model that addresses the challenge of Synthesizing realistic full-body human interactions with articulated objects.<n>Our method demonstrated strong generalization to unseen object configurations, surpassing current state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-07-08T19:30:44Z)
• FSAG: Enhancing Human-to-Dexterous-Hand Finger-Specific Affordance Grounding via Diffusion Models [11.581489292735418]
  Dexterous grasp synthesis must satisfy functional intent and physical feasibility, yet existing pipelines often decouple semantic grounding from refinement.<n>We propose a data-efficient framework that bypasses robot grasp data collection by exploiting object-centric semantic priors in pretrained generative diffusion models.<n>Our results highlight a path toward scalable, hardware-agnostic dexterous manipulation driven by human demonstrations and pretrained generative models.
  arXiv  Detail & Related papers  (2026-01-13T06:08:56Z)
• MaskedManipulator: Versatile Whole-Body Manipulation [38.02818493367002]
  We introduce MaskedManipulator, a generative control policy distilled from a tracking controller trained on large-scale human motion capture data.<n>This two-stage learning process allows the system to perform complex interaction behaviors, while providing intuitive user control over both character and object motions.
  arXiv  Detail & Related papers  (2025-05-25T10:46:14Z)
• SIGHT: Synthesizing Image-Text Conditioned and Geometry-Guided 3D Hand-Object Trajectories [124.24041272390954]
  Modeling hand-object interaction priors holds significant potential to advance robotic and embodied AI systems.<n>We introduce SIGHT, a novel task focused on generating realistic and physically plausible 3D hand-object interaction trajectories from a single image.<n>We propose SIGHT-Fusion, a novel diffusion-based image-text conditioned generative model that tackles this task by retrieving the most similar 3D object mesh from a database.
  arXiv  Detail & Related papers  (2025-03-28T20:53:20Z)
• Learning Visuotactile Skills with Two Multifingered Hands [80.99370364907278]
  We explore learning from human demonstrations using a bimanual system with multifingered hands and visuotactile data. Our results mark a promising step forward in bimanual multifingered manipulation from visuotactile data.
  arXiv  Detail & Related papers  (2024-04-25T17:59:41Z)
• DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions [15.417836855005087]
  We propose a novel method, dubbed DiffH2O, which can synthesize realistic, one or two-handed object interactions.<n>The method introduces three techniques that enable effective learning from limited data.
  arXiv  Detail & Related papers  (2024-03-26T16:06:42Z)
• TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding [44.206222326616526]
  TACO is an extensive dataset spanning a large variety of tool-action-object compositions for daily human activities. TACO contains 2.5K motion sequences paired with third-person and egocentric views, precise hand-object 3D meshes, and action labels. We benchmark three generalizable hand-object-interaction tasks: compositional action recognition, generalizable hand-object motion forecasting, and cooperative grasp synthesis.
  arXiv  Detail & Related papers  (2024-01-16T14:41:42Z)
• Object Discovery from Motion-Guided Tokens [50.988525184497334]
  We augment the auto-encoder representation learning framework with motion-guidance and mid-level feature tokenization. Our approach enables the emergence of interpretable object-specific mid-level features.
  arXiv  Detail & Related papers  (2023-03-27T19:14:00Z)
• Towards unconstrained joint hand-object reconstruction from RGB videos [81.97694449736414]
  Reconstructing hand-object manipulations holds a great potential for robotics and learning from human demonstrations. We first propose a learning-free fitting approach for hand-object reconstruction which can seamlessly handle two-hand object interactions.
  arXiv  Detail & Related papers  (2021-08-16T12:26:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.