Dexterous World Models
Recent progress in 3D reconstruction has made it easy to create realistic digital twins from everyday environments. However, current digital twins remain largely static and are limited to navigation and view synthesis without embodied interactivity. To bridge this gap, we introduce Dexterous World Model (DWM), a scene-action-conditioned video diffusion framework that models how dexterous human actions induce dynamic changes in static 3D scenes. Given a static 3D scene rendering and an egocentric hand motion sequence, DWM generates temporally coherent videos depicting plausible human-scene interactions. Our approach conditions video generation on (1) static scene renderings following a specified camera trajectory to ensure spatial consistency, and (2) egocentric hand mesh renderings that encode both geometry and motion cues to model action-conditioned dynamics directly. To train DWM, we construct a hybrid interaction video dataset. Synthetic egocentric interactions provide fully aligned supervision for joint locomotion and manipulation learning, while fixed-camera real-world videos contribute diverse and realistic object dynamics. Experiments demonstrate that DWM enables realistic and physically plausible interactions, such as grasping, opening, and moving objects, while maintaining camera and scene consistency. This framework represents a first step toward video diffusion-based interactive digital twins and enables embodied simulation from egocentric actions.
Code (0)
등록된 구현이 없습니다.
Tasks
3D ReconstructionVideo GenerationSimilar Papers 제목 키워드 기반
TypeTele: Releasing Dexterity in Teleoperation by Dexterous Manipulation Types
Dexterous teleoperation plays a crucial role in robotic manipulation for real-world data collection and remote robot control. Previous dexterous teleoperation mostly relies on hand retargeting to closely mimic human hand…
World Models for Learning Dexterous Hand-Object Interactions from Human Videos
Modeling dexterous hand-object interactions is challenging as it requires understanding how subtle finger motions influence the environment through contact with objects. While recent world models address interaction mode…
BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models
Vision-Language-Action (VLA) models have emerged as a promising paradigm for grounding visual-language understanding into real-world robotic manipulation. However, dexterous manipulation remains challenging for VLA polic…
Reinforcement LearningInteractive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A Survey
Dexterous manipulation is a crucial yet highly complex challenge in humanoid robotics, demanding precise, adaptable, and sample-efficient learning methods. As humanoid robots are usually designed to operate in human-cent…
Imitation LearningDexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation
We propose a sim-to-real framework for dexterous manipulation which can generalize to new objects of the same category in the real world. The key of our framework is to train the manipulation policy with point cloud inpu…
reinforcement-learningReinforcement Learning (RL)