Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction

Documenti analoghi

• Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions
  di: Chen, Hongyi, et al.
  Pubblicazione: (2025)
• ObjectForesight: Predicting Future 3D Object Trajectories from Human Videos
  di: Soraki, Rustin, et al.
  Pubblicazione: (2026)
• HandsOnVLM: Vision-Language Models for Hand-Object Interaction Prediction
  di: Bao, Chen, et al.
  Pubblicazione: (2024)
• DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy
  di: Park, Sungjae, et al.
  Pubblicazione: (2025)
• Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation
  di: Bharadhwaj, Homanga, et al.
  Pubblicazione: (2024)