FlashDexRetarget: Accelerating Dexterous Manipulation Data Generation through Multi-Motion Retargeting
FlashDexRetarget uses a single reinforcement learning policy to retarget human hand-object demonstrations by jointly training it across multiple references. It conditions this policy on current and future reference states using multi-reference tracking and interaction-aware observations. This method achieves high success in dexterous motion retargeting with 100x lower training compute than existing physics-based or RL approaches.