Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting
This work proposes a framework dubbed Exo2EgoPose, which innovatively leverages holistic and stable exocentric (Exo) demonstrations as guidance to compensate for partial and dynamic Ego-view cues, and demonstrates an effective human-to-robot transfer capability and yields improvements on the CALVIN dataset.