AI RESEARCH
EgoFun3D: Modeling Interactive Objects from Egocentric Videos using Function Templates
arXiv CS.CV
•
ArXi:2604.11038v1 Announce Type: new We present EgoFun3D, a coordinated task formulation, dataset, and benchmark for modeling interactive 3D objects from egocentric videos. Interactive objects are of high interest for embodied AI but scarce, making modeling from readily available real-world videos valuable. Our task focuses on obtaining simulation-ready interactive 3D objects from egocentric video input.