UniAfford: Token-Routed Multitask Learning for Generalizable 2D-3D Affordance Perception
Affordance perception aims to localize actionable regions supporting embodied interaction, yet 2D and 3D affordance grounding have evolved as separate problems, with different task definitions, supervision formats, datasets, and evaluation protocols. This fragmentation limits the learning of transferable object-afforda...
Yu-Hao Liu, Yi-Ming Zhong, Han-Qing Wang et al.
· 0 citations