Affordance Grounding from Demonstration Video to Target Image

Humans excel at learning from expert demonstrations and solving their own problems. To equip intelligent robots and assistants, such as AR glasses, with this ability, it is essential to ground human hand interactions (i.e., affordances) from demonstration videos and apply them to a target image like a user's AR glass view. This video-toimage affordance grounding task is challenging due to (1) the need to predict fine-grained affordances, and ( 2 ) the limited training data, which inadequately covers video-image discrepancies and negatively impacts grounding. To tackle them, we propose Affordance Transformer (Afformer), which has a fine-grained transformer-based decoder that gradually refines affordance grounding. Moreover, we introduce Mask Affordance Hand (MaskAHand), a selfsupervised pre-training technique for synthesizing videoimage data and simulating context changes, enhancing affordance grounding across video-image discrepancies. Afformer with MaskAHand pre-training achieves state-of-theart performance on multiple benchmarks, including a substantial 37% improvement on the OPRA dataset. Code is made available at https://github.com/showlab/afformer .