In Defense of the Direct Perception of Affordances
It addresses the challenge of functional recognition in computer vision, offering a novel perspective that could influence long-term research directions, though it appears incremental in reviving an existing theory.
This paper tackles the problem of affordance estimation from images by proposing two direct perception approaches inspired by Gibson's theory, showing they achieve good results and can outperform mediated methods that first estimate semantics or geometry.
The field of functional recognition or affordance estimation from images has seen a revival in recent years. As originally proposed by Gibson, the affordances of a scene were directly perceived from the ambient light: in other words, functional properties like sittable were estimated directly from incoming pixels. Recent work, however, has taken a mediated approach in which affordances are derived by first estimating semantics or geometry and then reasoning about the affordances. In a tribute to Gibson, this paper explores his theory of affordances as originally proposed. We propose two approaches for direct perception of affordances and show that they obtain good results and can out-perform mediated approaches. We hope this paper can rekindle discussion around direct perception and its implications in the long term.