Research

Paper

TESTING February 24, 2026

Probing and Bridging Geometry-Interaction Cues for Affordance Reasoning in Vision Foundation Models

Authors

Qing Zhang, Xuesong Li, Jing Zhang

Abstract

What does it mean for a visual system to truly understand affordance? We argue that this understanding hinges on two complementary capacities: geometric perception, which identifies the structural parts of objects that enable interaction, and interaction perception, which models how an agent's actions engage with those parts. To test this hypothesis, we conduct a systematic probing of Visual Foundation Models (VFMs). We find that models like DINO inherently encode part-level geometric structures, while generative models like Flux contain rich, verb-conditioned spatial attention maps that serve as implicit interaction priors. Crucially, we demonstrate that these two dimensions are not merely correlated but are composable elements of affordance. By simply fusing DINO's geometric prototypes with Flux's interaction maps in a training-free and zero-shot manner, we achieve affordance estimation competitive with weakly-supervised methods. This final fusion experiment confirms that geometric and interaction perception are the fundamental building blocks of affordance understanding in VFMs, providing a mechanistic account of how perception grounds action.

Metadata

arXiv ID: 2602.20501
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-02-24
Fetched: 2026-02-25 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.20501v1</id>\n    <title>Probing and Bridging Geometry-Interaction Cues for Affordance Reasoning in Vision Foundation Models</title>\n    <updated>2026-02-24T02:59:15Z</updated>\n    <link href='https://arxiv.org/abs/2602.20501v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.20501v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>What does it mean for a visual system to truly understand affordance? We argue that this understanding hinges on two complementary capacities: geometric perception, which identifies the structural parts of objects that enable interaction, and interaction perception, which models how an agent's actions engage with those parts. To test this hypothesis, we conduct a systematic probing of Visual Foundation Models (VFMs). We find that models like DINO inherently encode part-level geometric structures, while generative models like Flux contain rich, verb-conditioned spatial attention maps that serve as implicit interaction priors. Crucially, we demonstrate that these two dimensions are not merely correlated but are composable elements of affordance. By simply fusing DINO's geometric prototypes with Flux's interaction maps in a training-free and zero-shot manner, we achieve affordance estimation competitive with weakly-supervised methods. This final fusion experiment confirms that geometric and interaction perception are the fundamental building blocks of affordance understanding in VFMs, providing a mechanistic account of how perception grounds action.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-02-24T02:59:15Z</published>\n    <arxiv:comment>11 pages, 12 figures, Accepted to CVPR 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Qing Zhang</name>\n    </author>\n    <author>\n      <name>Xuesong Li</name>\n    </author>\n    <author>\n      <name>Jing Zhang</name>\n    </author>\n  </entry>"
}