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

arXiv: https://arxiv.org/abs/2602.20501 · HTML: https://mlsanity.com/paper/2602.20501/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 50 references that are in the map.
- First posted on arXiv 24 Feb 2026.

## Builds on (most cited first, 30 of 39)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Emergent Correspondence from Image Diffusion](https://mlsanity.com/paper/2306.03881/) (2023)
- [Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation](https://mlsanity.com/paper/2404.15506/) (2024)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics](https://mlsanity.com/paper/2406.10721/) (2024)
- [Affordances from Human Videos as a Versatile Representation for Robotics](https://mlsanity.com/paper/2304.08488/) (2023)
- [MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining](https://mlsanity.com/paper/2208.12262/) (2022)
- [ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2212.03588/) (2022)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [Grounded Human-Object Interaction Hotspots from Video](https://mlsanity.com/paper/1812.04558/) (2018)
- [AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection](https://mlsanity.com/paper/1709.07326/) (2017)
- [Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos](https://mlsanity.com/paper/2204.01696/) (2022)
- [3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding](https://mlsanity.com/paper/2103.16397/) (2021)
- [Learning Affordance Grounding from Exocentric Images](https://mlsanity.com/paper/2203.09905/) (2022)
- [EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model](https://mlsanity.com/paper/2406.20076/) (2024)
- [LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding](https://mlsanity.com/paper/2303.09665/) (2023)
- [AffordanceLLM: Grounding Affordance from Vision Language Models](https://mlsanity.com/paper/2401.06341/) (2024)
- [Affordance-based Robot Manipulation with Flow Matching](https://mlsanity.com/paper/2409.01083/) (2024)
- [One-Shot Open Affordance Learning with Foundation Models](https://mlsanity.com/paper/2311.17776/) (2023)
- [PartAfford: Part-level Affordance Discovery from 3D Objects](https://mlsanity.com/paper/2202.13519/) (2022)
- [Affordance Grounding from Demonstration Video to Target Image](https://mlsanity.com/paper/2303.14644/) (2023)
- [Learning Precise Affordances from Egocentric Videos for Robotic Manipulation](https://mlsanity.com/paper/2408.10123/) (2024)

## Abstract (arXiv)

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.