# FOUND-IT: Foundation-model-first Task-driven 3D Scene Graphs with Granularity on Demand

arXiv: https://arxiv.org/abs/2605.25371 · HTML: https://mlsanity.com/paper/2605.25371/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2026.

## Built on by (most cited first, 4 of 4)

- [3D Scene Graphs: Open Challenges and Future Directions](https://mlsanity.com/paper/2606.19383/) (2026)
- [Just-In-Time Scene Graph Growth: Combating Perceptual Saturation in Long-Horizon Robotics](https://mlsanity.com/paper/2607.13245/) (2026)
- [PORTER: Edge-Cloud Residency for Persistent 3D Scene Graph Memory](https://mlsanity.com/paper/2609.33258/) (2026)
- [From Language Priors to Field Adaptation: Preference Learning for Traversability Estimation](https://mlsanity.com/paper/2610.02974/) (2026)

## Abstract (arXiv)

We present the first approach to build hierarchical task-driven 3D scene graphs of arbitrary indoor or outdoor environments using an uncalibrated monocular camera in real-time. We leverage geometric foundation models to estimate geometric attributes of the scene graph (e.g., object bounding boxes), but we also observe that traversability information (the "places" layer of a scene graph) can be directly reconstructed by adding an extra head to existing geometric foundation models, like VGGT. Our approach is task-driven in the sense that we adjust the granularity of the objects and regions in the map depending on the task; for instance, during a manipulation task, our approach is able to resolve small knobs on a stove, while during a navigation task it can focus on large objects (e.g., the entire stove). However, in a major departure from related work, we consider the realistic case where the list of tasks is not predefined and fixed, but evolves as the robot operates. This naturally allows dealing with complex loco-manipulation tasks, where the robot can dynamically adjust its representation as the task unfolds. We dub the resulting approach FOUND-IT. FOUND-IT also includes an agentic approach to query information in the scene graph. In addition to achieving 79% higher accuracy on the ASHiTA SG3D task grounding benchmark, we demonstrate FOUND-IT runs in real-time on a ground robot using a Jetson Thor. Furthermore, to highlight the robustness of our method, we demonstrate constructing 3D scene graphs on casually captured realtor apartment tours from YouTube. Code will be made available upon publication.