SOURCE-LINKED INTELLIGENCE

VLMs Can Describe, But Not Measure: Object-Centric Scene Understanding for Robotic Manipulation

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Robotic operation in previously unseen environments requires both semantic understanding and reliable metric information. While vision--language models (VLMs) provide strong semantic capabilities, their geometric estimates remain less reliable. In this paper, we propose a VLM-driven, modular perception framework for scene understanding using off-the-shelf approaches. Starting from a single RGB-D observation, the scene is segmented into object-level regions, annotated by a VLM, and grounded with depth information to construct a task-independent object-centric representation. Experiments on 151

Read original source ↗ Open in workspace

recordType

paper

region

Global