VLMは記述できるが計測できない：ロボットマニピュレーションのための物体中心シーン理解
VLMs Can Describe, But Not Measure: Object-Centric Scene Understanding for Robotic Manipulation
RGB-D画像から物体領域をセグメント化しVLMで注釈付けと深度情報を統合することで、VLM単体より位置・深度推定精度を高める物体中心表現を構築し、タスク計画と連携させた。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Enrico Saccon, Tommaso Faraci, Iñigo De La Ossa Zarzuelo, Luigi Palopoli, Marco Roveri, Matteo Saveriano
分類: cs.RO, cs.CV
原文アブストラクト
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 tabletop scenes show that the proposed decomposition preserves strong semantic performance while substantially improving localization and depth estimation over direct VLM inference. The resulting representation is also integrated with a task-planning framework for robotic execution.