EgoTrack3D: 自己中心視点3D物体追跡のためのモジュラーフレームワーク
EgoTrack3D: A Modular Framework for Egocentric 3D Object Tracking
自己中心視点のRGBビデオから動的な3Dシーン表現を再構築・維持するモジュラーフレームワークを提案し、静的・動的物体の持続的な3D追跡を実現した。
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: Jan Kulik, Bjarni Dagur Thor Karason, Yung-Hsu Yang, Boyang Sun, Marc Pollefeys, Xi Wang
分類: cs.CV
原文アブストラクト
Understanding 3D scenes from egocentric video is fundamental for robotics and autonomous navigation, yet rapid viewpoint changes and partial occlusions make building structured representations challenging. Existing 3D tracking and scene graph construction methods primarily address explicit interactions or assume static scenes, limiting their ability to capture complex dynamics. We introduce EgoTrack3D, a modular framework that reconstructs and maintains a dynamic 3D scene representation directly from egocentric RGB video. The framework lifts 2D segmentation masks into a global 3D coordinate frame, using a point-based motion scoring mechanism alongside a voxel-based merging heuristic to associate object tracks. EgoTrack3D maintains accurate representations over time, achieving an 11% improvement in percentage of correct locations (PCL) relative to the strongest baseline on the Aria Digital Twin (ADT) dataset, while addressing the more general setting of persistent 3D tracking for both static and dynamic objects. Furthermore, to demonstrate the system's robustness under degraded conditions that simulate real-world deployment constraints, we replace dense depth maps with sparse 3D bounding box estimation and integrate interaction-guided dynamic association, enabling EgoTrack3D to maintain accurate spatial representations despite noisy observations.