運動シーケンスによる多視点運転シーンの歩行者動画編集
Controllable Pedestrian Video Editing for Multi-View Driving Scenarios via Motion Sequence
多視点の運転シーン動画で、歩行者の姿勢シーケンスを制御条件に歩行者の挿入・置換・削除を可能にする動画編集フレームワークを提案した。
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: Danzhen Fu, Jiagao Hu, Daiguo Zhou, Fei Wang, Zepeng Wang, Wenhua Liao
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
Pedestrian detection models in autonomous driving systems often lack robustness due to insufficient representation of dangerous pedestrian scenarios in training datasets. To address this limitation, we present a novel framework for controllable pedestrian video editing in multi-view driving scenarios by integrating video inpainting and human motion control techniques. Our approach begins by identifying pedestrian regions of interest across multiple camera views, expanding detection bounding boxes with a fixed ratio, and resizing and stitching these regions into a unified canvas while preserving cross-view spatial relationships. A binary mask is then applied to designate the editable area, within which pedestrian editing is guided by pose sequence control conditions. This enables flexible editing functionalities, including pedestrian insertion, replacement, and removal. Extensive experiments demonstrate that our framework achieves high-quality pedestrian editing with strong visual realism, spatiotemporal coherence, and cross-view consistency. These results establish the proposed method as a robust and versatile solution for multi-view pedestrian video generation, with broad potential for applications in data augmentation and scenario simulation in autonomous driving.
