基于运动序列的多视角驾驶场景可控行人视频编辑
Controllable Pedestrian Video Editing for Multi-View Driving Scenarios via Motion Sequence
AI总结：
针对自动驾驶行人检测模型因训练数据危险场景不足鲁棒性差的问题，提出融合视频修复与运动控制的多视角行人视频编辑框架，可实现插入、替换、移除等编辑，效果真实连贯，可用于数据增强与场景模拟。
摘要：
自动驾驶系统中的行人检测模型因训练数据集中危险行人场景的表征不足，往往缺乏鲁棒性。为解决这一局限，我们提出了一种融合视频修复与人体运动控制技术的多视角驾驶场景可控行人视频编辑新框架。我们的方法首先在多个相机视角中识别行人感兴趣区域，按固定比例扩展检测边界框，再将这些区域调整大小并拼接至统一画布，同时保留跨视角空间关系。随后应用二值掩码指定可编辑区域，在该区域内通过姿态序列控制条件引导行人编辑，可实现行人插入、替换和移除等灵活编辑功能。大量实验表明，我们的框架能实现高质量行人编辑，具备强视觉真实感、时空连贯性与跨视角一致性。这些结果证明所提方法是多视角行人视频生成的鲁棒且通用的解决方案，在自动驾驶的数据增强与场景模拟中具有广泛应用潜力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
