HECTOR：混合可编辑组合对象引用用于视频生成
HECTOR: Hybrid Editable Compositional Object References for Video Generation
AI总结：
HECTOR通过混合可编辑组合对象引用，实现了视频生成中对复杂时空约束的高保真度满足和运动可控性提升。
摘要：
现实世界中的视频自然地展示了不同物理对象之间的复杂相互作用，有效地形成了动态的视觉元素组合。然而，大多数当前的视频生成模型是整体合成场景的，因此缺乏显式的组合操控机制。为了解决这一限制，我们提出了HECTOR，一个生成管道，使细粒度的组合控制成为可能。与先前的方法不同，HECTOR支持混合参考条件，允许生成同时受到静态图像和/或动态视频的引导。此外，用户可以明确指定每个参考元素的轨迹，精确控制其位置、尺度和速度（见图1）。这种设计使模型能够合成满足复杂时空约束的连贯视频，同时保持对参考的高保真度。大量实验表明，HECTOR在视觉质量、参考保持性和运动可控性方面均优于现有方法。
英文摘要：
Real-world videos naturally portray complex interactions among distinct physical objects, effectively forming dynamic compositions of visual elements. However, most current video generation models synthesize scenes holistically and therefore lack mechanisms for explicit compositional manipulation. To address this limitation, we propose HECTOR, a generative pipeline that enables fine-grained compositional control. In contrast to prior methods,HECTOR supports hybrid reference conditioning, allowing generation to be simultaneously guided by static images and/or dynamic videos. Moreover, users can explicitly specify the trajectory of each referenced element, precisely controlling its location, scale, and speed (see Figure1). This design allows the model to synthesize coherent videos that satisfy complex spatiotemporal constraints while preserving high-fidelity adherence to references. Extensive experiments demonstrate that HECTOR achieves superior visual quality, stronger reference preservation, and improved motion controllability compared with existing approaches.
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。
