CineLOG: 一种无需训练的电影长视频生成方法
CineLOG: A Training Free Approach for Cinematic Long Video Generation
AI总结：
CineLOG通过构建高质量、平衡的数据集和创新的生成管道，实现了对电影长视频中摄像机轨迹和类型等属性的精准控制，优于现有端到端模型。
摘要：
可控视频合成是计算机视觉中的核心挑战，但当前模型在文本提示之外的细粒度控制方面存在困难，尤其是在电影属性如摄像机轨迹和类型方面。现有数据集常面临严重的数据不平衡、噪声标签或模拟到现实的显著差距。为此，我们引入了CineLOG，一个包含5000个高质量、平衡且未剪辑的视频片段的新数据集。每个条目都带有详细的场景描述、基于标准电影分类法的明确摄像机指令和类型标签，确保在17种不同的摄像机运动和15种电影类型上实现平衡覆盖。我们还提出了一个新的管道，设计用于创建此数据集，将复杂的文本到视频（T2V）生成任务分解为四个更简单的阶段，使用更成熟的科技。为了实现连贯的多镜头序列，我们引入了一个新的轨迹引导过渡模块，生成平滑的时空插值。广泛的人员评估表明，我们的管道在遵守特定摄像机和剧本指令方面显著优于最先进的端到端T2V模型，同时保持专业视觉质量。所有代码和数据均可在https://cine-log.pages.dev获取。
英文摘要：
Controllable video synthesis is a central challenge in computer vision, yet current models struggle with fine grained control beyond textual prompts, particularly for cinematic attributes like camera trajectory and genre. Existing datasets often suffer from severe data imbalance, noisy labels, or a significant simulation to real gap. To address this, we introduce CineLOG, a new dataset of 5,000 high quality, balanced, and uncut video clips. Each entry is annotated with a detailed scene description, explicit camera instructions based on a standard cinematic taxonomy, and genre label, ensuring balanced coverage across 17 diverse camera movements and 15 film genres. We also present our novel pipeline designed to create this dataset, which decouples the complex text to video (T2V) generation task into four easier stages with more mature technology. To enable coherent, multi shot sequences, we introduce a novel Trajectory Guided Transition Module that generates smooth spatio-temporal interpolation. Extensive human evaluations show that our pipeline significantly outperforms SOTA end to end T2V models in adhering to specific camera and screenplay instructions, while maintaining professional visual quality. All codes and data are available at https://cine-log.pages.dev.
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。
