MagicEdit：高保真且时间连贯的视频编辑
MagicEdit: High-Fidelity and Temporally Coherent Video Editing
AI总结：
本研究提出文本引导视频编辑方法MagicEdit，通过训练时显式解耦内容、结构与运动信号的学习，实现高保真且时间连贯的视频编辑，支持风格化、局部编辑等多种下游任务。
摘要：
在本报告中，我们提出MagicEdit——一种针对文本引导视频编辑任务的极简却高效的解决方案。我们发现，通过在训练过程中显式解耦内容、结构与运动信号的学习，即可实现高保真且时间连贯的视频到视频转换。这与多数现有方法的思路相悖，这类方法试图在单一框架内联合建模外观与时间表征，我们认为这会导致单帧质量下降。尽管架构简单，实验表明MagicEdit可支持多种下游视频编辑任务，包括视频风格化、局部编辑、video-MagicMix以及视频外绘。
英文摘要：
In this report, we present MagicEdit, a surprisingly simple yet effective solution to the text-guided video editing task. We found that high-fidelity and temporally coherent video-to-video translation can be achieved by explicitly disentangling the learning of content, structure and motion signals during training. This is in contradict to most existing methods which attempt to jointly model both the appearance and temporal representation within a single framework, which we argue, would lead to degradation in per-frame quality. Despite its simplicity, we show that MagicEdit supports various downstream video editing tasks, including video stylization, local editing, video-MagicMix and video outpainting.
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。
