ImVideoEdit：通过2D空间差异注意力块实现图像学习的视频编辑
ImVideoEdit: Image-learning Video Editing via 2D Spatial Difference Attention Blocks
AI总结：
本文提出ImVideoEdit框架，通过图像对学习视频编辑能力，利用2D空间差异注意力模块实现高效视频编辑，无需昂贵配对视频数据，保持时间动态并实现精确空间修改。
摘要：
当前视频编辑模型常依赖昂贵的配对视频数据，限制了实际可扩展性。本质上，大多数视频编辑任务可以视为解耦的时空过程，其中预训练模型的时间动态被保留，而空间内容被选择性精确修改。基于此见解，我们提出ImVideoEdit，一个通过图像对学习视频编辑能力的高效框架。通过冻结预训练3D注意力模块并将图像视为单帧视频，我们将2D空间学习过程解耦，以帮助保留原始时间动态。我们的方法核心是一种预测-更新空间差异注意力模块，逐步提取和注入空间差异。而不是依赖刚性的外部掩码，我们结合文本引导的动态语义门控机制，实现适应性和隐含的文本驱动修改。尽管仅在13K图像对上训练5个周期，且计算开销极低，ImVideoEdit在编辑保真度和时间一致性上与在大规模视频数据集上训练的较大模型相当。
英文摘要：
Current video editing models often rely on expensive paired video data, which limits their practical scalability. In essence, most video editing tasks can be formulated as a decoupled spatiotemporal process, where the temporal dynamics of the pretrained model are preserved while spatial content is selectively and precisely modified. Based on this insight, we propose ImVideoEdit, an efficient framework that learns video editing capabilities entirely from image pairs. By freezing the pre-trained 3D attention modules and treating images as single-frame videos, we decouple the 2D spatial learning process to help preserve the original temporal dynamics. The core of our approach is a Predict-Update Spatial Difference Attention module that progressively extracts and injects spatial differences. Rather than relying on rigid external masks, we incorporate a Text-Guided Dynamic Semantic Gating mechanism for adaptive and implicit text-driven modifications. Despite training on only 13K image pairs for 5 epochs with exceptionally low computational overhead, ImVideoEdit achieves editing fidelity and temporal consistency comparable to larger models trained on extensive video datasets.
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。
