提出EEdit框架，通过消除空间时间冗余，实现高效图像编辑。
EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing
- 引入空间局部缓存与标记索引，跳过未编辑区域计算。
- 采用反演步跳过策略，复用潜在表示提升效率。
- 实测平均提速2.46倍，支持多种交互式编辑任务。
基于反演的图像编辑虽发展迅速，但计算开销大，难以用于实时交互场景。本文重新审视该方法在空间与时间维度上的冗余问题，如未编辑区域的无效计算及反演过程中的重复操作。为此，提出实用框架EEdit以实现高效编辑：针对空间冗余，设计空间局部缓存机制，仅计算编辑区及其邻域，跳过其他区域，并引入标记索引预处理加速缓存；针对时间冗余，提出反演步跳过策略，复用已有潜在表示。实验表明，在多种编辑任务（包括提示引导编辑、拖拽和图像合成）中，平均加速达2.46倍，且性能无损失。代码已开源：https://github.com/yuriYanZeXuan/EEdit。
原文摘要 · Abstract (English)
Inversion-based image editing is rapidly gaining momentum while suffering from significant computation overhead, hindering its application in real-time interactive scenarios. In this paper, we rethink that the redundancy in inversion-based image editing exists in both the spatial and temporal dimensions, such as the unnecessary computation in unedited regions and the redundancy in the inversion progress. To tackle these challenges, we propose a practical framework, named EEdit, to achieve efficient image editing. Specifically, we introduce three techniques to solve them one by one. For spatial redundancy, spatial locality caching is introduced to compute the edited region and its neighboring regions while skipping the unedited regions, and token indexing preprocessing is designed to further accelerate the caching. For temporal redundancy, inversion step skipping is proposed to reuse the latent for efficient editing. Our experiments demonstrate an average of 2.46 $\times$ acceleration without performance drop in a wide range of editing tasks including prompt-guided image editing, dragging and image composition. Our codes are available at https://github.com/yuriYanZeXuan/EEdit
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。