无需训练，通过图像对应关系实现跨图一致编辑。
Edicho: Consistent Image Editing in the Wild
- 利用预估的图像对应关系指导扩散模型编辑。
- 在多种光照、姿态下保持编辑一致性，效果优于基线方法。
- 可即插即用，适配ControlNet等主流编辑框架。
在真实场景图像中实现一致编辑仍面临诸多不可控因素带来的挑战，如物体姿态、光照条件和拍摄环境差异。Edicho 提出一种无需训练的扩散模型解决方案，核心思想是通过显式图像对应关系引导编辑过程。其关键组件包括注意力操控模块和经过精心优化的无分类器引导（CFG）去噪策略，均基于预估计的对应关系设计。该推理级算法具有即插即用特性，兼容多数基于扩散模型的编辑方法，如 ControlNet 与 BrushNet。大量实验表明，Edicho 在多样化设置下均能有效实现跨图像的一致编辑。代码将公开以促进后续研究。
原文摘要 · Abstract (English)
As a verified need, consistent editing across in-the-wild images remains a technical challenge arising from various unmanageable factors, like object poses, lighting conditions, and photography environments. Edicho steps in with a training-free solution based on diffusion models, featuring a fundamental design principle of using explicit image correspondence to direct editing. Specifically, the key components include an attention manipulation module and a carefully refined classifier-free guidance (CFG) denoising strategy, both of which take into account the pre-estimated correspondence. Such an inference-time algorithm enjoys a plug-and-play nature and is compatible to most diffusion-based editing methods, such as ControlNet and BrushNet. Extensive results demonstrate the efficacy of Edicho in consistent cross-image editing under diverse settings. We will release the code to facilitate future studies.
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。