Edicho：野外环境中的一致图像编辑

Edicho: Consistent Image Editing in the Wild

December 30, 2024

作者: Qingyan Bai, Hao Ouyang, Yinghao Xu, Qiuyu Wang, Ceyuan Yang, Ka Leong Cheng, Yujun Shen, Qifeng Chen

cs.AI

摘要

作为一个经过验证的需求，跨野外图像的一致编辑仍然是一个技术挑战，由于各种无法控制的因素，如物体姿势、光照条件和摄影环境。Edicho提出了一种基于扩散模型的无需训练的解决方案，其基本设计原则是利用显式图像对应关系来指导编辑。具体来说，关键组件包括一个注意力操纵模块和一个精心设计的无分类器引导（CFG）去噪策略，两者都考虑了预估的对应关系。这种推断时算法具有即插即用的特性，并与大多数基于扩散的编辑方法兼容，如ControlNet和BrushNet。大量结果展示了Edicho在不同设置下进行一致跨图像编辑的有效性。我们将发布代码以促进未来的研究。

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.