Edicho：野外環境中的一致圖像編輯

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

作為一個經過驗證的需求，跨越野外圖像的一致編輯仍然是一個技術挑戰，源於各種無法控制的因素，如物體姿勢、光線條件和攝影環境。Edicho 提出了一個基於擴散模型的無需訓練解決方案，具有一個基本設計原則，即使用明確的圖像對應來指導編輯。具體來說，關鍵組件包括一個注意力操作模塊和一個精心調整的無分類器指導（CFG）去噪策略，兩者都考慮了預估的對應關係。這種推理時間算法具有即插即用的特性，與大多數基於擴散的編輯方法（如 ControlNet 和 BrushNet）兼容。廣泛的結果展示了 Edicho 在不同設置下實現一致跨圖像編輯的有效性。我們將釋放代碼以促進未來的研究。

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.