arXiv 2506.133012025-06-16cs.CV

AttentionDrag：挖掘预训练扩散模型中的潜在关联知识用于图像编辑

AttentionDrag: Exploiting Latent Correlation Knowledge in Pre-trained Diffusion Models for Image Editing

Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University（上海数据科学关键实验室，计算机科学学院，复旦大学）；Rajax Network Technology (ele.me), Alibaba Group（RAJAX网络技术（饿了么），阿里巴巴集团）

Biao Yang, Muqi Huang, Yuhui Zhang, Yun Xiong, Kun Zhou, Xi Chen, Shiyang Zhou, Huishuai Bao, Chuan Li, Feng Shi, Hualei Liu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对传统点式图像编辑效率低、语义关系捕捉不足的问题，提出单步编辑方法AttentionDrag，复用预训练扩散模型的自注意力潜在关联知识并自适应生成掩码，实现了更高效且语义一致的高质量图像编辑，性能超越多数主流方法。

摘要：

传统的基于点的图像编辑方法依赖迭代潜变量优化或几何变换，要么处理效率低下，要么无法捕捉图像内部的语义关系。这些方法往往忽视了预训练扩散模型中固有的、尚未被充分利用的强大图像编辑能力。在本研究中，我们提出了一种全新的单步基于点的图像编辑方法AttentionDrag，该方法利用预训练扩散模型内部的固有潜在知识与特征关联来完成图像编辑任务。该框架无需大量重新优化或重新训练，即可实现语义一致的高质量编辑操作。具体而言，我们在DDIM逆扩散过程中复用U-Net模块内自注意力机制所学习到的潜在关联知识，自动识别并调整相关图像区域，确保语义合理性与一致性。此外，AttentionDrag可自适应生成掩码以引导编辑过程，实现精准且具备上下文感知能力的修改，交互体验友好。我们的实验结果表明，该方法性能超越了大多数现有最优方法，且速度显著更快，为基于点的图像编辑任务提供了一种更高效、语义更连贯的解决方案。

英文摘要：

Traditional point-based image editing methods rely on iterative latent optimization or geometric transformations, which are either inefficient in their processing or fail to capture the semantic relationships within the image. These methods often overlook the powerful yet underutilized image editing capabilities inherent in pre-trained diffusion models. In this work, we propose a novel one-step point-based image editing method, named AttentionDrag, which leverages the inherent latent knowledge and feature correlations within pre-trained diffusion models for image editing tasks. This framework enables semantic consistency and high-quality manipulation without the need for extensive re-optimization or retraining. Specifically, we reutilize the latent correlations knowledge learned by the self-attention mechanism in the U-Net module during the DDIM inversion process to automatically identify and adjust relevant image regions, ensuring semantic validity and consistency. Additionally, AttentionDrag adaptively generates masks to guide the editing process, enabling precise and context-aware modifications with friendly interaction. Our results demonstrate a performance that surpasses most state-of-the-art methods with significantly faster speeds, showing a more efficient and semantically coherent solution for point-based image editing tasks.

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。