提升扩散模型图像编辑的保真度，同时不牺牲修改能力。
Improving Diffusion-Based Image Editing Faithfulness via Guidance and Scheduling
- 引入保真度引导与调度策略，强化原图信息保留
- 在多种编辑任务中实现更高保真度，且修改能力不变
- 兼容多种编辑方法，适合高质量图像修改场景
文本引导的扩散模型已成为高质量图像生成的关键技术，支持动态图像编辑。在图像编辑中，可编辑性决定修改程度，保真度反映未改动部分的保留效果。然而，二者存在固有权衡，难以兼顾。为此，我们提出保真度引导与调度（FGS）方法，通过保真度引导增强输入图像信息的保留，并引入调度策略缓解可编辑性与保真度之间的错位。实验表明，FGS在保持可编辑性的同时显著提升保真度，且兼容多种编辑方法，可在多样化任务中实现精确、高质量的图像编辑。
原文摘要 · Abstract (English)
Text-guided diffusion models have become essential for high-quality image synthesis, enabling dynamic image editing. In image editing, two crucial aspects are editability, which determines the extent of modification, and faithfulness, which reflects how well unaltered elements are preserved. However, achieving optimal results is challenging because of the inherent trade-off between editability and faithfulness. To address this, we propose Faithfulness Guidance and Scheduling (FGS), which enhances faithfulness with minimal impact on editability. FGS incorporates faithfulness guidance to strengthen the preservation of input image information and introduces a scheduling strategy to resolve misalignment between editability and faithfulness. Experimental results demonstrate that FGS achieves superior faithfulness while maintaining editability. Moreover, its compatibility with various editing methods enables precise, high-quality image edits across diverse tasks.
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。