Differential Diffusion：赋予每个像素其自身强度
Differential Diffusion: Giving Each Pixel Its Strength
AI总结：
提出仅在推理阶段运行、可嵌入现有扩散模型的 Differential Diffusion 框架，实现逐像素或逐区域控制编辑变化量，并验证其在软修复等任务中的效果。
摘要：
扩散模型已经革新了图像生成与编辑，在有条件和无条件图像合成中取得了最先进结果。尽管现有技术允许用户控制图像编辑中的变化程度，但这种可控性仅限于整个编辑区域上的全局变化。本文提出一种新颖框架，支持按像素或按图像区域定制变化量。该框架可集成到任何现有扩散模型中，为其增强这一能力。这种对变化数量的细粒度控制开启了多种新的编辑能力，例如控制单个对象被修改的程度，或引入渐进式空间变化。此外，我们展示了该框架在软修复（soft-inpainting）中的有效性，即在补全图像部分内容的同时，微妙调整周围区域以确保无缝融合。我们还提出了一种用于探索不同变化量效果的新工具。该框架仅在推理阶段运行，无需模型训练或微调。我们使用当前开放的最先进模型展示了该方法，并通过定量和定性比较以及用户研究对其进行验证。代码位于 https://github.com/exx8/differential-diffusion。
英文摘要：
Diffusion models have revolutionized image generation and editing, producing state-of-the-art results in conditioned and unconditioned image synthesis. While current techniques enable user control over the degree of change in an image edit, the controllability is limited to global changes over an entire edited region. This paper introduces a novel framework that enables customization of the amount of change per pixel or per image region. Our framework can be integrated into any existing diffusion model, enhancing it with this capability. Such granular control on the quantity of change opens up a diverse array of new editing capabilities, such as control of the extent to which individual objects are modified, or the ability to introduce gradual spatial changes. Furthermore, we showcase the framework's effectiveness in soft-inpainting -- the completion of portions of an image while subtly adjusting the surrounding areas to ensure seamless integration. Additionally, we introduce a new tool for exploring the effects of different change quantities. Our framework operates solely during inference, requiring no model training or fine-tuning. We demonstrate our method with the current open state-of-the-art models, and validate it via both quantitative and qualitative comparisons, and a user study. Our code is available at: https://github.com/exx8/differential-diffusion
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。
