使用分层扩散画笔简化图像编辑
Streamlining Image Editing with Layered Diffusion Brushes
AI总结：
提出无训练的分层扩散画笔（LDB）框架，通过独立参数集和中间潜变量缓存实现快速、非破坏性的交互式图层编辑，在速度和质量上优于现有方法。
摘要：
去噪扩散模型已成为强大的图像处理工具，但交互式、局部化的编辑工作流仍不完善。我们引入了分层扩散画笔（LDB），这是一种新颖的无训练框架，可使用标准扩散模型进行交互式、基于图层的编辑。LDB将每个“图层”定义为引导生成过程的独立参数集，即使在重叠区域也能实现独立、非破坏性且细粒度的提示词引导编辑。LDB利用独特的中间潜变量缓存方法，将每次编辑减少至仅几个去噪步骤，在消费级GPU上实现每次编辑140毫秒的速度。一个实现LDB并结合熟悉图层概念的编辑器通过用户研究和定量指标进行了评估。结果表明，在各种序列图像处理任务中，LDB速度优越，且在图像质量、背景保留和编辑保真度方面与最先进方法相当或更优。研究结果凸显了LDB通过提供直观高效的扩散图像编辑方法显著增强创意工作流的能力，及其扩展到视频编辑等相关子领域的潜力。
英文摘要：
Denoising diffusion models have emerged as powerful tools for image manipulation, yet interactive, localized editing workflows remain underdeveloped. We introduce Layered Diffusion Brushes (LDB), a novel training-free framework that enables interactive, layer-based editing using standard diffusion models. LDB defines each "layer" as a self-contained set of parameters guiding the generative process, enabling independent, non-destructive, and fine-grained prompt-guided edits, even in overlapping regions. LDB leverages a unique intermediate latent caching approach to reduce each edit to only a few denoising steps, achieving 140~ms per edit on consumer GPUs. An editor implementing LDB, incorporating familiar layer concepts, was evaluated via user study and quantitative metrics. Results demonstrate LDB's superior speed alongside comparable or improved image quality, background preservation, and edit fidelity relative to state-of-the-art methods across various sequential image manipulation tasks. The findings highlight LDB's ability to significantly enhance creative workflows by providing an intuitive and efficient approach to diffusion-based image editing and its potential for expansion into related subdomains, such as video editing.
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。
