IntrinsicEdit：内在空间中的精确生成式图像操控
IntrinsicEdit: Precise generative image manipulation in intrinsic space
AI总结：
本文提出 IntrinsicEdit，在内在图像潜空间中结合精确扩散反演与解耦通道操控，实现无需训练的像素级多任务图像编辑。
摘要：
生成式扩散模型凭借高质量结果以及提示词和语义绘图等直观界面推动了图像编辑的发展。然而，这些界面缺乏精确控制，且相关方法通常只擅长单一编辑任务。我们提出一种在内在图像潜空间中运行的通用生成式工作流，能够为一系列编辑操作实现具备像素级精度的语义化局部操控。在 RGB-X 扩散框架的基础上，我们解决了身份保持和内在通道纠缠的关键挑战。通过引入精确扩散反演和解耦通道操控，我们实现了精确、高效的编辑，并能自动处理全局光照效果——这一切无需额外收集数据或微调模型。我们在复杂图像的多种任务上展示了最先进性能，包括颜色和纹理调整、对象插入与移除、全局重照明，以及这些任务的组合。
英文摘要：
Generative diffusion models have advanced image editing with high-quality results and intuitive interfaces such as prompts and semantic drawing. However, these interfaces lack precise control, and the associated methods typically specialize on a single editing task. We introduce a versatile, generative workflow that operates in an intrinsic-image latent space, enabling semantic, local manipulation with pixel precision for a range of editing operations. Building atop the RGB-X diffusion framework, we address key challenges of identity preservation and intrinsic-channel entanglement. By incorporating exact diffusion inversion and disentangled channel manipulation, we enable precise, efficient editing with automatic resolution of global illumination effects -- all without additional data collection or model fine-tuning. We demonstrate state-of-the-art performance across a variety of tasks on complex images, including color and texture adjustments, object insertion and removal, global relighting, and their combinations.
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。
