CannyEdit：选择性Canny控制与双提示引导的无训练图像编辑
CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editing
AI总结：
CannyEdit提出无训练图像编辑框架，通过选择性Canny控制和双提示引导，在对象添加、替换和移除中平衡文本一致性、上下文保真度与编辑无缝性。
摘要：
文本到图像（T2I）模型的最新进展，通过利用基础模型的生成先验，实现了无需训练的区域图像编辑。然而，现有方法难以在编辑区域的文本一致性、未编辑区域的上下文保真度以及编辑的无缝集成之间取得平衡。我们提出了CannyEdit，一个新颖的无训练框架，通过两项关键创新来解决这一三重困境。首先，选择性Canny控制（Selective Canny Control）仅将来自Canny ControlNet的结构引导应用于未编辑区域，在保留原始图像细节的同时，允许在指定的可编辑区域内进行精确的、由文本驱动的更改。其次，双提示引导（Dual-Prompt Guidance）同时利用针对特定编辑的局部提示和针对整体场景连贯性的全局提示。通过这种协同方法，这些组件实现了可控的局部编辑，用于对象添加、替换和移除，与当前基于区域的方法相比，在文本一致性、上下文保真度和编辑无缝性之间取得了更优的权衡。此外，CannyEdit提供了非凡的灵活性：它可以在粗略掩码甚至单点提示下有效运行，适用于添加任务。更进一步，该框架可以以无训练方式与视觉-语言模型无缝集成，用于需要规划和推理的复杂指令式编辑。我们的大量评估表明，在复杂的对象添加场景中，CannyEdit相较于领先的指令式编辑器表现出强大的性能。
英文摘要：
Recent advances in text-to-image (T2I) models have enabled training-free regional image editing by leveraging the generative priors of foundation models. However, existing methods struggle to balance text adherence in edited regions, context fidelity in unedited areas, and seamless integration of edits. We introduce CannyEdit, a novel training-free framework that addresses this trilemma through two key innovations. First, Selective Canny Control applies structural guidance from a Canny ControlNet only to the unedited regions, preserving the original image's details while allowing for precise, text-driven changes in the specified editable area. Second, Dual-Prompt Guidance utilizes both a local prompt for the specific edit and a global prompt for overall scene coherence. Through this synergistic approach, these components enable controllable local editing for object addition, replacement, and removal, achieving a superior trade-off among text adherence, context fidelity, and editing seamlessness compared to current region-based methods. Beyond this, CannyEdit offers exceptional flexibility: it operates effectively with rough masks or even single-point hints in addition tasks. Furthermore, the framework can seamlessly integrate with vision-language models in a training-free manner for complex instruction-based editing that requires planning and reasoning. Our extensive evaluations demonstrate CannyEdit's strong performance against leading instruction-based editors in complex object addition scenarios.
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。
