Click2Mask：基于动态掩码生成的局部编辑
Click2Mask: Local Editing with Dynamic Mask Generation
AI总结：
本文提出 Click2Mask，仅需一个点击参考点和内容描述，即可在 BLD 过程中借助掩码 CLIP 语义损失动态生成编辑区域，实现低用户成本且优于现有方法的局部图像添加。
摘要：
生成模型的最新进展彻底改变了图像生成与编辑，使非专业用户也能完成这些任务。本文聚焦局部图像编辑，尤其是向粗略指定区域添加新内容的任务。现有方法通常需要精确的掩码或对位置的详细描述，这既繁琐又容易出错。我们提出 Click2Mask，这是一种新颖方法，除内容描述外仅需一个参考点即可简化局部编辑流程。在 Blended Latent Diffusion（BLD，混合潜空间扩散）过程中，掩码围绕该点动态生长，并由基于掩码 CLIP 的语义损失引导。Click2Mask 克服了基于分割和依赖微调的方法的局限，提供了更易用且上下文更准确的解决方案。实验表明，根据人类判断和自动指标，Click2Mask 不仅最大限度减少了用户工作量，还能实现与 SoTA 方法相比具有竞争力或更优的局部图像操控。主要贡献包括简化用户输入、能够自由添加不受现有分割区域约束的对象，以及我们的动态掩码方法集成到其他编辑方法中的潜力。
英文摘要：
Recent advancements in generative models have revolutionized image generation and editing, making these tasks accessible to non-experts. This paper focuses on local image editing, particularly the task of adding new content to a loosely specified area. Existing methods often require a precise mask or a detailed description of the location, which can be cumbersome and prone to errors. We propose Click2Mask, a novel approach that simplifies the local editing process by requiring only a single point of reference (in addition to the content description). A mask is dynamically grown around this point during a Blended Latent Diffusion (BLD) process, guided by a masked CLIP-based semantic loss. Click2Mask surpasses the limitations of segmentation-based and fine-tuning dependent methods, offering a more user-friendly and contextually accurate solution. Our experiments demonstrate that Click2Mask not only minimizes user effort but also enables competitive or superior local image manipulations compared to SoTA methods, according to both human judgement and automatic metrics. Key contributions include the simplification of user input, the ability to freely add objects unconstrained by existing segments, and the integration potential of our dynamic mask approach within other editing methods.
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。
