MetaShadow：以对象为中心的阴影检测、去除与合成
MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis
AI总结：
提出三合一框架 MetaShadow，通过协同的 Shadow Analyzer 与 Shadow Synthesizer 及中间特征引导，实现以对象为中心的阴影检测、去除和可控合成，并在多项基准与图像编辑任务上优于现有方法。
摘要：
阴影在图像编辑应用中往往考虑不足甚至被忽略，限制了编辑结果的真实感。本文提出 MetaShadow，这是一个三合一的多功能框架，能够以对象为中心的方式对自然图像中的阴影进行检测、去除和可控合成。MetaShadow 结合了两个协同组件的优势：Shadow Analyzer 用于以对象为中心的阴影检测与去除，Shadow Synthesizer 用于基于参考的可控阴影合成。值得注意的是，我们优化了来自 Shadow Analyzer 的中间特征学习，以引导 Shadow Synthesizer 生成更逼真、并与场景无缝融合的阴影。在多个阴影基准数据集上的大量评估表明，MetaShadow 在以对象为中心的阴影检测、去除和合成方面相较现有最先进方法取得了显著提升。MetaShadow 在对象移除、重定位和插入等图像编辑任务中表现出色，推动了以对象为中心的图像编辑边界。
英文摘要：
Shadows are often under-considered or even ignored in image editing applications, limiting the realism of the edited results. In this paper, we introduce MetaShadow, a three-in-one versatile framework that enables detection, removal, and controllable synthesis of shadows in natural images in an object-centered fashion. MetaShadow combines the strengths of two cooperative components: Shadow Analyzer, for object-centered shadow detection and removal, and Shadow Synthesizer, for reference-based controllable shadow synthesis. Notably, we optimize the learning of the intermediate features from Shadow Analyzer to guide Shadow Synthesizer to generate more realistic shadows that blend seamlessly with the scene. Extensive evaluations on multiple shadow benchmark datasets show significant improvements of MetaShadow over the existing state-of-the-art methods on object-centered shadow detection, removal, and synthesis. MetaShadow excels in image-editing tasks such as object removal, relocation, and insertion, pushing the boundaries of object-centered image 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。
