让阴影检测、消除与生成更真实，专为物体为中心的图像编辑设计
MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis
- 基于物体中心的三合一框架，分步处理阴影问题
- 在多个基准数据集上超越现有最佳方法，提升显著
- 适合需要高真实感图像编辑的设计师与开发者
阴影在图像编辑中常被忽视，影响结果的真实感。本文提出 MetaShadow，一种以物体为中心的三合一通用框架，实现自然图像中阴影的检测、移除与可控合成。该框架由两个协同组件构成：阴影分析器（Shadow Analyzer），用于物体中心的阴影检测与移除；阴影合成器（Shadow Synthesizer），支持参考驱动的可控阴影合成。特别地，通过优化阴影分析器的中间特征，引导合成器生成更逼真的阴影，使其与场景无缝融合。在多个阴影基准数据集上的大量评估表明，MetaShadow 在物体中心阴影检测、移除与合成方面均显著优于现有最先进方法。其在物体移除、重定位和插入等图像编辑任务中表现优异，推动了物体中心图像编辑的边界。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。