开放世界非模态外观补全
Open-World Amodal Appearance Completion
AI总结：
本文提出无需训练的开放世界非模态外观补全框架，通过文本查询驱动分割、遮挡分析与修复，生成RGBA对象，实现对任意新对象和遮挡的泛化。
摘要：
理解和重建被遮挡对象是一个具有挑战性的问题，尤其是在类别和上下文多样且不可预测的开放世界场景中。然而，传统方法通常局限于封闭的对象类别集合，限制了它们在复杂的开放世界场景中的应用。我们提出了开放世界非模态外观补全（Open-World Amodal Appearance Completion），这是一个无需训练的框架，通过接受灵活的文本查询作为输入来扩展非模态补全能力。我们的方法能够泛化到由直接术语和抽象查询指定的任意对象。我们将这种能力称为推理式非模态补全，即系统根据提供的图像和语言查询重建所查询对象的完整外观。我们的框架统一了分割、遮挡分析和图像修复，以处理复杂遮挡，并生成作为RGBA元素的补全对象，从而能够无缝集成到三维重建和图像编辑等应用中。大量评估证明了我们的方法在泛化到新对象和新遮挡方面的有效性，为开放世界环境中的非模态补全建立了新的基准。代码和数据集将在论文被接收后发布。
英文摘要：
Understanding and reconstructing occluded objects is a challenging problem, especially in open-world scenarios where categories and contexts are diverse and unpredictable. Traditional methods, however, are typically restricted to closed sets of object categories, limiting their use in complex, open-world scenes. We introduce Open-World Amodal Appearance Completion, a training-free framework that expands amodal completion capabilities by accepting flexible text queries as input. Our approach generalizes to arbitrary objects specified by both direct terms and abstract queries. We term this capability reasoning amodal completion, where the system reconstructs the full appearance of the queried object based on the provided image and language query. Our framework unifies segmentation, occlusion analysis, and inpainting to handle complex occlusions and generates completed objects as RGBA elements, enabling seamless integration into applications such as 3D reconstruction and image editing. Extensive evaluations demonstrate the effectiveness of our approach in generalizing to novel objects and occlusions, establishing a new benchmark for amodal completion in open-world settings. The code and datasets will be released after paper acceptance.
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。
