A²-Edit：基于精确参考的任意物体和模糊掩码图像编辑
A$^2$-Edit: Precise Reference-Guided Image Editing of Arbitrary Objects and Ambiguous Masks
AI总结：
本文提出A²-Edit框架，通过大规模多类别数据集UniEdit-500K解决现有数据集的同质化和类别覆盖不足问题，引入Transformer混合模块和Mask Annealing训练策略，实现高效任意物体编辑。
摘要：
我们提出A²-Edit，一种统一的补全框架，用于任意物体类别，允许用户仅使用粗略掩码将目标区域替换为参考物体。为解决现有数据集的严重同质化和有限类别覆盖问题，我们构建了一个大规模多类别数据集UniEdit-500K，包含8个主要类别、209个细粒度子类别和总计500,104对图像。此类丰富的类别多样性对模型提出了新的挑战，要求其自动学习跨类别的语义关系和区别。为此，我们引入了Transformer混合模块，通过动态专家选择对各种物体类别进行差异化建模，并通过专家间的协作进一步增强跨类别的语义迁移和泛化能力。此外，我们提出了一种Mask Annealing训练策略（MATS），在训练过程中逐步放松掩码精度，减少模型对准确掩码的依赖，提高在多样化编辑任务中的鲁棒性。在VITON-HD和AnyInsertion等基准测试中，A²-Edit在所有指标上均优于现有方法，提供了一种新的、高效的任意物体编辑解决方案。
英文摘要：
We propose A^2-Edit, a unified inpainting framework for arbitrary object categories, which allows users to replace any target region with a reference object using only a coarse mask. To address the issues of severe homogenization and limited category coverage in existing datasets, we construct a large-scale multi-category dataset, UniEdit-500K, which includes 8 major categories, 209 fine-grained subcategories, and a total of 500,104 image pairs. Such rich category diversity poses new challenges for the model, requiring it to automatically learn semantic relationships and distinctions across categories. To this end, we introduce the Mixture of Transformer module, which performs differentiated modeling of various object categories through dynamic expert selection, and further enhances cross-category semantic transfer and generalization through collaboration among experts. In addition, we propose a Mask Annealing Training Strategy (MATS) that progressively relaxes mask precision during training, reducing the model's reliance on accurate masks and improving robustness across diverse editing tasks. Extensive experiments on benchmarks such as VITON-HD and AnyInsertion demonstrate that A^2-Edit consistently outperforms existing approaches across all metrics, providing a new and efficient solution for arbitrary object 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。
