arXiv 2512.151382026-09-29cs.CV

从任何事物中借鉴：一种用于参考引导实例编辑的通用框架

Borrowing from anything: A generalizable framework for reference-guided instance editing

Shengxiao Zhou, Chenghua Li, Jianhao Huang, Qinghao Hu, Yifan Zhang

备注：: We have identified substantive issues in the current version of the paper that require further correction and validation. We therefore withdraw this version while we address these issues

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

研究参考引导实例编辑中语义纠缠问题，提出GENIE框架，通过空间对齐模块、自适应残差缩放模块和渐进注意力融合机制，实现显式解缠，在AnyInsertion数据集实验中达到了最新的保真度和鲁棒性。

摘要：

参考引导的实例编辑从根本上受到语义纠缠的限制，即参考的内在外观与其外在属性相互交织。关键挑战在于解开应从参考中借用哪些信息，并确定如何将其适当地应用于目标。为应对这一挑战，我们提出了GENIE，一个能够实现显式解缠的通用实例编辑框架。GENIE首先使用空间对齐模块（SAM）校正空间错位。然后，自适应残差缩放模块（ARSM）通过放大显著的内在线索同时抑制外在属性来学习借鉴内容，而渐进注意力融合（PAF）机制学习如何将这种外观呈现到目标上并保留其结构。在具有挑战性的AnyInsertion数据集上的大量实验表明，GENIE实现了最新的保真度和鲁棒性，为基于解缠的实例编辑设定了新标准。

英文摘要：

Reference-guided instance editing is fundamentally limited by semantic entanglement, where a reference's intrinsic appearance is intertwined with its extrinsic attributes. The key challenge lies in disentangling what information should be borrowed from the reference, and determining how to apply it appropriately to the target. To tackle this challenge, we propose GENIE, a Generalizable Instance Editing framework capable of achieving explicit disentanglement. GENIE first corrects spatial misalignments with a Spatial Alignment Module (SAM). Then, an Adaptive Residual Scaling Module (ARSM) learns what to borrow by amplifying salient intrinsic cues while suppressing extrinsic attributes, while a Progressive Attention Fusion (PAF) mechanism learns how to render this appearance onto the target, preserving its structure. Extensive experiments on the challenging AnyInsertion dataset demonstrate that GENIE achieves state-of-the-art fidelity and robustness, setting a new standard for disentanglement-based instance 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。