arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.08749cs.CV
收藏

将流匹配的断裂点转向多实例编辑

Shifting the Breaking Point of Flow Matching for Multi-Instance Editing

University of Bologna(博洛尼亚大学)

Carmine Zaccagnino, Fabio Quattrini, Enis Simsar, Marta Tintoré Gazulla, Rita Cucchiara, Alessio Tonioni, Silvia Cascianelli

AI总结:

针对流匹配模型在多实例编辑中语义纠缠的问题,提出实例解耦注意力机制,通过分割联合注意力操作强制实例-文本指令与空间区域的绑定,实现单次前向传播的实例级编辑。

摘要:

流匹配模型最近作为扩散模型的高效替代方案出现,特别是在文本引导的图像生成和编辑中,通过连续时间动力学提供更快的推理。然而,现有的基于流的编辑器主要支持全局或单指令编辑,在多实例场景中表现不佳,其中参考输入的多个部分必须独立编辑而不受语义干扰。我们将此限制归因于全局条件速度场和联合注意力机制,它们纠缠了并发编辑。为了解决这个问题,我们引入了实例解耦注意力,一种分割联合注意力操作的机制,在速度场估计期间强制实例特定文本指令与空间区域之间的绑定。我们在自然图像编辑和新引入的具有区域级编辑指令的文本密集信息图表基准上评估了我们的方法。实验结果表明,我们的方法促进了编辑解耦和局部性,同时保持了全局输出的一致性,实现了单次前向传播的实例级编辑。

英文摘要:

Flow matching models have recently emerged as an efficient alternative to diffusion, especially for text-guided image generation and editing, offering faster inference through continuous-time dynamics. However, existing flow-based editors predominantly support global or single-instruction edits and struggle with multi-instance scenarios, where multiple parts of a reference input must be edited independently without semantic interference. We identify this limitation as a consequence of globally conditioned velocity fields and joint attention mechanisms, which entangle concurrent edits. To address this issue, we introduce Instance-Disentangled Attention, a mechanism that partitions joint attention operations, enforcing binding between instance-specific textual instructions and spatial regions during velocity field estimation. We evaluate our approach on both natural image editing and a newly introduced benchmark of text-dense infographics with region-level editing instructions. Experimental results demonstrate that our approach promotes edit disentanglement and locality while preserving global output coherence, enabling single-pass, instance-level 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。

↑