利用层级记忆提升图像生成的可编辑性
Improving Editability in Image Generation with Layer-wise Memory
AI总结：
针对顺序图像编辑中难以保持先前修改并自然融入新物体的问题，提出基于层级记忆的框架，通过背景一致性引导与多查询解耦技术，仅需粗略掩码即可在多次编辑中实现高质量且一致的图像编辑。
摘要：
大多数现实世界的图像编辑任务需要多次顺序编辑才能达到理想效果。当前的编辑方法主要为单物体修改而设计，在顺序编辑方面存在困难：尤其是在保持先前编辑的同时将新物体自然融入现有内容方面。这些局限性严重阻碍了需要在修改多个物体同时保持其上下文关系的复杂编辑场景。我们通过两个关键提议来解决这一根本挑战：支持保留现有内容同时自然整合新元素的粗略掩码输入，以及支持跨多次修改的一致性编辑。我们的框架通过层级记忆实现这一点，该记忆存储先前编辑的潜在表示和提示词嵌入。我们提出了背景一致性引导，利用记忆的潜在变量来维持场景连贯性，并在交叉注意力中提出多查询解耦以确保对现有内容的自然适应。为了评估我们的方法，我们提出了一个结合语义对齐指标和交互式编辑场景的新基准数据集。通过全面的实验，我们证明了该方法在迭代图像编辑任务中表现出色，只需极少的用户精力，仅需粗略掩码即可在多次编辑步骤中保持高质量结果。
英文摘要：
Most real-world image editing tasks require multiple sequential edits to achieve desired results. Current editing approaches, primarily designed for single-object modifications, struggle with sequential editing: especially with maintaining previous edits along with adapting new objects naturally into the existing content. These limitations significantly hinder complex editing scenarios where multiple objects need to be modified while preserving their contextual relationships. We address this fundamental challenge through two key proposals: enabling rough mask inputs that preserve existing content while naturally integrating new elements and supporting consistent editing across multiple modifications. Our framework achieves this through layer-wise memory, which stores latent representations and prompt embeddings from previous edits. We propose Background Consistency Guidance that leverages memorized latents to maintain scene coherence and Multi-Query Disentanglement in cross-attention that ensures natural adaptation to existing content. To evaluate our method, we present a new benchmark dataset incorporating semantic alignment metrics and interactive editing scenarios. Through comprehensive experiments, we demonstrate superior performance in iterative image editing tasks with minimal user effort, requiring only rough masks while maintaining high-quality results throughout multiple editing steps.
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。
