解决基于扩散的图像编辑中的文本嵌入泄漏问题
Addressing Text Embedding Leakage in Diffusion-based Image Editing
AI总结：
针对基于扩散模型的文本图像编辑中属性泄漏问题，提出ALE框架，通过ORE解耦文本嵌入、RGB-CAM实现精确注意力及BB保留背景，结合ALE-Bench基准，大幅减少泄漏并实现准确多对象编辑。
摘要：
由生成式扩散模型驱动的文本图像编辑允许用户通过自然语言提示修改图像，极大简化了传统工作流程。尽管取得这些进展，当前方法仍存在关键问题：属性泄漏，即针对特定对象的编辑意外影响无关区域或其他目标对象。我们的分析揭示根本原因是自回归文本编码器生成的序列结束（EOS）嵌入中固有的语义纠缠，这种纠缠会不加区分地聚合提示中的属性。为解决该问题，我们引入无属性泄漏编辑（ALE）框架，从源头解决属性泄漏。ALE结合对象限制嵌入（ORE）以解耦文本嵌入、用于交叉注意力掩码的区域引导融合（RGB-CAM）以实现空间精确注意力，以及背景融合（BB）以保留未编辑内容。为定量评估不同编辑方法的属性泄漏，我们提出属性泄漏评估基准（ALE-Bench），包含全面的编辑场景和新指标。大量实验表明，ALE大幅减少了属性泄漏，从而实现准确的多对象文本驱动图像编辑，同时忠实保留非目标内容。
英文摘要：
Text-based image editing, powered by generative diffusion models, lets users modify images through natural-language prompts and has dramatically simplified traditional workflows. Despite these advances, current methods still suffer from a critical problem: attribute leakage, where edits meant for specific objects unintentionally affect unrelated regions or other target objects. Our analysis reveals the root cause as the semantic entanglement inherent in End-of-Sequence (EOS) embeddings generated by autoregressive text encoders, which indiscriminately aggregate attributes across prompts. To address this issue, we introduce Attribute-Leakage-free Editing (ALE), a framework that tackles attribute leakage at its source. ALE combines Object-Restricted Embeddings (ORE) to disentangle text embeddings, Region-Guided Blending for Cross-Attention Masking (RGB-CAM) for spatially precise attention, and Background Blending (BB) to preserve non-edited content. To quantitatively evaluate attribute leakage across various editing methods, we propose the Attribute-Leakage Evaluation Benchmark (ALE-Bench), featuring comprehensive editing scenarios and new metrics. Extensive experiments show that ALE reduces attribute leakage by large margins, thereby enabling accurate, multi-object, text-driven image editing while faithfully preserving non-target content.
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。
