从竞争到协竞：基于文本引导的无训练图像编辑协竞训练方法
From Competition to Coopetition: Coopetitive Training-Free Image Editing Based on Text Guidance
AI总结：
本文提出CoEdit，通过将注意力控制从竞争转为协竞谈判，提升图像编辑的时空一致性，引入双熵注意力操控和熵 latent 修正机制，改进可编辑区域定位并增强语义一致性。
摘要：
文本引导的图像编辑是现代多媒体内容创作中的关键任务，已通过无需训练的方法取得显著进展。尽管近期有进展，现有方法通常受限于竞争范式，编辑与重建分支独立驱动各自目标以最大化与目标和源提示的对齐。对抗策略导致语义冲突和不可预测的结果，因分支间缺乏协调。为解决这些问题，我们提出Coopetitive Training-Free Image Editing (CoEdit)，一种新的零样本框架，将注意力控制从竞争转为协竞谈判，实现时空维度上的编辑和谐。在空间上，CoEdit引入双熵注意力操控，量化分支间的方向熵互动，将注意力控制重新表述为和谐最大化问题，最终提高可编辑和可保留区域的定位。在时间上，我们提出熵 latent 修正机制，动态调整 latent 表示，最小化累积编辑误差，确保去噪轨迹中的语义一致性。此外，我们提出保真度约束编辑分数，一个联合评估语义编辑和背景保真的复合指标。在标准基准上的广泛实验表明，CoEdit在编辑质量和结构保真度上均取得优越表现，通过增强视觉和文本模态之间的有效交互，提升多媒体信息利用。代码将在https://github.com/JinhaoShen/CoEdit提供。
英文摘要：
Text-guided image editing, a pivotal task in modern multimedia content creation, has seen remarkable progress with training-free methods that eliminate the need for additional optimization. Despite recent progress, existing methods are typically constrained by a competitive paradigm in which the editing and reconstruction branches are independently driven by their respective objectives to maximize alignment with target and source prompts. The adversarial strategy causes semantic conflicts and unpredictable outcomes due to the lack of coordination between branches. To overcome these issues, we propose Coopetitive Training-Free Image Editing (CoEdit), a novel zero-shot framework that transforms attention control from competition to coopetitive negotiation, achieving editing harmony across spatial and temporal dimensions. Spatially, CoEdit introduces Dual-Entropy Attention Manipulation, which quantifies directional entropic interactions between branches to reformulate attention control as a harmony-maximization problem, eventually improving the localization of editable and preservable regions. Temporally, we present Entropic Latent Refinement mechanism to dynamically adjust latent representations over time, minimizing accumulated editing errors and ensuring consistent semantic transitions throughout the denoising trajectory. Additionally, we propose the Fidelity-Constrained Editing Score, a composite metric that jointly evaluates semantic editing and background fidelity. Extensive experiments on standard benchmarks demonstrate that CoEdit achieves superior performance in both editing quality and structural preservation, enhancing multimedia information utilization by enabling more effective interaction between visual and textual modalities. The code will be available at https://github.com/JinhaoShen/CoEdit.
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。
