多轮一致性图像编辑
Multi-turn Consistent Image Editing
AI总结：
本文提出一种多轮图像编辑框架，结合流匹配反演、双目标LQR稳定采样和自适应注意力突出方法，以迭代细化方式提升编辑成功率、视觉保真度与多轮一致性。
摘要：
许多现实世界应用，如交互式照片修饰、艺术内容创作和产品设计，都需要灵活且迭代式的图像编辑。然而，现有的图像编辑方法主要侧重于在单一步骤中实现期望的修改，这在用户意图模糊、变换复杂或需要逐步细化时往往力不从心。因此，这些方法经常产生不一致的结果或无法满足用户期望。为应对这些挑战，我们提出了一种多轮图像编辑框架，使用户能够迭代地细化其编辑，逐步获得更令人满意的结果。我们的方法利用流匹配（flow matching）实现精确的图像反演，并采用双目标线性二次调节器（Linear Quadratic Regulators, LQR）进行稳定采样，有效缓解误差累积。此外，通过分析Transformer的逐层作用，我们引入了一种自适应注意力突出方法，在保持多轮一致性的同时增强可编辑性。大量实验表明，与现有方法相比，我们的框架显著提高了编辑成功率和视觉保真度。
英文摘要：
Many real-world applications, such as interactive photo retouching, artistic content creation, and product design, require flexible and iterative image editing. However, existing image editing methods primarily focus on achieving the desired modifications in a single step, which often struggles with ambiguous user intent, complex transformations, or the need for progressive refinements. As a result, these methods frequently produce inconsistent outcomes or fail to meet user expectations. To address these challenges, we propose a multi-turn image editing framework that enables users to iteratively refine their edits, progressively achieving more satisfactory results. Our approach leverages flow matching for accurate image inversion and a dual-objective Linear Quadratic Regulators (LQR) for stable sampling, effectively mitigating error accumulation. Additionally, by analyzing the layer-wise roles of transformers, we introduce a adaptive attention highlighting method that enhances editability while preserving multi-turn coherence. Extensive experiments demonstrate that our framework significantly improves edit success rates and visual fidelity compared to existing methods.
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。
