重新思考基于视觉自回归模型的文本引导图像编辑中的结构保持
Rethinking Structure Preservation in Text-Guided Image Editing with Visual Autoregressive Models
AI总结：
本文提出基于视觉自回归模型的文本引导图像编辑框架，通过分析中间特征分布，改进可编辑区域定位和结构一致性，提升编辑质量和结构保持性。
摘要：
视觉自回归（VAR）模型最近涌现出作为生成模型的有希望家族，能够执行广泛的下游视觉任务，如文本引导的图像编辑。通过将编辑范式从扩散方法中的噪声操控转移到令牌级别操作，VAR方法实现了更好的背景保持和显著更快的推理。然而，现有的基于VAR的编辑方法仍然面临两个关键挑战：准确局部化可编辑令牌和保持编辑结果的结构一致性。在本文中，我们提出了一种基于VAR模型中间特征分布分析的新型文本引导图像编辑框架。首先，我们引入了一种粗到细的令牌定位策略，可以细化可编辑区域，平衡编辑保真度和背景保持。其次，我们分析VAR模型的中间表示，并识别出与结构相关的特征，从而设计出一种简单而有效的特征注入机制，以增强编辑图像与源图像之间的结构一致性。第三，我们开发了一种基于强化学习的自适应特征注入方案，该方案能够自动学习尺度和层特定的注入比例，以联合优化编辑保真度和结构保持。广泛的实验表明，我们的方法在局部和全局编辑场景中均优于最先进的方法，在结构一致性和编辑质量方面均表现更优。
英文摘要：
Visual autoregressive (VAR) models have recently emerged as a promising family of generative models, enabling a wide range of downstream vision tasks such as text-guided image editing. By shifting the editing paradigm from noise manipulation in diffusion-based methods to token-level operations, VAR-based approaches achieve better background preservation and significantly faster inference. However, existing VAR-based editing methods still face two key challenges: accurately localizing editable tokens and maintaining structural consistency in the edited results. In this work, we propose a novel text-guided image editing framework rooted in an analysis of intermediate feature distributions within VAR models. First, we introduce a coarse-to-fine token localization strategy that can refine editable regions, balancing editing fidelity and background preservation. Second, we analyze the intermediate representations of VAR models and identify structure-related features, by which we design a simple yet effective feature injection mechanism to enhance structural consistency between the edited and source images. Third, we develop a reinforcement learning-based adaptive feature injection scheme that automatically learns scale- and layer-specific injection ratios to jointly optimize editing fidelity and structure preservation. Extensive experiments demonstrate that our method achieves superior structural consistency and editing quality compared with state-of-the-art approaches, across both local and global editing scenarios.
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。
