用参考图引导注意力对齐，自动修复生成图像的细节不一致问题。
The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment
- 基于参考图构建三元组数据集，模拟生成模型常见错误。
- 设计注意力对齐损失与细节编码器，精准修正局部不一致。
- 可嵌入智能体框架，支持多轮局部编辑，适用于复杂场景。
现有方法在给定参考图的定制化生成任务中仍难以保持细粒度细节的一致性。本文提出 ImageCritic，通过参考引导的后处理方式解决生成图像的不一致问题。我们首先利用视觉语言模型筛选并显式降质构造参考-退化-目标三元组数据集，有效模拟现有生成模型常见的误差。基于对模型注意力机制与内在表征的深入分析，设计了注意力对齐损失和细节编码器，实现对不一致性的精确修正。ImageCritic 可集成至智能体框架，在复杂场景中实现自动检测与多轮局部编辑。大量实验表明，该方法在多种定制化生成场景中显著优于现有方法，有效解决细节相关问题。
原文摘要 · Abstract (English)
Previous works have explored various customized generation tasks given a reference image, but they still face limitations in generating consistent fine-grained details. In this paper, our aim is to solve the inconsistency problem of generated images by applying a reference-guided post-editing approach and present our ImageCritic. We first construct a dataset of reference-degraded-target triplets obtained via VLM-based selection and explicit degradation, which effectively simulates the common inaccuracies or inconsistencies observed in existing generation models. Furthermore, building on a thorough examination of the model's attention mechanisms and intrinsic representations, we accordingly devise an attention alignment loss and a detail encoder to precisely rectify inconsistencies. ImageCritic can be integrated into an agent framework to automatically detect inconsistencies and correct them with multi-round and local editing in complex scenarios. Extensive experiments demonstrate that ImageCritic can effectively resolve detail-related issues in various customized generation scenarios, providing significant improvements over existing methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。