RAVEL：通过图驱动的关系引导进行罕见概念生成与编辑
RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance
AI总结：
RAVEL通过图驱动的关系引导方法，提升罕见概念生成与编辑的可控性和可解释性，适用于长尾领域。
摘要：
尽管视觉保真度令人印象深刻，当前的文本到图像（T2I）扩散模型在描绘罕见、复杂或文化上微妙的概念时仍存在困难，这是由于训练数据的限制。我们引入了RAVEL，一个无需训练的框架，通过将基于图的检索增强生成（RAG）整合到扩散管道中，显著提高了罕见概念生成、上下文驱动的图像编辑和自我纠正能力。与之前依赖于视觉示例、静态描述或模型预训练知识的RAG和LLM增强方法不同，RAVEL利用结构化知识图谱来检索组成、符号和关系上下文，即使在没有视觉先验的情况下也能实现细腻的定位。为了进一步提高生成质量，我们提出了SRD，一个新颖的自我纠正模块，通过多方面对齐反馈迭代更新提示，提高属性准确性、叙述连贯性和语义保真度。我们的框架是模型无关的，并且与领先的扩散模型包括Stable Diffusion XL、Flux和DALL-E 3兼容。我们进行了广泛的评估，涉及三个新提出的基准测试——MythoBench、Rare-Concept-1K和NovelBench。RAVEL在感知、对齐和LLM-as-a-Judge指标上均一致优于现有最先进方法。这些结果使RAVEL成为长尾领域可控和可解释的T2I生成的稳健范式。
英文摘要：
Despite impressive visual fidelity, current text-to-image (T2I) diffusion models struggle to depict rare, complex, or culturally nuanced concepts due to training data limitations. We introduce RAVEL, a training-free framework that significantly improves rare concept generation, context-driven image editing, and self-correction by integrating graph-based retrieval-augmented generation (RAG) into diffusion pipelines. Unlike prior RAG and LLM-enhanced methods reliant on visual exemplars, static captions or pre-trained knowledge of models, RAVEL leverages structured knowledge graphs to retrieve compositional, symbolic, and relational context, enabling nuanced grounding even in the absence of visual priors. To further refine generation quality, we propose SRD, a novel self-correction module that iteratively updates prompts via multi-aspect alignment feedback, enhancing attribute accuracy, narrative coherence, and semantic fidelity. Our framework is model-agnostic and compatible with leading diffusion models including Stable Diffusion XL, Flux, and DALL-E 3. We conduct extensive evaluations across three newly proposed benchmarks - MythoBench, Rare-Concept-1K, and NovelBench. RAVEL also consistently outperforms SOTA methods across perceptual, alignment, and LLM-as-a-Judge metrics. These results position RAVEL as a robust paradigm for controllable and interpretable T2I generation in long-tail domains.
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。
