系统梳理工业异常生成方法，构建首个细粒度分类体系。
A Survey on Industrial Anomalies Synthesis
- 提出涵盖40种方法的统一框架，分四类：手工设计、分布假设、生成模型、视觉语言模型。
- 建立首个工业异常合成（IAS）细粒度分类体系，支持方法对比与趋势分析。
- 首次分析多模态融合与大模型在异常生成中的应用，为未来研究指明方向。
本文全面回顾了异常合成的方法论。现有综述仅关注有限技术，缺乏整体视角及方法间关联的理解。相比之下，本研究提供了一个统一的综述，涵盖约40种代表性方法，分为手工设计、分布假设、生成模型（GM）和视觉语言模型（VLM）四类。我们提出了首个工业异常合成（IAS）分类体系。先前工作缺乏正式分类或使用简化分类，阻碍了结构化比较与趋势识别。本分类体系提供了反映方法演进与实际意义的细粒度框架，为未来研究奠定基础。此外，我们探讨了跨模态合成与大规模视觉语言模型的应用。以往综述忽视了多模态数据与大模型在异常合成中的作用，限制了对其优势的深入理解。本综述分析了其融合方式、优势、挑战与前景，为推动基于多模态学习的工业异常合成提供路线图。更多资源见 https://github.com/M-3LAB/awesome-anomaly-synthesis。
原文摘要 · Abstract (English)
This paper comprehensively reviews anomaly synthesis methodologies. Existing surveys focus on limited techniques, missing an overall field view and understanding method interconnections. In contrast, our study offers a unified review, covering about 40 representative methods across Hand-crafted, Distribution-hypothesis-based, Generative models (GM)-based, and Vision-language models (VLM)-based synthesis. We introduce the first industrial anomaly synthesis (IAS) taxonomy. Prior works lack formal classification or use simplistic taxonomies, hampering structured comparisons and trend identification. Our taxonomy provides a fine-grained framework reflecting methodological progress and practical implications, grounding future research. Furthermore, we explore cross-modality synthesis and large-scale VLM. Previous surveys overlooked multimodal data and VLM in anomaly synthesis, limiting insights into their advantages. Our survey analyzes their integration, benefits, challenges, and prospects, offering a roadmap to boost IAS with multimodal learning. More resources are available at https://github.com/M-3LAB/awesome-anomaly-synthesis.
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。