AnomalyPainter: Vision-Language-Diffusion Synergy for Realistic and Diverse Unseen Industrial Anomaly Synthesis

Zhangyu Lai; Yilin Lu; Xinyang Li; Jianghang Lin; Yansong Qu; Ming Li; Liujuan Cao

AAAI 2026technical0 citations

AnomalyPainter: Vision-Language-Diffusion Synergy for Realistic and Diverse Unseen Industrial Anomaly Synthesis

Zhangyu Lai, Yilin Lu, Xinyang Li, Jianghang Lin, Yansong Qu, Ming Li, Liujuan Cao

Abstract

Visual anomaly detection is limited by the lack of sufficient anomaly data. While existing anomaly synthesis methods have made remarkable progress, achieving both realism and diversity in synthesis remains a major obstacle. To address this, we propose AnomalyPainter, a novel framework that breaks the diversity-realism trade-off dilemma through synergizing Vision Language Large Model (VLLM), Latent Diffusion Model (LDM), and our newly introduced texture library Tex-9K. Tex-9K is a professional texture library containing 75 categories and 8792 texture assets crafted for diverse anomaly synthesis. Leveraging VLLM

BibTeX

@inproceedings{aaai2026_anomalypaintervi,
  title = {AnomalyPainter: Vision-Language-Diffusion Synergy for Realistic and Diverse Unseen Industrial Anomaly Synthesis},
  author = {Zhangyu Lai and Yilin Lu and Xinyang Li and Jianghang Lin and Yansong Qu and Ming Li and Liujuan Cao},
  booktitle = {AAAI 2026},
  year = {2026}
}