cs.CVNov 7, 2026

REDiff-AD: No Training and No Target Masks for Industrial Anomaly Image Generation via Diversity-Driven In-Context MMDiT

Authors: Chih-Yu Tsai, Chih-Heng Chang, Jian-Jiun Ding

Organizations: National Taiwan University, Taipei, Taiwan

Abstract

Industrial anomaly detection is challenged by the scarcity and diversity of real defects, leaving insufficient anomalous data to effectively train downstream models. Existing anomaly generation methods often require product-specific fine-tuning, target mask annotation, or costly procedures to achieve realistic and diverse defects. We propose REDiff-AD, a framework that requires neither model training nor target masks and introduces Rectified Flow MMDiT into industrial anomaly generation for efficient sampling with fewer generation steps. Given a normal product image and a single masked reference anomaly, REDiff-AD employs in-context learning to transfer the defect appearance from the reference into the normal image. Internal attention signals generated during this process are further reused to localize the synthesized anomaly, while edge and color cues refine the localization into pixel-level pseudo-masks. Two lightweight modules further improve generation quality: adaptive reference conditioning enhances defect fidelity, while diversity guidance promotes varied defect patterns without additional training. Experiments demonstrate that REDiff-AD can well address the tradeoff between realism and diversity for anomaly pattern generation and achieve competitive downstream anomaly classification, detection, and localization performance. These results show that REDiff-AD is a simple, efficient, and effective solution for large-scale anomaly data augmentation and pixel-level data construction. Github code: https://github.com/efdefe4-droid/REDiff-AD

Figures & tables

Explore similar work

CardsList
  1. AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning

    Apr 9, 2026Jiaming Su, Tengchao Yang, Ruikang Zhang +3Synthetic Anomaly GenerationTool-Using Agents

  2. DeCo: Zero-Shot Industrial Anomaly Generation through Decoupling and Recoupling

    Aug 8, 2026Shilei Zeng, Xurui Li, Yaohan Tang +1Industrial Anomaly DetectionSynthetic Anomaly Generation