mlsanityData to 14 Oct 2026

OSAGEN: Object-Aware Mask Priors and Multistage Decoupled Diffusion for Industrial Anomaly Generation

arXiv 2607.29533 ↗First posted 31 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Industrial anomaly detection and localization are limited by scarce real anomalies and pixel-level annotations, a bottleneck that synthetic image-mask pairs can alleviate. However, existing few-shot mask-guided generation may over-follow mask geometry, produce weak anomalies, or use condition masks incompatible with the current object instance. We propose OSAGEN, which combines object-aware mask priors with multistage decoupled diffusion. Its three-stage adaptation sequentially learns normal appearance, defect appearance under coarse conditions, and fine-grained mask calibration, improving defect realization and local control. QBG injects object structure from a matched normal image into mask diffusion to produce object-aware priors, while ISC restricts anomaly propagation and preserves normal content during sampling. A lightweight materialization step recovers pixel-level labels aligned with the realized defects. On MVTec AD and VisA, OSAGEN achieves AP-P/F1-P scores of 88.1/82.2 and 68.5/66.1, respectively, under a unified downstream localization protocol. The code will be released upon acceptance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 31 Jul 2026.

Builds on

22 of 33 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  3. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  4. 2018Demystifying MMD GANscited by 1,293
  5. 2023Large Language Modelscited by 780
  6. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  7. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  8. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 207
  9. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  10. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 111
  11. 2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
  12. 2023Few-Shot Defect Image Generation via Defect-Aware Feature Manipulationcited by 67
10 more
  1. 2024Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generationcited by 32
  2. 2024SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuningcited by 27
  3. 2024AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusioncited by 21
  4. 2025DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspectioncited by 13
  5. 2025Normal-Abnormal Guided Generalist Anomaly Detectioncited by 10
  6. 2025Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspectioncited by 3
  7. 2026Reasoning-Driven Anomaly Detection and Localization with Image-Level Supervisioncited by 3
  8. 2025Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and Detectioncited by 2
  9. 2026One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Controlcited by 2
  10. 2025MAGIC: Few-Shot Mask-Guided Anomaly Inpainting with Prompt Perturbation, Spatially Adaptive Guidance, and Context Awarenesscited by 1

Built on by

Not cited yet.