mlsanityData to 14 Oct 2026

Multi-Flow: Multi-View-Enriched Normalizing Flows for Industrial Anomaly Detection

arXiv 2504.03306 ↗First posted 4 Apr 2025cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

With more well-performing anomaly detection methods proposed, many of the single-view tasks have been solved to a relatively good degree. However, real-world production scenarios often involve complex industrial products, whose properties may not be fully captured by one single image. While normalizing flow based approaches already work well in single-camera scenarios, they currently do not make use of the priors in multi-view data. We aim to bridge this gap by using these flow-based models as a strong foundation and propose Multi-Flow, a novel multi-view anomaly detection method. Multi-Flow makes use of a novel multi-view architecture, whose exact likelihood estimation is enhanced by fusing information across different views. For this, we propose a new cross-view message-passing scheme, letting information flow between neighboring views. We empirically validate it on the real-world multi-view data set Real-IAD and reach a new state-of-the-art, surpassing current baselines in both image-wise and sample-wise anomaly detection tasks.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 60 of its 74 references that are in the map. First posted on arXiv 4 Apr 2025.

Builds on

60 of 74 references.

References · 60

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  5. 2015Variational Inference with Normalizing Flowscited by 2,170
  6. 2016Density estimation using Real NVPcited by 2,042
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  8. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  9. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  10. 2017Masked Autoregressive Flow for Density Estimationcited by 684
  11. 2019Neural Spline Flowscited by 596
  12. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
38 more
  1. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  2. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  3. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  4. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  5. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  6. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  7. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  8. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  9. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 307
  10. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  11. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  12. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  13. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
  14. 2019Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Designcited by 262
  15. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  16. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 227
  17. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 221
  18. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  19. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  20. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 171
  21. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 160
  22. 2019Deep Anomaly Detection with Deviation Networkscited by 153
  23. 2019Guided Image Generation with Conditional Invertible Neural Networkscited by 147
  24. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 139
  25. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  26. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  27. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  28. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  29. 2020SoftFlow: Probabilistic Framework for Normalizing Flow on Manifoldscited by 98
  30. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  31. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 85
  32. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 80
  33. 2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
  34. 2023PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flowcited by 74
  35. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  36. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  37. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  38. 2022The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localizationcited by 57

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Modelcited by 4
  2. 2026BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detectioncited by 0
  3. 2026MATCH: Flow Matching for Multi-View Anomaly Detectioncited by 0
  4. 2026PADFormer: Pose-agnostic Anomaly Detection from Sparse View Imagescited by 0
  5. 2026Multi-View Reflective Surface Inspection via Semantic-Saliency Cross-Verificationcited by 0