mlsanityData to 7 Oct 2026

MATCH: Flow Matching for Multi-View Anomaly Detection

arXiv 2606.24375 ↗First posted 23 Jun 2026cs.CVcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Detecting anomalies in industrial objects is an important topic for increasing production efficiency. More complex objects often require the analysis of several view points, which has led to the field of multi-view anomaly detection. We present MATCH, the first multi-view anomaly detection method based on Flow Matching (FM). With the ODE formulation of Flow Matching, we can estimate likelihoods and thereby derive an anomaly score to detect anomalies in multi-view image data at object, image, and pixel-level. The architectural flexibility of FM models allows us to efficiently transform features of different spatial sizes to the normal distribution. We evaluate thoroughly on the already established Real-IAD data set and are also the first to provide a comprehensive evaluation of popular anomaly detection methods for the MANTA-Tiny data set. MATCH achieves state-of-the-art performance in both anomaly detection and segmentation, all while running on consumer-level hardware. By omitting the costly divergence term needed for likelihood estimation, we ensure that MATCH is usable in real-time production scenarios. Lastly, several ablation studies are conducted to validate the methodological choices.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 68 of its 83 references that are in the map. First posted on arXiv 23 Jun 2026.

Builds on

68 of 83 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling14 Apr
  2. 2024Flow Matching Guide and Code9 Dec
  3. 2023Flow Matching in Latent Space17 Jul
  4. 2023Improving and generalizing flow-based generative models with minibatch optimal transport1 Feb
  5. 2022Flow Matching for Generative Modeling6 Oct

Other references · 63

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  6. 2016Wide Residual Networkscited by 3,057
  7. 2015Variational Inference with Normalizing Flowscited by 2,161
  8. 2016Density estimation using Real NVPcited by 2,029
  9. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  10. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  11. 2025DINOv3cited by 1,297
  12. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
38 more
  1. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  2. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  3. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 584
  4. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  5. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  6. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  7. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  8. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  9. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  10. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  11. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  12. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  13. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  14. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  15. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
  16. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  17. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  18. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 174
  19. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 169
  20. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
  21. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 153
  22. 2019Guided Image Generation with Conditional Invertible Neural Networkscited by 147
  23. 2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 145
  24. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 138
  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. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  28. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 115
  29. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  30. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  31. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 92
  32. 2022DSR -- A dual subspace re-projection network for surface anomaly detectioncited by 89
  33. 2022Anomalib: A Deep Learning Library for Anomaly Detectioncited by 75
  34. 2023PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flowcited by 74
  35. 2023ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstructioncited by 62
  36. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  37. 2023PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detectioncited by 46
  38. 2025The MVTec AD 2 Dataset: Advanced Scenarios for Unsupervised Anomaly Detectioncited by 28

50 most cited of 63 All 63 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
  2. 2026MVFM-3DAD: Multi-view Flow Matching for 3D Anomaly Detection via Density Proxy Estimation
  3. 2024DFM: Interpolant-free Dual Flow Matching
  4. 2026Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection
  5. 2024AnomalySD: Few-Shot Multi-Class Anomaly Detection with Stable Diffusion Model
  6. 2025Time-reversed Flow Matching with Worst Transport in High-dimensional Latent Space for Image Anomaly Detection
  7. 2024Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation
  8. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model