mlsanityData to 14 Oct 2026

Towards Zero-shot 3D Anomaly Localization

arXiv 2412.04304 ↗First posted 5 Dec 2024cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

3D anomaly detection and localization is of great significance for industrial inspection. Prior 3D anomaly detection and localization methods focus on the setting that the testing data share the same category as the training data which is normal. However, in real-world applications, the normal training data for the target 3D objects can be unavailable due to issues like data privacy or export control regulation. To tackle these challenges, we identify a new task -- zero-shot 3D anomaly detection and localization, where the training and testing classes do not overlap. To this end, we design 3DzAL, a novel patch-level contrastive learning framework based on pseudo anomalies generated using the inductive bias from task-irrelevant 3D xyz data to learn more representative feature representations. Furthermore, we train a normalcy classifier network to classify the normal patches and pseudo anomalies and utilize the classification result jointly with feature distance to design anomaly scores. Instead of directly using the patch point clouds, we introduce adversarial perturbations to the input patch xyz data before feeding into the 3D normalcy classifier for the classification-based anomaly score. We show that 3DzAL outperforms the state-of-the-art anomaly detection and localization performance.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 39 of its 56 references that are in the map. First posted on arXiv 5 Dec 2024.

Builds on

39 of 56 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  6. 2016Wide Residual Networkscited by 3,070
  7. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  8. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  9. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  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. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
27 more
  1. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 152
  2. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 139
  3. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  4. 2020Explainable Deep One-Class Classificationcited by 127
  5. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  6. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  7. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 93
  8. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 75
  9. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
  10. 2022Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptorscited by 66
  11. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  12. 2020Few-shot Scene-adaptive Anomaly Detectioncited by 62
  13. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  14. 2023Collaborative Discrepancy Optimization for Reliable Image Anomaly Localizationcited by 57
  15. 2019Small-GAN: Speeding Up GAN Training Using Core-setscited by 41
  16. 2019Transductive Zero-Shot Learning for 3D Point Cloud Classificationcited by 39
  17. 2021Zero-Shot Learning on 3D Point Cloud Objects and Beyondcited by 38
  18. 2022Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Imagescited by 35
  19. 2023Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulationcited by 33
  20. 2022MAEDAY: MAE for few and zero shot AnomalY-Detectioncited by 30
  21. 2022Cross-Domain Video Anomaly Detection without Target Domain Adaptationcited by 20
  22. 2023Toward Unsupervised 3D Point Cloud Anomaly Detection using Variational Autoencodercited by 18
  23. 2021A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applicationscited by 15
  24. 2024Long-Tailed Anomaly Detection with Learnable Class Namescited by 14
  25. 2022Benchmarking Unsupervised Anomaly Detection and Localizationcited by 11
  26. 2023Making Reconstruction-based Method Great Again for Video Anomaly Detectioncited by 10
  27. 2021SLA2P: Self-supervised Anomaly Detection with Adversarial Perturbationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detectioncited by 11
  2. 2025Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detectioncited by 4
  3. 2025Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detectioncited by 4
  4. 2026GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learningcited by 4
  5. 2025MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samplescited by 3
  6. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  7. 2026Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detectioncited by 2
  8. 2026Open-Set Supervised 3D Anomaly Detection: An Industrial Dataset and a Generalisable Framework for Unknown Defectscited by 0