mlsanityData to 14 Oct 2026

Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network

arXiv 2311.14897 ↗First posted 25 Nov 2023cs.CVcited by 67

Not on the map. Why?

Abstract (arXiv)

Recently, 3D anomaly detection, a crucial problem involving fine-grained geometry discrimination, is getting more attention. However, the lack of abundant real 3D anomaly data limits the scalability of current models. To enable scalable anomaly data collection, we propose a 3D anomaly synthesis pipeline to adapt existing large-scale 3Dmodels for 3D anomaly detection. Specifically, we construct a synthetic dataset, i.e., Anomaly-ShapeNet, basedon ShapeNet. Anomaly-ShapeNet consists of 1600 point cloud samples under 40 categories, which provides a rich and varied collection of data, enabling efficient training and enhancing adaptability to industrial scenarios. Meanwhile,to enable scalable representation learning for 3D anomaly localization, we propose a self-supervised method, i.e., Iterative Mask Reconstruction Network (IMRNet). During training, we propose a geometry-aware sample module to preserve potentially anomalous local regions during point cloud down-sampling. Then, we randomly mask out point patches and sent the visible patches to a transformer for reconstruction-based self-supervision. During testing, the point cloud repeatedly goes through the Mask Reconstruction Network, with each iteration's output becoming the next input. By merging and contrasting the final reconstructed point cloud with the initial input, our method successfully locates anomalies. Experiments show that IMRNet outperforms previous state-of-the-art methods, achieving 66.1% in I-AUC on Anomaly-ShapeNet dataset and 72.5% in I-AUC on Real3D-AD dataset. Our dataset will be released at https://github.com/Chopper-233/Anomaly-ShapeNet

Key facts. Cited by 67 papers in the map (data through 14 Oct 2026). Builds on 37 of its 48 references that are in the map. First posted on arXiv 25 Nov 2023.

Builds on

37 of 48 references.

References · 37

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Segment Anythingcited by 8,234
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2020Point Transformercited by 1,470
  6. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  7. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  8. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  9. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  10. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  11. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  12. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
25 more
  1. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  2. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  3. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  4. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
  5. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  6. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  7. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 139
  8. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  9. 2023APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot ADcited by 130
  10. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  11. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  12. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 93
  13. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  14. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  15. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 75
  16. 2022Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptorscited by 66
  17. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  18. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 60
  19. 2022The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localizationcited by 57
  20. 2023Collaborative Discrepancy Optimization for Reliable Image Anomaly Localizationcited by 57
  21. 2023PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detectioncited by 46
  22. 2023EasyNet: An Easy Network for 3D Industrial Anomaly Detectioncited by 43
  23. 2018Image Anomalies: a Review and Synthesis of Detection Methodscited by 10
  24. 2021Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representationscited by 10
  25. 2020Combining GANs and AutoEncoders for Efficient Anomaly Detectioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 11; 2025: 28; 2026: 28.

67 papers.

Sort:

By area:

  1. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  2. 2024R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detectioncited by 45
  3. 2024PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detectioncited by 30
  4. 2024Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detectioncited by 30
  5. 2024PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detectioncited by 29
  6. 2024Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Propertiescited by 26
  7. 2024Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learningcited by 25
  8. 2024M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoisingcited by 24
  9. 2025MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detectioncited by 23
  10. 2025Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly Detectioncited by 16
  11. 2025Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defectscited by 15
  12. 2024Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspectivecited by 12
38 more
  1. 2025Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detectioncited by 11
  2. 2025Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detectioncited by 10
  3. 2025Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric Representationcited by 9
  4. 2025Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detectioncited by 7
  5. 2024PointCore: Efficient Unsupervised Point Cloud Anomaly Detector Using Local-Global Featurescited by 5
  6. 2024Uni-3DAD: GAN-Inversion Aided Universal 3D Anomaly Detection on Model-free Productscited by 5
  7. 2024DAS3D: Dual-modality Anomaly Synthesis for 3D Anomaly Detectioncited by 5
  8. 2025Multi-Flow: Multi-View-Enriched Normalizing Flows for Industrial Anomaly Detectioncited by 5
  9. 2025A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Featurescited by 5
  10. 2025Exploiting Point-Language Models with Dual-Prompts for 3D Anomaly Detectioncited by 4
  11. 2025Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detectioncited by 4
  12. 2025Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detectioncited by 4
  13. 2025SAGE: A Visual Language Model for Anomaly Detection via Fact Enhancement and Entropy-aware Alignmentcited by 4
  14. 2026GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learningcited by 4
  15. 2026Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspectivecited by 4
  16. 2025C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisorcited by 3
  17. 2025IEC3D-AD: A 3D Dataset of Industrial Equipment Components for Unsupervised Point Cloud Anomaly Detectioncited by 3
  18. 2025MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samplescited by 3
  19. 2026A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detectioncited by 3
  20. 2026Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detectioncited by 3
  21. 20253D-PNAS: 3D Industrial Surface Anomaly Synthesis with Perlin Noisecited by 2
  22. 2025Out-of-Distribution Semantic Occupancy Predictioncited by 2
  23. 20253DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clusteringcited by 2
  24. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  25. 2025IAENet: An Importance-Aware Ensemble Model for 3D Point Cloud-Based Anomaly Detectioncited by 2
  26. 2025MCL-AD: Multimodal Collaboration Learning for Zero-Shot 3D Anomaly Detectioncited by 2
  27. 2026Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detectioncited by 2
  28. 2025PointAD+: Learning Hierarchical Representations for Zero-shot 3D Anomaly Detectioncited by 1
  29. 2026Multimodal Industrial Anomaly Detection via Geometric Priorcited by 1
  30. 2026Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detectioncited by 1
  31. 2026CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detectioncited by 1
  32. 2026Physics-inspired Pseudo Anomaly Generation and Prototype Feature Guidance for 3D Anomaly Detectioncited by 1
  33. 2025Position: Untrained Machine Learning for Anomaly Detection by using 3D Point Cloud Datacited by 0
  34. 2025Mentor3AD: Feature Reconstruction-based 3D Anomaly Detection via Multi-modality Mentor Learningcited by 0
  35. 2025Multi-View Reconstruction with Global Context for 3D Anomaly Detectioncited by 0
  36. 2025The 3D Mirage: Probing and Taming 3D Hallucinationscited by 0
  37. 2026Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chainingcited by 0
  38. 2026Open-Set Supervised 3D Anomaly Detection: An Industrial Dataset and a Generalisable Framework for Unknown Defectscited by 0

50 most cited of 67 All 67 (JSON)