mlsanityData to 7 Oct 2026

PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection

arXiv 2410.00320 ↗First posted 1 Oct 2024cs.CV cs.CLcited by 29

Not on the map. Why?

Abstract (arXiv)

Zero-shot (ZS) 3D anomaly detection is a crucial yet unexplored field that addresses scenarios where target 3D training samples are unavailable due to practical concerns like privacy protection. This paper introduces PointAD, a novel approach that transfers the strong generalization capabilities of CLIP for recognizing 3D anomalies on unseen objects. PointAD provides a unified framework to comprehend 3D anomalies from both points and pixels. In this framework, PointAD renders 3D anomalies into multiple 2D renderings and projects them back into 3D space. To capture the generic anomaly semantics into PointAD, we propose hybrid representation learning that optimizes the learnable text prompts from 3D and 2D through auxiliary point clouds. The collaboration optimization between point and pixel representations jointly facilitates our model to grasp underlying 3D anomaly patterns, contributing to detecting and segmenting anomalies of unseen diverse 3D objects. Through the alignment of 3D and 2D space, our model can directly integrate RGB information, further enhancing the understanding of 3D anomalies in a plug-and-play manner. Extensive experiments show the superiority of PointAD in ZS 3D anomaly detection across diverse unseen objects.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 53 of its 65 references that are in the map. First posted on arXiv 1 Oct 2024.

Builds on

53 of 65 references.

References · 53

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023Segment Anythingcited by 8,158
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  6. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  7. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  8. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  9. 2022MaPLe: Multi-modal Prompt Learningcited by 685
  10. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  11. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 530
  12. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
38 more
  1. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  2. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  3. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  4. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  5. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  6. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  7. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  8. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
  9. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  10. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 186
  11. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  12. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 151
  13. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  14. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  15. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 138
  16. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  17. 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 128
  18. 2020Explainable Deep One-Class Classificationcited by 126
  19. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 115
  20. 2022DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotationscited by 102
  21. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 92
  22. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 87
  23. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  24. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  25. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 74
  26. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
  27. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  28. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  29. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  30. 2022Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptorscited by 66
  31. 2022The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localizationcited by 55
  32. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  33. 2021Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Imagescited by 45
  34. 2023EasyNet: An Easy Network for 3D Industrial Anomaly Detectioncited by 43
  35. 2021Zero-Shot Learning on 3D Point Cloud Objects and Beyondcited by 38
  36. 2022Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Imagescited by 35
  37. 2023Anomaly Detection under Distribution Shiftcited by 35
  38. 2023Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulationcited by 33

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 16; 2026: 13.

29 papers.

Sort:

By area:

  1. 2025MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detectioncited by 23
  2. 2025Normal-Abnormal Guided Generalist Anomaly Detectioncited by 10
  3. 2025AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detectioncited by 8
  4. 2025A Survey on Foundation-Model-Based Industrial Defect Detectioncited by 5
  5. 2025CASL: Curvature-Augmented Self-supervised Learning for 3D Anomaly Detectioncited by 5
  6. 2025Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detectioncited by 4
  7. 2025Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detectioncited by 4
  8. 2026GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learningcited by 4
  9. 2025MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samplescited by 3
  10. 2026Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detectioncited by 3
  11. 20253D-PNAS: 3D Industrial Surface Anomaly Synthesis with Perlin Noisecited by 2
  12. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
17 more
  1. 2025IAENet: An Importance-Aware Ensemble Model for 3D Point Cloud-Based Anomaly Detectioncited by 2
  2. 2025MCL-AD: Multimodal Collaboration Learning for Zero-Shot 3D Anomaly Detectioncited by 2
  3. 2026Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detectioncited by 2
  4. 2025PointAD+: Learning Hierarchical Representations for Zero-shot 3D Anomaly Detectioncited by 1
  5. 2026Multimodal Industrial Anomaly Detection via Geometric Priorcited by 1
  6. 2025Preference Isolation Forest for Structure-based Anomaly Detectioncited by 0
  7. 2025Mentor3AD: Feature Reconstruction-based 3D Anomaly Detection via Multi-modality Mentor Learningcited by 0
  8. 2025TokenCLIP: Token-wise Prompt Learning for Zero-shot Anomaly Detectioncited by 0
  9. 2026Open-Set Supervised 3D Anomaly Detection: An Industrial Dataset and a Generalisable Framework for Unknown Defectscited by 0
  10. 2026Synthesis4AD: Synthetic Anomalies are All You Need for 3D Anomaly Detectioncited by 0
  11. 2026SGANet: Semantic and Geometric Alignment for Multimodal Multi-view Anomaly Detectioncited by 0
  12. 2026Learning Discriminative Signed Distance Functions from Multi-scale Level-of-detail Features for 3D Anomaly Detectioncited by 0
  13. 2026Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detectioncited by 0
  14. 2026CoGeoAD: Hierarchical Color-Geometric Fusion with Multi-View Attention for Zero-Shot 3D Anomaly Detectioncited by 0
  15. 2026MVFM-3DAD: Multi-view Flow Matching for 3D Anomaly Detection via Density Proxy Estimationcited by 0
  16. 2026When Point Clouds Outperform Pixels: Rethinking Zero-Shot Multimodal Anomaly Detectioncited by 0
  17. 2026AT3D-AD: Anomaly Type-Aware 3D Anomaly Detection via Hierarchical Point-Language Alignmentcited by 0