mlsanityData to 14 Oct 2026

R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection

arXiv 2407.10862 ↗First posted 15 Jul 2024cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

3D anomaly detection plays a crucial role in monitoring parts for localized inherent defects in precision manufacturing. Embedding-based and reconstruction-based approaches are among the most popular and successful methods. However, there are two major challenges to the practical application of the current approaches: 1) the embedded models suffer the prohibitive computational and storage due to the memory bank structure; 2) the reconstructive models based on the MAE mechanism fail to detect anomalies in the unmasked regions. In this paper, we propose R3D-AD, reconstructing anomalous point clouds by diffusion model for precise 3D anomaly detection. Our approach capitalizes on the data distribution conversion of the diffusion process to entirely obscure the input's anomalous geometry. It step-wisely learns a strict point-level displacement behavior, which methodically corrects the aberrant points. To increase the generalization of the model, we further present a novel 3D anomaly simulation strategy named Patch-Gen to generate realistic and diverse defect shapes, which narrows the domain gap between training and testing. Our R3D-AD ensures a uniform spatial transformation, which allows straightforwardly generating anomaly results by distance comparison. Extensive experiments show that our R3D-AD outperforms previous state-of-the-art methods, achieving 73.4% Image-level AUROC on the Real3D-AD dataset and 74.9% Image-level AUROC on the Anomaly-ShapeNet dataset with an exceptional efficiency.

Key facts. Cited by 45 papers in the map (data through 14 Oct 2026). Builds on 40 of its 44 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

40 of 44 references.

References · 40

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  10. 2015Variational Inference with Normalizing Flowscited by 2,170
  11. 2016Density estimation using Real NVPcited by 2,042
  12. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
28 more
  1. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  2. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  3. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  4. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  5. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  6. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  7. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  8. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  9. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  10. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  11. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
  12. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 227
  13. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  14. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 199
  15. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 139
  16. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  17. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  18. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  19. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 111
  20. 2023DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generationcited by 110
  21. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 93
  22. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  23. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 75
  24. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  25. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  26. 2023DiffComplete: Diffusion-based Generative 3D Shape Completioncited by 35
  27. 2022FAPM: Fast Adaptive Patch Memory for Real-time Industrial Anomaly Detectioncited by 16
  28. 2022U-Flow: A U-shaped Normalizing Flow for Anomaly Detection with Unsupervised Thresholdcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 21; 2026: 21.

45 papers.

Sort:

By area:

  1. 2024PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detectioncited by 30
  2. 2025MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detectioncited by 23
  3. 2025Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defectscited by 15
  4. 2024Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspectivecited by 12
  5. 2025Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric Representationcited by 9
  6. 2025Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detectioncited by 7
  7. 2024Uni-3DAD: GAN-Inversion Aided Universal 3D Anomaly Detection on Model-free Productscited by 5
  8. 2025A Survey on Foundation-Model-Based Industrial Defect Detectioncited by 5
  9. 2025CASL: Curvature-Augmented Self-supervised Learning for 3D Anomaly Detectioncited by 5
  10. 2025A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Featurescited by 5
  11. 2025Exploiting Point-Language Models with Dual-Prompts for 3D Anomaly Detectioncited by 4
  12. 2025Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detectioncited by 4
33 more
  1. 2025Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detectioncited by 4
  2. 2026GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learningcited by 4
  3. 2025C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisorcited by 3
  4. 2025IEC3D-AD: A 3D Dataset of Industrial Equipment Components for Unsupervised Point Cloud Anomaly Detectioncited by 3
  5. 2025MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samplescited by 3
  6. 2026A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detectioncited by 3
  7. 2026Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detectioncited by 3
  8. 20253D-PNAS: 3D Industrial Surface Anomaly Synthesis with Perlin Noisecited by 2
  9. 2025Out-of-Distribution Semantic Occupancy Predictioncited by 2
  10. 20253DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clusteringcited by 2
  11. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  12. 2026Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detectioncited by 2
  13. 2025Time-reversed Flow Matching with Worst Transport in High-dimensional Latent Space for Image Anomaly Detectioncited by 1
  14. 2026Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detectioncited by 1
  15. 2026Physics-inspired Pseudo Anomaly Generation and Prototype Feature Guidance for 3D Anomaly Detectioncited by 1
  16. 2025Mentor3AD: Feature Reconstruction-based 3D Anomaly Detection via Multi-modality Mentor Learningcited by 0
  17. 2025Multi-View Reconstruction with Global Context for 3D Anomaly Detectioncited by 0
  18. 2025The 3D Mirage: Probing and Taming 3D Hallucinationscited by 0
  19. 2026Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chainingcited by 0
  20. 2026Open-Set Supervised 3D Anomaly Detection: An Industrial Dataset and a Generalisable Framework for Unknown Defectscited by 0
  21. 2026Synthesis4AD: Synthetic Anomalies are All You Need for 3D Anomaly Detectioncited by 0
  22. 2026Learning Discriminative Signed Distance Functions from Multi-scale Level-of-detail Features for 3D Anomaly Detectioncited by 0
  23. 2026Characterizing Detectability in 3DGS Poisoning: A Stage-wise Benchmarkcited by 0
  24. 2026CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detectioncited by 0
  25. 2026CoGeoAD: Hierarchical Color-Geometric Fusion with Multi-View Attention for Zero-Shot 3D Anomaly Detectioncited by 0
  26. 2026Point Cloud Diffusion with Global and Local Reconstruction for Instance-Level 3D Anomaly Detectioncited by 0
  27. 2026Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentationcited by 0
  28. 2026M2P-AD: Memory-to-Prototype Learning with Boundary-aware Score Refinement for 3D Anomaly Detectioncited by 0
  29. 2026MVFM-3DAD: Multi-view Flow Matching for 3D Anomaly Detection via Density Proxy Estimationcited by 0
  30. 2026PC2-AD: Point Cloud Upsampling to Safeguard 3D Anomaly Detection with Resolution-constrained Edge Devicescited by 0
  31. 2026AT3D-AD: Anomaly Type-Aware 3D Anomaly Detection via Hierarchical Point-Language Alignmentcited by 0
  32. 2026Beyond Geometry: Benchmarking and Consistency Reasoning for 3D Logical Anomaly Detectioncited by 0
  33. 2026Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modelingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Two Steps Are All You Need: Efficient 3D Point Cloud Anomaly Detection with Consistency Models
  2. 2023TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection
  3. 2026Cross-Modal Mapping and Dual-Branch Reconstruction for 2D-3D Multimodal Industrial Anomaly Detection
  4. 2023DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection
  5. 2024Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation
  6. 2025Single-Step Reconstruction-Free Anomaly Detection and Segmentation via Diffusion Models
  7. 2024Enhancing Multi-Class Anomaly Detection via Diffusion Refinement with Dual Conditioning
  8. 2025RcAE: Recursive Reconstruction Framework for Unsupervised Industrial Anomaly Detection