mlsanityData to 14 Oct 2026

Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection

arXiv 2507.03903 ↗First posted 5 Jul 2025cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Reconstruction-based methods have demonstrated very promising results for 3D anomaly detection. However, these methods face great challenges in handling high-precision point clouds due to the large scale and complex structure. In this study, a Down-Up Sampling Network (DUS-Net) is proposed to reconstruct high-precision point clouds for 3D anomaly detection by preserving the group center geometric structure. The DUS-Net first introduces a Noise Generation module to generate noisy patches, which facilitates the diversity of training data and strengthens the feature representation for reconstruction. Then, a Down-sampling Network (Down-Net) is developed to learn an anomaly-free center point cloud from patches with noise injection. Subsequently, an Up-sampling Network (Up-Net) is designed to reconstruct high-precision point clouds by fusing multi-scale up-sampling features. Our method leverages group centers for construction, enabling the preservation of geometric structure and providing a more precise point cloud. Extensive experiments demonstrate the effectiveness of our proposed method, achieving state-of-the-art (SOTA) performance with an Object-level AUROC of 79.9% and 79.5%, and a Point-level AUROC of 71.2% and 84.7% on the Real3D-AD and Anomaly-ShapeNet datasets, respectively.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 35 of its 43 references that are in the map. First posted on arXiv 5 Jul 2025.

Builds on

35 of 43 references.

References · 35

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  4. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  5. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  6. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  7. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  8. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  9. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  10. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 139
  11. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  12. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 112
23 more
  1. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  2. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 93
  3. 2022Balanced MSE for Imbalanced Visual Regressioncited by 89
  4. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  5. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 75
  6. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  7. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 68
  8. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  9. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  10. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  11. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  12. 2023Multimodal Industrial Anomaly Detection by Crossmodal Feature Mappingcited by 42
  13. 2024Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detectioncited by 30
  14. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  15. 2024SplatPose & Detect: Pose-Agnostic 3D Anomaly Detectioncited by 25
  16. 2024Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learningcited by 25
  17. 2022Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detectioncited by 18
  18. 2025Exploring the Potential of Encoder-free Architectures in 3D LMMscited by 16
  19. 2024Looking 3D: Anomaly Detection with 2D-3D Alignmentcited by 13
  20. 2024Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspectivecited by 12
  21. 2024SplatPose+: Real-time Image-Based Pose-Agnostic 3D Anomaly Detectioncited by 11
  22. 2024Towards Zero-shot 3D Anomaly Localizationcited by 8
  23. 2024Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Surveycited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 6.

11 papers.

  1. 2025A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Featurescited by 5
  2. 2025C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisorcited by 3
  3. 2025IEC3D-AD: A 3D Dataset of Industrial Equipment Components for Unsupervised Point Cloud Anomaly Detectioncited by 3
  4. 20253DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clusteringcited by 2
  5. 2025The 1st International Workshop on Disentangled Representation Learning for Controllable Generation (DRL4Real): Methods and Resultscited by 0
  6. 2026Open-Set Supervised 3D Anomaly Detection: An Industrial Dataset and a Generalisable Framework for Unknown Defectscited by 0
  7. 2026Learning Discriminative Signed Distance Functions from Multi-scale Level-of-detail Features for 3D Anomaly Detectioncited by 0
  8. 2026CoGeoAD: Hierarchical Color-Geometric Fusion with Multi-View Attention for Zero-Shot 3D Anomaly Detectioncited by 0
  9. 2026MVFM-3DAD: Multi-view Flow Matching for 3D Anomaly Detection via Density Proxy Estimationcited by 0
  10. 2026PC2-AD: Point Cloud Upsampling to Safeguard 3D Anomaly Detection with Resolution-constrained Edge Devicescited by 0
  11. 2026Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modelingcited by 0