mlsanityData to 14 Oct 2026

Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric Representation

arXiv 2505.24431 ↗First posted 30 May 2025cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

3D point cloud anomaly detection is essential for robust vision systems but is challenged by pose variations and complex geometric anomalies. Existing patch-based methods often suffer from geometric fidelity issues due to discrete voxelization or projection-based representations, limiting fine-grained anomaly localization. We introduce Pose-Aware Signed Distance Field (PASDF), a novel framework that integrates 3D anomaly detection and repair by learning a continuous, pose-invariant shape representation. PASDF leverages a Pose Alignment Module for canonicalization and a SDF Network to dynamically incorporate pose, enabling implicit learning of high-fidelity anomaly repair templates from the continuous SDF. This facilitates precise pixel-level anomaly localization through an Anomaly-Aware Scoring Module. Crucially, the continuous 3D representation in PASDF extends beyond detection, facilitating in-situ anomaly repair. Experiments on Real3D-AD and Anomaly-ShapeNet demonstrate state-of-the-art performance, achieving high object-level AUROC scores of 80.2% and 90.0%, respectively. These results highlight the effectiveness of continuous geometric representations in advancing 3D anomaly detection and facilitating practical anomaly region repair. The code is available at https://github.com/ZZZBBBZZZ/PASDF to support further research.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 28 of its 43 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

28 of 43 references.

References · 28

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  3. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  4. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  5. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  6. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  7. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  8. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  9. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  10. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 148
  11. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 139
  12. 2022Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functionscited by 133
16 more
  1. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  2. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 93
  3. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  4. 2021Learning Signed Distance Field for Multi-view Surface Reconstructioncited by 76
  5. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 75
  6. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  7. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  8. 2022Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptorscited by 66
  9. 2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 63
  10. 2024R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detectioncited by 45
  11. 2023EasyNet: An Easy Network for 3D Industrial Anomaly Detectioncited by 43
  12. 2023Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulationcited by 33
  13. 2024PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detectioncited by 30
  14. 2024Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learningcited by 25
  15. 2024Self-supervised Feature Adaptation for 3D Industrial Anomaly Detectioncited by 16
  16. 2024Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Frameworkcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 7.

9 papers.

  1. 2025A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Featurescited by 5
  2. 2025The 3D Mirage: Probing and Taming 3D Hallucinationscited by 0
  3. 2026Open-Set Supervised 3D Anomaly Detection: An Industrial Dataset and a Generalisable Framework for Unknown Defectscited by 0
  4. 2026Breaking the Rigid Prior: Towards Articulated 3D Anomaly Detectioncited by 0
  5. 2026CoGeoAD: Hierarchical Color-Geometric Fusion with Multi-View Attention for Zero-Shot 3D Anomaly Detectioncited by 0
  6. 2026Point Cloud Diffusion with Global and Local Reconstruction for Instance-Level 3D Anomaly Detectioncited by 0
  7. 2026Understanding and Overcoming Cross-modal Fusion Bias in Multimodal Anomaly Detection From A Fisher Information Perspectivecited by 0
  8. 2026PC2-AD: Point Cloud Upsampling to Safeguard 3D Anomaly Detection with Resolution-constrained Edge Devicescited by 0
  9. 2026Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modelingcited by 0