mlsanityData to 14 Oct 2026

Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modeling

arXiv 2609.35059 ↗First posted 28 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

3D anomaly detection (3DAD) aims to identify defective regions in point cloud data, serving as a critical component in industrial inspection systems. Existing methods are normality-centered -- learning the distribution of normal samples and treating deviations as anomalies -- without explicitly modeling what constitutes a defect. This leads to ambiguous decision boundaries with increased false positives and negatives, particularly in unified and cross-domain settings where diverse normal distributions further blur the boundaries. We propose a relational inconsistency modeling framework that characterizes defects as violations of geometric consistency among neighboring structures. Our approach learns category-agnostic defect cues through pseudo-anomalies designed as controlled relational violations, instantiated by two key modules: Edge-aware Graph Refinement (EGR) for encoding geometric relationships among local regions, and Cluster-Deviation Modeling (CDM) for identifying regions that are relationally incompatible within their structural peer group. Extensive experiments on Anomaly-ShapeNet and Real3D-AD demonstrate consistent improvements over prior state-of-the-art methods in both in-domain and cross-domain settings, validating the effectiveness of learning an explicit, relation-based defect criterion for 3D anomaly detection. Project page: https://visualsciencelab-khu.github.io/GRIM_project/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 44 references that are in the map. First posted on arXiv 28 Sep 2026.

Builds on

35 of 44 references.

References · 35

  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  2. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  3. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  4. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  5. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  6. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  7. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  8. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  9. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  10. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 154
  11. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 139
  12. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
23 more
  1. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  2. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  3. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  4. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 111
  5. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 93
  6. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 93
  7. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  8. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 75
  9. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  10. 2022Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptorscited by 66
  11. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  12. 2022The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localizationcited by 57
  13. 2024R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detectioncited by 45
  14. 2024PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detectioncited by 30
  15. 2024Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detectioncited by 30
  16. 2024Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learningcited by 25
  17. 2024ResAD: A Simple Framework for Class Generalizable Anomaly Detectioncited by 25
  18. 2025MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detectioncited by 23
  19. 2025Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly Detectioncited by 16
  20. 2024Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detectioncited by 15
  21. 2025Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detectioncited by 11
  22. 2025Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric Representationcited by 9
  23. 2025Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detectioncited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Synthesis4AD: Synthetic Anomalies are All You Need for 3D Anomaly Detection
  2. 2026Two Steps Are All You Need: Efficient 3D Point Cloud Anomaly Detection with Consistency Models
  3. 2026Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection
  4. 2025Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection
  5. 2026Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space
  6. 2026Cross-Modal Mapping and Dual-Branch Reconstruction for 2D-3D Multimodal Industrial Anomaly Detection
  7. 2025AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection
  8. 2025Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Process