mlsanityData to 7 Oct 2026

A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detection

arXiv 2603.25159 ↗First posted 26 Mar 2026cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

3D anomaly detection targets the detection and localization of defects in 3D point clouds trained solely on normal data. While a unified model improves scalability by learning across multiple categories, it often suffers from Inter-Category Entanglement (ICE)-where latent features from different categories overlap, causing the model to adopt incorrect semantic priors during reconstruction and ultimately yielding unreliable anomaly scores. To address this issue, we propose the Semantically Disentangled Unified Model for 3D Anomaly Detection, which reconstructs features conditioned on disentangled semantic representations. Our framework consists of three key components: (i) Coarse-to-Fine Global Tokenization for forming instance-level semantic identity, (ii) Category-Conditioned Contrastive Learning for disentangling category semantics, and (iii) a Geometry-Guided Decoder for semantically consistent reconstruction. Extensive experiments on Real3D-AD and Anomaly-ShapeNet demonstrate that our method achieves state-of-the-art for both unified and category-specific models, improving object-level AUROC by 2.8% and 9.1%, respectively, while enhancing the reliability of unified 3D anomaly detection.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 35 of its 46 references that are in the map. First posted on arXiv 26 Mar 2026.

Builds on

35 of 46 references.

References · 35

  1. 2016Layer Normalizationcited by 5,579
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  4. 2020Supervised Contrastive Learningcited by 2,803
  5. 2020Point Transformercited by 1,462
  6. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  7. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  8. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  9. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  10. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 138
  11. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  12. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
23 more
  1. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 92
  2. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 92
  3. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  4. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  5. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 79
  6. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 74
  7. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  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. 2024R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detectioncited by 45
  11. 2022Self-Supervised Masking for Unsupervised Anomaly Detection and Localizationcited by 43
  12. 2023TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detectioncited by 43
  13. 2024GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detectioncited by 42
  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. 2024GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Featurescited by 29
  17. 2024Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learningcited by 25
  18. 2024ResAD: A Simple Framework for Class Generalizable Anomaly Detectioncited by 24
  19. 2025MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detectioncited by 23
  20. 2024Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detectioncited by 19
  21. 2024Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detectioncited by 15
  22. 2025Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detectioncited by 10
  23. 2024Boosting Fine-Grained Visual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learningcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026MVFM-3DAD: Multi-view Flow Matching for 3D Anomaly Detection via Density Proxy Estimationcited by 0
  2. 2026AT3D-AD: Anomaly Type-Aware 3D Anomaly Detection via Hierarchical Point-Language Alignmentcited by 0
  3. 2026Beyond Geometry: Benchmarking and Consistency Reasoning for 3D Logical Anomaly Detectioncited by 0