# Towards Zero-shot 3D Anomaly Localization

arXiv: https://arxiv.org/abs/2412.04304 · HTML: https://mlsanity.com/paper/2412.04304/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 56 references that are in the map.
- First posted on arXiv 5 Dec 2024.

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [Sub-Image Anomaly Detection with Deep Pyramid Correspondences](https://mlsanity.com/paper/2005.02357/) (2020)
- [AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2310.18961/) (2023)
- [The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization](https://mlsanity.com/paper/2112.09045/) (2021)
- [Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP](https://mlsanity.com/paper/2109.02748/) (2021)
- [Multimodal Industrial Anomaly Detection via Hybrid Fusion](https://mlsanity.com/paper/2303.00601/) (2023)
- [Registration based Few-Shot Anomaly Detection](https://mlsanity.com/paper/2207.07361/) (2022)
- [Explainable Deep One-Class Classification](https://mlsanity.com/paper/2007.01760/) (2020)
- [Asymmetric Student-Teacher Networks for Industrial Anomaly Detection](https://mlsanity.com/paper/2210.07829/) (2022)
- [Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection](https://mlsanity.com/paper/2203.14506/) (2022)
- [Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection](https://mlsanity.com/paper/2203.05550/) (2022)
- [Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection](https://mlsanity.com/paper/2303.13194/) (2023)
- [Explainable Deep Few-shot Anomaly Detection with Deviation Networks](https://mlsanity.com/paper/2108.00462/) (2021)
- [Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptors](https://mlsanity.com/paper/2202.11660/) (2022)
- [IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing](https://mlsanity.com/paper/2301.13359/) (2023)
- [Few-shot Scene-adaptive Anomaly Detection](https://mlsanity.com/paper/2007.07843/) (2020)
- [A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection](https://mlsanity.com/paper/2104.14535/) (2021)
- [Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization](https://mlsanity.com/paper/2302.08769/) (2023)
- [Small-GAN: Speeding Up GAN Training Using Core-sets](https://mlsanity.com/paper/1910.13540/) (2019)
- [Transductive Zero-Shot Learning for 3D Point Cloud Classification](https://mlsanity.com/paper/1912.07161/) (2019)
- [Zero-Shot Learning on 3D Point Cloud Objects and Beyond](https://mlsanity.com/paper/2104.04980/) (2021)
- [Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images](https://mlsanity.com/paper/2205.11474/) (2022)

## Built on by (most cited first, 8 of 8)

- [Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection](https://mlsanity.com/paper/2507.03903/) (2025)
- [Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detection](https://mlsanity.com/paper/2503.01100/) (2025)
- [Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detection](https://mlsanity.com/paper/2505.05901/) (2025)
- [GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learning](https://mlsanity.com/paper/2602.19206/) (2026)
- [MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samples](https://mlsanity.com/paper/2511.10047/) (2025)
- [A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospects](https://mlsanity.com/paper/2507.13378/) (2025)
- [Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection](https://mlsanity.com/paper/2603.21511/) (2026)
- [Open-Set Supervised 3D Anomaly Detection: An Industrial Dataset and a Generalisable Framework for Unknown Defects](https://mlsanity.com/paper/2604.01171/) (2026)

## Abstract (arXiv)

3D anomaly detection and localization is of great significance for industrial inspection. Prior 3D anomaly detection and localization methods focus on the setting that the testing data share the same category as the training data which is normal. However, in real-world applications, the normal training data for the target 3D objects can be unavailable due to issues like data privacy or export control regulation. To tackle these challenges, we identify a new task -- zero-shot 3D anomaly detection and localization, where the training and testing classes do not overlap. To this end, we design 3DzAL, a novel patch-level contrastive learning framework based on pseudo anomalies generated using the inductive bias from task-irrelevant 3D xyz data to learn more representative feature representations. Furthermore, we train a normalcy classifier network to classify the normal patches and pseudo anomalies and utilize the classification result jointly with feature distance to design anomaly scores. Instead of directly using the patch point clouds, we introduce adversarial perturbations to the input patch xyz data before feeding into the 3D normalcy classifier for the classification-based anomaly score. We show that 3DzAL outperforms the state-of-the-art anomaly detection and localization performance.