# VT-3DAD: Cross-Category 3D Anomaly Detection via Visual-Text Normal Space Alignment

arXiv: https://arxiv.org/abs/2606.04369 · HTML: https://mlsanity.com/paper/2606.04369/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 14 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2310.18961/) (2023)
- [PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning](https://mlsanity.com/paper/2211.11682/) (2022)
- [The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization](https://mlsanity.com/paper/2112.09045/) (2021)
- [Multimodal Industrial Anomaly Detection via Hybrid Fusion](https://mlsanity.com/paper/2303.00601/) (2023)
- [Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection](https://mlsanity.com/paper/2203.05550/) (2022)
- [Real3D-AD: A Dataset of Point Cloud Anomaly Detection](https://mlsanity.com/paper/2309.13226/) (2023)
- [AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP](https://mlsanity.com/paper/2503.06661/) (2025)
- [Toward Unsupervised 3D Point Cloud Anomaly Detection using Variational Autoencoder](https://mlsanity.com/paper/2304.03420/) (2023)
- [CLIP3D-AD: Extending CLIP for 3D Few-Shot Anomaly Detection with Multi-View Images Generation](https://mlsanity.com/paper/2406.18941/) (2024)
- [Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55](https://mlsanity.com/paper/1710.06104/) (2017)
- [Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Framework](https://mlsanity.com/paper/2409.13162/) (2024)
- [Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samples](https://mlsanity.com/paper/2210.17258/) (2022)
- [DMP-3DAD: Cross-Category 3D Anomaly Detection via Realistic Depth Map Projection with Few Normal Samples](https://mlsanity.com/paper/2602.10806/) (2026)

## Abstract (arXiv)

Few-shot cross-category 3D anomaly detection aims to determine whether an unknown point cloud belongs to a target normal category using only a few normal references. Existing training-based methods usually require category-wise optimization, while recent training-free methods based on multi-view CLIP visual features mainly rely on visual similarity and may be confused by geometrically similar categories. In this paper, we propose VT-3DAD, a training-free framework for cross-category 3D anomaly detection via Visual-Text Normal Space Alignment. Given few-shot normal references and a test point cloud, VT-3DAD first generates realistic multi-view depth maps and extracts view-wise features using a frozen CLIP visual encoder. The visual branch measures reference-test deviation in the multi-view feature space. In parallel, depth-aware and 3D-aware prompts are encoded by the frozen CLIP text encoder to construct textual normal anchors, which provide semantic normality constraints for the target category. The final anomaly score is obtained by fusing visual deviation from normal references and semantic deviation from the textual normal space. Experiments on the ShapeNetPart dataset demonstrate that VT-3DAD achieves state-of-the-art performance. In particular, VT-3DAD improves the one-shot average AUC-ROC from 92.49% to 94.80% compared with the visual-only baseline, while also reducing the average standard deviation from 5.64 to 3.41.