Articles added in the last year, sorted by date

CLIP3D-AD: Extending CLIP for 3D Few-Shot Anomaly Detection with Multi-View Images Generation

Z Zuo, J Dong, Y Wu, Y Qu, Z Wu - arXiv preprint arXiv:2406.18941, 2024 - arxiv.org
19 days ago - Few-shot anomaly detection methods can effectively address data collecting
difficulty in industrial scenarios. Compared to 2D few-shot anomaly detection (2D-FSAD), 3D …

An Anomaly Detection Method for Railway Track Using Semi-supervised Learning and Vision-Lidar Decision Fusion

X Ge, Z Cao, Y Qin, Y Gao, L Lian… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
26 days ago - Anomaly detection of the railway track is essential to protect the safety of
railway transportation. However, the railway track is often disturbed by unknown anomalies …

[PDF][PDF] Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping Supplementary Material

A Costanzino, PZ Ramirez, G Lisanti, L Di Stefano - openaccess.thecvf.com
36 days ago - The chart in Fig. 1 reports the Per-Region Overlap curve provided by our
method on class Foam of the MVTec 3D-AD dataset. The chart shows how most of the …

Back to the Metrics: Exploration of Distance Metrics in Anomaly Detection

Y Lin, X Li - 2024 - preprints.org
37 days ago - With increasing research focus on industrial anomaly detection, numerous
methods have emerged in this domain. Notably, memory bank-based approaches, coupled …

M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising

C Wang, H Zhu, J Peng, Y Wang, R Yi, Y Wu… - arXiv preprint arXiv …, 2024 - arxiv.org
42 days ago - Existing industrial anomaly detection methods primarily concentrate on
unsupervised learning with pristine RGB images. Yet, both RGB and 3D data are crucial for …

Cross-Modal Distillation in Industrial Anomaly Detection: Exploring Efficient Multi-Modal IAD

W Sui, D Lichau, J Lefèvre, H Phelippeau - arXiv preprint arXiv …, 2024 - arxiv.org
56 days ago - Recent studies of multi-modal Industrial Anomaly Detection (IAD) based on
point clouds and RGB images indicated the importance of exploiting redundancy and …

Beyond Traditional Driving Scenes: A Robotic-Centric Paradigm for 2D+ 3D Human Tracking Using Siamese Transformer Network

S Xin, L Liu, X Kang, Z Zhang… - 2024 7th International …, 2024 - ieeexplore.ieee.org
71 days ago - 3D human tracking plays a crucial role in the automation intelligence system.
Current approaches focus on achieving higher performance on traditional driving datasets …

Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection

C Tang, S Zhou, Y Li, Y Dong, L Wang - arXiv preprint arXiv:2405.02068, 2024 - arxiv.org
75 days ago - With the wide application of knowledge distillation between an ImageNet pre-
trained teacher model and a learnable student model, industrial anomaly detection has …

AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion

J Hu, Y Huang, Y Lu, G Xie, G Jiang… - arXiv preprint arXiv …, 2024 - arxiv.org
77 days ago - Anomaly synthesis is one of the effective methods to augment abnormal
samples for training. However, current anomaly synthesis methods predominantly rely on …

Daup: Enhancing Point Cloud Homogeneity for 3d Industrial Anomaly Detection Via Density-Aware Point Cloud Upsampling

H Li, Y Niu, H Yin, Y Mo, Y Liu, B Huang, R Wu… - Available at SSRN … - papers.ssrn.com
85 days ago - The use of 3D information in industrial anomaly detection tasks has been
shown to enhance performance by uncovering unseen abnormal patterns in the RGB …