Open Source library for easy and modular Visual Anomaly Detection
-
Updated
Apr 20, 2026 - Python
Open Source library for easy and modular Visual Anomaly Detection
[WACV-2026] VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion
Clean reproduction of UniAD (You et al., NeurIPS 2022 Spotlight) on MVTec-AD - multi-class anomaly detection and localization with one unified transformer-based reconstruction model.
Clean reproduction of WinCLIP (Jeong et al., CVPR 2023) on MVTec-AD and VisA — zero-shot and few-normal-shot anomaly classification and segmentation with CLIP.
Product Inspection with FOMO AD (Visual Anomaly Detection) by Edge Impulse on Sony Spresense camera and LCD 1602
Clean reproduction of PatchCore (Roth et al., CVPR 2022) on MVTec-AD with image-level AUROC, pixel-level AUROC, and pixel-level AUPRO. First in a series of visual anomaly detection reproductions.
Add a description, image, and links to the visual-anomaly-detection topic page so that developers can more easily learn about it.
To associate your repository with the visual-anomaly-detection topic, visit your repo's landing page and select "manage topics."