Real-IAD D3: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Wenbing, Wang, Lidong, Zhou, Ziqing, Wang, Chengjie, Pan, Yurui, Zhang, Ruoyi, Chen, Zhuhao, Cheng, Linjie, Gao, Bin-Bin, Zhang, Jiangning, Gan, Zhenye, Wang, Yuxie, Chen, Yulong, Qian, Shuguang, Chi, Mingmin, Peng, Bo, Ma, Lizhuang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916698493288448
author Zhu, Wenbing
Wang, Lidong
Zhou, Ziqing
Wang, Chengjie
Pan, Yurui
Zhang, Ruoyi
Chen, Zhuhao
Cheng, Linjie
Gao, Bin-Bin
Zhang, Jiangning
Gan, Zhenye
Wang, Yuxie
Chen, Yulong
Qian, Shuguang
Chi, Mingmin
Peng, Bo
Ma, Lizhuang
author_facet Zhu, Wenbing
Wang, Lidong
Zhou, Ziqing
Wang, Chengjie
Pan, Yurui
Zhang, Ruoyi
Chen, Zhuhao
Cheng, Linjie
Gao, Bin-Bin
Zhang, Jiangning
Gan, Zhenye
Wang, Yuxie
Chen, Yulong
Qian, Shuguang
Chi, Mingmin
Peng, Bo
Ma, Lizhuang
contents The increasing complexity of industrial anomaly detection (IAD) has positioned multimodal detection methods as a focal area of machine vision research. However, dedicated multimodal datasets specifically tailored for IAD remain limited. Pioneering datasets like MVTec 3D have laid essential groundwork in multimodal IAD by incorporating RGB+3D data, but still face challenges in bridging the gap with real industrial environments due to limitations in scale and resolution. To address these challenges, we introduce Real-IAD D3, a high-precision multimodal dataset that uniquely incorporates an additional pseudo3D modality generated through photometric stereo, alongside high-resolution RGB images and micrometer-level 3D point clouds. Real-IAD D3 features finer defects, diverse anomalies, and greater scale across 20 categories, providing a challenging benchmark for multimodal IAD Additionally, we introduce an effective approach that integrates RGB, point cloud, and pseudo-3D depth information to leverage the complementary strengths of each modality, enhancing detection performance. Our experiments highlight the importance of these modalities in boosting detection robustness and overall IAD performance. The dataset and code are publicly accessible for research purposes at https://realiad4ad.github.io/Real-IAD D3
format Preprint
id arxiv_https___arxiv_org_abs_2504_14221
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Real-IAD D3: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detection
Zhu, Wenbing
Wang, Lidong
Zhou, Ziqing
Wang, Chengjie
Pan, Yurui
Zhang, Ruoyi
Chen, Zhuhao
Cheng, Linjie
Gao, Bin-Bin
Zhang, Jiangning
Gan, Zhenye
Wang, Yuxie
Chen, Yulong
Qian, Shuguang
Chi, Mingmin
Peng, Bo
Ma, Lizhuang
Computer Vision and Pattern Recognition
The increasing complexity of industrial anomaly detection (IAD) has positioned multimodal detection methods as a focal area of machine vision research. However, dedicated multimodal datasets specifically tailored for IAD remain limited. Pioneering datasets like MVTec 3D have laid essential groundwork in multimodal IAD by incorporating RGB+3D data, but still face challenges in bridging the gap with real industrial environments due to limitations in scale and resolution. To address these challenges, we introduce Real-IAD D3, a high-precision multimodal dataset that uniquely incorporates an additional pseudo3D modality generated through photometric stereo, alongside high-resolution RGB images and micrometer-level 3D point clouds. Real-IAD D3 features finer defects, diverse anomalies, and greater scale across 20 categories, providing a challenging benchmark for multimodal IAD Additionally, we introduce an effective approach that integrates RGB, point cloud, and pseudo-3D depth information to leverage the complementary strengths of each modality, enhancing detection performance. Our experiments highlight the importance of these modalities in boosting detection robustness and overall IAD performance. The dataset and code are publicly accessible for research purposes at https://realiad4ad.github.io/Real-IAD D3
title Real-IAD D3: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.14221