Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defects
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908444138668032 |
|---|---|
| author | Cheng, Yuqi Sun, Yihan Zhang, Hui Shen, Weiming Cao, Yunkang |
| author_facet | Cheng, Yuqi Sun, Yihan Zhang, Hui Shen, Weiming Cao, Yunkang |
| contents | In industrial point cloud analysis, detecting subtle anomalies demands high-resolution spatial data, yet prevailing benchmarks emphasize low-resolution inputs. To address this disparity, we propose a scalable pipeline for generating realistic and subtle 3D anomalies. Employing this pipeline, we developed MiniShift, the inaugural high-resolution 3D anomaly detection dataset, encompassing 2,577 point clouds, each with 500,000 points and anomalies occupying less than 1\% of the total. We further introduce Simple3D, an efficient framework integrating Multi-scale Neighborhood Descriptors (MSND) and Local Feature Spatial Aggregation (LFSA) to capture intricate geometric details with minimal computational overhead, achieving real-time inference exceeding 20 fps. Extensive evaluations on MiniShift and established benchmarks demonstrate that Simple3D surpasses state-of-the-art methods in both accuracy and speed, highlighting the pivotal role of high-resolution data and effective feature aggregation in advancing practical 3D anomaly detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07435 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defects Cheng, Yuqi Sun, Yihan Zhang, Hui Shen, Weiming Cao, Yunkang Computer Vision and Pattern Recognition In industrial point cloud analysis, detecting subtle anomalies demands high-resolution spatial data, yet prevailing benchmarks emphasize low-resolution inputs. To address this disparity, we propose a scalable pipeline for generating realistic and subtle 3D anomalies. Employing this pipeline, we developed MiniShift, the inaugural high-resolution 3D anomaly detection dataset, encompassing 2,577 point clouds, each with 500,000 points and anomalies occupying less than 1\% of the total. We further introduce Simple3D, an efficient framework integrating Multi-scale Neighborhood Descriptors (MSND) and Local Feature Spatial Aggregation (LFSA) to capture intricate geometric details with minimal computational overhead, achieving real-time inference exceeding 20 fps. Extensive evaluations on MiniShift and established benchmarks demonstrate that Simple3D surpasses state-of-the-art methods in both accuracy and speed, highlighting the pivotal role of high-resolution data and effective feature aggregation in advancing practical 3D anomaly detection. |
| title | Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defects |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.07435 |