Finding Outliers in a Haystack: Anomaly Detection for Large Pointcloud Scenes
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908503330783232 |
|---|---|
| author | Faulkner, Ryan Haub, Luke Ratcliffe, Simon Chin, Tat-Jun |
| author_facet | Faulkner, Ryan Haub, Luke Ratcliffe, Simon Chin, Tat-Jun |
| contents | LiDAR scanning in outdoor scenes acquires accurate distance measurements over wide areas, producing large-scale point clouds. Application examples for this data include robotics, automotive vehicles, and land surveillance. During such applications, outlier objects from outside the training data will inevitably appear. Our research contributes a novel approach to open-set segmentation, leveraging the learnings of object defect-detection research. We also draw on the Mamba architecture's strong performance in utilising long-range dependencies and scalability to large data. Combining both, we create a reconstruction based approach for the task of outdoor scene open-set segmentation. We show that our approach improves performance not only when applied to our our own open-set segmentation method, but also when applied to existing methods. Furthermore we contribute a Mamba based architecture which is competitive with existing voxel-convolution based methods on challenging, large-scale pointclouds. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17634 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Finding Outliers in a Haystack: Anomaly Detection for Large Pointcloud Scenes Faulkner, Ryan Haub, Luke Ratcliffe, Simon Chin, Tat-Jun Computer Vision and Pattern Recognition Artificial Intelligence LiDAR scanning in outdoor scenes acquires accurate distance measurements over wide areas, producing large-scale point clouds. Application examples for this data include robotics, automotive vehicles, and land surveillance. During such applications, outlier objects from outside the training data will inevitably appear. Our research contributes a novel approach to open-set segmentation, leveraging the learnings of object defect-detection research. We also draw on the Mamba architecture's strong performance in utilising long-range dependencies and scalability to large data. Combining both, we create a reconstruction based approach for the task of outdoor scene open-set segmentation. We show that our approach improves performance not only when applied to our our own open-set segmentation method, but also when applied to existing methods. Furthermore we contribute a Mamba based architecture which is competitive with existing voxel-convolution based methods on challenging, large-scale pointclouds. |
| title | Finding Outliers in a Haystack: Anomaly Detection for Large Pointcloud Scenes |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.17634 |