English

Finding Outliers in a Haystack: Anomaly Detection for Large Pointcloud Scenes

Computer Vision and Pattern Recognition 2025-08-27 v2 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2508.17634,
  title  = {Finding Outliers in a Haystack: Anomaly Detection for Large Pointcloud Scenes},
  author = {Ryan Faulkner and Luke Haub and Simon Ratcliffe and Tat-Jun Chin},
  journal= {arXiv preprint arXiv:2508.17634},
  year   = {2025}
}

Comments

arXiv Preprint, paper has since been accepted to ACPR 2025

R2 v1 2026-07-01T05:03:56.305Z