3D point cloud samples across multiple object categories labeled for anomaly detection and localization tasks. This dataset establishes a benchmark for identifying spatial defects in 3D geometry as presented at NeurIPS 2023.
Use Cases
- Train point cloud-based models to detect structural anomalies using 3D spatial coordinates
- Evaluate the performance of unsupervised learning algorithms on 3D geometric defect identification
- Develop 3D feature extraction methods to differentiate between normal and anomalous object surfaces
Strengths
- Focuses on 3D point cloud data formats for spatial anomaly detection
- Introduced as a benchmark at the NeurIPS 2023 conference
- Includes official implementation code for standardized evaluation of 3D defect detection models