NSS
Notes on the Dataset
- For the test split, no ground truth poses are provided
Detailed Information
| General Information | |
| Name | NSS |
| Release Year | 2025 |
| Terms of Use | Free use for research |
| Access Requirements | None |
| Dataset Size | 3.79 GB |
| Documentation | In-depth documentation of acquisition and characteristics of the dataset, e.g., via an explicit dataset paper or a comprehensive multi-page metadata document |
| Code | Yes |
| Applications | Multi-temporal registration |
| Detailed Applications | Point cloud registration under large changes |
| Acquisition | |
| Number of Scenes | 4 |
| Number of Epochs per Scene (minimum) | 3 |
| Number of Epochs per Scene (median) | 5 |
| Number of Epochs per Scene (maximum) | 6 |
| General Scene Type | Indoor |
| Specific Scene Type | Construction site |
| Location | Unclear |
| Acquisition Type | Terrestrial laser scanning |
| Acquisition Device | Matterport Camera |
| Acquisition Platform | Tripod |
| Scan Interval | Weeks to Months |
| Acquisition Months | |
| Representation | |
| Data Representation | Unstructured, local (e.g., local point clouds or laser scans with poses) |
| Specific Data Representation | Local point clouds |
| File Format/Encoding | PLY |
| Raw Data | - |
| Additional Data | - |
| Coordinate System | m |
| Quality and Usability | |
| Registration | Finely registered |
| Number of Partial Epochs | 33.33% |
| Unusable Data Reason | Not multi-temporal | Other (e.g., no poses for alignment available or in proprietary format) |
| Splits | Yes |
| Per-Point Attributes | |
| Intensity/Reflectivity | No |
| Color | No |
| Semantic Labels | - |
| Instance Labels | No |
| Change Labels | - |
| Statistics | |
| Number of Points per Epoch (minimum) | 352K |
| Number of Points per Epoch (median) | 4M |
| Number of Points per Epoch (maximum) | 13M |
| Avg. Point Spacing (minimum) | 1.7cm |
| Avg. Point Spacing (median) | 2.1cm |
| Avg. Point Spacing (maximum) | 3.2cm |
| Avg. Change Points per Epoch | - |
Paper Reference 1
@article{sun2025datasetnss,
title = {Nothing Stands Still: A spatiotemporal benchmark on 3D point cloud registration under large geometric and temporal change},
journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
volume = {220},
pages = {799--823},
year = {2025},
issn = {0924-2716},
doi = {10.1016/j.isprsjprs.2025.01.010},
author = {Tao Sun and Yan Hao and Shengyu Huang and Silvio Savarese and Konrad Schindler and Marc Pollefeys and Iro Armeni},
}