Download
License
This dataset is licensed under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license.
You are free to:
Share — copy and redistribute the material in any medium or format
Adapt — remix, transform, and build upon the material
Under the following terms:
Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made
NonCommercial — You may not use the material for commercial purposes
Access - download links
By downloading this dataset, you agree to the terms of the License.
| Reference Data | Download link |
| Query Sequences | Download link |
We provide the data bundled as zip-archive. The bundles are created per camera system for the reference data and per scene for the query sequences. Under the download link above you can select the bundles you would like to download. Please note that the size of the bundles varies greatly and the download may take some time.
Checksums
Use these SHA-256 checksums to verify the completeness/integrity of a downloaded bundle. Click a checksum to copy it, or download the full checksums manifest as JSON. You can compute a bundle’s checksum yourself using scripts/compute_sha256.py.
Reference data — 2023 campaign
| Camera system | File name | SHA-256 checksum |
|---|---|---|
| Panorama camera | 2023_panorama_camera.zip (73.74 GB) | 9fdd712db0f4c9091fcc07f6af1ac9b844d4282a9e3c41be79ef372e4aac8727 |
| Stereo front | 2023_stereo_front.zip (168.47 GB) | ee576d1fe853334eba7c051bd1915f3de1dd7ee4aa103f48298076b6ec1577b8 |
| Stereo back left | 2023_stereo_back_left.zip (175.42 GB) | c76684b8249ea20c5ced7fd6f83d7502af3435dd72a76ebeaf3a695fc7abaf09 |
| Stereo back right | 2023_stereo_back_right.zip (188.28 GB) | 1080eadee3d5a00c0d6e7227402ee918eb6dcfbed1922d58abfdbd45853e9df5 |
Reference data — 2025 campaign
| Camera system | File name | SHA-256 checksum |
|---|---|---|
| Panorama camera | 2025_panorama_camera.zip (254.04 GB) | ce8b8132d07e93c4560c39c302c6c76e4894f070fad3cb804bc9cd0a7aed87bf |
| Mono front | 2025_mono_front.zip (100.9 GB) | d360ced42a4bb2bd3483f03fd9976c443c8e7b34eca6b04d6b97641be39f07c2 |
Query data
| Scene | File name | SHA-256 checksum |
|---|---|---|
| Scene 1 | scene_1.zip (5.08 GB) | f8edcc3f52657ad42568b2abc76cd9c46cc6788865a6785bb0217390523de7e3 |
| Scene 2 | scene_2.zip (4.4 GB) | 7da9ee964eb98316e74d2d2c7288953168eb2eaa02ac11bfb8e5c9a07ffbb1f5 |
| Scene 3 | scene_3.zip (3.37 GB) | b64ac09e60e1fe5061f9a7fdadf913a344101f903b3b428ee275f62ad62b9586 |
| Scene 4 | scene_4.zip (4.61 GB) | b7ae9c59de24da9088589fe6679b87a64940baf77a816e7b881642a1bb9df044 |
| Scene 5 | scene_5.zip (5.08 GB) | b14bfaf364a4c834926270d64d7d5ebd3ebf4d7a60ad4be65fbc29a118b7d276 |
Privacy & anonymization
All personal data captured in the imagery of the FHNW Muttenz visual localization dataset has been completely anonymized. This goes beyond blurring faces and license plates: entire bodies and vehicles are blurred, ensuring that no personally identifiable content remains in the released images.