RIO: 3D Object Instance Re-Localization in Changing Indoor Environments (ICCV Oral)

Johanna Wald     Armen Avetisyan     Nassir Navab     Federico Tombari*     Matthias Nießner*    

Technical Unviersity of Munich    Google Zürich
* Authors share senior authorship.




News

Description

3R-Scan is a large scale, real-world dataset which contains multiple 3D snapshots of naturally changing indoor environments, designed for benchmarking emerging tasks such as long-term SLAM, scene change detection and object instance re-localization (more benchmarks coming). See example scans of four different scenes (3D Viewer):


If you would like to download the data, participate in our benchmark see the documentation for more information. If you find the data useful please consider citing:


@inproceedings{Wald2019RIO,
    title={RIO: 3D Object Instance Re-Localization in Changing Indoor Environments},
    author={Johanna Wald, Armen Avetisyan, Nassir Navab, Federico Tombari, Matthias Niessner},
    booktitle={Proceedings IEEE International Conference on Computer Vision (ICCV)},
    year = {2019}
}