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

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

Technical University of Munich    Google
* Authors share senior authorship.

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.


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

Dataset Download

Download: If you would like to download the 3RScan data, please fill out this form 3RScan Terms of Use.


For questions please contact us via our group email the 3RScan group email For more information regarding the 3RScan dataset, please see our git repo.


We would like to thank the volunteers who helped with 3D scanning, all expert annotators, as well as Jürgen Sturm, Tom Funkhouser and Maciej Halber for fruitful discussions. This work was funded by the Bavarian State Ministry of Education, Science and the Arts in the framework of the Centre Digitisation.Bavaria (ZD.B), the ERC Starting Grant Scan2CAD (804724), TUM-IAS for the Rudolf Mößbauer Fellowship, and a Google Research and Faculty award.