3DRMS Challenge Dataset Repository
Part of the 3D Reconstruction meets Semantics workshop was a challenge on combining 3D and semantic information in complex scenes. To this end, a challenging outdoor dataset, captured by a robot driving through a semantically-rich garden that contains fine geometric details, was released. A multi-camera rig is mounted on top of the robot, enabling the use of both stereo and motion stereo information. Precise ground truth for the 3D structure of the garden has been obtained with a laser scanner and accurate pose estimates for the robot are available as well. Ground truth semantic labels and ground truth depth from a laser scan will be used for benchmarking the quality of the 3D reconstructions.
For detailed instructions on file usage see the individual challenge volume.
3D Reconstruction meets Semantics 2017
3D Reconstruction meets Semantics 2018
You are free to use the contents of this page, but if you publish anything based on the content,
please use this acknowledgement:
We thank the TrimBot2020 project,
which was funded by the European Commission under Horizon 2020 project IST 688007.
Email: Prof. Robert Fisher at rbf -a-t- inf.ed.ac.uk.
School of Informatics, Univ. of Edinburgh
1.11 Bayes Centre, 47 Potterrow
Edinburgh EH8 9BT, UK
Tel: +44-(131)-651-3441 (direct line), +44-(131)-651-3443 (secretary)
Date of last change to this page: 01/17/2022 23:18:36