Text2Pos: Text-to-point-cloud cross-modal localization

Manuel Kolmet, Qunjie Zhou, Aljosa Osep, Laura Leal-Taixe
Technical University Munich

[Paper - coming soon] [Bibtex - coming soon] [Github]

Overview Video - coming soon


Natural language-based communication with mobile devices and home appliances is becoming increasingly popular and has the potential to become natural for communicating with mobile robots in the future. Towards this goal, we investigate cross-modal text-to-point-cloud localization that will allow us to specify, for example, a vehicle pick-up or goods delivery location. In particular, we propose Text2Pos, a cross-modal localization module that learns to align textual descriptions with localization cues in a coarse-to-fine manner. Given a point cloud of the environment, Text2Pos locates a position that is specified via a natural language-based description of the immediate surroundings. To train Text2Pos and study its performance, we construct KITTI360Pose, the first dataset for this task based on the recently introduced KITTI360 dataset. Our experiments show that we can localize 65% of textual queries within 15m distance to query locations for top-10 retrieved locations. This is a starting point that we hope will spark future developments towards language-based navigation.

Key Ideas

Our key idea is Text2Pos, a first method to perform text-to-pointcloud localization.


Text2Pos: Text-to-point-cloud cross-modal localization

CVPR 2020

[Paper - coming soon]     [Bibtex - coming soon]     [Github]


 [GitHub]  [Dataset]


This work was partially funded by the Sofja Kovalevskaja Award from the Humboldt Foundation.
This webpage was inspired by Colorful Image Colorization.