Title
RGB2LIDAR: Towards Solving Large-Scale Cross-Modal Visual Localization
Abstract
We study an important, yet largely unexplored problem of large-scale cross-modal visual localization by matching ground RGB images to a geo-referenced aerial LIDAR 3D point cloud (rendered as depth images). Prior works were demonstrated on small datasets and did not lend themselves to scaling up for large-scale applications. To enable large-scale evaluation, we introduce a new dataset containing over 550K pairs (covering 143 km2 area) of RGB and aerial LIDAR depth images. We propose a novel joint embedding based method that effectively combines the appearance and semantic cues from both modalities to handle drastic cross-modal variations. Experiments on the proposed dataset show that our model achieves a strong result of a median rank of 5 in matching across a large test set of 50K location pairs collected from a 14km^2 area. This represents a significant advancement over prior works in performance and scale. We conclude with qualitative results to highlight the challenging nature of this task and the benefits of the proposed model. Our work provides a foundation for further research in cross-modal visual localization.
Year
DOI
Venue
2020
10.1145/3394171.3413647
MM '20: The 28th ACM International Conference on Multimedia Seattle WA USA October, 2020
DocType
ISBN
Citations 
Conference
978-1-4503-7988-5
0
PageRank 
References 
Authors
0.34
0
5
Name
Order
Citations
PageRank
Niluthpol Chowdhury Mithun1897.70
Karan Sikka211.02
Han-Pang Chiu39410.83
Supun Samarasekera479285.72
Rakesh Kumar51923157.44