# RGB2LIDAR: Towards Solving Large-Scale Cross-Modal Visual Localization

arXiv: https://arxiv.org/abs/2009.05695 · HTML: https://mlsanity.com/paper/2009.05695/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2020.

## Built on by (most cited first, 5 of 5)

- [Grounding 3D Object Affordance from 2D Interactions in Images](https://mlsanity.com/paper/2303.10437/) (2023)
- [Cross-View Visual Geo-Localization for Outdoor Augmented Reality](https://mlsanity.com/paper/2303.15676/) (2023)
- [LaneTCA: Enhancing Video Lane Detection with Temporal Context Aggregation](https://mlsanity.com/paper/2408.13852/) (2024)
- [Ground-to-Satellite Localization in Unconstrained Image Collections for 3D Scene Reconstruction](https://mlsanity.com/paper/2608.29211/) (2026)
- [M3GA-Wild: A Large-Scale Dataset and Benchmark for Multi-Modal Multi-session Ground-to-Aerial Place Recognition in Forests](https://mlsanity.com/paper/2609.23003/) (2026)

## Abstract (arXiv)

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 km^2 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.