A data generation tool to generate realistic aerial imagery data and benchmark datasets

Released in: CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data



Despite significant progress in recent years, most learning-based approaches to visual localization target at a single domain and require a dense database of geo-tagged images to function well. To mitigate the data scarcity issue and improve the scalability of the neural localization models, the TOPO-DataGen includes a versatile synthetic data generation tool that traverses smoothly between the real and virtual world, hinged on the geographic camera viewpoint. New large-scale sim-to-real benchmark datasets are proposed to showcase and evaluate the utility of the said synthetic data. The authors’ experiments reveal that synthetic data generically enhances the neural network performance on real data. Furthermore, the authors introduce CrossLoc, a cross-modal visual representation learning approach to pose estimation that makes full use of the scene coordinate ground truth via self-supervision. Without any extra data, CrossLoc significantly outperforms the state-of-the-art methods and achieves substantially higher real-data sample efficiency.


Images in dataset


Year Released

Key Links & Stats


@misc{iordan2022crossloc, title={CrossLoc Benchmark Datasets}, author={Doytchinov, Iordan and Yan, Qi and Zheng, Jianhao and Reding, Simon and Li, Shanci}, publisher={Dryad}, doi={10.5061/DRYAD.MGQNK991C}, url={}, year={2022} }



  1. Still Image
  2. Point Cloud
  3. LiDAR


  1. Satellite
  2. A/V

ML Task

  1. Semantic Segmentation
  2. Object Recognition
  3. Object Tracking

Related organizations

École Polytechnique Fédérale de Lausanne