Topo-DataGen

This repo introduces an open and scalable aerial synthetic data generation workflow TOPO-DataGen. It takes common geo-data as inputs and outputs diverse synthetic visual data such as 2D image-3D geometry-semantics-camera pose. The rendering engine is developed upon CesiumJS.

• Getting started
  • Requirements
  • Installation guide
  • Get Started
• Data
  • Input data
  • Output data
• Data processing
  • Step 1 : Define your dataset name and folder
  • Step 2 : Start you conda environment
  • Step 3 : Data downloading and preprocessing
  • Step 4 : Data loading into Cesium Ion
  • Step 5 : Data Processing
  • Step 6 : Retrieve semantics
  • Step 7 : Create raster
• Command line utilities
  • Download + preprocess data
  • Process data
  • Create rasters final products

The TOPO-DataGen workflow is officially presented in the paper
CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data
Qi Yan, Jianhao Zheng, Simon Reding, Shanci Li, Iordan Doytchinov
École Polytechnique Fédérale de Lausanne (EPFL)
Links: arXiv | code repos