Datasets & Code

Our lab is committed to open science. We publicly release the datasets, benchmarks, and code developed through our research. Most resources are hosted on our GitHub organization and Hugging Face organization.

Datasets and Benchmarks

  • YUTO MMS – A comprehensive SLAM benchmark for urban mobile mapping with tilted LiDAR and panoramic camera integration; four sequences totalling 20.1 km (IJRR, 2025). Project page | GitHub
  • YUTO Semantic – A large-scale aerial LiDAR dataset for 3D semantic segmentation: ~738 million points covering 9.46 km² of the York University campus, annotated with nine semantic classes (ISPRS Archives, 2023). GitHub | Hugging Face
  • Q-Drone UWB Benchmark – Benchmark dataset of ultra-wideband radio based UAV positioning (IEEE ITSC, 2020). Benchmark site
  • YUTO Tree5000 – A large-scale airborne LiDAR dataset for single tree detection with 5,000 annotated trees (ICPR Workshops, 2022).
  • Smokestack Plume Images and Plume Identification Masks – Image dataset for industrial plume rise measurement (Federated Research Data Repository, 2026).
  • Unmanned Aerial Image Dataset – UAV imagery ready for 3D reconstruction (Data in Brief, 2019).

Community