Paul-Edouard Sarlin
Scholar

Paul-Edouard Sarlin

Google Scholar ID: 2fAUgfAAAAAJ
Researcher at Google
Computer VisionDeep Learning3D GeometryVisual LocalizationStructure-from-Motion
Citations & Impact
All-time
Citations
6,679
 
H-index
12
 
i10-index
12
 
Publications
18
 
Co-authors
30
list available
Resume (English only)
Academic Achievements
  • 2025: Released a new dataset and benchmark for large-scale egocentric SLAM; paper accepted to ICCV 2025
  • 2025: Received DAGM MVTec Dissertation Award at GCPR 2025
  • 2025: Presented MP-SfM at CVPR 2025
  • 2024: Awarded the prestigious ETH Silver Medal for PhD thesis
  • 2024: Presented GeoCalib at ECCV 2024
  • 2023: LightGlue accepted to ICCV 2023
  • 2023: Worked on SNAP framework during Google internship
  • 2023: OrienterNet accepted to CVPR 2023
  • 2022: Released LaMAR benchmark for AR-based visual localization (ECCV 2022)
  • 2022: Received Best Presentation Award at ICVSS 2022
  • 2021: Pixel-Perfect Structure-from-Motion received Best Student Paper Award at ICCV 2021
  • 2021: Back to the Feature published at CVPR 2021
  • 2020: SuperGlue and hloc won 4 ECCV 2020 visual localization challenges
  • 2020: SuperGlue won 3 CVPR 2020 competitions and was selected for oral presentation
  • 2019: Hierarchical Localization won the Visual Localization Challenge at CVPR 2019 workshop
  • 2019: Fishyscapes Benchmark presented orally at ICCV 2019 workshop on Autonomous Driving
Research Experience
  • Researcher at Google Geo (Maps, StreetView, Earth), Zurich (since Oct 2024): working on mapping problems
  • Intern at Google Research Zurich: developed SNAP, a self-supervised framework for neural map inference from streetview and aerial images
  • Research Intern at Facebook Reality Labs, London: worked on OrienterNet
  • Research Intern at Microsoft Mixed Reality & AI Lab, Zurich
  • Conducted Master’s thesis at Magic Leap, San Francisco
  • Spent time at ASL, Traverse.ai, NUS, and EPFL