Scholar
Jonah Philion
Google Scholar ID: VVIAoY0AAAAJ
University of Toronto
Citations & Impact
Citations
2,920
H-index
16
i10-index
17
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation (In submission)
- Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior (CVPR 2022)
- How Much More Data Do I Need? Estimating Requirements for Downstream Tasks (CVPR 2022)
- Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation (NeurIPS 2021)
- Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting (ICCV 2021, oral)
- DriveGAN: Towards a Controllable High-Quality Neural Simulation (CVPR 2021, oral)
- Emergent Road Rules In Multi-Agent Driving Environments (ICLR 2020)
- The Efficacy of Neural Planning Metrics: A Meta-Analysis of PKL on nuScenes (IROS 2020 Workshop on Benchmarking Progress in Autonomous Driving)
- Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)
- Learning to Simulate Dynamic Environments With GameGAN (CVPR 2020)
- Learning to Evaluate Perception Models Using Planner-Centric Metrics (CVPR 2020)
- FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network (CVPR 2019)
Research Experience
- Worked for a year on the perception team at ISEE before coming to the University of Toronto.
Education
- Undergraduate at Harvard University where he studied Physics and Math and minored in Computer Science. Was also part of the Harvard/NEC program for jazz performance (alto saxophone).
Background
- PhD student at University of Toronto working on machine learning and computer vision, primarily with applications to self-driving. Advised by Sanja Fidler. Also a part-time research scientist at NVIDIA.
Miscellany
- Music enthusiast, performs music with his brother Ethan Philion, and is part of a courtyard saxophone trio. Has also live-coded music in Python on YouTube.