J
Jonah Philion
Researcher at University of Toronto
Publications - 18
Citations - 733
Jonah Philion is an academic researcher from University of Toronto. The author has contributed to research in topics: Computer science & Metric (mathematics). The author has an hindex of 6, co-authored 16 publications receiving 170 citations. Previous affiliations of Jonah Philion include Nvidia.
Papers
More filters
Posted Content
Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D
Jonah Philion,Sanja Fidler +1 more
TL;DR: In pursuit of the goal of learning dense representations for motion planning, it is shown that the representations inferred by the model enable interpretable end-to-end motion planning by "shooting" template trajectories into a bird's-eye-view cost map output by the network.
Proceedings ArticleDOI
FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network
TL;DR: A novel fully convolutional model of lane detection that learns to decode lane structures instead of delegating structure inference to post-processing is introduced and a simple yet effective approach to adapt the model to new environments using unsupervised style transfer is demonstrated.
Book ChapterDOI
Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D
Jonah Philion,Sanja Fidler +1 more
TL;DR: LIFT-splat-shoot as mentioned in this paper proposes an end-to-end architecture that directly extracts a bird's-eye-view representation of a scene given image data from an arbitrary number of cameras.
Proceedings ArticleDOI
Learning to Simulate Dynamic Environments With GameGAN
TL;DR: GameGAN as mentioned in this paper is a generative model that learns to visually imitate a desired game by ingesting screenplay and keyboard actions during training, given a key pressed by the agent, GameGAN "renders" the next screen using a carefully designed generative adversarial network.
Journal ArticleDOI
M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation
Enze Xie,Zhiding Yu,Daquan Zhou,Jonah Philion,Animashree Anandkumar,Sanja Fidler,Ping Luo,Jose M. Alvarez +7 more
TL;DR: M 2 BEV is memory efficient, allowing significantly higher resolution images as input, with faster inference speed, and achieves state-of-the-art results in both 3D object detection and BEV segmentation, with the best single model achieving 42.5 mAP and 57.0 mIoU in these two tasks.