Cody Reading

I am a 3D computer vision researcher, interested in 3D perception, 3D reconstruction, and 3D generation. and. I aim to develop tools that understand our surrounding 3D world.

I received my master's degree from the University of Toronto supervised by Steven Waslander, and received my bachelor's degree from the University of Waterloo. I also worked at MARZ developing Vanity AI, an AI solution for facial editing for VFX. I am currently at Huawei Technologies working on 3D perception for robotic applications.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

profile photo
Publications
Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields
Lily Goli, Cody Reading, Silvia Sellán, Alec Jacobson, Andrea Tagliasacchi
CVPR, 2024 (Highlight)
Project Page / arXiv / Code

We introduce a post-hoc framework to evaluate uncertainty in any pre-trained NeRF without modifying the training process.

BANF: Band-limited Neural Fields for Levels of Detail Reconstruction
Ahan Shabanov, Shrisudhan Govindarajan, Cody Reading, Lily Goli, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi
CVPR, 2024
Project Page / Paper

We introduce BANF, a method for band-limited frequency decomposition in neural fields.

InterTrack: Interaction Transformer for 3D Multi-Object Tracking
John Willes*, Cody Reading*, Steven Waslander
CRV, 2023 (Oral Presentation)
arXiv / Video

We introduce the Interaction Transformer to 3D multi-object tracking to generate discriminative object representations for data association.

Categorical Depth Distribution Network for Monocular 3D Object Detection
Cody Reading, Ali Harakeh, Julia Chae, Steven Waslander
CVPR, 2021 (Oral Presentation)
Project Page / arXiv / Video / Code

We estimate categorical depth distributions to project image feature information to 3D space for improved 3D monocular object detection.

Unlimited Road-scene Synthetic Annotation (URSA) Dataset
Matt Angus, Mohamed ElBalkini, Samin Khan, Ali Harakeh, Oles Andrienko, Cody Reading, Steven Waslander, Krzysztof Czarnecki
ITSC, 2018
Project Page / arXiv / Video / Dataset

We generate a synthetic dataset for semantic segmentation based on GTA V.

Experience
sfu Senior Researcher
Huawei Technologies
July 2024 - Present

Implemented a 3D scene graph estimation method to enable robotic navigation and developed a 3D object labeling tool for generating perception labels.

sfu 3D Content Creation Researcher
Simon Fraser University
Sept. 2023 - April 2024
PhD Candidate, Computing Science

Implemented novel techniques in 3D content creation and generative models, involving optimizing NeRF and 3D Gaussian representations with diffusion guidance.

sfu Machine Learning Research Associate
Monsters Aliens Robots Zombies
Jan. 2022 - Aug. 2023

Developed a facial de-aging tool Vanity AI designed for VFX applications, achieving 300x speed up compared to traditional VFX workflows.

sfu 3D Perception Researcher
University of Toronto
Sept. 2019 - Dec. 2021
Master’s of Applied Science, Aerospace Engineering

Innovated methodologies in autonomous vehicle 3D perception, achieving 1st and 2nd place on 3D monocular object detection and 3D multi-object tracking benchmarks respectively

sfu Software Engineer - Autonomous Driving
NVIDIA Corporation
Jan. 2018 - Aug. 2018

Developed a vehicle trajectory generation library within the NVIDIA DriveWorks SDK using C++ to generate a sequence of vehicle poses from GPS, IMU, and CAN sensor data

sfu Semantic Segmentation Research Co-op
University of Waterloo
May 2017 - Aug. 2017

Developed semantic segmentation training infrastructure to support unified training of the SegNet and FCN methods on the Cityscapes, Playing-for-data, and Synthia datasets.


Website template from Jon Barron.
Last updated: April, 2024