Bonjour, Hello!

I am a Ph.D. candidate at the McGill Graphics Lab (MGL), where I am advised by Derek Nowrouzezahrai. I am currently an intern at Facebook Reality Labs (FRL) Research. From May 2020 to April 2021, I was a research intern at NVIDIA, working in Sanja Fidler's AI group.

My main research interests lie at the intersection of realistic image synthesis and machine learning, where I focus on designing efficient and practical algorithms for solving forward and inverse rendering problems. In particular, I am interested in differentiable rendering, 3D representation learning and neural signed distance fields (SDFs). I also have an interest for high-dimensional sampling and Monte Carlo denoising.

If you'd like to chat, feel free to send me an email.

Latest News (See more )

2021.06.01
I have officially joined Facebook Reality Labs (FRL) Research, where I will be interning remotely in the Display Systems Research team!
2021.04.30
All good things come to an end: my internship at NVIDIA is officially over after almost a year. Stay tuned for my next adventure!
2021.03.03
Neural LOD has been accepted for oral presentation at CVPR 2021.

Recent Publications (See more )

Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes

T. Takikawa, J. Litalien, K. Yin, K. Kreis, C. Loop, D. Nowrouzezahrai, A. Jacobson, M. McGuire, and S. Fidler
Computer Vision and Pattern Recognition (CVPR), January 2021

Selected Projects (See more )

Online Test Suite for Rendering Research

A web comparison tool for rendering research written in Python+JS, based on the online test suite with interactive viewer by Disney Research. Useful for assembling supplementary material (comparison metrics, convergence plots, etc.)

Noise2Noise PyTorch Implementation

Unofficial PyTorch implementation of Noise2Noise: Learning Image Restoration without Clean Data by Lehtinen et al., 2018