Bonjour, Hello!

I am a Ph.D. candidate at the McGill Graphics Lab (MGL), working under Derek Nowrouzezahrai. I am currently interning at NVIDIA AI as a Research Scientist in Deep Learning, where I have joined Sanja Fidler's group for the summer.

My main research interests lie at the intersection of physically-based rendering and machine learning. More precisely, I am interested in applying deep learning techniques to improve current rendering algorithms (e.g., denoising, path guiding, sampling). I also have an interest for differentiable rendering, 3D representation learning and Markov chain Monte Carlo (MCMC) methods for light transport simulations.

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

Latest News (See more )

I have started my internship at NVIDIA remotely due to COVID-19. Let's do this!
Our paper on applying delayed rejection to Metropolis light transport was accepted to ACM TOG.
I will be presenting some of my early research work at MOTOGRAPH 2019 held at UWaterloo.

Recent Publications (See more )

Delayed Rejection Metropolis Light Transport

D. Rioux-Lavoie, J. Litalien, A. Gruson, T. Hachisuka, and D. Nowrouzezahrai
ACM Transactions on Graphics (To be presented at SIGGRAPH), May 2020

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