TinyDiffRast

While working at Mila - Quebec AI Institute, I developed an open course on differentiable rasterization. Differentiable rasterization is a type of inverse rendering approach, which allows 3D scene parameters (materials, lights, cameras, geometry) to be learned from 2D image supervision. You can find the course and code-base here.

Learnable Fractal Flames

I developed a differentiable fractal rendering algorithm that allows latent fractal flame parameters to be learned from image supervision. The algorithm extends the state-of-the-art in differentiable iterated function system fractal rendering through support for color images, non-linear generator functions, and multi-fractal compositions. You can read the paper here .

Deep Surface AI

I co-founded a surgical facial morphing software company during graduate school. Our web app allows surgeons to quickly and easily create realistic simulations for patients considering facial surgery. Read more about it in this article.

3D Facial Shape Models

As part of my doctoral thesis, I developed models of 3D facial shape for computer-assisted genetic syndrome diagnosis. Check out my papers (1, 2, 3, 4) for more details.

Autonomous Robotics

During my undergrad, I was part of a team that fabricated and programmed an autonomous target shooting robot "Squeaky" that won the annual Eng Fizz robotics competition. See it in action below.