Parsa Mirdehghan

I am a Computer Science PhD candidate at University of Toronto, advised by Kyros Kutulakos, and a Junior Fellow at Massey College. I am also affiliated with Vector Institute, Dynamic Grphics Project (DGP), and Toronto Computational Imaging Group.

My research focus lies primarily in the intersection of Machine Learning and Computational Imaging. I am particularly interested in developing an ensemble of machine learning and optimization methods that, given a set of sensors and illumination sources, can generate the optimal encodings and reconstruction functions for joint estimation of scene unknowns such as 3D geometry, appearance, velocity, and polarization.

Previously, I was a research intern at Disney Research Zurich in 2016, Huawei Research Canada in 2018, and Microsoft Research Redmond in 2019.

Twitter  /  Google Scholar /  Email

TurboSL provides sub-pixel-accurate surfaces and normals at mega-pixel resolution from structured light images, captured at fractions of a second.

We introduce a method to do novel view lidar synthesis, allowing sparse view scene reconstruction.

We present optical SGD, a computational imaging technique that allows an active depth imaging system to automatically discover optimal illuminations & decoding.

We propose a framework for optimizing structured light patterns given a set of imaging conditions and an error metric.

We present a system specifically designed for capturing the optical properties of live human teeth such that they can be realistically re-rendered in computer graphics

Template from Jon Barron's website.