Maxx Wu

I'm a Computer Science MSc candidate at the University of Toronto, co-advised by David Lindell and Kyros Kutulakos. I work with the Toronto Computational Imaging Group within the Dynamic Graphics Project (DGP). My research lies at the intersection of Machine Learning and Computational Imaging, with a focus on active imaging for 3D reconstruction. I am particularly interested in implicit neural representations, inverse rendering, and imaging.

I received my BASc in Engineering Science at the Univetsity of Toronto, specializing in Machine Intelligence. I conducted my undergraduate thesis with the Biophotonics Group advised by Ofer Levi. My work focused on remote human vital sign measurement using IR and depth cameras.

I previously interned at ModiFace as an AR application developer.

LinkedIn /  GitHub /  Email

We show how to turn a noisy and fragile active triangulation technique—three-pattern structured light with a grayscale camera—into a fast and powerful tool for 3D capture: able to output sub-pixel accurate disparities at megapixel resolution, along with reflectance, normals, and a no-reference estimate of its own pixelwise 3D error. We use TurboSL to reconstruct a variety of complex scenes from images captured at up to 60 fps with a camera and a common projector. Our experiments highlight TurboSL’s potential for dense and highly-accurate 3D acquisition from data captured in fractions of a second.

We introduce full-wavefield lidar: a new imaging modality that repurposes off-the-shelf coherent optical modems to simultaneously measure distance, axial velocity, and polarization. We demonstrate this modality by combining a 74 GHz-bandwidth coherent optical modem with free-space coupling optics and scanning mirrors. We develop a time-resolved image formation model for this system to recover depth, velocity, and polarization information at each scene point.

Template from Jon Barron's website.