Ilya Chugunov

I'm a PhD student in the Princeton Computational Imaging Lab, advised by Professor Felix Heide.
I received my bachelor's in electrical engineering and computer science from UC Berkeley, and am an NSF graduate research fellow.

Contact: [Last-Name]@princeton.edu

CV  /  Google Scholar  /  Github  /  LinkedIn  /  My Photography

I'm interested in the end-to-end optimization of imaging pipelines, from modeling signal collection to feature extraction and high-level scene understanding tasks. MRIs or Time-of-Flight cameras, I love getting hands-on with real devices and noisy data.

Flying pixels are pervasive depth artifacts in time-of-flight imaging, formed by light paths from both an object and its background connecting to the same sensor pixel. Mask-ToF jointly learns a microlens-level occlusion mask and refinement network to respectively encode and decode geometric information in device measurements, helping reduce these artifacts while remaining light efficient.

Jupyter Notebook labs can offer a similar experience to in-person lab sections while being self-contained, with relevant resources embedded in their cells. They interactively demonstrate real-life applications of signal processing while reducing overhead for course staff.

Leveraging sparsity in the Z-spectrum domain, multi-scale low rank reconstruction of cardiac chemical exchange saturation transfer (CEST) MRI can allow for 4-fold acceleration of scans while providing accurate Lorentzian line-fit analysis.

Point cloud data integrated from two structured light sensors for gesture recognition implicitly via a 3D spatial transform network can lead to improved results as compared to iterative closest point (ICP) registered point clouds.

Property inspection routes can be formulated into graph optimization problem, decomposed into weekly/yearly constraints for reduction to team orienteering problem (TOP).

Website template stolen from Jon Barron.