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  /  Photography  /  Coding Art

I'm interested in computational photography and inverse problems that look at the whole imaging pipeline, from signal collection to scene reconstruction. MRIs, microscopes, or modulated light sources, I love working with real devices and weird data.

"If you try and take a cat apart to see how it works, the first thing you have on your hands is a non-working cat."
- Douglas Adams

In a “long-burst”, forty-two 12-megapixel RAW frames captured in a two-second sequence, there is enough parallax information from natural hand tremor alone to recover high-quality scene depth. We fit a neural RGB-D model directly to this long-burst data to recover depth and camera motion with no LiDAR, no external pose estimates, and no disjoint preprocessing steps.

Signed distance fields (SDFs) can be a compact and convenient way of representing 3D objects, but state-of-the-art learned methods for SDF estimation struggle to fit more than a few shapes at a time. This work presents a two stage semi-supervised meta-learning approach that learns generic shape priors to reconstruct over a hundred unseen object classes.

Modern AMCW time-of-flight (ToF) cameras are limited to modulation frequencies of several hundred MHz by silicon absorption limits. In this work we leverage electro-optic modulators to build the first free-space GHz ToF imager. To solve high-frequency phase ambiguities we alongside introduce a segmentation-inspired neural phase unwrapping network.

Modern smartphones can stream multi-megapixel RGB images, high-quality 3D pose information, and low-resolution depth estimates at 60Hz. In tandem, the natural shake of a phone photographer's hand provides us with dense micro-baseline parallax depth cues during viewfinding. This work explores how we can combine these data streams to get a high-fidelity depth map from a single snapshot.

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.

Website template stolen from Jon Barron.