Signal Processing for Photon Limited Imaging
Instructors: Stanley Chan, Purdue University and Abhiram Gnanasambandam, Samsung Research America
Level: Introductory
Duration: 2 hours
Course Date/Time: Tuesday 17 January 10:45 - 12:45

Benefits:
This course enables the attendee to:

• Understand the challenges of image processing at low-light.
• Understand classical and deep learning techniques for image denoising.
• Understand modeling and denoising photon shot noise.
• Understand handling motion, burst, and generalization.

Course Description:
The continuous shrinkage of pixel pitch has led to a smaller full well capacity, causing the signal-to-noise to drop when imaging in low-light conditions. Overcoming the photon shot noise has been the biggest challenge in imaging because shot noise is present even if the sensors are perfect. This short course provides an overview of image denoising in the photon-limited regime. Topics to discuss include:

• statistical models of shot noise and read noise
• classical image denoising algorithms and their limits
• deep neural network denoisers
• the Plug-and-play framework and network unrolling techniques
• motion estimation in the presence of noise
• regularizing features for noisy input
• how to generalize one denoiser to a range of noise levels

Intended Audience:
Professionals working in the camera / image processing industry and graduate students interested in doing image processing and computational photography.

Stanley Chan is currently the Elmore Associate Professor of electrical and computer engineering at Purdue University, West Lafayette, IN. He received his PhD in electrical engineering from UC San Diego (2011), MA in mathematics from UC San Diego (2009), and BEng in electrical engineering from the University of Hong Kong (2007). In 2012-2014, he was a postdoctoral research fellow at Harvard University. He is a senior member of IEEE. He is currently an Associate Editor of the IEEE Transactions on Computational Imaging, where he is recognized by the IEEE Signal Processing Society as an outstanding editorial board member. In IEEE, he was an elected member of the technical committee on computational imaging. He also served as an associate editor for OSA Optics Express in 2016-2018.

Abhiram Gnanasambandam graduated from Purdue University with a PhD in ECE (2022). He is currently a research engineer at Samsung Research America.

Discounts given for multiple classes. See Registration Page for details to register.

For office use only: