Computational Imaging
Course Description
Computational imaging systems have a wide range of applications in consumer electronics, scientific imaging, HCI, medical imaging, microscopy, and remote sensing. This course covers digital photography, image processing, convolutional neural networks for imaging, denoising, deconvolution, single pixel imaging, inverse problems, wave optics, and end-to-end optimization of optics and imaging processing. Emphasis is on applied image processing and solving inverse problems using classic algorithms, formal optimization, and modern AI techniques.
Topics Include
- Human visual perception
- Digital cameras and ISPs
- Denoising, deconvolution, and other inverse problems
- Convolutional neural networks for imaging
- Diffusion models for inverse problems
- Proximal gradient methods / formal optimization
- High dynamic range imaging
- Light field imaging
- Wave optics
- End-to-end optimization of optics and image processing
Course Goals
Students will learn about computational imaging methods and applications with a focus on solving inverse problems in imaging, such as denoising, deconvolution, and single-pixel imaging. The course covers classic algorithms, modern data-driven approaches using CNNs, and proximal gradient methods. Assignments require programming and image processing in Python.
Instructors
- Praneeth Chakravarthula (Instructor)
Schedule & Syllabus
Class meets in Spring 2026. Details and weekly topics will be posted here.
- Week 1: Introduction and course overview
- Week 2: Human visual system and digital photography
- Week 3: Inverse problems and denoising
- Week 4: Neural networks for imaging
- Week 5: Wave optics and light field imaging
- Week 6: Optimization and end-to-end systems