Computational Imaging

The aim of this course is to provide a theoretical and practical of computational imaging with applications focusing on solving inverse problems in imaging, such as denoising, deconvolution, single-pixel imaging. - The course introduces modern human visual perception, digital cameras and ISPs, Light field imaging, wave optics. - The second goal is to teach classic algorithms, modern data-driven approaches using convolutional neural networks (CNNs) and Vision Transformers (ViT), and proximal gradient methods, that combine formal optimization with Deep Learning Methods. The homeworks will be given based on programming and image processing in Python. - The third goal is to develop next-generation computation and display systems. These systems will have applications in consumer electronics, microscopy, human interaction, health, optics.

More info here

After passing the course the student will acquire:

- Acquire theoretical knowledge and practical knowledge in computational imaging with focus on bio-imaging.

- Develop next-generation computational imaging systems for imaging around corners and through scattering media etc.

- Develop machine learning algorithms for representing and processing signals.

- Applications to computer graphics, remote sensing, and robotic vision