Computational Imaging has driven rapid advancements across a wide range of application domains, including mobile phones, autonomous vehicles, VR/AR systems, consumer electronics, robotics, microscopy, and telescopy. This course covers the core concepts and key applications of computational imaging, with a particular emphasis on digital photography, AI-based computational imaging methods, optics, human visual perception, and inverse problems in computational imaging.

Tuesdays and Thursdays, 9:30 AM – 10:45 AM, Engineering Building #2, Room 106.

Course slides and lecture recordings will be available on PLMS.

PLMS will serve as our main communication platform.

Questions are welcome before, during, and after lectures.

Office hours are available by appointment via email with the instructor.

TA Office hours are available by appointment via email with the TA.

Python programming proficiency and a background in linear algebra.

Prior knowledge in computer graphics, computer vision, machine learning, optics, or signal processing is helpful but not required.

CSED551 Computational Photography

CSED451 Computer Graphics

CSED539 Computer Vision

CSED538 Deep Learning

CSED429F Signal Processing

CSED520 3D Reconstruction

Stanford Computational Imaging

CMU Computational Photography

University of Toronto Computational Imaging

Columbia Fundamentals of Computer Vision

5 Minutes Graphics

Assignments: 40%

• Four assignments involving theory, programming, and hands-on projects.

• Late submissions incur a 1% penalty per hour.

• Peer discussion is encouraged, but each student must submit their own solution.

• Submissions should be made via PLMS.

Project: 60%

• Select a research topic in computational imaging.

• Conduct experiments and analyze the results.

• Present your findings.

• Projects may be completed individually or in teams of up to three.

• Discuss your project ideas with the TA and instructor.