Course information

Time and location: MWF 1:50 - 2:40 pm in 126 HRBB
Office hours: T 2:00 - 3:00 pm
Office location: 527B HRBB
Email: nimak@tamu.edu

Overview

Computational photography is a collection of computational algorithms and system designs (e.g., sensors, optics) to avoid the limitations of standard cameras and enable novel applications. In recent years, there has been increasing interest in computational photography because of the widespread use of the cameras by the general public through smartphones and other cheap imaging devices. In this course, we first discuss the cameras and the image formation process. We then study basic image and video processing tools like sampling, filtering, and pyramids. Finally, we discuss several image-based algorithms, such as image retargeting, high dynamic range imaging, and texture synthesis.

Prerequisites

Programming experience (MATLAB or Python), as well as knowledge of linear algebra and calculus is necessary. Basic knowledge of computer graphics and vision, as well as image processing is helpful but not necessary.

Textbook

The primary reference of the course is the following book, which covers most of the topics related to computational photography:

Computer Vision: Algorithms and Applications, by Richard Szeliski, 2010

Grading

• Programming assignments (60%): There will be 4 programming assignments for this course.
• Final project (40%): Students are free to choose any project related to computational photography. They can work on the project individually or in teams. Students will propose the project at the middle of the semester. The final project presentation as well as a report will be due at the end of the semester.

Schedule*

*Schedule might change during the semester.

Acknowledgements

The slides in this class are heavily based on the slides from other instructors. Specifically, many slides are the exact or modified version of the slides by Alexei A. Efros, James Hays, and Rob Fergus, who in turn have used materials from Steve Seitz, Rick Szeliski, Paul Debevec, Stephen Palmer, Paul Heckbert, David Forsyth, Steve Marschner, Fredo Durand, Bill Freeman, and others, as noted in the slides. The instructor gives full permission to use these slides for academic and research purposes, but please maintain all the acknowlegements.