CSCI1950-G Computational Photography

Spring 2010, MWF 1:00 to 1:50, CIT 367.
Instructor: James Hays
HTA: Patrick Doran

Computational Photography Montage

Course Description

Course Catalog Entry
Computational Photography describes the convergence of computer graphics, computer vision, and the Internet with photography. Its goal is to overcome the limitations of traditional photography using computational techniques to enhance the way we capture, manipulate, and interact with visual media. In this course we will study many interesting, recent image based algorithms and implement them to the degree that is possible. We will cover topics such as The course will consist of five programming projects, several problem sets, a written exam, and a student-chosen final project. Students can earn graduate credit for the course but will need to meet higher requirements on all projects throughout the semester and need the instructor's permission. The graduate version can count towards a graphics specialization.

Prerequisites

This course requires programming experience as well as basic linear algebra, calculus, and probability. Previous knowledge of computer graphics or computer vision will be helpful. It is strongly recommended that students have taken one of the following courses (or equivalent courses at other institutions): Some of the course topics overlap with these related courses, but none of the assignments will.

Assignments (tentative)

Students are strongly encouraged to use a camera and tripod to capture their own data for assignments. There's no need for anything fancy -- any digital camera with manual controls should work. Cameras may be available for loan from the instructor.

It is strongly recommended that all projects be completed in Matlab and all starter code will be provided for Matlab. Students may implement projects through other means but it will generally be more difficult.

Textbook

We will not rely on a textbook, although I recommend the free, online "Computer Vision: Algorithms and Applications" by Richard Szeliski.

Grading

Your final grade will be made up from

Syllabus (tentative)

Class DateTopicMaterials
Wednesday, Jan 27thIntroduction to computational photographySlides .ppt, .pdf
F, Jan 29thCameras and optics
M, Feb 1stCapturing light, man vs machineProject 1 out
W, Feb 3rdTBD
F, Feb 5thSampling and reconstruction
M, Feb 8thThe frequency domain, part 1
W, Feb 10thThe frequency domain, part 2
F, Feb 12thProject 1 presentations
M, Feb 15thBlending and compositing, part 1Project 2 out
W, Feb 17thBlending and compositing, part 2
F, Feb 19thPoint processing
M, Feb 22ndNo Classes
W, Feb 24thImage warping
F, Feb 26thImage morphing
M, Mar 1stProject 2 presentations
W, Mar 3rdData-driven methods: video and textureProject 3 out
F, Mar 5thData-driven methods: hallucinating data
M, Mar 8thData-driven methods: features and image comparisons
W, Mar 10thData-driven methods: leveraging the Internet
F, Mar 12thData-driven methods: lots of images, part 1
M, Mar 15thData driven methods: lots of images, part 2
W, Mar 17thProject 3 presentations / midterm review
F, Mar 19thMidterm Exam
M, Mar 22ndModeling lightProject 4 out
W, Mar 24thHomographies and mosaics
F, Mar 26thAutomatic image correspondence
M, Mar 29thNo Classes
W, Mar 31stNo Classes
F, Apr 2ndNo Classes
M, Apr 5thProject 4 presentations
W, Apr 7thSingle view reconstructionProject 5 out
F, Apr 9thMore reconstruction
M, Apr 12thCoded aperture photography
W, Apr 14thNovel capture methods
F, Apr 16thMatting, part 1
M, Apr 19thMatting, part 2
W, Apr 21stProject 5 presentations
F, Apr 23rdHigh Dynamic RangeStart on final project
M, Apr 26thImage-based lighting, part 1
W, Apr 28thImage-based lighting, part 2
F, Apr 30thTBD
M, May 3rdPhoto quality assessment
W, May 5thImproving photos
F, May 7thTBD
M, May 10thTBD
Exam PeriodFinal project presentations

Similar Courses at other Universities