CSCI1950-G Computational Photography

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

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 linear algebra, basic calculus, and basic 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

Winning projects

All Results

Image alignment with pyramids Evan Donahue, Evan Wallace Proj 1
Gradient domain fusion using Poisson blending Evan Wallace, Steve Gomez Proj 2
Image stitching with graph cuts Evan Wallace, Jason Pacheco Proj 3
Scene Completion Evan Wallace, Linda Fong Proj 4
Face morphing Sam Potasznik, Evan Wallace Proj 5
Panorama correspondence and stitching Steven Gomez, Evan Wallace Proj 6
Your choice for final project (single view reconstruction, high dynamic range, flash / no flash, interactive cut out, matting, whatever else you want) Your project here! Public Final Projects
*All Final Projects
*(Internally available only)
Students are required to capture their own photographic 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 You have three "late days" for the whole course. That is to say, the first 24 hours after the due date and time counts as 1 day, up to 48 hours is two and 72 for the third late day. This will not be reflected in the initial grade reports for your assignment, but they will be factored in and distributed at the end of the semester so that you get the most points possible.

Graduate credit is available and each project will specifiy the minimum requirements to earn such credit.

Important Links:

Contact Info and Office Hours:

You can contact the professor or TA staff with any of the following: Professor James' office hours will be held in his office (CIT 445). TA office hours will be held in the Brindy Bowl (CIT 271).

Syllabus (tentative)

Class Date Topic Materials Out Due Results
W, Jan 27th Introduction to computational photography .ppt
Szeliski chapter 1
F, Jan 29th Cameras and optics .ppt
Szeliski chapter 2
Project 1 out
M, Feb 1st Capturing light, man vs machine .ppt
Szeliski chapter 2
W, Feb 3rd Sampling and reconstruction 1 .ppt
Szeliski chapter 3.2
F, Feb 5th Sampling and reconstruction 2 .ppt Project 1 due
M, Feb 8th Project 1 Presentations, Frequency Domain .ppt
Szeliski Chapter 3.3
Project 2 out Project 1 results
W, Feb 10th Frequency domain / Blending and compositing .ppt
Szeliski Chapter 9.3.3
F, Feb 12th In class blending demo and Morphology .ppt
Szeliski Chapter 3.2.3
M, Feb 15th Point Processing and DCT/JPEG .ppt 1, .ppt 2
Szeliski Chapter 3.1
W, Feb 17th Image Warping .ppt
Szeliski Chapter 3.5
Project 3 out Project 2 due
F, Feb 19th Project 2 presentations, Project 3 intro .pptx
Project 2 results
M, Feb 22nd No Classes
W, Feb 24th Graph cut image compositing In class demos,
Szeliski Chapter 9.3.2
F, Feb 26th Data-driven methods: video and texture .ppt
Szeliski Chapter 13.5 and 10.5
Project 3 due
M, Mar 1st Project 3 presentations, Project 4 intro .pptx
Project 4 out Project 3 results
W, Mar 3rd Data-driven methods: texture synthesis and filling .ppt
F, Mar 5th Data-driven methods: Scene Completion .ppt
M, Mar 8th Data-driven methods: leveraging the Internet .pptx
W, Mar 10th Data driven methods: features and image comparisons .pptx
F, Mar 12th Data driven methods: more features with im2gps .pptx Project 4 due
M, Mar 15th Project 4 presentations Project 5 out Project 4 results
W, Mar 17th Image morphing .ppt
F, Mar 19th Matting and Transparancy .ppt
M, Mar 22nd Midterm review
W, Mar 24th Midterm Exam
F, Mar 26th Class cancelled Project 5 due
M, Mar 29th No Classes
W, Mar 31st No Classes
F, Apr 2nd No Classes
M, Apr 5th Project 5 presentations, Midterm discussion, Project 6 intro Project 6 out Project 5 results
W, Apr 7th Modeling light and lightfields .ppt
Szeliski chapter 13.3
F, Apr 9th Homographies and mosaics .ppt
Szeliski chapter 9.1
M, Apr 12th Automatic image correspondence .pptx
Szeliski chapter 9.1
W, Apr 14th RANSAC and mosaic wrapup .pptx
Szeliski chapter 9.1.5
F, Apr 16th Capturing and compressing high dynamic range .pptx
Debevec and Malik, SIGGRAPH 97
Szeliski Chapter 10.2
Final out Project 6 due
M, Apr 19th Local tone mapping and bilateral filters .pptx
Durand and Dorsey, SIGGRAPH 2002
Szeliski Chapter 10.2
Project 6 results
W, Apr 21st Project 6 presentations, Novel capture methods
F, Apr 23rd High Dynamic Range
Invited Lecture by Sam Hasinoff
M, Apr 26th Coded Aperture Photography .ppt, Levin et al., SIGGRAPH 2007
W, Apr 28th Image-based lighting .ppt
F, Apr 30th Light Fields
Invited Lecture by Douglas Lanman
M, May 3rd Photo quality assessment .ppt
W, May 5th No Classes
F, May 7th Improving photos
Invited Lecture by Vladimir Bychkovsky
Exam Period, Tuesday May 18th, 2:00pm Final project presentations Final results

Acknowledgements

The materials from this class rely heavily on slides prepared by other instructors. In particular, many materials are modified from those of Alexei A. Efros, who in turn uses materials from Steve Seitz, Rick Szeliski, Paul Debevec, Stephen Palmer, Paul Heckbert, David Forsyth, Steve Marschner and others, as noted in the slides. Feel free to use these slides for academic or research purposes, but please maintain all acknowledgements.

Similar Courses at other Universities