CSE 590: Computational Photography

Instructor: Tamara Berg  (tlberg -at- cs.sunysb.edu)
Office: 1411 Computer Science
Lectures: Tues/Thurs 4:00-5:20pm, Rm 69 Earth and Space
Office Hours: Tues/Thurs 3:00-4:00pm (and by appointment)
Course Webpage: http://tamaraberg.com/teaching/Spring_13/compphotog
TA: Anthony Jose (akjose -at- cs.stonybrook.edu)


Introduction

This course will explore topics in computational photography, a field at the intersection of computer vision, graphics, and photography. Over the semester we will look at how computation can be used to capture, create, and enhance digital imagery in an effort to move beyond the constraints of traditional cameras. Main areas covered will include: a) exploiting large corpora, b) images, manipulation, and editing, and c) the computational camera.


MS Basic Project Option
  • Sign up as CSE 522 to complete the MS Basic Project Option

Announcements


Schedule (subject to change)

DateTopic Readings (S=Szeliski book) Assignments
Jan 29Course Intro - Slides--
Jan 31Intro to Images - SlidesS3-
Feb 5Representations and Features - SlidesS4Do a matlab tutorial (links below)
Feb 7Big Data Intro - Slides80 Million Tiny Images,
Scene Completion Using Millions of Photographs
HW1 out
Feb 12Matlab Intro and Demos--
Feb 14Big Data Places - SlidesIm2GPS,
Data-Driven Visual Similarity for Cross-Domain Image Matching
-
Feb 19Big Data Places (cont) - SlidesPhoto-Tourism,
Creating and Exploring a Large Photorealistic Virtual Space
-
Feb 21Big Data (cont) --
Feb 26 Pixels & Pyramids - SlidesThe Laplacian Pyramid-
Feb 28Compositing and Blending - SlidesS10.4,
Poisson Image Editing,
Interactive Digital Photomontage
HW2 out
March 5Image Resizing - SlidesSeam Carving for Content-Aware Image Resizing,
GrabCut
-
March 7Image Resizing (cont - see slides for March 5)S10.5-10.6, Texture Synthesis
March 12Image Warping - SlidesS2.1, S3, S6.1-
March 14Image Morphing - SlidesView MorphingHW3 out
March 19Spring Break--
March 21Spring Break--
March 26Big Data for Image DescriptionGuest Lecture - Vicente Ordonez-
March 28Project Proposals-Prepare a 5 minute presentation and submit a 2 paragraph summary
April 2Fun with Faces - SlidesExploring Photobios,
Being John Malkovich
-
April 4Image Stitching - SlidesS9,
AutoStitch
-
April 9No Class - Traveling-Work on Projects
April 11Cameras - SlidesS2, Light Field Photography with a Hand-held Plenoptic Camera-
April 16Project Updates-Prepare a 10 minute presentation and submit a 4 paragraph summary
April 18Project Updates-Prepare a 10 minute presentation and submit a 4 paragraph summary
April 23Image Based LightingRendering Synthetic Objects into Legacy Photographs
April 25What Makes a Good Picture?High Level Describable Attributes for Predicting Aesthetics and Interestingness-
April 30The KinectGuest lecture (Tim Vallier & Jay Loomis), Real-Time Human Pose Recognition in Parts from a Single Depth Image-
May 2What Else Makes a Photo Good?--
May 7Final Project Presentations 1) Rohan & Manish, 2) Smriti & Surya, 3) Yaroslav & Rucha, 4) Weijie & Wenbin, 5) Yafei & Ying, 6) Sourabh & Gaurav, 7) Rishi & Neha, 8) Keerthi & Sivaram, 9) ChaitanyaPrepare a 10 minute presentation (submit by 12pm Tues)
May 9Final Project Presentations 1) Pallavi & Krishna, 2) Vyankatesh & Rohit, 3) Marina, 4) Prajwal & Keerthi, 5) Matt & Shaun, 6) Yi & Jianqi, 7) Kun & Puhua, 8) ZhonqiPrepare a 10 minute presentation (submit by 12pm Tues)
May 21Final Project Write-Up-Submit Project Write-Up (8 pages including abstract, intro, method, figures, experiments, conclusion)

Grading
There will be 3 homeworks during the first few months of the course to get students aquainted with computational photography. Over the final few months of the course students will develop and present a project related to computational photography. There will also be in class quizzes over the course of the semester approximately every other week.

Grading breakdown: Assignments (40%), Project (30%), Quizzes (20%), participation (10%),
Late homeworks will be accepted with 10% penalty per day. To accomodate for missed quizzes students will be able to drop their lowest quiz grade.


No prior experience in computer vision or graphics is required to take this course. Homeworks and projects may be completed in pairs. Homeworks and Projects are strongly recommended to be completed in Matlab (to take advantage of built-in functionality).

Submit all homeworks and project presentations to: sbu590@gmail.com


Text Book
Computer Vision: Algorithms and Applications by Rick Szeliski (draft)

Other Reference Books
Forsyth, David A., and Ponce, J. Computer Vision: A Modern Approach, Prentice Hall, 2003.
Hartley, R. and Zisserman, A. Multiple View Geometry in Computer Vision, Academic Press, 2002.

Matlab
Student Matlab licenses can be purchased from mathworks for $99 - Link.
Example Matlab tutorial 1
Example Matlab tutorial 2
Example Matlab tutorial 3

Credits
Many thanks to Alyosha Efros for excellent course and project design. Also thanks to Derek Hoeim, James Hays and others for their computational photography course materials, slides, etc.


Americans with Disabilities Act: If you have a physical, psychological, medical or learning disability that may impact your course work, please contact Disability Support Services, ECC (Educational Communications Center) Building, room 128, (631) 632-6748. They will determine with you what accommodations, if any, are necessary and appropriate. All information and documentation is confidential.

Academic Integrity: Each student must pursue his or her academic goals honestly and be personally accountable for all submitted work. Representing another person's work as your own is always wrong. Faculty are required to report any suspected instances of academic dishonesty to the Academic Judiciary. Faculty in the Health Sciences Center (School of Health Technology & Management, Nursing, Social Welfare, Dental Medicine) and School of Medicine are required to follow their school-specific procedures. For more comprehensive information on academic integrity, including categories of academic dishonesty, please refer to the academic judiciary website at http://www.stonybrook.edu/uaa/academicjudiciary/

Critical Incident Management: Stony Brook University expects students to respect the rights, privileges, and property of other people. Faculty are required to report to the Office of Judicial Affairs any disruptive behavior that interrupts their ability to teach, compromises the safety of the learning environment, or inhibits students' ability to learn. Faculty in the HSC Schools and the School of Medicine are required to follow their school-specific procedures.