BIL 721 - Computational Photography (Spring 2015)

Lectures: Tue 13:00-15:45_D5

Philipp Otto Runge's Sphere (Die Farbenkugel) (1810) Animated movie still from The Royal Tenenbaums (2001), by If We Don't, Remember Me.

Instructor: Aykut Erdem

aykut-at-cs-hacettepe.edu.tr
111
+90 312 297 7500, 146

Course Description

This course introduces graduate students to a broad selection of topics in computational photography, an emerging new field at the intersection of computer graphics, computer vision and photography. The main focus of the course will be on software-based solutions, and to that end, we will discuss ways of using computational techniques to overcome the limitations of conventional photography and to enhance how we capture, manipulate and interact with images.

Prerequisites

Good programming skills (especially Matlab) and basic knowledge of linear algebra and calculus. Previous knowledge of computer graphics, computer vision or image processing will be helpful but not absolutely required.

Schedule (Tentative)

Week Date Topic Notes
1 Feb 17 Introduction to the course [slides] [4-per-page] Readings:
2 Feb 24 Cameras and sensors [slides] [4-per-page] PA1 is out
Readings: Demo: Photography applets (by Marc Levoy, Andrew Adams, Katie Dektar, and Nora Willett)
3 Mar 3 Image processing basics [slides] [4-per-page] Paper selections due
Readings:
  • A. Oliva, A. Torralba, and P.G. Schyns, Hybrid Images, ACM SIGGRAPH 2006
4 Mar 10 Texture synthesis, video textures [slides] [4-per-page] PA1 and project proposals due
Readings: Paper presentation:
  • D. Dai, H. Riemenschneider, and L. Van Gool, The Synthesizability of Texture Examples, CVPR 2014 (Samet Hicsonmez)
    5 Mar 17 Image resizing and blending [slides] [4-per-page] PA2 is out
    Readings: Paper presentation:
    6 Mar 24 Stitching and matting [slides] [4-per-page] Readings: Paper presentation:
    7 Mar 31 Warping and morphing [slides] [4-per-page] PA2 due
    Readings: Paper presentation:
    8 Apr 7 Panoramas and mosaics [slides] [4-per-page] PA3 is out [starter code]
    Readings: Paper presentation:
    9 Apr 14 HDR and tone mapping [slides] [4-per-page] Readings: Paper presentation:
    10 Apr 21 Faces [slides] [4-per-page] PA3 due
    Readings: Paper presentation:
    11 Apr 28 Better photos [slides] [4-per-page] Project progress reports due
    Readings: Paper presentation:
    12 May 5 Big visual data (part 1) [slides] [4-per-page] Readings: Paper presentation:
    13 May 12 Big visual data (part 2) [slides] [4-per-page] Readings: Paper presentation:
    14 May 19 No class (Commemoration of Ataturk, Youth and Sports Day)

    Grading

    Paper presentations and Quizzes

    The students will be required to present at least one research paper either of their choice or from the suggested reading list. These papers should be read by every student as the quizzes about the presented papers will be given on the weeks of the presentations.

    Programming Assignments

    There will be four assignments related to the topics covered in the class. Each assignment will involve implementing an algorithm, carrying out a set of experiments to evaluate it, and writing up a report on the experimental results. All assignments have to be done individually, unless stated otherwise.

    Project

    The students will be required to do a project in computational photography. For a detailed description of the course project, follow this link. In preparing your progress and final project reports, you should use the provided template and submit them electronically in PDF format.

    Reference Books

    Resources

    Communication:

    The course webpage will be updated regularly throughout the semester with lecture notes, programming and reading assignments and important deadlines. All other course related communications will be carried out through Piazza. Please enroll it by following the link https://piazza.com/hacettepe.edu.tr/spring2014/bil721

    Policies:

    All work on assignments must be done individually unless stated otherwise. You are encouraged to discuss with your classmates about the given assignments, but these discussions should be carried out in an abstract way. That is, discussions related to a particular solution to a specific problem (either in actual code or in the pseudocode) will not be tolerated.

    In short, turning in someone else’s work, in whole or in part, as your own will be considered as a violation of academic integrity. Please note that the former condition also holds for the material found on the web as everything on the web has been written by someone else.

    Acknowledgements:

    The materials used in this class largely rely on lecture notes by other researchers. In particular, the slides are adapted from those of Alexei A. Efros, Steve Seitz, Rick Szeliski, Paul Debevec, Stephen Palmer, Paul Heckbert, David Forsyth, Steve Marschner, Lana Lazebnik, Silvio Savarese, Rob Fergus, Marc Levoy, Peter N. Belhumeur, Derek Hoiem, James Hays, Tamara Berg, Fredo Durand, Bill Freeman (as credited within).

    © 2015 Hacettepe University