An image abstraction example produced by the method of Karacan, Erdem and Erdem (work in progress)

Course Description:

This advanced undergraduate course is about the fundamentals of computational photography, an emerging new research area which brings together the advancements in computer graphics, computer vision and image processing to overcome the limitations of conventional photography. The course is structured around basic topics such as cameras and image formation, blending, compositing, resizing, warping, morphing, texture synthesis, super resolution, panoramas, mosaics, collages, denoising, image inpainting, high dynamic range imaging, tone mapping, photo quality assessment and non-photorealistic rendering.

The main goal of this course is to introduce students a number of different computational techniques to capture, manipulate and enrich visual media. The students are expected to develop a foundational understanding and knowledge of concepts that underly computational photography. The students will also be expected to gain hand-on experience via a set of programming assignments supplied in the complementary BBM 446 Computational Photography Practicum. Hence, the students are strongly advised to register both BBM 444 and BBM 446 classes.

Prerequisites:

Good math (calculus, linear algebra, statistics) and programming skills. An introductory course in image processing (BBM 413) is highly recommended.

Reference books:

• Computer Vision: Algorithms and Applications, Richard Szeliski, Springer, 2010 (draft available online).
• Photography (10th edition), Barbara London, Jim Stone, and John Upton, Pearson, 2010
• Computer Vision: A Modern Approach (2nd Edition), David Forsyth and Jean Ponce, Prentice Hall, 2012.

Grading Policy:

Grading for BBM 444 will be based on a set of written assignments (15%), a midterm exam (35%) and a final exam (45%). Participation in class discussions will also be an important factor for the grade (5%). In BBM 446, the grading will be based on at least 4 problem sets which will be done individually.

Important Dates:

Detailed Schedule:

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).

Additional Resources:

• MATLAB Resources:
  • Introduction to MATLAB, by Danilo Šćepanović
  • MATLAB Tutorial, by Stefan Roth
  • MATLAB Primer, by MathWorks
  • Code Vectorization Guide, by MathWorks
  • Writing Fast MATLAB code, by Pascal Getreuer
  • MATLAB array manipulation tips and tricks, by Peter J. Acklam


• Linear Algebra:
  • A Geometric Review of Linear Algebra, by Eero Simoncelli
  • An Introduction to Linear Algebra in Parallel Distributed Processing, by M.I. Jordan

Communication:

The course webpage will be updated regularly throughout the semester with lecture notes, programming and reading assignments and important deadlines. All other communications will be carried out through Piazza. Please enroll it by following the link https://piazza.com/hacettepe.edu.tr/spring2013/bbm444

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.