Course Information

About

This graduate 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 covers some fundemental topics such as cameras and image formation, high dynamic range imaging, edge-aware filtering, gradient-domain processing, deconvolution, blending and compositing, visual quality assessment, deep image enhancement, neural rendering.

The aim of this course is to demonstrate students variety of different computational methods to capture, manipulate and enrich visual media. The students are expected to gain a foundational understanding and knowledge of concepts related to computational photography. The students will also be expected to gain hand-on experience via a project supplied during the semester.

The course is taught by Ahmet Selman Bozkır.

Exam Dates

Midterm: 2 April 2024, Tuesday at 13:30 (D5)
Final: To be announced later

Time and Location

Lectures: Tuesdays at 13:30-15:50 (D5)

Reference Books

  • Computer Vision: Algorithms and Applications, Richard Szeliski, Second Edition, 2022 (pdf 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.

Policies: All work on project must be done with pairs unless stated otherwise. You are encouraged to discuss with your classmates about the given project, 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. The conducted study must be reported in a suitable format and be sent through email.

Communication

The course webpage will be updated regularly throughout the semester with lecture notes, presentations, and important deadlines.

Pre-requisites

Good math (calculus, linear algebra, statistics) and programming skills. An introductory course in image processing (BBM413), and/or computer vision (BBM416) and/or machine learning (BBM406) is highly recommended.

Course Requirements and Grading

Grading for CMP721 will be based on

  • Class participation (5%),
  • Course project (done in pairs) (40%),
  • Midterm exam (20%), and
  • Final exam (35%).

Schedule

Date Topic Notes
Feb 20-27 Introduction, Digital photography [slides] Brian Hayes, Computational Photography, American Scientist 96, 94-99, 2008

Resources

Related Conferences

  • IEEE International Conference on Computer Vision (ICCV)
  • European Conference on Computer Vision (ECCV)
  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • SIGGRAPH
  • SIGGRAPH Asia
  • IEEE International Conference on Computational Photography (ICCP)
  • Advances in Neural Information Processing Systems (NeurIPS)
  • International Conference on Learning Representations (ICLR)

Reference Journals

  • ACM Transactions on Graphics (ACM TOG)
  • IEEE Transactions on Image Processing (IEEE TIP)
  • IEEE Transactions on Multimedia (IEEE TMM)
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI)
  • International Journal of Computer Vision (IJCV)
  • Computer Vision and Image Understanding (CVIU)
  • Image and Vision Computing (IMAVIS)
  • Journal of Electronic Imaging

Python Resources

Linear Algebra