Academics / Courses / DescriptionsCOMP_SCI 397, 497: Computational Photography Seminar
VIEW ALL COURSE TIMES AND SESSIONS
Description
This course is second in a two-part series that explores the emerging new field of Computational Photography. Computational photography combines ideas in computer vision, computer graphics, and image processing to overcome limitations in image quality such as resolution, dynamic range, and defocus/motion blur. This course will first cover state-of-the-art topics in computational photography such as motion/defocus deblurring cameras, light field cameras, computational displays, and much more!
Course assignments will consist of 2-4 paper presentations and a final project. There will be no midterm or final exam. Students will choose 2-4 papers to read for the list of topics on the course webpage. For each of these papers a brief 15-20 minute presentation will be given in class, explaining the core idea and technical novelty. A discussion will then follow on how the technique relates to other recent work in the field.
- This course fulfills the CS Project Course & Interfaces breadth requirement.
COURSE GOALS- To teach the state-of-the art in computational photography, including computational cameras, computational lighting, and computational displays. Students will read and present 2-4 papers in a number of current topics in the field. There will be a final project where students will have a chance to implement a research project of their choosing. The goal of the project will be to synthesize the concepts learned in the course to produce novel imaging systems with new functionality.
FINAL PROJECTS- For the final project, students will have an opportunity to implement a project on their own or in teams. The project may include some camera, lighting/projector, optics, or image processing development. Resources will be provided to assist students in their research projects (e.g. SLR cameras, lenses, light field cameras, projectors, etc.). The project may be to reproduce results from one of the papers discussed in class, or it may be to do something entirely different. Project proposals will be due Wednesday April 30, and the final results for the project will be presented in the final day of class on June 4.
Students who do not wish to implement a project may alternatively read an additional 3 papers from the course website not presented in class. A presentation summarizing these papers will be given on the final day of class, and a written 6-8 page report (total, for all papers) will be submitted at the last class.
PREREQUISITES- This course will be seminar, offered to all students with knowledge in any of the three core areas: computer vision, computer graphics, or photography. If you are interested, please contact the instructor to discuss!
Topics Covered
- Week 1: Introduction to Computational Photography
- Week 2: Extended Depth of Field and Coded Aperture
- Week 3: Motion Deblurring and Video Processing
- Week 4: Light Field Imaging
- Week 5: Spectral and Multimodal Imaging
- Week 6: Light Transport Acquisition and Processing
- Week 7: Structured Illumination and 3D Capture
- Week 8: Computational Displays
- Week 9: Transient and Compressive Imaging
- Week 10: Final Projects
GRADING-
- Presentations and Discussions - 50%
- Paper Review – 10%
- Final Project – 40%
TEXTS- There will be no text, readings will be posted on the course website
COURSE INSTRUCTOR- Prof. Oliver Cossairt