CSCI1950-G Computational Photography
Spring 2010, MWF 1:00 to 1:50, CIT 367.
Instructor: James Hays
HTA: Patrick Doran
Course Description
Course Catalog EntryComputational Photography describes the convergence of computer graphics, computer vision, and the Internet with photography. Its goal is to overcome the limitations of traditional photography using computational techniques to enhance the way we capture, manipulate, and interact with visual media. In this course we will study many interesting, recent image based algorithms and implement them to the degree that is possible. We will cover topics such as
- Cameras and image formation
- Human visual perception
- Image processing (filtering, pyramids)
- Image blending and compositing
- Texture synthesis, super-resolution, denoising.
- Image completion / inpainting
- Image based lighting and rendering
- High dynamic range
- Depth and defocus
- Flash / no flash photography
- Coded aperture photography
- Single / multi view reconstruction
- Photo quality assessment
- Non photorealistic rendering
- Modeling and synthesis using Internet data
- ... more interesting topics.
Prerequisites
This course requires programming experience as well as basic linear algebra, calculus, and probability. Previous knowledge of computer graphics or computer vision will be helpful. It is strongly recommended that students have taken one of the following courses (or equivalent courses at other institutions):- CSCI 1230, Introduction to Computer Graphics
- CSCI 1430, Introduction to Computer Vision
- CSCI 2240, Interactive Computer Graphics
- ENGN 1610, Image Understanding
Assignments (tentative)
- Image alignment with pyramids
- Gradient domain fusion
- Image completion
- Panorama correspondence and stitching
- Single view reconstruction
- Your choice for final project (HDR, flash / no flash, matting, whatever else you want)
It is strongly recommended that all projects be completed in Matlab and all starter code will be provided for Matlab. Students may implement projects through other means but it will generally be more difficult.
Textbook
We will not rely on a textbook, although I recommend the free, online "Computer Vision: Algorithms and Applications" by Richard Szeliski.Grading
Your final grade will be made up from- 60% programming projects and written assignments
- 20% final project
- 20% written examination
Syllabus (tentative)
| Class Date | Topic | Materials |
| Wednesday, Jan 27th | Introduction to computational photography | Slides .ppt, .pdf |
| F, Jan 29th | Cameras and optics | |
| M, Feb 1st | Capturing light, man vs machine | Project 1 out |
| W, Feb 3rd | TBD | |
| F, Feb 5th | Sampling and reconstruction | |
| M, Feb 8th | The frequency domain, part 1 | |
| W, Feb 10th | The frequency domain, part 2 | |
| F, Feb 12th | Project 1 presentations | |
| M, Feb 15th | Blending and compositing, part 1 | Project 2 out |
| W, Feb 17th | Blending and compositing, part 2 | |
| F, Feb 19th | Point processing | |
| M, Feb 22nd | No Classes | |
| W, Feb 24th | Image warping | |
| F, Feb 26th | Image morphing | |
| M, Mar 1st | Project 2 presentations | |
| W, Mar 3rd | Data-driven methods: video and texture | Project 3 out |
| F, Mar 5th | Data-driven methods: hallucinating data | |
| M, Mar 8th | Data-driven methods: features and image comparisons | |
| W, Mar 10th | Data-driven methods: leveraging the Internet | |
| F, Mar 12th | Data-driven methods: lots of images, part 1 | |
| M, Mar 15th | Data driven methods: lots of images, part 2 | |
| W, Mar 17th | Project 3 presentations / midterm review | |
| F, Mar 19th | Midterm Exam | |
| M, Mar 22nd | Modeling light | Project 4 out |
| W, Mar 24th | Homographies and mosaics | |
| F, Mar 26th | Automatic image correspondence | |
| M, Mar 29th | No Classes | |
| W, Mar 31st | No Classes | |
| F, Apr 2nd | No Classes | |
| M, Apr 5th | Project 4 presentations | |
| W, Apr 7th | Single view reconstruction | Project 5 out |
| F, Apr 9th | More reconstruction | |
| M, Apr 12th | Coded aperture photography | |
| W, Apr 14th | Novel capture methods | |
| F, Apr 16th | Matting, part 1 | |
| M, Apr 19th | Matting, part 2 | |
| W, Apr 21st | Project 5 presentations | |
| F, Apr 23rd | High Dynamic Range | Start on final project |
| M, Apr 26th | Image-based lighting, part 1 | |
| W, Apr 28th | Image-based lighting, part 2 | |
| F, Apr 30th | TBD | |
| M, May 3rd | Photo quality assessment | |
| W, May 5th | Improving photos | |
| F, May 7th | TBD | |
| M, May 10th | TBD | |
| Exam Period | Final project presentations |