Course description
This course provides a comprehensive introduction to computer vision. Major topics include image processing, detection and recognition, geometry-based vision, video analysis, and generative models. Students will learn basic concepts of computer vision, and get hands-on experience to solve real-life vision problems.
Prerequisites
This course requires familiarity with linear algebra, probability, and calculus.
Textbooks
Readings will be assigned primarily from the following textbook, which can also be a useful reference in general.
- Computer Vision: Algorithms and Applications, by Rickhard Szeliski.
Evaluation
The final grade will comprise two two-week programming assignments (50% each). The programming assignments involve implementing and using standard computer vision pipelines.
Submitting homework and deadlines: We will use Gradescope for submitting and grading homeworks.
Late days: Late days will each incur a 10% penalty. Additionally, no programming assignment may be submitted more than three days after its due date, and any such submission will not be graded. Submission deadlines will be enforced strictly for the purposes of counting late days. In particular, no exceptions will be made for reasons such as upload delays, submitting incorrect files, and so on.
Collaboration policy: We encourage students to work in groups, but each student must submit their own work. This includes: writing their own code, coming up with their own math solutions, and producing their own writeup. If students work as a group, they must include the names of their collaborators in their writeup. Students absolutely must not share or copy code, data, or text from any source. Additionally, students must not use any external code or data unless explicitly permitted. These and any other forms of cheating are prohibited and will result in a failing grade for the entire course (not just the assignment they are caught on). If you are uncertain about whether some activity would be cheating, just be cautious and ask the teaching staff before proceeding. Additionally, students must not supply any code or writeups they complete during this course to other students in future instances of the course, or make this material available (e.g., on the web) for use in future instances of the course. Students must make sure any online repositories they use for the course are kept private.
Email, office hours, and discussion
Email: Please use [16705] in the title when emailing the teaching staff!
Office hours: Teaching staff will have regular office hours during the semester at the following times:
- Mondays 4:00–5:00 pm ET, Haoran.
- Wednesdays 3:00–4:00 pm ET, Yannis.
- Fridays 2:00–3:00 pm ET, Yehonathan.
All office hours will take place in person in Smith Hall (EDSH) 236 (graphics lounge).
Feel free to email us about scheduling additional office hours. Please do not email the teaching staff with questions about homework or grading. You should post those on Slack.
Discussion: We will use Slack for course discussion and announcements.
(Tentative) syllabus
Dates and topics are likely to change during the semester. Slides will be uploaded on this website before each lecture.
| Date | Topics | Homework |
|---|---|---|
| Mon, Mar 9 | Introduction | |
| Wed, Mar 11 | Image processing pipeline | |
| Mon, Mar 16 | Camera models and calibration | |
| Wed, Mar 18 | Two-view Stereo | |
| Mon, Mar 23 | Structure from motion | |
| Wed, Mar 25 | Structure from motion | |
| Fri, Mar 27 | PA1 out | |
| Mon, Mar 30 | Classification | |
| Wed, Apr 1 | Neural networks | |
| Mon, Apr 6 | Optical flow | |
| Wed, Apr 8 | Tracking | |
| Fri, Apr 10 | PA1 due, PA2 out | |
| Mon, Apr 13 | Feature detectors and descriptors | |
| Wed, Apr 15 | Neural rendering | |
| Mon, Apr 20 | Rendering with primitives | |
| Wed, Apr 22 | Wrap up | |
| Fri, Apr 24 | PA2 due |
Acknowledgments
The materials for this course have been pieced together from many different people and places. Special thanks to colleagues for sharing their slides: Kris Kitani, Bob Collins, Srinivasa Narashiman, Martial Hebert, Alyosha Efros, Ali Faharadi, Deva Ramanan, Yaser Sheikh, and Todd Zickler. Many thanks also to the following people for making their lecture notes and materials available online: Steve Seitz, Richard Szeliski, Larry Zitnick, Noah Snavely, Lana Lazebnik, Kristen Grauman, Yung-Yu Chuang, Tinne Tuytelaars, Fei-Fei Li, Antonio Torralba, Rob Fergus, David Claus, and Dan Jurafsky.