This course is an introduction to fundamental and advanced topics in computer vision. Topics include image formation and optics, image sensing, binary images, image processing and filtering, edge extraction and boundary detection, region growing and segmentation, pattern classification methods, brightness and reflectance, shape from shading and photometric stereo, texture, binocular stereo, optical flow and motion, 2D and 3D object representation, object recognition, vision systems and applications.
- Due to demand, we have added another section (Section H01). If you could not get into the main section, please join this new section instead.
- The course wait list is managed by the computer science department. The course staff cannot sign your add forms or change your wait list status.
- Carl Vondrick, Tuesdays at 5:30 PM - 6:30 PM, in CEPSR 618
- Basile Van Hoorick, Mondays at 1:30 PM - 2:30 PM, in TA room
- Haoyu Qin, Mondays at 4:00 PM - 5:00 PM, in TA room
- Param Popat, Tuesdays at 1:00 PM - 2:00 PM, in TA room
- Neha Arora, Wednesdays at 12:00 PM - 1:00 PM, in TA room
- Varun Chanddra, Wednesdays at 6:00 PM - 7:00 PM, in TA room
- Minghao Chen, Wednesdays at 7:30 PM - 8:30 PM, in TA room
- Janane Sekaran, Thursdays at 12:00 PM - 1:00 PM, in TA room
- Junhao Wang, Thursday at 1:00 PM - 2:00 PM, in TA room
- Yueqi Wang, Thursdays at 6:00 PM - 7:00 PM, in TA room
- Yicun Liu, Fridays at 11:00 AM - 12:00 PM, in TA room
- For full credit, homework must be turned in by the posted deadline. One minute late is late. No exceptions. Each homework is worth 100 points. Homework 0 cannot be turned in late. For homework 1 and above, the late penalty applied to your homework is:
- 1 day late = lose 10 points
- 2 days late = lose 20 points
- 3 days late = lose 30 points
- 4 days late = lose 40 points
- 5 days late = lose 50 points
- 6 days and beyond = lose all points
- Due to class size, we cannot offer extensions. If you have an emergency, please ask your advising dean to contact us.
- If any part of the homework is late, the whole problem set is late.
- You may discuss homework in groups of max 3 people, but homework must be written up individually.
- There will be no make-up quizzes.
- Academic dishonesty will result in a zero for the full course and your case will be sent to the dean's office.
We do not require a textbook. However, you may find the following books are useful resources:
- Computer Vision: A Modern Approach by Forsyth and Ponce
- Computer Vision Algorithms and Applications by Szeliski
- Multiple View Geometry in Computer Vision by Hartley and Zisserman
- Machine Learning: A Probabilistic Perspective by Murphy
We gratefully acknowledge several instructors for course material and slides: Shree Nayar, Antonio Torralba, William Freeman, Deva Ramanan, Kristen Grauman, Alyosha Efros, James Hays, Fei-Fei Li, Jia Deng.