This class is an introduction to fundamental concepts in image understanding, the subdiscipline of artificial intelligence that tries to make the computers “see”. It will survey a variety of interesting vision problems and techniques. Specifically, the course will cover image formation, features, object and scene recognition and learning, multi-view geometry and video processing. The goal of the class will be to grasp a number of computer vision problems and understand basic approaches to tackle them for real-world applications.
Lectures: Mondays 1:00pm-3:00pm (LEC0101; MP 137) and 3:00pm-5:00pm (LEC0201; ES B149). Lectures will be recorded and made available on Quercus.
Tutorials: Wednesdays 1:00pm-2:00pm (LEC0101; MP 137) and 3:00pm-4:00pm (LEC0201; ES B149).
Instructor office hours: Mondays 5:00pm-6:00pm (BA 7228).
TA office hours: Wednesdays 2:00pm-3:00pm (BA 2270).
Forum: Course announcements and general information will be posted on the course forum at Piazza. Any questions can also be discussed on the course forum, though do not expect an immediate response from the TAs. Also, do not expect answers during weekends or at the last minute before assignments are due. Please only email the instructor for emergency inquiries that cannot be handled on the forum via a private post: lindell@cs.toronto.edu.
Attendance: While lectures will be recorded, in-person attendance is expected as the recording will not capture all presented material (e.g., handwritten annotations, chalkboard diagrams, etc.).Quercus: Assignment materials, tutorial code, and grades will be posted on Quercus.
Textbook: Readings are primarily assigned from Richard Szeliski's online textbook, which is online and freely available (2010 version). Some topics will have specific additional assigned reading materials as indicated in the course schedule.
Assignments: All assignments must be submitted on MarkUs. You will be automatically added to MarkUs if you're taking the course. Please do not email the staff if you are not yet added at the beginning of the term; it may take a week or two to be added.
Remark requests must be submitted within 1 week of graded assignments being returned. Late remark requests will not be accepted.
Lateness: Each student will be given a total of 5 late days without penalty. For example, you can hand in five of the assignments one day late, or one assignment five days late. These late days are to be used at your discretion. If you run out of late days, any subsequent assignments that are submitted late will not be accepted unless warranted by an emergent situation and an extension is granted.
Only request an extension on the assignment deadline if you really have a situation that warrants an extension as you judge. Please make the request through a private post on the course forum. In such cases, be aware that it may take much longer to grade and return your assignment. Remember that an extension may take away time from working on subsequent assignments. For non-emergent circumstances, use your late days to extend the deadline rather than requesting an extension.
Accessibility: If you have a consideration that may require accommodations, please contact Accessibility Services: https://www.studentlife.utoronto.ca/as, 416-978-8060 or accessibility.services@utoronto.ca
Collaboration Policy: For each assignment, you are allowed to work together with one other student in class. However, you are still expected to write the solutions, code, and writeup in your own words; i.e. no copying. If you choose to work together with another student, you must write the following on the first line of your writeup (after your own name and before answering any questions): “In solving the questions in this assignment, I worked together with my classmate [name & student number]. I confirm that I have written the solutions/code/report in my own words”.
Submitting plagiarized solutions is an academic offense and can have severe penalties.
ChatGPT/LLM Policy: Students must compose their own solutions in homework reports. This includes writing their own derivations and their own code implementations in keeping with the collaboration policy above. As such, they must not look at solutions from others (unless working with another student as described above) or from the web (including ChatGPT). Students who are found to be in violation of this policy can face severe consequences.
Timed three-hour exam. Combination of multiple choice and short-answer/long-answer.
April 17, 7-10pm — WB 116 (A-X) or WB 119 (Y-ZZ)
Completion of two surveys based on a course ethics module of the course will be worth 0.5% each.
Students with diverse learning styles and needs are welcome in this course. In particular, if you have a disability or health consideration that may require accommodations, please feel free to approach me and/or the Accessibility Services Office as soon as possible. The Accessibility Services staff are available by appointment to assess specific needs, provide referrals and arrange appropriate accommodations. The sooner you let them and me know your needs, the quicker we can assist you in achieving your learning goals in this course.
| Week | Date | Description | Material | Readings | Event | Deadline |
|---|---|---|---|---|---|---|
| Week 1 | Mon Jan 6 |
Lecture 1: Introduction & Linear filters |
[slides] |
Szeliski 3.2 (optional) Brain mechanisms of early vision (optional) Early vision |
Assignment 1 out on Quercus | |
| Wed Jan 8 |
Tutorial 1 | |||||
| Week 2 | Mon Jan 13 |
Lecture 2: Edges |
[slides] |
Szeliski 4.2 (optional) Fourier Transform (optional) Computer color is broken (optional) Fourier Transform Textbook |
||
| Wed Jan 15 |
Tutorial 2 | |||||
| Week 3 | Mon Jan 20 |
Lecture 3: Image pyramids |
[slides] |
Szeliski 3.5 (optional) Pyramid methods |
||
| Wed Jan 22 |
Tutorial 3 | |||||
| Fri Jan 24 |
Assignment 1 due at 11:59pm | |||||
| Week 4 | Mon Jan 27 |
Lecture 4: Deep learning |
[slides] |
What is a neural network? Gradient descent Backpropagation Backpropagation calculus (optional) Notes on backpropagation |
Assignment 2 out on Quercus | |
| Wed Jan 29 |
Tutorial 4 | Ethics Survey 1 due | ||||
| Week 5 | Mon Feb 3 |
Lecture 5: Embedded ethics module | [slides] |
CelebA-HQ Samples |
||
| Wed Feb 5 |
Tutorial 5 | |||||
| Week 6 | Mon Feb 10 |
Lecture 6: Corner detection & optical flow |
[slides] | Szeliski 4.1.1 | ||
| Wed Feb 12 |
Tutorial 6 | |||||
| Fri Feb 14 |
Assignment 2 due at 11:59pm | |||||
| Week 7 | Mon Feb 17 |
Reading Week (No Lecture) |
Assignment 3 out on Quercus | |||
| Week 8 | Mon Feb 24 |
Lecture 7: Scale-invariant keypoints & SIFT |
[slides] |
Szeliski 4.1.1, 4.1.2 (optional) SIFT paper (optional) Local features (optional) SURF paper (optional) SuperGlue (optional) LoFTR |
||
| Wed Feb 26 |
Tutorial 7 | |||||
| Week 9 | Mon Mar 3 |
Lecture 8: Homography & RANSAC | [slides] | |||
| Wed Mar 5 |
Tutorial 8 | |||||
| Fri Mar 7 |
Assignment 3 due at 11:59pm | |||||
| Week 10 | Mon Mar 10 |
Lecture 9: Camera models |
[slides] |
Szeliski 6.1, 2.1.5 (optional) Moore-Penroose Inverse and Least Squares (optional) Recognising Panoramas |
Assignment 4 out on Quercus | |
| Wed Mar 12 |
Tutorial 9 | |||||
| Week 11 | Mon Mar 17 |
Lecture 10: Stereo I | [slides] | |||
| Wed Mar 19 |
Tutorial 10 | (optional) Face tracking | ||||
| Week 12 | Mon Mar 24 |
Lecture 11: Stereo II | [slides] |
Szeliski 11.1 (optional) Stereopsis (optional) Short notes on stereopsis (optional) 8-point algorithm (optional) Singular value decomposition |
||
| Fri Mar 28 |
Assignment 4 due at 11:59pm | |||||
| Week 13 | Mon Mar 31 |
Lecture 12: Object detection | [slides] | (optional) K-means demo | ||
| Fri Apr 11 |
Ethics Survey 2 due | |||||
| Thu Apr 17, 7-10pm (WB116/119) |
Final Exam |
We will only support Python 3.7 and recommend that you install it using Anaconda or Miniconda (see installation instructions here).
This course is adapted from previous offerings by Sanja Fidler, Ahmed Ashraf, and Babak Taati. The webpage is based on the website for CS231N and EE367 at Stanford University.
