Coursework

Helpful Background

• Coding Experience (especially Python): All assignments will be in Python. Even though we don't assume prior experience in Python, you should familiarize yourself, for example by working through some online Python tutorials.
• Calculus, Linear Algebra: Basic understanding of matrix algebra (e.g., least squares, orthogonality, SVD) will be helpful (e.g., CSC336, MAT221, MAT223, MAT240).
• Statistical Signal Processing: Familiarity with probability theory and Bayes' theorem (e.g., MAT377).
• Discrete Signal Processing: Basic understanding of discrete Fourier transform, convolution theorem (e.g., ECE362).

Related courses

• CSC2530: Computational Imaging and 3D Sensing
• CSC2305: Numerical Methods for Optimization Problems
• CSC2503: Foundations of Computer Vision
• CSC2516: Neural Networks and Deep Learning
• ECE537: Random Processes
• ECE1505: Convex Optimization
• ECE1512: Digital Image Processing and Applications

Quercus

All assignments and the final project proposal and report should be submitted on Quercus. If you work as a team, make sure to indicate your team member in the submission.

Assignments (20%)

There will be 5 homework assignments (see schedule) in this class. These assignments will contain some theoretical questions and also implementations of techniques that we will discuss in class. Please refer to assignment writeups (available in the Files tab on Quercus) for details. After you finish, submit your code and report on Quercus. Homeworks are graded on completion, so each is worth an equal share of the 20% (4% per assignment); the midterm is where your understanding of the homework material is assessed.

Although homeworks are graded on completion, submissions after the deadline will still receive a 1% deduction per hour late.

Collaboration Policy: Homework assignments may be completed collaboratively. You are welcome to work together in groups—discussing the problems, working through the derivations, and writing and debugging code together—if you wish. Because the homeworks are graded on completion and are meant as low-stakes practice, there are no restrictions on working with classmates. We only ask that you (1) submit your own writeup on Quercus and (2) list the names of anyone you worked with. Note that the midterm is completed individually and is where your understanding of this material is assessed, so it is in your own interest to make sure you can do the work yourself.

AI Assistants Policy: You may use AI assistants (e.g., ChatGPT, Claude, Copilot) on the homework assignments, just as you may collaborate with classmates or consult references. The homeworks are practice—the goal is for you to learn the material, and the midterm is where that learning is assessed—so use these tools in a way that helps you understand the techniques rather than just produce an answer. Please include a brief acknowledgment of any AI tools you used and how you used them. 

For the final project, you are welcome to use AI assistants as a tool (e.g., for coding support or polishing writing). However, you must be thoroughly familiar with the details of your own implementation—this will be assessed during your poster presentation, where we will ask you to explain how your method works. We also expect project reports to be written and carefully edited by your team so that they read clearly and accurately and are specific to your work; ultimately you are responsible for what is written in the report. Any use of AI should be acknowledged in your report.

Midterm (30%)

There will be one in-class midterm exam (see schedule) covering the lecture and homework material from the first part of the course. The midterm is closed-book and completed individually; it is the primary assessment of your understanding of the course material.

Final Project (50%)

The final project grade takes into account your poster presentation (organization of poster, clarify of presentation, ability to answer question), your source code submission (code organization and documentation), and your final project report (appropriate format and length, abstract, introduction, related work, description of your method, quantitative and qualitative evaluation of your method, results, discussion & conclusion, bibliography).

You can work in teams of up to 3 students for the project. Submit only one proposal and final report for each team. The expected amount of work is relative to the number of team members, so if two teams work on a similar project, we'd expect less work from a smaller team. Before you start to work on the proposal or the report, take a look at some of the past project proposals and reports to give you sense for what's expected (see link at the bottom of this page).

The project proposal is a 1-2 page document that should contain the following elements: clear motivation of your idea, a discussion of related work along at least 3 scientific references (i.e., scientific papers not blog articles or websites), an overview of what exactly your project is about and what the final goals are, milestones for your team with a timeline and intermediate goals. Once you send us your proposal, we may ask you to revise it and we will assign a project mentor to your team.

The final project report should look like a short (~6 pages) conference paper. We expect the following sections, which are standard practice for conference papers: abstract, introduction, related work, theory (i.e., your approach), analysis and evaluation, results, discussion and conclusion, references. To make your life easier, we provide an LaTex template that you can use to get started on your report (see schedule for link). A detailed rubric can be found on Quercus under the final project report assignment.

Schedule and Syllabus

Previous Course Offerings

This course is adapted from the Computational Imaging course designed by Gordon Wetzstein and offered at Stanford University (EE367). Below you can find links to pinhole camera photos and course projects from these previous iterations of the course.

Pinhole Camera Gallery

Links to notable pinhole camera photos:

• Winter 2020 (Stanford)
• Winter 2021 (Stanford)
• Fall 2024 (Toronto)

Previous Course Projects

• Winter 2020 (Stanford)
• Winter 2021 (Stanford)
• Winter 2022 (Stanford)
• Fall 2022 (Toronto)
• Fall 2023 (Toronto)
• Fall 2024 (Toronto)
• Fall 2025 (Toronto)

Acknowledgements

The course is adapted from EE367 at Stanford University by Gordon Wetzstein. Some of the materials used in class build on that from other instructors, including Yannis Gkioulekas, Marc Levoy, Fredo Durand, Ramesh Raskar, Shree Nayar, Paul Debevec, Matthew O'Toole and others, as noted in the slides. Feel free to use these slides for academic or research purposes, but please maintain all acknowledgments. This webpage is based on the website for CS231N and EE367 at Stanford University.