This course is a first-principles introduction to the acquisition and computational processing of 2D images. It is aimed at undergraduates interested in learning about computer vision, digital photography and computer graphics.
The course serves as a stepping stone for tackling more advanced courses in those subjects and covers four broad themes:
Instructor office hour (week 2 onwards): Tuesday noon-1pm (BA7250) right before class.
TA office hour: TBD
Contact: Course announcements and general information will be posted Quercus. Q&A related to lectures, assignments and practice problems will take place on Piazza.
Course dropbox: The one-stop shop for all course materials. See Quercus for the link.
Links to slides for all lectures will be available on the course Dropbox approximately an hour before each lecture (see Quercus for Dropbox link). The full set of lecture slides from a recent offering of the course, taught by Kyros Kutulakos, is already available on dropbox. This years course slides will be very similar to pervious term's offering so students who prefer reviewing the lecture content well in advance of a lecture can simply refer to those slides.
Recordings should be available on Quercus soon after each lecture. Since recording glitches are not uncommon due to issues with the system in specific classrooms (eg. missing sound, incomplete recordings, delays in posting) the completeness and timely availability of these recordings cannot be guaranteed, and they should not be treated as a substitute for in-person attendance.
In addition to lecture slides, assigned readings consist of selected sections from the following textbooks. The vast majority of required readings come from the first two; the rest will be used very occasionally and/or only as optional readings for those interested in delving more deeply into the lecture's subjects. Several of these books are freely available online; the rest can be found in the library and/or are available for purchase. See the course schedule for full details.
For the first half of the course, selected cartoon videos from Steve Seitz' "Graphics in 5 minutes (G5M)" channel on youtube must be watched before each week's lecture. In addition to these videos, Shree Nayar's video lectures on the First Principles of Computer Vision are an excellent source of lectures for optional viewing after class. See the course schedule for full details.
Solutions to all past term tests and final exams since 2016 can be found on the course Dropbox. The TAs have also compiled a selected set of practice problems from a variety of textbooks to test your knowledge of each lecture. See the course schedule for full details.
There will be 4 programming assignments (see schedule). Each assignment comes with a partial implementation that you must complete, test, and write a report about. All except the first assignment will require reading an associated research paper and implementing (and testing) the technique it describes. Assignments will be exclusively in Python. All assignments will be posted on lecture day (Tuesdays) and will be due 3+ weeks later on the Tutorial day (Thursdays), with the exception of the last assignment, A4, that will be due on exactly 3 weeks later on Tuesday 02/12. Assginments are submited via MarkUs. The three best assignments will each count for 16% of the mark; the worst will count for 12%.
Late policy: All assignments are due 1 minute before midnight (11:59pm) on the due date. To account for unexpected technical last-minute issues with submissions, each student will be recieve one-hour grace period for every assignment. For an extension of an assignment deadline (at most 7 days) please use the special considerations form (link available on Quercus). You must submit this form even if you have already made an absence declaration request on Acorn. Requests made over email to an instructor or TA will not be honored.
Academic honesty policy for written components: All reports submitted as part of your assignments are strictly individual work. No part of these reports should be shared with others, or taken from others. This includes verbatim text, paraphrased text, and/or images used. You are, however, allowed to discuss these components with others at the level of ideas, and indeed you are welcome and encouraged to brainstorm together.
Academic honesty policy for programming components: Collaboration on a programming component by individuals (whether or not they are taking the class) is encouraged at the level of ideas. Feel free to ask each other questions, brainstorm on algorithms, or work together on a (virtual or real) whiteboard. Be careful, however, about copying actual code for programming assignments or merely adapting someone else's code. This sort of collaboration at the level of artifacts is permitted if explicitly acknowledged, but will result in marks deduction. Full details about how to acknowledge such collaborations (and what deductions to expect) will be provided in the individual assignment handouts.
The use of generative artificial intelligence (AI) tools is strictly prohibited in all programming assignments. This includes, but is not limited to, ChatGPT, GitHub Copilot, and open-source models that you have trained and/or deployed yourself. You may not interact with, nor copy, paraphrase, or adapt any content from any generative AI for the purpose of completing programming assignments in this course. Use of generative AI will be considered use of an unauthorized aid, which is a form of academic misconduct under the Code of Behavior on Academic Matters. This course policy is designed to promote your learning and intellectual development and to ensure that our evaluations are a fair and accurate assessment of your learning. To that end, you will be required to include detailed comments along with the code you submit, and a random subset of students may be selected by a TA to explain their implementation in a live 1-1 meeting.
Final exam (no auto-fail): Date and time TBD.
| Lecture Week |
Date | Description | G5M Videos to Watch Before Class | Readings & Exercises |
Event | Deadline |
|---|---|---|---|---|---|---|
| Part I: Foundations | ||||||
| 1 | Tue 02/09 |
Course Intro Image Geometry 1 Homogeneous 2D coordinates, 2D transformations, homographies, image warping algorithms. |
Affine transforms
|
[materials01] | ||
| Thu 04/09 |
Tutorial Image I/O in OpenCV and Python. |
|||||
| 2 | Tue 09/09 |
Image Geometry 2 Homogeneous 3D coordinates, pinhole imaging & perspective projection, imaging of 3D planes, panoramic image stitching, homography estimation. |
Perspective projection, Perspective projection--the math |
[materials02] | A1 out on Dropbox | |
| Thu 11/09 |
Tutorial Linear algebra refresher: solving systems of linear equations. Lecture 1 practice problems. |
|||||
| 3 | Tue 16/09 |
Image Filtering 1 Linear shift-invariant filters, convolution, basic filters. |
Images, Image filtering | [materials03] | ||
| Thu 18/09 |
Tutorial Lecture 2 practice problems. A1 Q&A. |
|||||
| 4 | Tue 23/09 |
Image Filtering 2 Gaussian filters, derivative filters, sharpening filters. The Bilateral filter. Discrete image formation, image interpolation. |
Interpolation | [materials04] | ||
| Thu 25/09 |
Tutorial Image filtering in action with OpenCV. Lecture 3 practice problems. Lecture 6 prep: Math refresher on complex numbers and their Euler representation |
|||||
| 5 | Tue 30/09 |
Image Filtering 3 Introduction to Fourier transforms, convolution theorem. |
Fourier transforms | [materials05] | A2 out on Dropbox | |
| Thu 02/10 |
Image Filtering 3 continued (no tutorial this week). | A1 due at 11:59pm | ||||
| 6 | Tue 07/10 |
Image Filtering 4 Fourier-domain image filtering, hybrid images. Sampling theory basics, aliasing, anti-aliasing methods. |
[materials06] | |||
| Thu 09/10 |
Tutorial Lecture 3 & 4 practice problems. A2 overview and Q&A. |
|||||
| 7 | Tue 14/10 |
Color Vision & Camera ISPs Color perception in the human visual system, color imaging, color spaces, color displays. Smartphone Image Signal Processing pipelines. |
Color | [materials07] | ||
| Thu 16/10 |
Tutorial Fourier-domain filtering & anti-aliasing in action with OpenCV. A2 Q&A. |
|||||
| Part II: Image Representations | ||||||
| 8 | Tue 21/10 |
Differentiable 1D & 2D Representations Representing smooth 2D curves, curve tangent, curve normal and the moving frame. Image gradient, image Laplacian, edge enhancement, Canny edge detection. Intelligent scissors, painterly rendering. |
[no video] | [materials08] | A3 out on Dropbox | |
| Thu 23/10 |
Tutorial Lecture 7 practice problems. A3 Q&A. |
A2 due at 11:59pm | ||||
| 28/10 30/10 |
Reading week break (No Lecture, Tutorial, Office hours) | |||||
| 9 | Tue 04/11 |
Vector-Based Representations 1 Template matching, measuring image similarity, Harris/Foerstner corner detection. Introduction to PCA. |
[no video] | [materials09] | ||
| Thu 06/11 |
Tutorial Lecture 8 practice problems. Lecture 10 prep: Linear algebra refresher on matrix eigenvectors and eigenvalues. |
|||||
| 10 | Tue 11/11 |
Vector-Based Representations 2 Principal component analysis, face recognition using eigenfaces. |
[no video] | [materials10] | A4 out on Dropbox | |
| Thu 13/11 |
Tutorial Lecture 9 practice problems. Overview of A4. |
A3 due at 11:59pm | ||||
| 11 | Tue 18/11 |
Multi-Scale Representations 1 The Discrete Haar Wavelet Transform, wavelet-based image compression, wavelet-based image processing. |
[no video] | [materials11] | ||
| Thu 20/11 |
Tutorial Lecture 10 practice problems. A4 Q&A. |
|||||
| 12 | Tue 25/11 |
Multi-Scale Representations 2 Panoramic image stitching revisited. SIFT keypoints and SIFT-based correspondence-finding. Robust model fiting using RANSAC. Gaussian and Laplacian pyramids. Laplacian image blending. |
[no video] | [materials12] | ||
| Thu 27/11 |
Tutorial Preparing for the final. |
|||||
| Tue 02/12 |
End of term |
A4 due at 11:59pm |
You are welcome to use your personal computer (OSX, Windows or Linux) for programming assignments. Be aware, however, that TAs will test your code on Teaching Labs computers and thus it is essential that you verify your code there before submission.
We will support only one of the latest versions of python and recommend that you install it using Anaconda or Miniconda (see installation instructions here). Further information about setting up your computing environment for the course's programming assignents will be given at the first tutorial and will also be available in the Tutorial 1 slides.
This version of the course was built (and taught in previous terms) by Kyros Kutulakos. The lecture slides have been revised significantly from offerings of the course prior to 2021, and include slides from several other instructors. Feel free to use these slides for academic or research purposes, but please maintain all acknowledgments and source information. The format and style of this webpage are based on those of CS2529, taught by David Lindell.
