Fall 2026 CS 543/ECE 549: Computer Vision

Instructor

D.A. Forsyth --- 3310 Siebel Center
DAF in rebreather
Other times and locations may be available.

webpage email: (daf -at- illinois.edu)

Note As to email, you may need to be get lucky or be persistent. I get a ton of the stuff, mostly to do with herbal supplements, and often miss things

Office Hours: Tue: 13h00-14h00

In person

Lecture Time:Tue/Thur 11h00-12h15 mostly at 1404 Siebel

TA: Office Hour Procedures

CONFIRMEDWe will conduct office hours through zoom. Students can access the Zoom link here . We will use a queue. Students should submit questions when the queue is open and join the zoom. They should then wait for their turn. The TA might answer queries out of order  in the zoom or in a breakout room depending on the question. Discussing individual homework solutions will generally happen in breakout rooms. Some queries in an office hour might remain unanswered because of the time constraint. These will be moved to the next office hour automatically by the queuing system

  • Vardhan Dongre email: vdongre2@illinois.edu Office hours: Mon, 15h00-16h00
  • Ayush Sarkar email: ayushs2@illinois.edu Office hours: Thur, 15h00-16h00
  • Jose Cuaran Valenzuela email: jrc9@illinois.edu Office hours: Fri, 15h00-16h00
  • Ziyin Wang email: ziyin@illinois.edu Office hours: Wed, 15h00-16h00
DAF photo of Bob Thorpe at 55 m at The Bluffs, Lake MI
Other times and locations may be available.

Quick links:

  • The planned schedule is below, but plans change...
  • Campuswire (I think) but you should have received an email invitation (announcements and discussion)
  • Not Yet Right You should likely get an email from Canvas (assignment submission and grades)
  • Mediaspace Link(lecture recordings - )

Contacting course staff

For emergencies and special circumstances, please email the instructor. Put 'URGENT URGENT URGENT' in your subject. If your email is not in fact urgent, the curse of Gnome may strike you. Urgent means major catastrophes that need immediate attention.

For questions about lectures and assignments, use Campuswire. For questions about your scores (including regrade requests), email the responsible TAs.

Email Subject Line Format (Required)

To help course staff triage and respond faster, please use the following subject line format for all emails to the course staff:

  • Start with one of these exact course tags:
    • [CS543]
    • [ECE549]
    • [CS543/ECE549]
      • (if relevant to both)
  • Then use this template:

    [CS543] < Category>: < Short topic > < Your Name> (< NetID>)

    Allowed categories (pick one):
    • HW#
    • Quiz
    • Lecture
    • Regrade
    • Logistics
    • Office Hours

    Examples:

    • [CS543] HW2: clarification on Q3 Jane Doe (jdoe3)
    • [ECE549] Lecture: didn’t understand expectation maximization John Smith (jsmith7)
    • [CS543/ECE549] Logistics: enrollment issue Alex Lee (alee9)

    Emails that don’t follow this subject format may be delayed or worse, go unanswered.

    Overview

    In the simplest terms, computer vision is the discipline of "teaching machines how to see." This field dates back more than fifty years, but the recent explosive growth of digital imaging and machine learning technologies makes the problems of automated image interpretation more exciting and relevant than ever. There are two major themes in the computer vision literature: modelling and recognition. The key question in modelling is how to pass from pictures of the world to a model of the world. Usually, the model contains metric 3D information, but often it contains more -- surface properties, texture, and so on. There are many important cases. The key question in recognition is how to recover semantic information -- the categories of objects; the properties of objects; the names or behavior of people; and so on -- from pictures of the world. This course will provide a coherent perspective on the different aspects of computer vision, and give students the ability to understand state-of-the-art vision literature and implement components that are fundamental to many modern vision systems.

    Prerequisites: Basic knowledge of probability, linear algebra, and calculus. Python programming experience and previous exposure to image processing are highly desirable.

    Recommended textbooks: Grading scheme:

    I reserve the right to change weights depending on events and my judgement.

    The nature and number of assignments is changing; watch this space

    Course Policies

    Be sure to read the course policies!

    Warning: I will interpret these policies in what I take to be their spirit and intention. My intention is that you learn a lot about computer vision, and can display what you have learned in some detail and honestly.

    Projected course schedule

    Planned sequence of lectures intended exercises here shortly

    Syllabus

    I. Elementary image representations
    • Image sampling, interpolation, transformations
    • Linear filters and edges
    • Denoising
    • Feature extraction
    II. Mid-level Vision:
    • Voting
    • Fitting
    • Robustness, IRLS and RANSAC
    • Registration and ICP
    III. Learned Image Representations:
    • Learned Denoising
    • Mapping images to images
    • Classification
    • Detection
    IV. Image formation and geometric vision
    • Camera models
    • Light, shading and color
    • Camera calibration
    V. Pairs of Cameras and more
    • Geometry
    • Odometry
    • Optic Flow
    • Stereopsis
    • Structure from Motion
    • Tracking
    • Advanced topics (depending on time, student interest, and instructor choice): image generation and manipulation, deep learning for 3D vision, vision and language, video

    Resources

    Credits

    This course will follow closely the form established by Prof. Svetlana Lazebnik. The slides are very largely hers, too, though I will likely add some bits; likely, you'll be able to tell which bits I've added by a distinct dip in quality. The course web page very largely follows hers, too.