Fall 2021 CS 543/ECE 549: Computer Vision
Quick links:
schedule,
Piazza (announcements and discussion),
Compass (assignment submission and grades), lecture recordings
Instructor: Svetlana Lazebnik (slazebni -at- illinois.edu)
Lectures: W F 11:00-12:15 -- see Piazza for details
TAs: Mukesh Chugani (chugani2), Meha Goyal (mehagk2), Ryan Marten (marten4), Yuan Shen (yshen47)
Instructor and TA office hours: TBA
Contacting the course staff: For emergencies and special circumstances, please email the instructor. For questions about lectures and assignments, use Piazza. For questions about your scores (including regrade requests), email the responsible TAs.
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: 3D geometry and recognition. The first theme is about using vision as a source of metric 3D information: given one or more images of a scene taken by a camera with known or unknown parameters, how can we go from 2D to 3D, and how much can we tell about the 3D structure of the environment pictured in those images? The second theme, by contrast, is all about vision as a source of semantic information: can we recognize the objects, people, or activities pictured in the images, and understand the structure and relationships of different scene components just as a human would? 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:
- Computer Vision: A Modern Approach by David Forsyth and Jean Ponce (2nd ed.)
- Computer Vision: Algorithms and Applications by Richard Szeliski (2nd ed., PDF available online)
- Programming assignments: 50%
- Five MPs, done individually, in Python
- Final project: 30%
- Groups of two to four; deliverables include proposal, intermediate progress report, final report
- Unit quizzes: 20%
- Four multiple-choice online quizzes on the four units from the syllabus below
- Participation: up to 3% extra credit
- Students can get extra credit for actively participating in class, on Piazza, or during office hours
Be sure to read the course policies!
Syllabus
I. Image formation and low-level vision- Camera models
- Light and color
- Linear filters and edges
- Feature extraction
- Optical flow and feature tracking
- Least squares fitting, robust fitting
- RANSAC
- Alignment, image stitching
- Camera calibration
- Epipolar geometry
- Two-view and multi-view stereo
- Structure from motion
- Statistical learning framework
- Image classification
- Deep learning
- Object detection
- Segmentation
- Advanced topics (depending on time, student interest, and instructor choice): image generation and manipulation, deep learning for 3D vision, vision and language, video
Schedule (tentative)
| Date | Topic | Readings (F&P 2nd ed.), assignments | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| August 25 | Introduction: PPTX, PDF | Homework: Assignment 0 | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| August 27 | Perspective projection: PPTX, PDF | Reading: F&P ch. 1 | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| September 1 | Cameras: PPTX, PDF | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| September 3 | Light and shading: PPTX, PDF | Reading: F&P ch. 2 Assignment 0 due September 6 | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| September 8 | Color: PPTX, PDF | Reading: F&P ch. 3 Homework: Assignment 1 September 10
| Linear filtering: PPTX, PDF
| Reading: F&P ch. 4
| September 15
| Edge detection: PPTX, PDF
| Reading: F&P sec. 5.1-5.2
| September 17
| Corner detection: PPTX, PDF
| Reading: F&P sec. 5.3
| September 22
| SIFT keypoints: PPTX, PDF
| Reading: Distinctive image features from scale-invariant keypoints | Assignment 1 due September 23 September 24
| Optical flow: PPTX, PDF
| Reading: F&P sec. 11.1 | Homework: Assignment 2, project proposal September 29
| Fitting: PPTX, PDF
| Reading: F&P sec. 10.2-10.4, 22.1
| October 1
| Alignment: PPTX, PDF
|
| October 6
| Alignment cont. (slides above)
| Reading: F&P sec. 12.1 | Project proposals due October 7 October 8
| Camera calibration: PPTX, PDF
| Reading: F&P ch. 1
| October 13
| Single-view modeling: PPTX, PDF
| Assignment 2 due October 14
| October 15
| Epipolar geometry: PPTX, PDF
| Reading: F&P sec. 7.1, H&Z ch. 9 | Homework: Assignment 3 October 20
| Structure from motion: PPTX, PDF
| Reading: F&P ch. 8
| October 22
| Two-view stereo: PPTX, PDF
| Reading: F&P ch. 7
| October 27
| Multi-view stereo: PPTX, PDF
|
| October 29
| Intro to recognition: PPTX, PDF
|
| November 3
| Intro to neural networks: PPTX, PDF
| Assignment 3 due November 4
| November 5
| Neural networks cont.
|
| November 10
| Convolutional networks: PPTX, PDF
| Project progress reports due November 11
| November 12
| Convolutional networks cont.
| Homework: Assignment 4
| November 17
| Detection: PPTX, PDF
|
| November 19
| Detection cont.
|
| December 1
| Dense prediction: PPTX,
PDF
| Assignment 4 due December 2
| December 3
| Generative networks, image-to-image translation: PPTX, PDF
|
| December 8
| Transformers, other trends: PPTX, PDF
| Final project reports due December 13th
| |