Columbia University

W4731 Computer Vision

Information

Instructor
Carl Vondrick
TAs
Oscar Chang
Xiaoning Wan
Boyuan Chen
James Shin
Wei Liu (Luc)
Time
MW 2:40pm-3:55pm
Location
451 CSB
Term
Fall 2018

Quick Links

Office Hours

  • Carl
    Mon 5-6pm, CEPSR 611
  • Oscar
    Thr 3-4pm, Mudd 535A
  • Xiaoning
    Mon 5-6pm, CS TA Room
  • Boyuan
    Tue 3-4pm, CS TA Room
  • James
    Thr 12-1pm, CS TA Toom
  • Luc
    Tue 4-5pm, CS TA Room

Grading

  • Homework 60%
  • Final Project 40%

Overview

This course is an introduction to fundamental and advanced topics in computer vision. Topics include image formation and optics, image sensing, binary images, image processing and filtering, edge extraction and boundary detection, region growing and segmentation, pattern classification methods, brightness and reflectance, shape from shading and photometric stereo, texture, binocular stereo, optical flow and motion, 2D and 3D object representation, object recognition, vision systems and applications.

Announcements

  • Details about the final project are now available
  • The course is currently full. It is unlikely that we will be able to add you.
  • You do not need to know C/C++ to take this course. We will use Python / Matlab.
  • The course website is under construction and subject to change.

Syllabus

This schedule is preliminary and subject to change as the term evolves.

# Date Topic Reading Assignments
1 Sep 5 Introduction pdf
Image Processing
2 Sep 10 Image Processing I pdf Szeliski 3.2, 3.5 HW1 Out
3 Sep 12 Image Processing II pdf Szeliski 3.4
Cameras and Physics
4 Sep 17 Image Formation Szeliski 2.1, 2.2, 2.3
5 Sep 19 Image Sensing Szeliski 2.1, 2.2, 2.3
6 Sep 24 Radiometry and Reflectance Szeliski 2.2 HW1 Due, HW2 Out
Recognition and Matching
7 Sep 26 Grouping: Edges and Boundaries pdf Szeliski 4.1, 4.2, 4.3
8 Oct 1 Feature Descriptors pdf
9 Oct 3 Matching and Image Alignment pdf
10 Oct 8 Learning-based Vision I pdf Goodfellow 6, 6.5 HW2 Due, HW3 Out
11 Oct 10 Learning-based Vision II pdf
12 Oct 15 Object Recognition pdf
13 Oct 17 Object Recognition pdf
3D Vision
14 Oct 22 Stereo pdf HW3 Due, HW4 Out
15 Oct 24 Geometry and Structure from Motion pdf
16 Oct 29 Photometric Stereo pdf
17 Oct 31 Learning 3D pdf Project Proposal Due
- Nov 5 Academic Holiday
Video
18 Nov 7 Motion and Optical Flow pdf HW4 Due
19 Nov 12 Object Tracking pdf HW5 Out
20 Nov 14 Activity Recognition pdf
21 Nov 19 Vision and Sound pdf
- Nov 21 Academic Holiday (Thanksgiving)
Frontiers
22 Nov 26 Self-supervised Learning pdf HW5 Due
23 Nov 28 Negative Results pdf
24 Dec 3 Bias and Ethics pdf
25 Dec 5 Project Presentations slides
26 Dec 10 Project Presentations slides Project Report Due

Course Policy

  • Homework must be turned in before lecture begins.
  • You are allowed to turn in one homework assignment a week late without penalty.
  • You may work in groups, but homework must be written up individually.
  • Academic dishonesty will result in a zero for the full course and your case will be sent to the dean's office.

Course Materials

We do not require a textbook. However, you may find the following books are useful resources:

  • Computer Vision: A Modern Approach by Forsyth and Ponce
  • Computer Vision Algorithms and Applications by Szeliski
  • Multiple View Geometry in Computer Vision by Hartley and Zisserman
  • Machine Learning: A Probabilistic Perspective by Murphy

We gratefully acknowledge several instructors for course material and slides: Shree Nayar, Antonio Torralba, William Freeman, Deva Ramanan, Kristen Grauman, Alyosha Efros, James Hays, Fei-Fei Li, Jia Deng.