Home / Courses / CS576



CS576: Computer Vision

Spring 2019



Min H. Kim, [Room] 3429, [email]

Course description


This course provides advanced topics to computer vision, including the foundations and applications of camera image formation, geometric optics, feature detection, stereo matching, motion estimation, image recognition, scene understanding, etc. This course will help students develop intuitions and mathematics of various advanced computer vision applications.

Lecture time and place

Monday and Wednesday 1:00PM—2:30PM, Rm. 117, Bldg. N-1

TA office hours

(Suk Jun Jeon, Hyeonjoong Jang) Tuesday and Thursday 2:30PM—5:30PM, Rm. 2443, Bldg. E3-1
(Inseung Hwang) Thursday 2:30PM—5:30PM, Rm. 2443, Bldg. E3-1

Teaching assistants

Suk Jun Jeon, [e-mail]
Hyunho Ha, [e-mail]
Hyeonjoong Jang, [e-mail]
Shinyoung Yi, [e-mail]
Inseung Hwang, [e-mail]


Richard Szeliski (2010) Computer Vision: Algorithms and Applications, Springer [site]


Gary Bradski, Adrian Kaehler (2016) Learning OpenCV 3, O'Reilly Media [site]


There are no official course prerequisites.

Course goal

Student will establish theoretical and practical foundations of computer vision and be familiar with various computer vision applications.

Tentative schedule


  Week Date Lecture Readings Slides HW Due
  1 2/25 Introduction to computer vision chapter 1 slide01   
    2/27 Image formation and camera chapter 2 slide02   
  2 3/4 Epipolar geometry chapter 11 slide03    
    3/6 Camera calibration chapters 6 and 11 slide04   
  3 3/11 Stereo matching chapters 6 and 11 slide05v2    
  3/13 Structure from motion chapters 7 slide06  
  4 3/18 Thin lens and optics chapters 2 and 10 slide07    
    3/20 Light-field imaging chapter 13 slide08v2 HW1  
  5 3/25 High dynamic range (HDR) imaging      
  3/27 High dynamic range (HDR) rendering      
  6 4/1Hyperspectral imaging        
    4/3 Light      
  7 4/8Color     HW2  
    4/10Frequency domain        
  8 4/15 Mid-term exam        
  9 4/22 Machine learning for computer vision        
    4/24 Linear regression      
  10 4/29Classification     HW3  
    5/1 Clustering        
  11 5/6 No lecture        
  5/8 Recognition        
  12 5/13Optical flow and visual tracking       
    5/15 Neural network     HW4  
  13 5/20No lecture        
    5/22 No lecture       
  14 5/27 Convolutional neural network (CNN) 1   
  5/29 Convolutional neural network (CNN) 2   
  15 6/3 Training neural networks      
    6/5 Understanding what CNNs learn      
  16 6/10 Final exam        


Attendance (10%), midterm/final exams (50%), assignments (30%), quizzes (10%)


Computer Graphics papers
Computer Vision papers

Hosted by Visual Computing Laboratory, School of Computing, KAIST.