Home / Courses / CS484



CS484: Introduction to Computer Vision

Fall 2022


Min Hyuk Kim, [Room] 2403, [email]

Course description


This course provides a comprehensive introduction to low-level computer vision, including the foundations 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 computer vision applications.

Lecture time and place

Tuesday and Thursday 1:00PM—2:30PM, Creative Learning Bldg., Rm. 311

TA office hours

Tuesday and Thursday 3:00PM—6:00PM, E3-1, Rm. 2401

Teaching Assistants

Shinyoung Yi (Head TA, ex. 7864, )
Donggun Kim (ex. 7864, )
Inseung Hwang (ex. 7864, )
Jaemin Cho (ex. 7864, )
Sanghyeon Lee (ex. 7864, )

Reference books

Richard Szeliski (2010) Computer Vision: Algorithms and Applications, Springer [site]
Richard Hartley and Andrew Zisserman (2011) Multiple View Geometry in Computer Vision, Cambridge Press [site]
Christopher M. Bishop (2006) Pattern Recognition and Machine Learning, Springer [site]
Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016) Deep Learning, MIT Press [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

(Note that this curriculum will be revised adaptively.)

  Index Date Lecture Slides HW Due
  1 08/30 Introduction to computer vision slide01    
  2 09/01 Light slide02    
  3 09/06 Human visual system slide02    
  4 09/08 Color camera, photography slide03    
  5 09/13 Digital imaging slide04    
  6 09/15 Image filter slide05    
  7 09/20 Fourier Series & Transform slide06v5    
  8 09/22 Image formation of camera slide07    
  9 09/27 Epipolar geometry slide08v2    
  10 09/29 Homography, calibration, thin-lens optics slide09    
    10/04 No lecture for all Tuesday classes at KAIST      
  11 10/06 Stereo matching slide10    
  12 10/11 Multiview geometry slide11    
  13 10/13 3D scanning workflow slide12v2    
    10/18 Mid-term exam      
  14 10/25 Feature detection (Harris corner detector) slide13    
  15 10/27 Feature matching (blob dectection) slide14    
  16 11/01 Feature descriptor (SIFT) slide15    
  17 11/03 Optical flow and tracking slide16    
  18 11/08 Machine learning for computer vision slide17    
  19 11/10 Linear regression and denoising slide18    
  20 11/15 RANSAC, generalization error slide19    
  21 11/17 Classification slide20    
  22 11/22 Clustering, demension reduction slide21    
  23 11/24 Recognition (Bag-of-words) slide22    
  24 11/29 Introduction to neural network slide23  
    12/01 No lecture (KAIST entrance exam)      
    12/06 No lecture (SIGGRAPH Asia 22)      
    12/13 Final exam      


Attendance (10%), mid-term exam (25%), final exam (25%), homework assignments (40%)

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