• All materials can be found here
  • usr: CV
  • pwd: sose24

• Use the keys left/right for navigating through the slides.
• Click icon (top left) to open the navigation menu.
• Press f/ESC to enter/leave fullscreen mode.
• Double-click an item (e.g. an image) to zoom in/out.
• If the bottom boundary flashes on slide change, something was written on the virtual whiteboard.
  • Scroll down to see it.

• SWS 2V + 2Ü, 6 ECTS, Total Workload: 180h
• Lecture (14)
  • Friday, 10:00-11:30, D17/18
  • Apr. 19/26, May 03/10/17/24/31, June 07/14/21/28, July 05/12/19
    
• Exercise Sessions
  • Friday, 11:45-13:15, D17/18. Submission each Thursday until 16:00 via read.MI
  • Exercises are mandatory
• Exam
  • Content: lectures and exercises
  • Very likely oral (date and time will be announced)

• Books
  • R. Szeliski, Computer Vision: Algorithms and Applications, Springer 2011
    https://szeliski.org/Book
  • I. Gooldfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press 2016
    https://www.deeplearningbook.org
  • J. E. Solem, Programming Computer Vision with Python, O’Reilly 2012
  • V. K. Ayyadevara, Y. Reddy, Modern Computer Vision with PyTorch, Packt 2020
  • M. P. Deisenroth, A. A. Faisal, C. S. Ong, Mathematics for Machine Learning
    https://mml-book.github.io
  • K. B. Petersen, M. S. Pedersen, The Matrix Cookbook
    http://www.cs.toronto.edu/~bonner/courses/2012s/csc338/matrix_cookbook.pdf

• Tutorials
  • The Python Tutorial: https://docs.python.org/3/tutorial
  • Numpy Quickstart: https://numpy.org/devdocs/user/quickstart.html
  • PyTorch Tutorial: https://pytorch.org/tutorials
• Frameworks, IDEs
  • Visual Studio Code: https://code.visualstudio.com/
  • Google Colab: https://colab.research.google.com
• Courses
  • Slide deck covering Szeliski’s book https://szeliski.org/Book
    
  • I. Gkioulekas, Computer Vision https://www.cs.cmu.edu/~16385/
  • A. Owens, Foundations of Computer Vision https://web.eecs.umich.edu/~ahowens/eecs504/w20/

• Basic math skills
  • Linear Algebra, Calculus, Probability
• Basis computer science skills
  • Variables, functions, loops, classes, algoritms
• Basic Python coding skills
  • https://docs.python.org/3/turorial/
• Basic PyTorch coding skills
  • https://pytorch.org/turorials

• Goal of Computer Vision is to convert light into meaning (geometric, semantic, …)

• Human Vision is the process of discovering what is present in the world and where it is by looking

• Over 50% of the processing in the human brain is dedicated to visual information

• Computer Vision is the study of analyzing images to achieve results similar to those as by humans

“An attempt will be made to find how to make machines use language, form abstractions and concepts, solve kinds of problems now reserved for humans, and improve themselves”

• Computer Vision seeks to achieve full scene understanding (in contrast to (classical) Image Processing)

• ImageNet https://www.image-net.org/

• Image are 2D Projections of the 3D World
  • Many 3D scenes yield the same 2D image
  • Additional constraints (knowledge about world) are required

Adelson and Pentland’s workshop metaphor:

• To explain an image (a) in terms of reflectance, lighting and shape, a painter (b), a light designer (c) and a sculptor (d) will design three different, but plausible, solutions.

Perspective Illusion:

Perspective Illusion (Ames Room)

• Primitives
  • Points, Lines and Planes
  • Homogeneous Coordinates
• Transformations
  • 2D / 3D Transformations
  • Homography Estimation
• Geometric Image Formation
  • Pinhole Camera
  • Projection Models
  • Lens Distortion