Computer Vision: Algorithms and Applications, 2nd ed.

© 2022 Richard Szeliski, The University of Washington

Welcome to the website (https://szeliski.org/Book) for the second edition of my computer vision textbook, which is now available for purchase at Amazon, Springer, and other booksellers.

To download an electronic version of the book, please fill in your information on this page. You are welcome to download the PDF website for personal use, but not to repost it on any other website; please post a link to this URL instead.

Note that while the content of this electronic version and the hardcopy versions are the same, the page layout is different, since the electronic version is optimized for online reading. The PDF should be enabled for commenting in your viewer. Also, hyper-links to sections, equations, and references are enabled. To get back to where you were, use the Previous View (Alt-Left-Arrow) command in Acrobat.

The current download count is  76445  (since 1/23/2022).

This book is largely based on the computer vision courses that I have co-taught at the University of Washington (2020, 2008, 2005, 2001) with Steve Seitz and Harpreet Sawhney and at Stanford (2003) with David Fleet.

If you're curious about the process that went into writing my book, I did an interview with Computer Vision News (March 2022).

First edition

You can still download the first edition or potentially purchase it online. The first edition is also available in Chinese and Japanese (translated by Prof. Toru Tamaki).

Additional good sources for related courses (sorted roughly by most recent first) include:

• Noah Snavely's CS5670 - Introduction to Computer Vision class at Cornell Tech (Spring 2022)
• Bill Freeman, Antonio Torralba, and Phillip Isola's 6.819/6.869: Advances in Computer Vision class at MIT (Spring 2021)
• Yann LeCun and Alfredo Canziani's DS-GA 1008: Deep Learning class at NYU (Spring 2021)
• Yasutaka Furukawa's CMPT 762 - Computer Vision class at Simon Fraser University (Spring 2021)
• Luiz Velho's Fundamentals and Trends in Vision and Image Processing class at IMPA (Spring 2021)
• David Fouhey's and Justin Johnson's EECS 442: Computer Vision class at the University of Michigan (Winter 2021)
• Justin Johnson's EECS 498-007 / 598-005: Deep Learning for Computer Vision class at the University of Michigan (Fall 2020),
  which is an outstanding introduction to deep learning and visual recognition
• Alyosha Efros' CS194-26/294-26: Intro to Computer Vision and Computational Photography class at Berkeley (Fall 2020)
• Ioannis Gkioulekas's 15-463, 15-663, 15-862 Computational Photography class at CMU (Fall 2020)
• Ioannis Gkioulekas's 16-385 Computer Vision class at CMU (Spring 202-)
• UC Berkeley's CS294-158-SP20: Deep Unsupervised Learning class (Spring 2020)
• Scott Wehrwein's CSCI 497P/597P - Introduction to Computer Vision class at Western Washington University (Spring 2020)
• Andrew Owens' EECS 504: Foundations of Computer Vision class at the University of Michigan (Winter 2020)
• Frank Dellaert's CS 4476 Introduction to Computer Vision class at Georgia Tech (Fall 2019)
• Pascal Fua's CS-442 Introduction to Computer Vision class at EPFL (Spring 2019)
• Alyosha Efros, Jitendra Malik, and Stella Yu's CS280: Computer Vision class at Berkeley (Spring 2018)
• Deva Ramanan's 16-720 Computer Vision class at CMU (Spring 2017)
• Trevor Darrell's CS 280 Computer Vision class at Berkeley
• Antonio Torralba's 6.869 Advances in Computer Vision class at MIT
• Michael Black's CS 143 Introduction to Computer Vision class at Brown
• Kristen Grauman's CS 378 Computer Vision class at UT Austin
• Alyosha Efros' 15-463 Computational Photography and 16-721 Learning-Based Methods in Vision classes at Carnegie Mellon

If you would like your course listed here, please contact me.