Literature and Resources

Book

Computer Vision: Algorithms and Applications, Richard Szeliski In the 2nd edition, especially chapters 2, 11, 12, and 13, available at http://szeliski.org/book

Slides/Courses

• Introduction to Computer Vision, CS5670, Spring 2025, Cornell Tech
  • Authors: (primarily) Noah Snavely and others: Yung-Yu Chuang, Fredo Durand, Alexei Efros, William Freeman, James Hays, Svetlana Lazebnik, Andrej Karpathy, Fei-Fei Li, Srinivasa Narasimhan, Silvio Savarese, Steve Seitz, Richard Szeliski, and Li Zhang.
  • Most slides are copied from this course (2022+2024 versions).

Videos

• Shree Nayar: https://fpcv.cs.columbia.edu/, especially Reconstruction I + II
  • The full series is highly recommended.
• 3Blue1Brown: Linear Algebra and Calculus are useful to review as foundational material.

Additional Links

• YouTube Playlist for the Course This playlist collects all videos shown in class.
• 3Blue1Brown YouTube channel by Grant Sanderson, which explains many mathematical foundations visually. The following playlists and videos are relevant or helpful for this course:
  • Essence of linear algebra
  • Essence of calculus
  • Convolutions in image processing | Week 1 | MIT 18.S191 Fall 2020 | Grant Sanderson
  • What is a Discrete Fourier Transform? | Week 14 | MIT 18.S191 Fall 2020 | Grant Sanderson
  • But what is the Fourier Transform? A visual introduction.
• Math Dictionary, Dietmar Henke lists many math terms in German and English.
• The Computer Vision Foundation Organisation for Computer Vision conferences and publications, check out the YouTube channel as well.
• ACM SIGGRAPH Association for Computing Machinery’s Special Interest Group on Computer Graphics and Interactive Techniques. An organisation for the main Computer Graphics conferences and publications.
• GitHub repository 3DCV SoSe 2023 The GitHub repository for the lecture (SoSe 2023) with demo code.
• GitHub repository BildComp SoSe2022 The GitHub repository for the exercise from the previous semester.
• Skydio 3D Scan State of the art 3D reconstruction with drones. Impressive (marketing) video. Sound on!
• Image Resizing with Seam Carving Link to the video shown in class on Dynamic Programming
• ICP explained without math Video from Computerphile that explains the ICP algorithm with pen and paper. Whole channel is recommendable and has also a good video about kd-trees.
• Graphics in 5 minutes YouTube playlist curated by Steve Seitz (Professor at the University of Washington) that includes 5-minute comic videos explaining computer graphics and vision topics.
  • See https://g5m.cs.washington.edu/ for more details about this project. Especially the three videos about the Splotched Van Gogh are helpful to understand image frequencies.