A basic problem in computer vision is to reconstruct a real world scene given several images of it.

The goal of this course is to provide students with both a good theoretical and intuitive understanding of the intricate relations between multiple views of a scene, and to allow them to use these concepts to compute properties of scene and camera from real world images.  

Course Objectives

1. To understand the geometric relations between multiple views of scenes.
2. To understand the general principles of parameter estimation.
   
3. To be able to compute scene and camera properties from real world images using state-of-the-art algorithms.
   

Target audience
The target audience of this course are graduate students that are doing research in computer vision, computer graphics or image processing and/or are interested in understanding the geometry of multiple views or the possibility to compute geometric scene properties from images.  Note that this course will probably only be organized every two years.

Textbook
This course will heavily rely on the book "Multiple View Geometry in Computer Vision" by Richard Hartley and Andrew Zisserman (will be available at Student Stores).  This book has only recently been published, but has become a classic that can be found on the desk of many researcher in computer vision and related areas.  It covers the recent theoretical advances made in the field of scene reconstruction from images, as well as practical approaches needed to compute geometric properties from real world images.  

Learning approach

• Students should read the relevant chapters of the books and/or reading assignements before the course.  
• In the course the material will then be covered in detail and motivated with real world examples and applications. 
• Small hands-on assignements will be provided to give students a "feel" of the practical aspects.
• Students will also read and present some seminal papers to provide a complementary view on some of the covered topics.
  
• Finally, there will also be a project where students will implement an algorithm or approach using concepts covered by the course.   

Grade distribution

• Class participation: 20%
• Hands-on assignments: 10%
• Paper presentation: 10%
• Implementation assignement: 40%
• Final: 20%

[Schedule and Slides]

Marc Pollefeys, January 16, 2003.