Structure Fom Motion (


This is an advanced course on graduate computer vision and computational photography. This course will explore image formation, image features, image segmentation, image stitching, image recognition, motion estimation, 3D point clouds and will touch upon basics of augmented reality.

For further information, please see the course syllabus.

General Information

Class Time Tuesdays & Thursdays 12:30PM - 1:45PM
LocationCSI 2118  
Instructor Yiannis Aloimonos
Office AVW 4475
Office Hours By Appointment
Yiannis Aloimonos
Teaching Assistants
Name Nitin J. Sanket
Office AVW 4103
Office Hours TBA
Nitin J. Sanket

If you cannot make it to any of the above office hours due to some commitment, please do e-mail us and fix up an appointment so that we can help you.


Important class announcements will be made through the Piazza system. The class piazza can be found here.


Special thanks to Dr. Cornelia Fermüller for providing most of the lecture materials for this class.

A lot of projects in this course are based on graduate and doctoral courses from other universities. Links to these courses can be found in the Logistics section under the title Other Good Computer Vision Courses and Tutorials.

The course website is based on Prof. David Mount's website for CMSC 754: Computational Geometry found here. We loved the simplicity and lightness of his website design.

Server Login

The server login procedure can be found here.

Some Useful Resources

The links to e-books of the reference books if available are given in the Logistics section under the title Reference Books.

Online resource of computer vision topics (contains short descriptions and tutorials on basic and advanced topics)

Image Processing Learning resources

Image Processing Online Journal. Contains many good algorithms with implementations for free.

MATLAB Speed Up Tricks

Image Filtering Tutorial

Peter Kovesi's awesome computer vision and image processing functions for MATLAB. Literally has everything you need.

VLFeat for MATLAB. Has a lot of new algorithms and supports all platforms.

Peter Corke's Machine Vision Toolbox for MATLAB. Has a lot of new algorithms and supports all platforms.

Some slides for using MATLAB in Image Processing from ETH Zurich

MATLAB tutorial from University of Toronto

  Return to CMSC 733 Home  —  The cool image at top of page is from the Structure From Motion by Princeton University's Vision and Robotics Group