Topics will vary from semester to semester. See Computer Science Division announcements.

This course gives a systematic introduction to the geometric principles and computational methods of recovering three-dimensional (3D) scene structure and camera motion from multiple, or a sequence of, two-dimensional (2D) images. The first part of the course provides a complete and unified characterization of all fundamental geometric relationships among multiple 2D images of 3D points, lines, planes, and symmetric structures etc., as well as the associated geometric reconstruction algorithms. Complementary to the geometry, the second part of the course introduces latest development in supervised or unsupervised learning-based methods for detecting and recognizing local features or global geometric structures (e.g. wireframes, planes, regular textures, symmetric objects) in 2D images, for robust and accurate 3D reconstruction. Although principles and methods introduced are fundamental and general, this course emphasizes applications in augmented reality and autonomous 3D mapping and navigation. This course can be viewed as an advanced course in computer vision with a focus on 3D Vision. It can be taken as a follow-up of the Computer Vision course CS 280 or the 3D Image Processing course ECE290 (offered by Zakhor). It is also designed for students who have taken an introductory Robotics course, say EECS 106, and wish to systematically learn about machine vision for purposes such as localization, mapping, and navigation. However, this course is entirely self-contained, nec- essary background knowledge in linear algebra, rigid-body motions, image formation, and camera models will be covered in the very beginning.

* Pre-requisite: CS C280

* Time conflicts are NOT allowed

Repeat Rules