RI_Vision Courses Webpage

Courses for Visionaries

Course Number	Course Name	Offerings
16-823	Physics-based methods in Computer Vision		Most recent offer: Spring 2011
16-721/824	Learning-based methods in Computer Vision		Every Spring Most recent offer: Spring 2012
16-822	Geometry-based methods in Computer Vision		Spring 2008
16-899B	Algebraic methods in Computer Vision		(Not offered on regular basis) Most recent offer: Fall 2005
15-869	Human Motion Modeling and Analysis		(Not offered on regular basis) Most recent offer: Fall 2012


16-823 Physics-based methods in Computer Vision



Instructor: Srinivasa Narasimhan
University Units : 12
Semester Offered:
Most recent offer: Spring 2011
Course Description:
Everyday we observe an extraordinary array of light and color phenomena around us, ranging from the dazzling effects of the atmosphere, the complex appearances of surfaces and materials and underwater scenarios. For a long time, artists, scientists and photographers have been fascinated by these effects, and have focused their attention on capturing and understanding these phenomena. In this course, we take a computational approach to modeling and analyzing these phenomena, which we collectively call as "visual appearance". The first half of the course focuses on the physical fundamentals of visual appearance, while the second half of the course focuses on algorithms and applications in a variety of fields such as computer vision, graphics and remote sensing and technologies such as underwater and aerial imaging. This course is an initial attempt to unify concepts usually learnt in physical sciences and their application in imaging sciences. The course will also include a photography competition in addition to analytical and practical assignments.
Prerequisites:
Linear Algebra, Calculus, Undergraduate or Graduate level Vision or Graphics
Topic Covered:
Principles of Photometry Light Fields Reflection, Refraction, Polarization, Diffraction, Interference Surface Reflection Mechanisms Signal Processing framework for Reflection Textures and Spatially Varying BRDFs(BTF) Lighting and Shadows Inter reflections Caustics Scattering and Volumetric Light Transport Fluids Photometric 'Shape-from-X' algorithms Image and Vision-based Rendering Monte Carlo Simulations Appearances of Transparent, Translucent, Wet, Woven surfaces Appearances of Atmospheric and Underwater scattering effects Appearances of Fluids - smoke, fire, water Vision in Bad Weather Applications in Aerial, Underwater, Medical and Microscopic Imaging Principles of Nature Photography

For more information, visit the course homepage:
http://www.cs.cmu.edu/afs/cs/academic/class/16823-f06/

Back to Top


16-721/824: Learning-based methods in Computer Vision



Instructor: Alexei (Alyosha) Efros
University Units : 12
Semester Offered:
Every Spring. Most recent offer: Spring 2006
Course Description:
This course is a graduate seminar devoted to recent research on computer vision. We will be reading an eclectic mix of vision papers on topics such as perception, object and scene recognition, segmentation, tracking, as well as "best papers of all time".
Prerequisites:
Computer Vision (16-720 or equivalent)
Topic Covered:
Low-level Vision (images as texture) Mid-level Vision (Image Segmentation) Part III: 2D Recognition Recognition with Segmentation Machine Translation Approaches Intrinsic Images Manifold Learning

For more information, visit the course homepage:
https://docs.google.com/document/pub?id=1jGBn7zPDEaU33fJwi3YI_usWS-U6gpSSJotV_2gDrL0

Back to Top


16-822 Geometry-based methods in Computer Vision



Instructor: Martial Hebert
University Units : 12
Semester Offered:
Spring 2008
Course Description:
The course focuses on the geometric aspects of computer vision: The geometry of image formation and its use for 3D reconstruction and calibration. The objective of the course is to introduce the formal tools and results that are necessary for developing multi-view reconstruction algorithms. The fundamental tools introduced in the first part of the course are in the standard Euclidean geometry, but, more importantly, in the study of affine and projective geometry, which are essential to the development of image formation models. Additional algebraic tools, such as exterior algebras are also introduced at the beginning of the course. These tools are then used to develop formal models of geometric image formation for a single view (camera model), two views (fundamental matrix), and three views (trifocal tensor); 3D reconstruction from multiple images; and auto-calibration.
Prerequisites:
Computer Vision (16-721 or equivalent)
Book:
The Geometry of Multiple Images. Faugeras and Long, MIT Press.
Topic Covered:
Fundamentals of projective, affine, and Euclidean geometries Invariance and duality Exterior and Grassman algebras Single view geometry: The pinhole model Calibration techniques 2-view geometry: The Fundamental matrix 2-view reconstruction 3-view geometry: The trifocal tensor Parameter estimation and uncertainty n-view reconstruction Self-calibration

Back to Top


16-899B Algebraic Methods in Computer Vision



Instructor: Yanxi Liu
University Units : 12
Semester Offered:
(Not offered on regular basis). Most recent offer: Fall 2005.
Course Description
Group theory, the ultimate theory for symmetry, is a powerful tool that has a direct impact on research in robotics, computer vision, computer graphics and medical image analysis. This course starts by introducing the basics of group theory but abandons the classical definition-theorem-proof model. Instead, it relies heavily on intuitions in (1) 3D Euclidean space, images and patterns; (2) a geometric computational model; and (3) concrete, real world applications in robotics, computer vision, computer graphics and medical image analysis drawing from the instructor��s many years of research experience and from an emerging, vibrant, interdisciplinary international research community. The material will be taught in a bottom-up (problems to theory) style based on the instructor's manuscript of "Group Theory Applications in Robotics, Computer Vision and Computer Graphics", state of art research papers and classical articles in prominent journals/books. The course emphasizes on motivations and justifications for the algorithmic usage of group theory in different domains, computational issues, and hands-on experimentation and illustration. The instructor encourages students to explore new applications while providing a handle on an elegant methodology and available computational tools. This course should be appropriate to any students who have an interest in real world problems that involve 3D Euclidean geometry, regularity, near-regular patterns and symmetry. It should be particularly attractive to students with computational inclinations of using algebraic theory in combination with other tools (e.g. graph theory, statistics). The goal is to provide the course material in a fairly high level of sophistication with intuition, formal justification and algorithmic ease.
Prerequisites:
Basic algebra, transformations, computer vision/image analysis, robotics or approval of the instructor.

For more information, visit the course homepage:
http://www.cs.cmu.edu/~yanxi/www/fall2005.htm

Back to Top


15-869 Human Motion Modeling and Analysis



Instructor: Yaser Sheikh (CMU), Leonid Sigal (Disney Research), Iain Matthews (Disney Research)
University Units : 12
Semester Offered:
(Not offered on regular basis). Most recent offer: Fall 2012.
Course Description
Human motion analysis is used in applications as varied as special effects in movies, animation, sport training, physical rehabilitation for the disabled, and human-robot/human-computer interaction. This course will survey state-of-the-art techniques, in the industry and academia, to capture, model, and analyze human motion. The course will be a mix between lectures and seminar-style paper reading of recent research into human motion modeling and analysis. The course evaluation will be project-based, in which students will capture their own body and face motion, and build projects around the data they collect individually and as a group.
Prerequisites:
Linear algebra, statistical methods, and a programming course.
Topic Covered:
Capture Techniques: We will describe and use various systems including motion capture, video-based capture, depth sensors, scanners, and eye-gaze trackers. Modeling and Representation: We will cover classic and contemporary representations of face and body pose and motion, including statistical and physics-based techniques. Applications: As human motion analysis becomes increasingly mature, new applications are emerging. We will study recent progress in animation, synthesis, classification, and rehabilitation.

For more information, visit the course homepage:
http://www.cs.cmu.edu/~yaser/Fall2012_15869.html

Back to Top

School of computer science | Carnegie Mellon University