Budapest University of Technology and Economics, Faculty of Electrical Engineering and Informatics

    Belépés
    címtáras azonosítással

    vissza a tantárgylistához   nyomtatható verzió    

    Computer Vision for Digital Film Post-Production

    A tantárgy neve magyarul / Name of the subject in Hungarian: Filmek digitális utómunkálatai

    Last updated: 2010. november 12.

    Tantárgy lejárati dátuma: 2014. július 31.

    Budapest University of Technology and Economics
    Faculty of Electrical Engineering and Informatics

    Mérnök informatikus szak

    BSc képzés

    Course ID Semester Assessment Credit Tantárgyfélév
    VISZA092   0/0/2/f 2  
    3. Course coordinator and department Dr. Wiener Gábor,
    4. Instructors
    Name

     

    Position

     

    Department

     

    Gergely VASS

     

    Lecturer

     

    Department of Computer Science and Information Theory

     

    Gábor WIENER

     

    Assoc. professor

     

    Department of Computer Science and Information Theory

     

    5. Required knowledge A knowledge of linear algebra foundations and programming experience (in any language such as C, C++, objective C, Java, Pascal) are required.

     

     

    In addition students should have a passion for movies and science.

     

    7. Objectives, learning outcomes and obtained knowledge The primary aim of the course is to educate and inspire at the same time. By understanding how essential mathematical techniques – such as solving a set of linear equations – are utilized in the high-end filmmaking process, one soon develops a new appreciation for software research and development. The “true”, practical value of mathematics and computer science introduced in this and other courses is revealed through numerous exciting examples from real projects and innovative software solutions.

     

     

    The core academic material is not only relevant to computer vision but to other computer science problems as well. Learning about the application of linear algebra and concepts such as parameter estimation from an industry expert provides students with a versatile understanding of these academic subjects. 

     

    8. Synopsis The first studio visit will be a guided tour in the Colorfront facilities, hosted by Márk Jászberényi, founder of the company. Students will see the most advanced digital projection rooms with advanced color grading equipment, film scanners, sound mixing boards and high-end visual effects suites, to name a few things. Not only the full digital post-production pipeline will be introduced, but also the adventurous story of developing the first software color corrector for which the team recently won the Oscar award for Scientific and Technical Achievement. 

     

     

    The academic material begins with image processing basics. The computational costs, advantages and limitations, and application of different classes of image filters will be discussed. Students will learn how to smooth and sharpen images, and how to compute the image gradients. Based on these rather simple algorithms robust feature detectors can be built, that identify interest points in images. Most high-level computer vision tools are based on these interest points, which encode all necessary information from the original image. 

     

     

    One class session is dedicated to an overview of linear algebra foundations from a software developer’s point of view: a “practical guide” to analyzing and solving large sets of linear equations. The majority of parameter estimation problems in computer vision are based on such linear constructions. Examples include aligning multiple overlapping photographs to form a single panoramic image, or tracking a moving object in a sequence of frames. Both are essential techniques in digital film post-production, and will be examined in class. 

     

     

    Object and class recognition is a very challenging problem. Understanding the various approaches also helps students get familiar with general concepts such as distance metrics, principal component analysis and linear subspaces. By focusing on real problems and their solutions – instead of the often overwhelming theory – students will grasp the power of such mathematical tools. 

     

     

    The most complex computer vision problem in film post-production is camera tracking, or matchmoving: the process of matching the motion of a virtual camera to the real camera used to capture the image sequence. This allows artists to seamlessly insert computer graphics into live-action footage with correct position, scale and orientation. While this very complex problem may seem unique to computer vision, the challenges are common in computer science and it is worth looking at the innovative solutions used in the field. 

     

    The last studio visit focuses on the application of the theory presented throughout the course. The lead visual effect artist recreates some stunning “invisible” effects from real projects and explains step-by-step how to manipulate shots of a movie using computer vision-based tools.  

     

    9. Method of instruction The course is lecture-oriented with assigned readings and team-oriented programming and image manipulation projects as homework. There will be two visits to the Colorfront studio, one at the beginning and one at the end of the course.

     

    10. Assessment Students will be evaluated based on assigned homework and final written exam.

     

    13. References, textbooks and resources Richard Hartley, Andrew Zisserman: Multiple View Geometry in Computer Vision, Cambridge Univ. Press, 2003. 

     

    Richard Szeliski: Computer Vision: Algorithms and Applications, Springer, 2010.
    http://research.microsoft.com/en-us/um/people/szeliski/Book/

     

     

    14. Required learning hours and assignment
    Number of contact hours

     

    28

     

    Preparation to the classes

     

    -

     

    Preparation to the tests

     

    -

     

    Homework

     

    10

     

    Assigned reading

     

    12

     

    Preparation to the exam

     

    10

     

    Total

     

    60

     

    15. Syllabus prepared by
    Name

     

    Position

     

    Department

     

    Gergely VASS

     

    Lecturer

     

    Department of Computer Science and Information Theory