2011 | OriginalPaper | Chapter
The Application of Vision Algorithms to Visual Effects Production
Author : Sebastian Sylwan
Published in: Computer Vision – ACCV 2010
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Visual Effects Production, despite being fundamentally an artistic endeavor, is a very technically oriented business. Like many other businesses in their early ages, it still requires constant innovation and in many cases a great amount of craftsmanship. Given these premises, most VFX companies (especially those at the leading edge) are hungry for novel and better solutions to the problems they encounter everyday. Many published machine vision algorithms are designed to be real-time and fully automatic with low computational complexity. These attributes are essential for applications such as robotic vision, but in most cases overkill or ill-conditioned for Motion Picture Digital Visual Effects facilities, where massive computation resources are commonplace and expert human interaction is available to initialise algorithms and to guide them towards an optimal solution. Conversely, motion pictures have significantly higher accuracy requirements and other unique challenges. Not all machine vision algorithms can readily be adapted to this environment. This talk outlines the requirements of visual effects and indicate several challenges and possible solutions involved in adopting image processing and machine vision algorithms for motion picture visual effects.