Towards automated post-production and semantic annotation of films

Film post-production nowadays can be, and most often is, done in the digital domain using computers. There are plenty of tools available for 3D CGI effects, 2D image manipulation of individual frames, color correction and grading, audio-visual synchronization and video editing. Every task, however, still requires a considerable amount of human interaction. In this paper, we will provide an overview of the relevant computer vision technologies which could be used to automate the more time intensive parts of these tasks, provided their performance reaches the high quality standards of the film industry, and semantically annotate the films.