Speaker: Rémi Ronfard, research director, INRIA Rhône-Alpes, Montbonnot, France

Abstract: In 1968, Alfred Hitchcock dreamed of a machine in which he would insert the screenplay at one end and the film would emerge at the other end, completed, and in color. In this talk, I would like to examine how such a machine can be built now, drawing on 50 years of research in computer graphics and animation and recent advances in artificial intelligence and machine learning. I will quickly review research work addressing the different stages of movie-making with highlights on existing machinima and previz tools, interactive storytelling systems, and end-to-end text-to-movie applications. Then I will take a closer look at the three main components of a movie-making machine, leading from script to storyboard to character animation and to film editing. I will present some ongoing work in all three areas. Finally, I will reflect on the respective roles of the user and the machine in future movie-making environments.