Workshop Report 08w5070 Multi-View and Geometry Processing for 3D Cinematography

By 3D cinematography we refer to techniques to generate 3D models of dynamic scenes from multiple cameras at video frame rates. Recent developments in computer vision and computer graphics, especially in such areas as multiple-view geometry and image-based rendering have made 3D cinematography possible. Important applications areas include production of stereoscopic movies, full 3D animation from multiple videos, special effects for more traditional movies, and broadcasting of multiple-viewpoint television, among others. The aim of this workshop was to bring together scientists and practitioner who have contributed to the mathematical foundations of the field, as well as those who have developed working systems. There were 20 participants from Canada, the United States, Europe and Asia. A total of 20 talks of length 30 minutes were presented during the five-day workshop. A book comprising extended versions of these presentations is currently under production, and will be published by Springer-Verlag in 2010 [3]. 1 Overview of the Field The name 3D cinematography is motivated by the fact that it extends traditional cinematography from 2D (images) to 3D (solid objects that we can render with photorealistic textures from arbitrary viewpoints) at the same frame rate. A first workshop on 3D Cinematography took place in New York City in June 200