papers, illustrated with examples. They include wavelet bases, implicit functions de ned on a space grid, etc. It appears that a common pattern is the recovery of a controllable model of the scene, such that the resulting images can be edited (interaction). Changing the viewpoint is only one (important) aspect, but changing the lighting and action is equally important [2]. Recording and representing three-dimensional scenes is an emerging technology made possible by the convergence of optics, geometry and computer science, with many applications in the movie industry, and more generally in entertainment. Note that the invention of cinema (camera and projector) was also primarily a scienti c invention that evolved into an art form. We suspect the same thing will probably happen with 3-D movies. 3 Book Contents The book is composed of 12 chapters, which elaborate on the content of talks given at the BANFF workshop. The chapters are organized into three sections. The rst section presents an overview of the inter-relations between the art of cinemat- raphy and the science of image and geometry processing; the second section is devoted to recent developments in geometry; and the third section is devoted to recent developmentsin image processing. 3.1 3-D Cinematography and Applications The rst section of the book presents an overview of the inter-relations between the art of cinematography and the science of image and geometry processing. Image and geometry processing for 3-D cinematography : an introduction -- Rémi Ronfard and Gabriel Taubin Stereoscopic cinema -- Frédéric Devernay and Paul Beardsley Free-viewpoint television -- Masayuki Tanimoto Free-viewpoint video for TV sport production -- Adrian Hilton, Jean-Yves Guillemaut, Joe Kilner, Oliver Grau, and Graham Thomas Challenges for multi-view video capture -- Bennett Wilburn Performance capture from multi-view video -- Christian Theobalt, Edilson de Aguiar, Carsten Stoll, Hans-Peter Seidel, and Sebastian Thrun Combining multi-view stereo and bundle adjustment for accurate camera calibration -- Yasutaka Furukawa and Jean Ponce Cell-based 3D video capture method with active cameras -- Tatsuhisa Yamaguchi, Hiromasa Yoshimoto, and Takashi Matsuyama Dense 3D motion capture from synchronized video streams -- Yasutaka Furukawa and Jean Ponce Wavelet-based inverse light and reflectance from images of a known object -- Dana Cobzas, Cameron Upright, and Martin Jagersand 3-D lighting environment estimation with shading and shadows -- Takeshi Takai, Susumu Iino, Atsuto Maki, and Takashi Matsuyama 3-D cinematography with approximate or no geometry -- Martin Eisemann, Timo Stich, and Marcus Magnor View dependent texturing using a linear basis -- Martin Jagersand, Neil Birkbeck, and Dana Cobzas. The book presents an overview of 3-D cinematography, the science and technology of generating 3-D models of dynamic scenes from multiple cameras at video frame rates. The book covers recent developments in computer vision and computer graphics that have made 3-D cinematography possible, and reviews the challenges and open issues that need to be addressed in future work. Important applications areas are presented, including production of stereoscopic movies, full 3-D animation from multiple videos, special effects for more traditional movies, and broadcasting of multiple-viewpoint television. The book brings together researchers and practitioners from computer graphics, computer vision, broadcasting and motion pictures, to offer a broad perspective on all current areas of research related to the production of high quality 3-D models of live-action scenes Image and Geometry Processing for 3-D Cinematography 4 Acknowledgements 8 Contents 10 Image and Geometry Processing for 3-D Cinematography: An Introduction 12 Part I 3-D Cinematography and Applications 20 Part II Recent Developments in Geometry 133 Part III Recent Developments in Image Processing 216
