Image-Based Modeling, Rendering, and Lighting Image-based modeling and rendering differs from traditional graphics in that both the geometry and appearance of the scene are derived from real photographs. The techniques often allow for shorter modeling times, faster rendering speeds, and unprecedented levels of photorealism. This course explained and demonstrated a variety of ways of turning images into models and then back into renderings, including movie maps, panoramas, image warping, photogrammetry, light fields, and 3D scanning.   Topics included: computer vision and how it relates to image-based rendering techniques, and how to apply the techniques to animation and 3D navigation. The course also showed how global illumination techniques allow photorealistic modifications of image-based models and illustrates results from recent research and creative applications.   Organizer Paul Debevec University of California, Berkeley   Lecturers Christoph Bregler Stanford University   Michael F. Cohen Richard Szeliski Microsoft Research   Paul Debevec University of California, Berkeley   Leonard McMillan Massachusetts Institute of Technology   François X. Sillion French National Institute for Computer Science and Control