“Image-Based Modeling” by Grzeszczuk, Nishino, Bouguet, Pfister, McMillan, et al. …

  • ©Radek Grzeszczuk, Ko Nishino, Jean-Yves Bouguet, Hanspeter Pfister, Leonard McMillan, and Marc Pollefeys


Entry Number: 44


    Image-Based Modeling

Course Organizer(s):



    Basic knowledge of rendering and illumination, including reflectance models, shading, and texture mapping. Some knowledge of 3D modeling from images is helpful but not required.

    As the complexity of image-based models grows, researchers are facing an increasingly challenging problem of collecting and processing massive amounts of radiance data. Nowadays image-based data sets often consist of tens of thousands of images or hundreds of gigabytes. Clearly, acquisition of these data requires new methodologies. New techniques must also be developed for compact representation and efficient visualization of resulting image-based models. This course is an overview of new technologies for collecting and analyzing densely sampled radiance data and building image-based models that are compact, accurate and easy to render.


    The authors would like to acknowledge the help and advice we received in the conception. implementation and writing of this paper. Thanks to Marc Levoy and Pat Hanrahan for discussions on issues related to the 50 to 40 simplification, the two-plane parameterization and the camera-based aperture analog. Jim Kajiya and Tony DeRose provided a terrific sounding board throughout this project. The ray tracer used for the synthetic fruit bowl was written by John Snyder. The mesh simplification code used for the bunny was written by Hugues Hoppe. Portions of the camera capture code were implemented by Matthew Turk. Jim Blinn, Hugues Hoppe. Andrew Glassner and Jutm Joesch provided excellent editing suggestions. Erynn Ryan is deeply thanked for her creative crisis management. Finally, we wish to thank the anonymous reviewers who pointed us toward a number of significant references we had missed.

Contents/Schedule PDF:

Contributed By:

    Mary Whitton


    Charles Babbage Institute Archives, University of Minnesota