Modeling and Rendering Architecture from Photographs

Paul E. Debevec, Ph.D. Thesis, UC Berkeley, 1996

Thesis committee: Professors John Canny, Jitendra Malik, and David Wessel

Abstract

This thesis presents an approach for modeling and rendering existing architectural scenes from sparse sets of still photographs. The modeling approach, which combines both geometry-based and image-based techniques, has two components. The first component is an interactive photogrammetric modeling method which facilitates the recovery of the basic geometry of the photographed scene. The photogrammetric modeling approach is effective, convenient, and robust because it exploits the constraints that are characteristic of architectural scenes. The second component is a model-based stereo algorithm, which recovers how the real scene deviates from the basic model. By making use of the model, this new technique robustly recovers accurate depth from widely-spaced image pairs. Consequently, this approach can model large architectural environments with far fewer photographs than current image-based modeling approaches. For producing renderings, this thesis presents view-dependent texture mapping, a method of compositing multiple views of a scene that better simulates geometric detail on basic models.

This approach can be used to recover models for use in either geometry-based or image-based rendering systems. This work presents results that demonstrate the approach's ability to create realistic renderings of architectural scenes from viewpoints far from the original photographs. This thesis concludes with a presentation of how these modeling and rendering techniques were used to create the interactive art installation Rouen Revisited, presented at the SIGGRAPH '96 art show.

Complete thesis	debevec-phdthesis-1996.pdf Adobe Acrobat PDF, 154 pages, 5.6 MB
Frontmatter, Contents, Introduction, Related Work, and Overview (Chapters 1-3)	debevec-phdthesis-1996_ch1-3_intro.pdf Adobe Acrobat PDF, 38 pages, 1.0 MB
Chapter 4: Camera Calibration	debevec-phdthesis-1996_ch4_calib.pdf Adobe Acrobat PDF, 17 pages, 273 KB
Chapter 5: Photogrammetric Modeling	debevec-phdthesis-1996_ch5_facade.pdf Adobe Acrobat PDF, 39 pages, 1.7 MB
Chapter 6: View-Dependent Texture Mapping	debevec-phdthesis-1996_ch6_vdtm.pdf Adobe Acrobat PDF, 15 pages, 539 KB
Chapter 7: Model-Based Stereo	debevec-phdthesis-1996_ch7_stereo.pdf Adobe Acrobat PDF, 9 pages, 194 KB
Chapter 8: Rouen Revisited	debevec-phdthesis-1996_ch8_rouen.pdf Adobe Acrobat PDF, 27 pages, 1.8 MB
Bibliography and end notes	debevec-phdthesis-1996_end.pdf Adobe Acrobat PDF, 9 pages, 25 KB

Click here to download the free Adobe Acrobat Reader

Complete Cross-linked Table of Contents (html)

BibTeX Entry

@phdthesis{DebevecPhd1996,
    AUTHOR  = {Paul E. Debevec},
    TITLE   = {Modeling and Rendering Architecture from Photographs},
    SCHOOL  = {University of California at Berkeley},
    ADDRESS = {Computer Science Division, Berkeley CA}
    YEAR    = {1996},
}

Related Publications:

Paul E. Debevec, Camillo J. Taylor, and Jitendra Malik. Modeling and Rendering Architecture from Photographs. In SIGGRAPH '96, August 1996.
George Borshukov. New Algorithms for Modeling and Rendering Architecture from Photographs. Master's Thesis, University of California at Berkeley, May 1997.
Paul E. Debevec, George Borshukov, and Yizhou Yu. Efficient View-Dependent Image-Based Rendering with Projective Texture-Mapping. In 9th Eurographics Rendering Workshop, Vienna, Austria, June 1998

Photos:

There are a few photos from the final night/day of writing the thesis: writing in EMACS on the Indigo2, general state of my desk, finished packets with Jitendra Malik.

Related Projects:

Successive Work:

Paul E. Debevec / debevec@cs.berkeley.edu