Boston; The SIGGRAPH 2006 Papers Program has opened in Boston, revealing the latest achievements and research innovations in computer graphics and interactive techniques. Of 474 international submissions to this year’s program, 86 papers were accepted for SIGGRAPH 2006, which is taking place now through August 3.
The primary criteria used to determine paper acceptance were the excellence of ideas and expected impact on the field. Among the leading contributors are Columbia University, Microsoft Research, Mitsubishi Electric Research Laboratories, Princeton University, Stanford University, and the University of Washington.
The countries represented by the SIGGRAPH 2006 Papers Program span the globe, and include Austria, Belgium, Canada, China, England, Finland, France, Germany, Hong Kong, Israel, Korea, Scotland, Switzerland, and the United States.
"The Papers Program is a premier forum for disseminating ground-breaking, provocative, and important new work in computer graphics," says Julie Dorsey, SIGGRAPH 2006 Papers Chair from Yale University. "This year's program represents the latest and best work in computer graphics. The program covers a wide range of topics including animation, modeling, rendering, imaging, matting, and image manipulation; capture -- of shape, appearance, and motion -- and synthesis; and physically based simulation of natural phenomena, such as fluids."
Highlights from the SIGGRAPH 2006 Papers Program include:
Removing Camera Shake From a Single Photograph
Camera shake, in which an unsteady camera causes blurry photographs, is a chronic problem for photographers. This paper introduces an algorithm to remove these effects from seriously blurred images.
William Freeman
Rob Fergus
Barun Singh
Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory
Aaron Hertzmann
Sam Roweis
University of Toronto
Photo Tourism: Exploring Photo Collections in 3D
A system for interactively touring and annotating world sites in a 3D explorer by leveraging massive internet photo databases and large personal photo collections to construct browsable scene models.
Noah Snavely
Steven M. Seitz
University of Washington
Richard Szeliski
Microsoft Research
Procedural Modeling of Buildings
A novel shape grammar for the procedural modeling of CG architecture. The results show extensive building models of high geometric detail and visual quality.
Peter Wonka
Arizona State University
Simon Haegler
Pascal Müller
Andreas Ulmer
Luc Van Gool
Eidgenössische Technische Hochschule Zürich
Drag-and-Drop Pasting
Using this method (with a simple outlining of yourself in the source image followed by dragging-and-dropping), you will be seamlessly keyed into desired cinematic scenes.
Jiaya Jia
Chinese University of Hong Kong
Jian Sun
Heung-Yeung Shum
Microsoft Research Asia
Chi-Keung Tang
Hong Kong University of Science and Technology
Image-Based Material Editing
Given only a single high-dynamic-range image as input, this method replaces materials of objects in the image with completely different materials.
Erum Arif Khan
University of Central Florida
Erik Reinhard
University of Bristol
Roland Fleming
Heinrich Bülthoff
Max-Planck-Institut für biologische Kybernetic
Capturing and Animating Skin Deformation in Human Motion
Using a commercial motion capture system and a very large marker set, this technique captures and animates dynamic skin deformation, such as bending, bulging, jiggling, and stretching.
Sang Il Park
Jessica K. Hodgins
Carnegie Mellon University
Real-Time Video Abstraction
An automatic real-time abstraction framework to produce cartoon-like videos. This work is based on several image-processing algorithms that have been modified for parallel implementation, extensibility, and increased temporal coherence.
Holger Winnemöller
Sven Olsen
Bruce Gooch
Northwestern University