The SIGGRAPH 2007 Papers Program features the year's best research innovations in computer graphics and interactive techniques. Of 455 international submissions, a record-breaking 108 of the world's most prestigious papers will be presented at SIGGRAPH 2007 taking place Aug. 5-9 in San Diego, California.

Excellence of ideas and expected impact on the field were the primary acceptance criteria. Paper topics include the core areas of modeling, animation, rendering, and imaging, and also touch on related areas such as visualization, computer vision, human-computer interaction, and applications of computer graphics. Countries represented span the globe from Germany to Japan.

"The SIGGRAPH Papers review process, with its unique blend of internal and external reviewers, its long and detailed reviews, and its large face-to-face committee meeting, is recognized as being one of the fairest and most thorough peer review systems in computer science," stated Marc Levoy, SIGGRAPH 2007 Papers chair from Stanford University.

To promote a lively exchange of ideas during the program, Levoy introduced a system of per-paper discussants. Each paper in the program will be allotted 25 minutes, 20 minutes for presentation and five minutes for discussion of the paper, with the session chair serving as discussant.

Select highlights from the SIGGRAPH 2007 Papers Program:

* Image Deblurring With Blurred/Noisy Image Pairs
A novel method to deblur an image, with the help of another noisy image of the same scene. The paper also proposes new methods of de-ringing the deconvoluted image.

Long Quan
Lu Yuan
The Hong Kong University of Science and Technology

Heung-Yeung Shum
Jian Sun
Microsoft Research Asia

* Scene Completion Using Millions of Photographs
A method for filling holes in images using semantically and structurally similar scenes from a large Internet photo library.

Alexei A. Efros
James Hays
Carnegie Mellon University

* Active Refocusing of Images and Videos
A system for refocusing images and videos of dynamic scenes using a single-view depth estimation method. This method is based on the defocus of a sparse set of projected dots.

Francesc Moreno-Noguer
CVLAB, Ecole Polytechnique Fédérale de Lausanne

Peter N. Belhumeur
Shree K. Nayar
Columbia University

* Interactive Cutaway Illustrations of Complex 3D Models
A system for authoring and viewing interactive cutaway illustrations of complex 3D models using conventions of traditional scientific and technical illustration.

Brian Curless
Wilmot Li
Lincoln Ritter
David Salesin
University of Washington

Maneesh Agrawala
University of California, Berkeley

* Prakash: Lighting-Aware Motion Capture Using Photosensing Markers and Multiplexed Illuminators
A high-speed optical motion capture system also measures orientation and incident illumination via photosensing tags. Imperceptible tags work in natural lighting, to support on-set MoCap or realtime broadcast of virtual sets.

Philippe Bekaert
Bert de Decker
Universiteit Hasselt

Masahiko Inami
University of Electrocommunications

Shree Nayar
Columbia University

John Barnwell
Vlad Branzoi
Erich Bruns
Paul Dietz
Yuki Hashimoto
Dylan Moore
Hideaki Nii
Michael Noland
Ramesh Raskar
Jay Summet
Jonathan Westhues
Yong Zhao
Mitsubishi Electric Research Laboratories (MERL)

* Bubbling and Frothing Liquids
A method to generate bubbles from gas contained in liquids and simulate their dynamic behavior using a particle-based fluid simulation technique.

Mahesh Prakash
Paul Cleary
Commonwealth Scientific and Industrial Research Organisation

Bon Ki Koo
Soon Hyoung Pyo
Electronics and Telecommunications Research Institute