Papers: Markus Gross
Dr. Markus Gross is the SIGGRAPH 2005 Paper Chair. Dr. Gross is a professor of computer science and director of the Computer Graphics Laboratory of the Swiss Federal Institute of Technology (ETH) in Zürich. He received a Master of Science in electrical and computer engineering and a PhD in computer graphics and image analysis, both from the University of Saarbrucken, Germany. From 1990 to 1994, Dr. Gross worked for the Computer Graphics Center in Darmstadt, where he established and directed the Visual Computing Group. His research interests include point-based graphics, physics-based modeling, multiresolution analysis, and virtual reality. He has been widely publishing and lecturing on computer graphics and scientific visualization, and he authored the book "Visual Computing", Springer, 1994. Dr. Gross has taught courses at major graphics conferences including ACM SIGGRAPH, IEEE Visualization, and Eurographics. He is the associate editor of the IEEE Computer Graphics and Applications and has served as a member of international program committees of many graphics conferences. Dr. Gross has been a papers co-chair of the IEEE Visualization '99, the Eurographics 2000, and the IEEE Visualization 2002 conferences. He is a senior member of IEEE, a member of the IEEE Computer Society, a member of ACM and ACM SIGGRAPH, and a member of the Eurographics Association. He is on the advisory boards of various international research institutes and governmental agencies, and is also co-founder of Cyfex AG and Novodex AG.
You have served on the Paper Committee since 2002. This year you have the honor of being the chair. What sort of vision did you have in mind for this year's program?
My first year as a committee member was 1999 and I have served four times before accepting the role as a papers chair. Also, I have chaired other conferences, such as IEEE Visualization (2 times) and Eurographics, before. This prior service gave me some of the expertise needed to run the SIGGRAPH Papers program.
The SIGGRAPH papers track continues to define excellence in research in our discipline. It serves as the world's premier forum for innovation and creativity in graphics. Keeping this high standard is vital for the progress of graphics and, hence, my first and foremost goal.
My specific goals have been:
- To maintain SIGGRAPH's status as the premier venue for presenting new research in computer graphics.
- To continue to motivate researchers to submit their top results to the SIGGRAPH Papers program
- To put emphasis on systems and the fusion of 3D graphics and video
- To deal with the increasing influx of papers while preserving the quality of the decision making process by the jury
- To adapt and further develop the electronic submission process
- To refine the rebuttal process, to stimulate discussions between the committee members before the meeting, and to make the jury meeting more efficient
Computer graphics and interactive techniques is a relatively young field. Each year at SIGGRAPH there are some extraordinary research papers. From all the submissions you received, did any of them catch you off guard or surprise you?
Regarding content, we can clearly spot a number of trends:
The first one is that graphics researchers are doing more and more to bring reality into the computer. Complex lighting and shading models have now become "data-driven"; that is, they are based on samples from the real world. This makes it possible to alter and simulate the appearance of human faces photorealistically. To this end, novel camera and acquisition devices have been created.
A second trend is the increasingly sophisticated simulation of physics. Various papers deal with simulation of the complex interaction of media, such as liquids, smoke, or gas, and solid materials. Also, researchers have started to question the utility of triangle meshes for simulations and have proposed point-sampled models instead. Finally, various innovations make physics simulations interactive and real time on personal computers. This is very important for the development of more realistic games and will be supported by novel hardware architectures and processing units to be released by the industry very soon. In particular, novel chip generations and physics processing units will accelerate computations in computer games.
A third trend points toward advanced picture and video processing. We will see a variety of methods for panoramic stitching of videos, for making pictures three-dimensional, and for intelligent and user-friendly editing of video. Such methods might soon become tools people will utilize to edit their latest home videos.
A Few Highlights From the SIGGRAPH 2005 Papers Program:
Capturing reality deals with novel methods to bring reality into the computer by acquiring complex shape and appearance information from real world objects. This allows for unprecedented realism and novel effects in visual simulation.
Performance Relighting and Reflectance Transformation With Time-Multiplexed Illumination, Andreas Wenger, Andrew Gardner, Chris Tchou, Jonas Unger, Tim Hawkins, Paul Debevec (University of Southern California, Institute for Creative Technologies)
SCAPE: Shape Completion and Animation of People, Dragomir Anguelov, Praveen Srinivasan, Daphne Koller, Sebastian Thrun, Jim Rodgers (Stanford University), James Davis (University of California, Santa Cruz)
High-Performance Imaging Using Large Camera Arrays, Bennett Wilburn (Stanford University), Neel Joshi (University of California, San Diego), Vaibhav Vaish, Eino-Ville Talvala, Emilio Antunez, Adam Barth, Andrew Adams, Mark Horowitz, Marc Levoy (Stanford University)
The following deal with physically based simulations of the complex interaction of media, such as liquids, smoke, and solids. They permit the simulation of novel and even more stunning visual effects and might become tools to enhance the visual experience in the next generation computer games.
A Vortex Particle Method for Smoke, Water, and Explosions, Andrew Selle (Stanford University and Intel Corporation), Nick Rasmussen (Industrial Light & Magic), Ronald Fedkiw (Stanford University and Industrial Light & Magic)
Discontinuous Fluids, Jeong-Mo Hong, Chang-Hun Kim (Korea University)
Water Drops on Surfaces, Huamin Wang, Peter J. Mucha, Greg Turk (Georgia Institute of Technology)
Meshless Deformations Based on Shape Matching, Matthias Müller, Bruno Heidelberger (NovodeX/Eidgenössische Technische Hochschule Zürich), Matthias Teschner (Universität Freiburg), Markus Gross (Eidgenössische Technische Hochschule Zürich)
This year, we experience a renaissance of ray-tracing algorithms and architectures. Such prototypes encourage designers of graphics hardware to rethink the way they define the graphics pipeline.
Soft Shadow Volumes for Ray Tracing, Samuli Laine (Helsinki University of Technology), Timo Aila (Helsinki University of Technology and Hybrid Graphics Ltd.), Ulf Assarsson (ARTIS, INRIA and Illuminate Labs Ltd.), Jaakko Lehtinen (Helsinki University of Technology and Remedy Entertainment Ltd.), Tomas Akenine-Möller (Lunds Universitet)
RPU: A Programmable Ray Processing Unit for Realtime Ray Tracing, Sven Woop, Jörg Schmittler, Philipp Slusallek (Universität des Saarlandes)
We will see advanced methods for panoramic stitching of videos, for making pictures three-dimensional, and for intelligent and user-friendly editing of video. Such methods might soon become tools people will utilize to edit their latest home videos.
TextureMontage: Seamless Texturing of Arbitrary Surfaces From Multiple Images, Kun Zhou, Xi Wang (Microsoft Research Asia), Yiying Tong, Mathieu Desbrun (California Institute of Technology), Baining Guo, Heung-Yeung Shum (Microsoft Research Asia)
Defocus Video Matting, Morgan McGuire (Brown University), Wojciech Matusik, Hanspeter Pfister (Mitsubishi Electric Research Laboratories (MERL)), John F. Hughes (Brown University), Frédo Durand (Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory)
Automatic Photo Pop-Up, Derek Hoiem, Alexei Efros, Martial Hebert (Carnegie Mellon University)
Panoramic Video Textures, Aseem Agarwala, Ke Colin Zheng (University of Washington), Chris Pal (University of Massachusetts Amherst), Maneesh Agrawala, Michael F. Cohen, (Microsoft Research), Brian Curless (University of Washington), David H. Salesin (University of Washington & Microsoft Research), Richard Szeliski (Microsoft Research)
Novel fundamental insights are also a facet of many of these sessions, in particular the following contribution provides an in-depth analysis.
A Frequency Analysis of Light Transport, Frédo Durand, (Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory), Nicolas Holzschuch, Cyril Soler (ARTIS, GRAVIR/IMAG - INRIA), Eric Chan, (Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory), François X. Sillion (ARTIS, GRAVIR/IMAG - INRIA)
Being the Paper Chair must mean masterminding the entire reviewing process. How many submissions did you receive this year and how quickly did you need to review them?
A total of 461 submissions were received by the deadline (January 26) and 98 papers were selected for presentation at SIGGRAPH.
The selection procedure was complex and followed rigorous rules. The actual selections were made by a committee of approximately 50 of the finest senior researchers covering all areas of computer graphics. After the submission deadline, the Papers Chair and the Papers Advisory Board-a group of three very senior peers-assigned each Paper to two committee members: a so-called primary reviewer and a so-called secondary reviewer. The primary and secondary reviewers solicited at least three additional blind tertiary reviews from top international experts in their respective subfields. This amounted to more than 2200 tertiary reviews conducted within approximately six weeks.
Once these reviews were in, the authors went through an extensive process to rebut possible factual errors, clarify issues, and make revisions. In cases of further doubt, additional Papers committee members were asked for their opinions.
The final and most important stage of the selection procedure was the committee meeting (this year's meeting was held at MIT in Cambridge, Mass. from March 31 to April 3). There, all submissions were discussed at length and a final decision was made on each paper. This very intense process took a few days to complete.
After the final selection, papers were conditionally accepted subject to changes required by the committee. Authors had to revise their submissions, resubmit, and get final approval for publication. This last step guarantees maximum quality of the conference proceedings.
Jim Kajiya's `How to Get Your SIGGRAPH Paper Rejected <http://www.siggraph.org/publications/instructions/rejected.html>`_, was published in 1993. Is the advice in that article still pertinent? What would your article on getting your SIGGRAPH paper accepted recommend?
This is, in fact, a key question I get from many young SIGGRAPH authors.
Kajiya's article, while 12 years old now, still captures the very essence of the SIGGRAPH Papers program selection process and is therefore a very valuable source of wisdom for every novice SIGGRAPH author. I would definitely recommend every young scientist in our field to read it.
For one thing, this selection process has been established and optimized over many years and, as such, is pretty stable. Papers chairs typically do some fine-tuning from one year to the next, but usually do not introduce dramatic changes.
While the essence of the article is kind of timeless and clearly still valid, some of the constraints have changed.
For instance, the submission number in 2005 is almost 2.5 times higher than in 1993. Preserving the quality of the selection has been a major challenge and has required some modifications of the procedure.
For instance, thanks to the rebuttal process, the selection has been somewhat less of a black-box for the authors and there is interaction between the committee members and the authors before the actual meeting. In particular, factual errors due to misunderstandings can now be corrected.
Also, the senior reviewers of a paper are encouraged to confer about the paper before the Papers Committee meeting. As such, the so-called "triage" already starts right after the rebuttal.
Finally, the newly introduced shepherding process and "conditionally accept" status after the selection meeting allow for minor revisions of the paper. This makes it possible to accept outstanding innovative ideas presented in less than perfect initial submissions.
It is the tradition of the SIGGRAPH Papers program that technical excellence and innovation are the first and foremost selection criteria. We pick the submissions with the most exciting and most creative novel methods, the ones that stimulate future work by others, and the ones that constitute a tangible improvement over the state of the art. Equally important are technical soundness and a proof of concept. The authors have to provide a technically sound description of their innovation, and they have to clearly demonstrate-by comparison and analysis-that their methods work properly and are useful.
Chairing the Paper Committee must have been a rewarding experience. What contributions to the SIGGRAPH community are you most proud of?
Well, I guess we have to separate between service activities and scientific contributions.
In terms of service, chairing the SIGGRAPH Papers program (in particular as the first Papers committee chair from Europe) is the highlight of my career. It has been a unique experience in many ways, in particular in team building and leadership. I learned a lot, and it was worth every minute I invested into it.
In terms of scientific contributions to the graphics community I'm probably most proud of my contributions to the field of Point Based Computer Graphics. I think I can say without reservation that my lab at ETH has been playing a leading role in pioneering and developing this new subfield of Graphics. Point Graphics has received a lot of attention worldwide and many researchers have started working on this subject meanwhile. We have established a Symposium on Point Based Graphics in Zürich in 2004. We plan to collocate it with SIGGRAPH 2006.