Multimedia
Blogs
Forum
Affordable HD
Whitepapers
Newsletters
Events
Advertisers
Blogcast
MillimeterRiveting Research
Jun 16, 2003 12:00 PM, By Audrey Doyle
Click here to register for SIGGRAPH.
for a PDF.
SIGGRAPH 2003 Papers
 Detailed Papers sessions tackle classic concerns including Human Bodies and Shadows. |
IF YOU THINK IN STATISTICS, CONSIDER THIS: The Papers Committee of SIGGRAPH 2003 has been 18% busier than last year. According to Papers chair Jessica Hodgins, associate professor at the School of Computer Science at Pittsburgh's Carnegie Mellon University, the 2003 Committee obtained a record number of submissions at 424 and accepted 81 papers; a 19% acceptance rate similar to that of past years.
But ultimately, numbers are not the point, Hodgins says, explaining that the Papers Committee continued the tradition of not counting papers, and instead accepted every paper they thought should appear at SIGGRAPH. Although this resulted in some overlapping sessions, it also resulted in the "best possible overall program."
The acceptance process began early this year, when the five-member Advisory Committee met for a Papers Sort meeting, during which each paper was assigned to two committee members. Those members each assigned one or two outside referees to review the papers as well. These initial reviews were submitted to the authors, and during a newly added Rebuttals phase of the review process, the authors were allowed to correct factual errors via posts to an electronic bulletin board system. Approximately 75% of the authors took advantage of the Rebuttals phase. "Despite the extra workload, the committee felt that this extra step in the review process improved the quality of the final decisions," Hodgins says.
Once the papers were conditionally accepted in late March, they went through a second review process, during which the authors responded to required changes and made additional changes as appropriate. The papers were read once more, and the final versions were approved.
Graphcut Textures and Wang Tiles
Overall, the 2003 papers represent significant leaps forward in many areas. One such area is texturing. In "Graphcut Textures: Image and Video Synthesis Using Graph Cuts," a paper in the "Texture Synthesis by Example" session, authors Vivek Kwatra, Arno Schödl, Irfan Essa, Greg Turk, and Aaron Bobick of the Georgia Institute of Technology/GVU Center introduce a new algorithm for image and video texture synthesis.
In their approach, as stated in their abstract, "patch regions from a sample image or video are transformed and copied to the output and then stitched together along optimal seams to generate a new (and typically larger) output."
According to the authors, this process is different from current approaches in that instead of choosing the size of the patch "a priori," a graphcut technique determines the optimal patch region for any given offset between the input and output texture. In their paper, the authors explore graphcut textures in both 2D and 3D to perform video texture synthesis and traditional image synthesis. They also show results for synthesizing regular, random, and natural images and videos, and they demonstrate how the graphcut technique can be used to interactively merge different images to generate new scenes.
Another paper in the "Texture Synthesis by Example" session is "Wang Tiles for Image and Texture Generation," authored by Michael F. Cohen (Microsoft Research), Jonathan Shade (Wild Tangent), and Stefan Hiller and Oliver Deussen (Dresden University of Technology). In this paper, the authors present a new stochastic algorithm for non-periodically tiling a plane with a small set of Wang Tiles. Wang Tiles are squares in which each edge of each tile is assigned a color. The authors discuss how Wang Tiles can be used and re-used to efficiently create large expanses of complex textures, patterns, or prelighted geometry at runtime, while avoiding obvious visual artifacts of repetition.
Reanimating the Dead and Skinning the Animated
Another area of note is human modeling and animation. The "Human Bodies" session features five papers, each highlighting a breakthrough in this arena.
In "Reanimating the Dead: Reconstruction of Expressive Faces from Skull Data," for instance, authors Kolja Kähler, Jörg Haber, and Hans-Peter Seidel of MPI Informatik explore the possibilities for anatomically correct modeling and physics-based simulation in an interactive environment.
They do this using Medusa, a facial modeling and animation system that Haber and Kähler developed for research and educational purposes. As the authors explain in their abstract, the system includes tools and techniques for a variety of subtasks that must be accomplished to generate photorealistic facial animations in realtime on standard PCs. In their paper they discuss the topics of data acquisition, muscle modeling, skin simulation, textures and rendering, multiresolution surfaces, speech synchronization, and anthropometric modeling.
In "Building Efficient, Accurate Character Skins from Examples," authors Alex Mohr and Michael Gleicher from the University of Wisconsin, Madison, present an automated framework for building convincing skin deformations for interactive applications. As Mohr and Gleicher explain, good character animation requires subtle yet detailed deformation. Commercial animation packages provide tools for achieving such deformation; however, these programs are not optimal for interactive applications because they are too slow to compute or require too much memory.
The method outlined in this paper begins with an arbitrarily rigged character in an animation system. The authors export a set of examples consisting of skeleton configurations paired with the deformed geometry as static meshes, and then use these examples to fit the parameters of a deformation model that best approximates the original data.
According to the abstract, "the underlying deformation model we use is an extension of the traditional linear blend skinning model widely used in interactive applications. This extension allows us to capture subtle and detailed effects required for believable characters but remains nearly as fast and compact as linear blend skinning."
Skin deformation also is the focus of "Continuous Capture of Skin Deformation," presented by Peter Sand and Jovan Popovic from the Massachusetts Institute of Technology, and Leonard McMillan from MIT and the University of North Carolina at Chapel Hill. In this paper, the authors describe a method for acquiring deformable human geometry from silhouettes.
"Our technique uses a commercial tracking system to determine the motion of the skeleton, then estimates geometry for each bone using constraints provided by the silhouettes from one or more cameras," write the authors. "These silhouettes do not give a complete characterization of the geometry for a particular point in time, but when the subject moves, many observations of the same local geometries allow the construction of a complete model."
The authors' reconstruction algorithm provides a simple mechanism for solving the problems of view aggregation, occlusion handling, hole filling, noise removal, and deformation modeling.
Mocap and Range Scans
The paper "Free Viewpoint Video of Human Actors," by Joel Carranza, Christian Theobalt, Marcus A. Magnor, and Hans-Peter Seidel of MPI Informatik, describes a system that uses multi-view synchronized video footage of an actor's performance to estimate motion parameters and to interactively re-render the actor's appearance from any viewpoint. According to the abstract, "the actor's silhouettes are extracted from synchronized video frames via background segmentation and then used to determine a sequence of poses for a 3D human body model. By employing multi-view texturing during rendering, time-dependent changes in the body surface are reproduced in high detail."
 Among the Fluids and Smoke papers are "Animated Supsended Particle Explosions" (pictured), and a groundbreaking presentation from ILM on smoke simulation. |
The authors write that the motion-capture subsystem, which runs offline, is non-intrusive yet yields robust motion parameter estimates, and the rendering system, which runs at realtime frame rates, yields highly natural results.
The final paper in the "Human Bodies" session is "The Space of Human Body Shapes: Reconstruction and Parameterization from Range Scans." Authored by Brett Allen, Brian Curless, and Zoran Popovic of the University of Washington, this paper describes a method the authors developed for creating a whole-body morphable model based on 3D scanned examples.
Shadows and GPU Computation
One subject that has been covered only periodically in the SIGGRAPH Papers Sessions over the last few years, but this year has an entire session devoted to it, is shadows. The appropriately titled "Shadows" session features four papers that describe the latest advances in shadow generation. Indeed, this session covers everything from extracting shadows from one natural scene and inserting them into another, described in "Shadow Matting and Compositing," to a new algorithm for interactive generation of hard-edged, umbral shadows in complex environments with a moving light source, outlined in "Interactive Shadow Generation in Complex Environments."
Also being presented are papers on meshing and surfaces, measurements for rendering, character animation, and animation of smoke, explosions, and cloth. This year also highlights the subject of algorithms for GPUs. Hodgins says that GPU computation, along with the capture of motion and body shape from video, are two techniques that may become commonplace in the not-too-distant future.
This year's Papers Sessions truly represent the best academic and industry research in computer graphics. "It's an exciting program," Hodgins concludes. "We're presenting a lot of new ideas and new technologies that will have a large, positive impact on the growing field of computer graphics."
Papers can be purchased as part of the SIGGRAPH 2003 technical materials, which include the Full-Conference DVD and "ACM Transactions on Graphics." The DVD contains the electronic version of the technical papers, images, and supplemental material; the course and tutorial notes, including supplemental material; and the permanent record of the Educators Program, Emerging Technologies, Sketches & Applications, Special Sessions, and Web Graphics programs, as well as the Art Gallery and Computer Animation Festival. "ACM Transactions on Graphics" contains the SIGGRAPH 2003 technical papers and the ACM SIGGRAPH awards. Publications are available for purchase at www.siggraph.org/publications and are available to ACM SIGGRAPH members at substantial discounts.
SIGGRAPH 2003 Papers Sessions
Sunday, July 27
Fast-Forward Papers Preview
6:00-7:30 p.m.
Monday, July 28
Session: "Texture Synthesis by Example"
10:30 a.m.-12:15 p.m.
Session: "Images, Video, and Texture"
1:45-3:30 p.m.
Session: "Parameterization"
3:45-5:30 p.m.
Session: "Precomputed Radiance Transfer"
5:45-7 p.m.
Tuesday, July 29
Session: "Character Animation"
8-10:15 a.m.
Session: "Visualization and Printing"
10:30 a.m.-12:15 p.m.
Session: "Surfaces"
1:45-3:30 p.m.
Session: "Shadows"
3:45-5:30 p.m.
Session: "Perception and Manipulation"
5:45-7 p.m.
Wednesday, July 30
Session: "Human Bodies"
8-10:15 a.m.
Session: "Light Fields and Visibility"
10:30 a.m.-12:15 p.m.
Session: "Points"
1:45-3:30 p.m.
Session: "Modeling and Simplification"
3:45-5:30 p.m.
Session: "Reprise of UIST '02 and I3D '03"
3:45-5:30 p.m.
Thursday, July 31
Session: "Fluids and Smoke"
8-10:15 a.m.
Session: "Scattering and Reflectance Measurement"
8-10:15 a.m.
Session: "Hardware and Displays"
10:30 a.m.-12:15 p.m.
Session: "Design and Depiction"
10:30 a.m.-12:15 p.m.
Session: "Dynamics"
1:45-3:30 p.m.
Session: "Computation on GPUs"
3:45-5:30 p.m.
Session: "Meshes"
3:45-5:30 p.m.
SIGGRAPH 2003 Papers Advisory Board
CHAIR: Jessica Hodgins, Carnegie Mellon University
Joe Marks, Mitsubishi Electric Research Laboratories (MERL)
Peter Shirley, University of Utah
Greg Turk, Georgia Institute of Technology/GVU Center
Marc Levoy, Stanford University
Click here to register for SIGGRAPH.
Continue the discussion on “Crosstalk” the Millimeter Forum.
