Keynotes
The keynotes at VMV 2011 will be held by Michael Black, Elmar Eisemann, Hans-Peter Seidel, and Jack van Wijk.
"On Modeling Bodies and Brains: From 3D Models to Decoding the Brain"
Prof. Dr. Michael J. Black
Max Planck Institute for Intelligent Systems
Perceiving Systems Department
Tübingen, Germany
Abstract: In the late 1800's a revolution started. Photography allowed the capture and study of human and animal motion. At the same time electrical signals were recorded from the surfaces of living brains. Today modern computer vision and neuroscience are coming together to reveal clues as to how the brain controls the complex movements of our bodies. I will review recent work on video-based human body shape and motion estimation that uses statistical models of 3D body shape learned from thousands of laser range scans of the human body. I will also describe how markerless motion capture is leading to a new understanding of the neural control of natural movement. Building on these insights it is now possible to restore or improve lost function in people with central nervous system injury by directly coupling brains with computers. I will summarize our recent work on developing brain-machine interfaces that allow paralyzed individuals to control movement in the world with only their thoughts.
Biography: Michael Black received his B.Sc. from the University of British Columbia (1985), his M.S. from Stanford (1989), and his Ph.D. from Yale University (1992). After post-doctoral research at the University of Toronto, he worked at Xerox PARC as a member of research staff and an area manager. From 2000 to 2010 he was on the faculty of Brown University in the Department of Computer Science (Assoc. Prof. 2000-2004, Prof. 2004-2010). He is presently one of the founding directors at the Max Planck Institute for Intelligent Systems in Tübingen, Germany, where he leads the Perceiving Systems department. He is also an Adjunct Professor (Research) in Computer Science at Brown University and a Visiting Professor of Electrical Engineering at Stanford University. His work has won several awards including the IEEE Computer Society Outstanding Paper Award (1991), Honorable Mention for the Marr Prize (1999 and 2005), and the 2010 Koenderink Prize for Fundamental Contributions in Computer Vision.
"Getting More for Less - Scalable and Perceptually-motivated High-Quality Rendering"
Prof. Dr. Elmar Eisemann
Telecom ParisTech
Paris, France
Abstract: Producing high-quality imagery is a challenging task and new hardware developments do not necessarily facilitate it; screen resolutions tend to improve constantly, frame rates should reach hundreds of Hertz to ensure visual fidelity, 3D stereo effects have become a standard feature, platforms are increasingly heterogeneous, and a general demand for more realism makes sophisticated approximations and computations necessary. Fortunately, these demands all have something in common: they introduce much redundancy. This observation makes it possible to develop particular solutions that exploit temporal coherence, perceptual limitations, and employ adapted representations that enable a fine and simple tradeoff between quality and performance. Hereby, despite a theoretically much higher cost, the actual performance can be kept high. In this talk, we will examine solutions that enable efficient high-quality rendering and address the aforementioned challenges. Precisely, we will discuss "unlimited" scene details, temporal frame upsampling, adaptive representations, apparent quality enhancement, and complex rendering effects that enable a precise balance between fidelity and rendering cost. We will show that besides algorithmic choices and appropriate approximations, an important aspect is to take human perception into account. The latter not only, allows us to increase performance, but also rendering quality, and serves as an invitation to speculate about the future of rendering.
Biography: Elmar Eisemann is an associate professor at Telecom ParisTech. Before, he was a senior scientist heading a research group in the Cluster of Excellence (Saarland University / MPI Informatik) until December 2009. He studied Mathematics (Cologne) and Computer Science (Ecole Normale Superieure Paris). He obtained a Master's (2004) and PhD. degree (2008) in Mathematics / Computer Science from Grenoble Universities. He worked at MIT (2003), UIUC (2006), and Adobe (Seattle - 2007, Boston - 2008). His interests include real-time and perceptual rendering, alternative representations, shadow algorithms, global illumination, and GPU acceleration techniques. He published several articles at various conferences, book chapters, and journal papers and coauthored the book "Real-time Shadows". He was local organizer of EGSR 2010 and received the Eurographics Young Researcher Award in 2011.
"Multimodal Computing and Interaction"
Prof. Dr. Hans-Peter Seidel
MPI Informatics and Saarland University
Saarbrücken, Germany
Abstract: The past three decades have brought dramatic changes in the way we live and work. This phenomenon is widely characterized as the advent of the Information Society. Ten years ago, most digital content was textual. Today, it has expanded to include audio, video, and graphical data. The challenge is now to interface, organize, understand, and search this multimodal information in a robust, efficient and intelligent way, and to create dependable systems that allow natural and intuitive multimodal interaction. The Cluster of Excellence on Multimodal Computing and Interaction (M2CI), established by the German Research Foundation (DFG) within the framework of the German Excellence Initiative, addresses this challenge. The term multimodal describes the different kinds of information such as text, speech, images, video, graphics, and geometry, and the way it is perceived and communicated, particularly through vision, hearing, and human expression. In this presentation I will briefly elaborate on the structure of this research cluster, and I will then highlight some of our ongoing research by means of examples that have been selected to fit into the overall scope of the conference. Topics covered include 3D reconstruction and digital geometry processing (both for urban and non-urban environments), motion and performance capture, 3D video processing, and multimodal music processing.
Biography: Hans-Peter Seidel is the scientific director and chair of the computer graphics group at the Max Planck Institute (MPI) for Informatics and a professor of computer science at Saarland University, Saarbrücken, Germany. He is co-chair of the Max Planck Center for Visual Computing and Communication (MPC-VCC) (since 2003), and he is the scientific coordinator of the Cluster of Excellence on Multimodal Computing and Interaction (M2CI) that was established by the German Research Foundation (DFG) within the framework of the German Excellence Initiative in 2007. In addition, Seidel is a member of the Governance Board of the newly established Intel Visual Computing Institute (IVCI) (since 2009).
"Views on Visualization"
Prof. Dr. Jarke J. van Wijk
Eindhoven University of Technology
Eindhoven, The Netherlands
Abstract: Visualization is a large and heterogeneous field, full of challenging problems. Different views towards these can be adopted, such as a technological, a scientific, or an artistic approach. In this presentation this is illustrated using work of the visualization group of Eindhoven University of Technology, The Netherlands. A wide variety of cases is shown and discussed using demos and animations. One focus of the group has been software visualization, aiming towards the development of technology that makes it easier to understand the structure of large software artifacts. An early example were Cushion Treemaps, developed to visualize hierarchical data, in particular file systems (SequoiaView). Combinations of hierarchical data and networks occur often in practice, a typical case is the visualization of call-graphs of software systems. Such data can be shown using an incidence-matrix or using hierarchical edge bundles. To obtain scientific insight, besides just new methods and techniques, evaluation is an important and also a difficult aspect of visualization. Various approaches can be used, varying from controlled user experiments via case studies to dissemination in the real world. This is illustrated with work we did on visual encoding and lessons we learned from spin-off companies. Finally, another approach is to take challenging visualization puzzles and try to solve these, disregarding immediate usability. Examples from mathematical visualization are shown. Some challenges are to visualize surfaces that are bounded by knots (Seifert surfaces); to generate cartographic maps that have almost no distortion; and to subdivide surfaces of genus 2 and higher as regularly as possible.
Biography: Jarke van Wijk received a MSc degree in industrial design engineering in 1982 and a PhD degree in computer science in 1986, both from Delft University of Technology, both with honors. He joined Eindhoven University of Technology in 1998, where he became a full professor of visualization in 2001. His main research interests are information visualization, visual analytics, mathematical visualization, and flow visualization. He is cofounder and VP Scientific Affairs of MagnaView. He has been paper cochair for IEEE Visualization (2003, 2004), IEEE InfoVis (2006, 2007), IEEE VAST 2009, IEEE Pacific Vis 2010 and EG/IEEE EuroVis 2011. He received the IEEE Visualization Technical Achievement Award in 2007 for his work on flow visualization, Best Paper awards at IEEE InfoVis 2003 and IEEE Visualization 2005, and the 2009 Henry Johns Award.