Keynotes program

Eurographics 2018 is proud to announce the keynote speakers! 

Challenges in Visual Analytics

Jack van Wijk

Date: Tuesday, April 17 11:00-12:00

Location: Aula Auditorium 

Abstract: 

Visual Analytics aims at the integration of automated analysis (statistics, machine learning, data mining) with interactive visualization, thereby exploiting the strengths of humans and computers. The concept is great, but there are many challenges ahead. In my talk I will reflect on this. Size, complexity, dynamics of data are major challenges, but also dealing with strengths and limitations of human perception and cognition are. A special challenge is to provide trust and transparency of complex models and their results, which is an important societal issue. I will illustrate these challenges using examples of our work in Eindhoven, for a variety of applications.

 

Bio:

Jack van Wijk is full professor in visualization at the Department of Mathematics and Computer Science of Eindhoven University of Technology (TU/e). He 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. He has worked for ten years at the Netherlands Energy Research Foundation ECN. 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 and visual analytics, with a focus on the development of new methods for the interactive exploration of large data-sets. The work of his group has led to two start-up companies: MagnaView BV and SynerScope BV. He has (co-)authored more than 150 papers in visualization and computer graphics and received six best paper awards. He received the IEEE Visualization Technical Achievement Award in 2007 and the Eurographics 2013 Outstanding Technical Contributions Award.

 


Semantic Scene Factorization via Multimodal Analysis

niloy mitra

Date: Thursday, April 19 11:00-12:00

Location: Aula Auditorium 

Abstract: 

Obtaining massive volumes of image, video, or scans is now possible. This provides unprecedented opportunities to perform scene analysis and understanding at large-scale. However, there are several fundamental challenges to overcome -- the raw data is often incomplete (e.g., due to occlusion), records complex interactions (e.g., between humans and objects), and lacks suitable annotations. In our research, we have studied the use of various regularizers in the form of transformation groups (e.g., symmetry types), data priors (e.g., database shapes), functional priors (e.g., object affordance), etc. to regularize the problem. More recently, we have been investigating the utility of non-geometric priors (e.g., physics-based) to simultaneously perform scene completion and scene understanding. In this talk, I will discuss our recent results and highlight the opportunities ahead.

 

Bio:

Niloy J. Mitra leads the Smart Geometry Processing group in the Department of Computer Science at University College London. He received his PhD degree from Stanford University under the guidance of Leonidas Guibas. His research interests include shape analysis, computational design and fabrication, and geometry processing. Niloy received the ACM Siggraph Significant New Researcher Award in 2013 and the BCS Roger Needham award in 2015. His work has twice been featured as research highlights in the Communications of the ACM, received best paper award at ACM Symposium on Geometry Processing 2014, and Honourable Mention at Eurographics 2014. Besides research, Niloy is an active DIYer and loves reading, bouldering, and cooking.


RGB+: Improving the Visible with the Invisible

Sabine Susstrunk

Date: Friday, April 20 11:30-12:30

Location: Aula Auditorium 

Abstract:
Conventional digital cameras exhibit a number of limitations that computational photography systems try to overcome. For example, the disambiguation of how much the illuminant(s) and the object reflectance contribute to a pixel value is mathematically ill-posed. Given how most modern cameras capture images, blur and limited depth-of-field may also introduce noise and unwanted artifacts. To solve this problem, experts have proposed modified hardware, smart algorithms using priors, and (deep) machine learning approaches. In our research, we use "extra information" in the form of near-infrared (NIR), the wavelength range adjacent to the visible spectrum and easily captured by conventional silicon sensors. Capturing NIR can improve computational photography tasks such as dehazing, white-balancing, shadow detection, deblurring, and depth-of-field extension, as well as computer vision applications such as detection and classification.

 

Bio:

Sabine Süsstrunk is full professor in the School of Computer and Communication Sciences (IC) at the Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland, where she leads the Images and Visual Representation Lab (IVRL) since 1999 and the Digital Humanities Institute since 2015. Her research areas are in computational photography, color computer vision and color image processing, image quality, and computational aesthetics. She has published over 150 scientific papers, of which 7 have received best paper/demos awards, and holds 10 patents. She received the IS&T/SPIE 2013 Electronic Imaging Scientist of the Year Award and IS&T’s 2018 Raymond C. Bowman Award. She is a Fellow of IEEE and IS&T.