Invited Talk 1: Image Enhancement by Regularization Methods
Andrey S. Krylov, Andrey V. Nasonov and Alexey S. Lukin, MSU
Many image processing problems are posed as ill-posed inverse problems. Deblurring is a well known example of such a problem. To solve these problems numerically one must introduce some additional information about the solution, such as an assumption on the smoothness or a bound on the norm. This process was theoretically proven by Russian mathematician Andrey Tikhonov and it is known as regularization. Regularization methods are widely used in multimedia data processing.
The talk will include some preliminaries on regularization methods along with their use in image processing. New applications of regularization procedures in image resampling, deringing and video data super-resolution will be shown.
Invited Talk 2: Design innovation technologies in education
Elena Shumilova, Autodesk
Designers and engineers are playing an important role in addressing the big challenges being presented by a range of global trends such as globalization, the infrastructure boom, climate change, and the growth of the digital life.
Computer graphics enables design professionals to create digital models and workflows that can be used to visualize, simulate, and analyze their designs. This enables them to experience their ideas before they are real and improve the way their projects and products will look, perform, and be used in the real world.
Autodesk is encouraging educators and students to use the technologies they need to respond to these challenges through design innovation.
Invited Talk 3: Vision-Simulated Imaging
Brian A. Barsky, UC Berkeley
Vision-simulated imaging (VSI) is the computer generation of synthetic images to simulate a subject's vision, by incorporating the characteristics of a particular individual's entire optical system. Using measured aberration data from a Shack-Hartmann wavefront aberrometry device, VSI modifies input images to simulate the appearance of the scene for the individual patient. Each input image can be a photograph, synthetic image created by computer, frame from a video, or standard Snellen acuity eye chart -- as long as there is accompanying depth information. An eye chart is very revealing, since it shows what the patient would see during an eye examination, and provides an accurate picture of his or her vision. Using wavefront aberration measurements, we determine a discrete blur function by sampling at a set of focusing distances, specified as a set of depth planes that discretize the three-dimensional space. For each depth plane, we construct an object-space blur filter. VSI methodology comprises several steps: (1) creation of a set of depth images, (2) computation of blur filters, (3) stratification of the image, (4) blurring of each depth image, and (5) composition of the blurred depth images to form a single vision-simulated image.
Invited Talk 4: From video-based eye-tracking to imaging brain and perceptual consciousness
Boris M. Velichkovsky, Kurchatov Research Center, Moscow, and Dresden University of Technology, Dresden
Recent progress in video-based eyetracking can be considered as a silent technological revolution in brain and behavioural sciences, approaching that of brain imaging methods. The importance of this methodology is quite obvious from the point of view of the ecological validity and practical implications of eyetracking. However, it is of a paramount significance for basic neurocognitive research as well. As a matter of fact, human eye movements are a common output of a number of philogenetically evolved and often (though not always) hierarchically organized brain systems. In this presentation, I will demonstrate how contemporary eyetracking research helps to disentangle their influences on task solution completing in a non-trivial way data obtained with neuroimaging methods.
Invited Talk 5: Transparent brain: towards 3D imaging of memory traces in the nervous system
Konstantin Anokhin, Anokhin Institute of Normal Physiology RAS
Invited Talk 6: Decomposition of High Angular Resolution Diffusion Images into a Sum of Self-Similar Polynomials on the Sphere
Luc Florack, Evgeniya Balmashnova, Eindhoven University of Technology
We propose a tensorial expansion of high resolution diffusion imaging (HARDI) data on the unit sphere into a sum of self-similar polynomials, i.e. polynomials that retain their form up to a scaling under the act of lowering resolution via the diffusion semigroup generated by the Laplace-Beltrami operator on the sphere. In this way we arrive at a hierarchy of HARDI degrees of freedom into contravariant tensors of successive ranks, each characterized by a corresponding level of detail. We provide a closed-form expression for the scaling behaviour of each homogeneous term in the expansion, and show that classical diffusion tensor imaging (DTI) arises as an asymptotic state of almost vanishing resolution.
Invited Talk 7: Radeon GPU Architecture
Michael Doggett, AMD
GPU architectures have evolved into massively parallel multi-core machines. This talk will review GPU architecture by looking at AMD's ATI Radeon 2900XT. This GPU is capable of massively parallel computation for high performance 3D graphics and general purpose algorithms. The shader uses multi-threading to hide latency of memory access so that compute units are kept busy. This high level of parallelism is achieved through a hierarchy of compute elements and programmed via an abstracted sequential API. New generations of GPUs are challenged to offer more programmable flexibility for compute and graphics while increasing performance for existing APIs and applications.
Invited Talk 8: Intel's Vision of Visual Computing
Alexander Chipizhko, Intel
What is Visual Computing? "Good question," - the most will say.
In general, Visual Computing refers to an emerging category of applications that include acquiring, analyzing, modeling, and synthesizing visual workloads. Major elements in VC are: photorealistic 3D rendering; interactive and immersive user interfaces; high-definition audio and video; and model-based computing.
That's right but what's more? Nowadays experts note early examples of visual computing emerge and so expect dramatic improvements in all areas.
Presentation describes Intel's vision of Visual Computing and steps that Intel does to make it a reality.