Für eine korrekte Darstellung dieser Seite benötigen Sie einen XHTML-standardkonformen Browser, der die Darstellung von CSS-Dateien zulässt.


  Faculty 12  /  Introduction  /  Teaching  /  Introduction  / 
Sitemap
 

Introduction to Visual Computing

Visual Computing deals with information technological challenges in acquiring, processing and analyzing image data and, on the other hand, in the generation of images based on a mathematical representation in a computer. Both topics become more and more interrelated in research and economical applications like production-planning, medicine or media.

Examples on Visual Computing

Reanimating Faces in Images

Based on the 3D reconstructions, faces can be re-animated in photographs and paintings. After reconstruction, we animate the faces in 3D, and draw the result back into the original image. The 3D deformations for animation are learned from scans of a face at different facial expressions. In our vector space representation, the difference between a smiling face and a neutral face is a "smile vector" that can be added to any other neutral face to make it smile. This technique, which we have also applied to video input, may be used in a wide range of media applications, including virtual museums, and for lip-synching movies.

Particle-based Effects

A significant amount of visual effects like smoke or water can not be adequately represented using geometric objects like polygons. An alternative representation uses a large amount of points (particles). Here, the challenge is to simulate the bahaviour of this large number of particles over time.
Our approach utilizes the growing performance of commodity graphics cards not only for the visualization the visual effects but also for the simulation. This reduces the amount of data to be transfered to the graphics card for rendering.

Requirements of Visual Computing

It is, in many ways, fascinating to deal with images and this is truly a major incitement for lecturers and student to involve themselves in the field of Visual Computing. If one would give Visual Compting a motto, What you see is what you want! would be a good one, since it also indicates, that there is a challenge in dealing with the technological fundamentals of image acquisition, image processing and image synthesis.
Besides the foundations of the classical disciplines in Computer Science, e.g. data structures or programming languages, Visual Computing requires a significant amount of knowledge in various mathematical or physical disciplines like linear algebra, calculus, stochastics or mechanics. This is due to the fact, that in merely all areas of Visual Computing, real-world objects and their behaviour play an important role. Synthetic images, for example, can only be generated on the basis of a profound computer model describing the shape and appearance of the objects to be displayed. On the other hand, the analysis of an image in order to recognize its content often requires a mathematical model in order to segment the image into meaningfull sub-regions. To handle this kind of tasks one needs a "mathematical tool-box" in conjunction with profound skills to apply it in a proper way.
However, based on the mentioned foundamentals, really impressive results already during the time of study can be obtained. To get an insight into current and recent project groups have a look at the project site of the graphics group.