ABOUT

GPU4Vision is a project founded by the Institute for Computer Graphics and Vision, Graz University of Technology. We'd like to make cutting edge research results in the field of GPU-based vision algorithms publicly available. We use Nvidia consumer graphics cards and their CUDA framework. More...

Stay updated to our software releases, publications and videos by subscribing to our news feed and youtube channel:

feed

news feed

http://gpu4vision.icg.tugraz.at/feed.xml

feed

youtube channel

http://www.youtube.com/user/gpu4vision

NEWS

2013-07-01 New Publication Online: Revisiting loss-specific training of filter-based MRFs for image restoration
Link This work will be presented at GCPR 2013
 
2013-03-27 New Publication Online: An iterated l1 Algorithm for Non-Smooth Non-Convex Optimization in Computer Vision
Link This work will be presented at CVPR 2013
 
2013-03-15 New Publication Online: Minimizing TGV-based Variational Models with Non-Convex Data Terms
Link This work will be presented at the International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) 2013
 
2012-09-07 New Publication Online: Convex Approaches for High Performance Video Processing
Link Manuel Werlberger's Phd Thesis
 

Previous news entries...

 

WHY GPUS?

Consumer graphics adapters have evolved from petite units with very limited general applicability to high-power computational devices, which are very flexible in terms of their usage. Their computational power and memory bandwith undertook vast increases during the last years. Offering high-level-language support, recent graphics hardware is able to outperform CPU clusters in a wide range of applications.

Computational Power Memory Bandwidth Computational Efficiency
Overview: Computational power, memory bandwith and efficiency of recent Nvidia GPUs compared to recent Intel desktop CPUs. (click to enlarge)

Modern graphics cards are highly parallel computational devices with fast shared memory. This allows for solving problems with high arithmetic density in realtime, which would take several minutes computed on CPUs. Computer vision problems usually fit perfectly to the architecture of modern graphics hardware, as beeing parallelizable and requiring plenty of operations on each pixel and its surroundings.

IMPRINT

Institute for Computer Graphics and Vision
Graz University of Technology
Inffeldgasse 16/II
A-8010 Graz, Austria
www.icg.tugraz.at

Google Analytics Disclaimer:

This website uses Google Analytics, a web analytics service provided by Google, Inc. ("Google"). Google Analytics uses "cookies", which are text files placed on your computer, to help the website analyze how users use the site. The information generated by the cookie about your use of the website (including your IP address) will be transmitted to and stored by Google on servers in the United States . Google will use this information for the purpose of evaluating your use of the website, compiling reports on website activity for website operators and providing other services relating to website activity and internet usage. Google may also transfer this information to third parties where required to do so by law, or where such third parties process the information on Google's behalf. Google will not associate your IP address with any other data held by Google. You may refuse the use of cookies by selecting the appropriate settings on your browser, however please note that if you do this you may not be able to use the full functionality of this website. By using this website, you consent to the processing of data about you by Google in the manner and for the purposes set out above.