Research and application of artificial intelligence within the context of visual computing and data analysis is a central theme at VRVis. Through our in-house basic research and the development and implementation of numerous AI-based solutions for the real challenges of our business partners at home and abroad, we have accumulated extensive expertise and already have several patents and a large number of publications in high-impact scientific journals under our belt.
Our strength is our versatility and experience in different sectors and in the most varied applications: Covering medicine and life sciences, business and industrial manufacturing or even space technology. In addition to new, general approaches for machine learning and deep learning in data analysis, we are also conducting research into AI-supported image-based decision-making, as well as methods for interpretable AI (e.g. for AI-supported assistance systems). The link between AI and visual computing establishes a bridge between computer graphics, visual data analysis and AI. Human beings lie at the heart of all our AI applications, giving the machine instructions (human-centred AI).
Artificial intelligence brings new technological dynamics into many sectors - AI-based applications are currently transforming whole markets. As Austrian AI Hub the VRVis portfolio covers the complete pipeline for AI supported data analysis:
Data preparation: The quality of training data in the context of each application is decisive for the quality of the result. Our experience and the use of elementary data science methods, as well as tools that simplify data annotation by experts, are the basis for preparing a sufficient volume of big data and compiling adequate training sets.
Generation of training data for AI systems: AI solutions are only as good as the data with which they are trained. But good training data is often scarce, sometimes not even available at all or difficult/expensive to obtain. We support our company partners by artificially simulating the necessary data to train neural networks. Synthetic data is secure, anonymized and unbureaucratic. The artificially generated training data sets are characterized by very good data quality and thus help to accelerate innovation processes, for example by greatly reducing time-to-market due to their rapid availability.
Development of tailor-made AI solutions: We develop deep learning and machine learning technologies in close cooperation with our partners and customers in order to design targeted solutions for processing, analyzing and visualizing large volumes of data, multi-terabyte laser scan data and for analyzing images.
Explainable Artificial Intelligence (XAI): Decisions that are made by machines must remain intelligible, reliable and transparent for humans, particularly in sensitive areas such as medicine or in self-driving vehicles ("ethical AI"). We develop methods that make machine behaviour explainable and consequently provide transparency for complex decisions that are made with the aid of artificial intelligence. Our methods therefore also support the evaluation of security and stability of trained networks.
Our research centre has already produced several AI-based applications and patents, as well as high-impact publications in the fields of image analysis and data science, and the areas of application of digital radiology, neuroscience, life science and manufacturing.
Within the framework of “AI for Green”-funded research project develops AI-based solutions aimed at optimizing free satellite data for monitoring agricultural areas of all sizes.
Based on real-world use cases from the field of intelligent logistics systems, the REINFORCE project investigates how reinforcement learning can solve complex control problems.
Im Projekt REINFORCE wird anhand von realen Anwendungsfällen aus der Praxis intelligenter Logistiksysteme untersucht, wie durch Reinforcement Learning komplexe Steuerungsprobleme gelöst werden können.
The research project CognitiveXR focuses on developing a platform that enables cognitive augmentation in the smart city domain by seamlessly integrating augmented reality, edge computing, and artificial intelligence.
The aim of the application project IVC Multi is to research novel intelligent visual computing methods supporting decision-making in automotive industry, medicine, and life sciences based on ensembles of heterogeneous, multi-scale and/or multi-temporal data.
The aim of the project IVC Stream is to research novel visual computing solutions for simulation and measurement data.
This project aims at accelerating and automating image-based decision making with an application focus on medicine, recycling and quality assurance processes in manufacturing.
The strategic project of the area is the organizational and scientific hub for the realization of the area-wide intelligent visual computing approach for analytics and modelling based on ensembles of dense grid-based data, derived data, and digital embedding.
The "Mars-DL" project is investigating how a deep learning system can support the research work of planetary scientists through object and pattern recognition. For this project VRVis has extended the functionality of PRo3D to automatically render shatter cone training images.
VRVis a founding member of the Austrian BioImaging/CMI, which is a professional consortium of multiple Austrian science institutions and the official Austrian Euro-BioImaging initiative.
Visual computing for medicine: image processing solutions for new applications in radiology.
In this project we develop new methods from the field of visual analysis and machine learning to automate the quality control and quality assurance of glass articles.
The long-term vision of this applied research project is to use available data resources to improve image-based diagnostics based on complex data in daily clinical routine.
Visual computing techniques for the automated detection of osteoporosis and osteoarthritis.