Visual Computing
Contact person
The Visual Computing group, part of SINTEF Mathematics and Cybernetics, perform world class research in high-performance, parallel scientific computing and visualization. Our goal is to combine the parallelism of traditional multi-core CPUs and accelerator cores to deliver unprecedented levels of performance.
Research Topics
Isogeometric volume visualisation
We developed a novel approach for interactive visualisation of isogeometric analysis results, ensuring correct, i.e., pixel-accurate geometry of the volume including its bounding surfaces.
Visual Computing
Interactive rendering of large models require research both in geometrical representations and computer graphics. Our main research focus is on high-quality rendering of smooth surfaces.
GPU Computing
Our research group was founded to study the potential for general purpose GPU computing. Ever since, we perform research on hardware adapted algorithms and how to use GPUs in multi-disiplanary teams.
Virtual and Augmented Reality
We develop enabling technology for virtual and augmented reality, both for entertainment and proffesional use. Virtual and augmented reality has the potential to be a game changer in how we interact with computers. Our research is focused on realtime algorithms that help unleash this potential.
Deep Learning
Deep Learning use advances in machine learning and GPU computing to solve complex problems. The two most known application areas are image classification and speech recognition. We perform research both on how to tackle new applications with deep learning and how to efficiently use the trained models in real time.
CloudiFacturing project
The mission of CloudiFacturing is to optimize production processes and producibility using Cloud/HPC-based modelling and simulation, leveraging online factory data and advanced data analytics, thus contributing to the competitiveness and resource efficiency of manufacturing SMEs. SINTEFs is the technical coordinator of CloudiFacturing, and develops services for scientific visualisation and hybrid physics (machine learning working together with numerical simulations for fast and accurate soulutions).