Current Projects

The project aims at designing and building a ray tracing infrastructure that will be fully open source, that can be used as a library/tool, that uses the proper compiler technology to be portable across a wide range of hardware platforms while offering close to optimal performance on each of them, and that explicitly aims at providing scalability across the different dimensions of ray tracing technology needed by users.

In this project we address the challenges both on the algorithmic and software/hardware infrastructure level in the context of typical use-cases in the film and video industry, taking advantage of the existing collaboration with industry within the EU project “Dreamspace” (including partners like The Foundry (London), Stargate Studios (LA), Filmakademie (Ludwigsburg), and others).

The scientific focus of" Efficient Multi-View Video Streaming" is the design and implementation of an efficient system for multiview video (MVV) streaming.

In this project, we are working on creating a library that allows the development of web applications that require efficient data processing including performance portability.

“Interactive Visualization and Analysis for Extreme Scale Science” works on the
the scientific goal of the efficient and effective visualization of large datasets.

The goal of this project is to investigate scalable algorithms for dynamic scene reconstruction for more general dynamic scenes with only a few handheld mobile cameras.

Within this project highly parallelized methods for lightfield acquisition and reconstruction are investigated.

This project researches and develops perceptual models for spatio-temporal visual perception as well as attention and fixation prediction for modern display technologies.

Realistic 3D content that is automatically reconstructed from photographs are and will not be flawless in the near future. This project aims at automatic evaluations of the quality of reconstructed scenes and pointing out errors to users.

Our novel Path-Space Regularization enabled us to compute light transport more robustly and to handle scenes which were impossible to render using previous unbiased methods.

The project "Scalable Adaptive Low Latency Streaming" focuses on research of a low-latency video delivery service with adaptive solution that fulfills the requirements of live video broadcasting.

The goal of this project is to develop new methods for finding structure in 3D shapes that can be used to assemble model variations from example geometry. Our approach consists of two parts: geometry analysis and synthesis, with the special case of compact storage and visualization.

This Intel VCI project investigates the algorithmic foundations of the next generation of motion capture, to reconstruct much more complete and detailed dynamic scene models.

The "Distributed 3D Object Design" network brings together leading laboratories in Visual Computing and 3D Computer Graphics research across Europe with the goal of training a new generation of scientists, technologists, and entrepreneurs that will move Europe into a leading role in the scientific and technological innovation within the area of distributed 3D object design, customization, and fabrication.

DreamSpace is a collaborative project funded under FP7 of the European Commission which develops a new platform and also tools for collaborative virtual productions in the production of visual effects, in film and TV, and in new immersive experiences.







Previous Projects

In the "3D Content Aware Display Interaction" project, we investigate a generic solution for user interaction happening at all ends around "Display as a Service" (DaaS) and creating a generic interaction framework, which allows as much flexibility and network transparency as it is already the case with DaaS.

Using active illumination for 3D object reconstruction is an established technique in quality control, reverse engineering, object recognition, medical applications, historical artifact conservation, animation, and virtual reality. In contrast to existing work, this project’s objective is the development of algorithms that are robust to occlusions.

In the project "A Scalable Hybrid Rendering System for Large Scale Visualizations"  we are developing a hybrid rendering and visualization system that combines the strengths of different rendering algorithms, hardware models, and display technologies while avoiding their weaknesses.

This project addresses some of the core issues in this area of 3D-Internet, including advanced rendering algorithms (for which 3D-Internet may be the killer app) and XML3D.

The aim of the this project is to focus on the "software side" of depth systems and to provide holistic algorithmic solutions to the imaging pipeline, ranging from preprocessing to image understanding.

This Intel VCI project investigates ways to assist drug designers with modern rendering techniques by greatly improved visual perception of three-dimensional molecular properties, and with 3D-internet and collaboration techniques by unlocking the potential of interdisciplinary, virtual cooperation.

The "Compiler Support for High-Performance Graphics" project aims at making programming of high-performance graphics systems easier while maintaining high performance.

The Intel VCI project “Display as a Service (DaaS)” targets the virtualization of the graphics pipeline, i.e., transferring the connection between pixel sources and displays to standard IP networks.


The goal of the project was to support users in understanding scenes by combining different visualizations by showing the actual scene with two representations: stereoscopic video and 3D computer graphics

This project focuses on developing an object recognition system for real-world environments with minimally constrained lighting conditions and camera pose, and densely clustered objects.

Research in this project focuses on the one hand on appropriate acceleration techniques to achieve high-quality rendering solutions, and on the other hand on solutions that allow artistic manipulation and offer novel solutions for the artists to realize their vision.

The goal of the local dimming technology is to achieve various physical and visual advantages on an LED LCD monitor for multimedia applications as well as significant power savings to allow longer battery operation. The specific objective of this project is a very efficient algorithm implemented on a GPU

This project investigates possible, intuitive combinations of traditional 2D and 3D user interfaces as well as dedicated interaction techniques suitable for the intuitive interaction in mixed 2D and immersive 3D environments.

In this project, we intend to develop a modular infrastructure which is able to store and process 3D content on the internet, thus enabling internet-enabled 3D processing workflows.

In the scalable rendering project we aim to improve this visual experience by creating models of these computational devices and then using those models to enhance the realistic images that are generated.

In this project, we address the problem that it requires experts with low-level 3D skills to develop 3D web applications by providing scalable client technology, the XML3D architecture, and scalable middle-ware to synchronize 3D scene across multiple users (FiVES).

The “User-centric Video Processing” project exploits content relationships within and between videos to make them easier approachable for amateur users and to
provide new empowering video experiences, ranging from novel content-based video browsing to dynamic object removal in videos.

In the SCENE project a consortium of nine leading European research institutes and companies thrives to revolutionize the way visual media is produced.

The joint project “Software Innovations for the Digital Enterprise” (SINNODIUM) links to the four ongoing projects within the framework of the Cluster Excellence Competition, connects the various fields of research, and guides the overall project to an integrated conclusion.

VERVE’s efforts focus on three situations, each targeting a different group of participants: (i) fear of falling and Parkinson’s disease; (ii) apathy related to cognitive decline and behavioral disturbances, in particular due to Alzheimer’s Disease; and (iii) other emotional disturbances linked to anxiety.