Vienna
Image Feature: 

Research: Vienna

intro
Content: 

The Vienna Corporate R&D center was established in March 2010 with a strong focus on augmented reality for mobile devices. The growing team of researchers and engineers features world class expertise in this very active field. Projects at our Vienna research center encompass basic research in AR and related areas as well as efforts to make these findings available in commercial products.

Expertise: computer vision, augmented reality, SW development and optimization

The Corporate R&D center in Vienna maintains close collaboration with Qualcomm teams in San Diego and Seoul. We also have strong relationships with some of the top institutes contributing in the field of computer vision and augmented reality, e.g. the Christian Doppler Lab for Handheld Augmented Reality in Graz.

Qualcomm Augmented Reality Lecture Series
o: 
o
SEO Level: 
h2
Header Style: 
h2 (Section level header)
Invert colors: 
Off
Content: 

The Qualcomm Augmented Reality Lecture Series aims to provide high level talks given by highly recognized speakers in the field of Augmented Reality. Speakers coming mainly from Academia, reporting either on recent results ore provide an overview on a specific topic. There will be 8-10 speakers per year. The program will be updated on a regular basis.

High Speed Matching and Tracking
o: 
o
SEO Level: 
h3
Header Style: 
h3 (Sub section level header)
Invert colors: 
Off
Content: 

This talk will explore the methodology behind high speed (computationally efficient) computer vision algorithms with reference to two recent publications: "rapidly constructed appearance models for tracking in augmented reality applications" and "Visual localization of a robot with an external RGBD sensor"

Prof. Tom Drummond
Department of Electrical and Computer Systems Engineering
Monash University
Clayton VIC 3800
AUSTRALIA
Date: 13-2-12
Time: 14:30 -15:45
Location: TU Vienna
Zemanek Lecture Room (Room Number: HHEG01)
1040 Vienna, Favoritenstraße 9-11,
Stiege III, ground floor, light green area

download the lecture presentation

The Potential of Light Fields — for imaging and beyond
o: 
o
SEO Level: 
h3
Header Style: 
h3 (Sub section level header)
Invert colors: 
Off
Content: 

Since the invention of the first camera, images always have been two-dimensional matrixes of pixels. Even though 3D scene points emit varying light rays in different directions, the lens and the sensor of cameras integrate them to a single pixel. By doing this for all imaged scene points, we end up with nothing else than a 2D image -- having lost most of the scene information. The same applies to many displays -- although in a dual way. Pixels of raster-displayed images emit (more or less) the same amount of light in all directions -- giving us nothing more than a 2D image.

What if the notion of images would change once and forever? What if instead of capturing, storing, processing and displaying only a single color per pixel, each pixel would consist of individual colors for each emitting direction? Images would no longer be two-dimensional matrices but four-dimensional ones (storing spatial information in two dimensions, and directional information in the other two dimensions). In electrical engineering, this four-dimensional structure is called photic field. In computer science, it is called light field.

Light fields have the potential to radically change everything that we relate to images -- from photography, over displays to image processing and analysis. While first light-fields display prototypes have already been introduced in scientific communities and first light-field cameras are already commercially available, many unsolved challenges remain in the processing of light fields. While common digital images store mega-bytes of data, corresponding light fields might require gigabytes.

In this talk, I will give an introduction to light-field imaging and processing, will summarize our current research activities along these lines, and outline the potential of light fields for AR/MR

Univ. Prof. Dr.-Ing. Oliver Bimber
Institute of Computer Graphics, Johannes Kepler University Linz, Austria
Date: 12-12-11
Time: 14:30 -15:45
School: Johannes Kepler University Linz, Austria
Location: TU Vienna
Zemanek Lecture Room (Room Number: HHEG01)
1040 Vienna, Favoritenstraße 9-11,
Stiege III, ground floor, light green area
download the lecture presentation
Computational 3D Photography: Extracting Shape, Motion and Appearance from Images
o: 
o
SEO Level: 
h3
Header Style: 
h3 (Sub section level header)
Invert colors: 
Off
Content: 

One of the fundamental problems of computer vision is to extract 3D shape and motion from images. This can be achieved when a scene or object is observed from different viewpoints or over a period of time. There is a wide range of applications, ranging from digitizing cultural heritage to vision-based autonomous robot navigation. This talk will present several approaches to solve this problem. First, we’ll discuss techniques for 3D shape recovery for static objects and scenes. One particular case is the 3D mapping and localization in large environments from images, e.g. urban 3D reconstruction from vehicle-borne cameras or localization from cell-phone images. Next, we’ll shift our focus to modeling dynamic scenes, e.g. people who are moving around. In addition to explicitly 3D modeling an event, we'll consider the possibility to perform video-based rendering from casually captured videos.

Prof. Marc Pollefeys
ETH Zürich, Switzerland
Date: 29-11-11
Time: 14:30 -15:45
School: ETH Zürich, Switzerland
Location: TU Vienna
Informatikhörsaal (room number: DEU116), – Institutsgebäude,
1040 Vienna, Treitlstraße 3
Ground Floor
download the lecture presentation
Interaction Techniques for Mobile Devices
o: 
o
SEO Level: 
h3
Header Style: 
h3 (Sub section level header)
Invert colors: 
Off
Content: 

In this talk I would like to present our current work on sensor-based interaction techniques for mobile devices. I would like to focus two projects in particular. The first one investigates the usefulness of visual context in handheld augmented map interfaces. The second one shows interaction concepts and application ideas for pressure-sensitive two-sided multitouch interaction. Regarding handheld augmented map interfaces I am going to present our approach of augmenting large-scale paper maps with dynamic content using the magic lens metaphor. In an eye-tracking study we investigated the effectiveness of visual context beyond the mobile device display, by comparing a dynamic peephole interface (without visual context beyond the device display) to a magic lens interface (with video see-through augmentation of external visual context). Regarding pressure-sensitive multitouch input I am going to show a number of application possibilities for handheld pressure input, such as pressure-based fisheye views and 3D object manipulation. I'll also report a study on the effectiveness of different device poses and pressure mapping functions.

Prof. Dr. Michael Rohs
Date: 11-10-11
Time: 14:15 -15:45
School: Institute for Media Informatics, Ludwig-Maximilians-Universität München (LMU), Germany
Location: TU Vienna
Zemanek Lecture Room (Room Number: HHEG01)
1040 Vienna, Favoritenstraße 9-11, Stiege III, ground floor, light green area
download the lecture presentation
Reconstruction and recognition for realistic augmented reality
o: 
o
SEO Level: 
h3
Header Style: 
h3 (Sub section level header)
Invert colors: 
Off
Reconstruction and recognition for realistic augmented reality
Content: 

Augmented reality involves the rendering of synthetic content into live video. The believable augmentation of reality requires that synthetic content interacts realistically with the real objects visible in this video. This means that real objects should occlude synthetic content which is at a greater distance, that synthetic labels should appear to adhere to real objects, and that synthetic objects should appear to bounce off the real environment where appropriate. In order to achieve these results the AR system needs to know what objects are visible, where they are relative to the camera, and what their shape is. This talk presents a range of approaches to this problem based on analysis of the incoming video stream, and particularly focusing on online reconstruction and recognition.

Prof. Anton van den Hengel
Australian Centre for Visual Technologies (ACVT), University of Adelaide
Date: 07-07-11
Time: 14:15 -15:45
School: Australian Centre for Visual Technologies (ACVT), University of Adelaide
Location: TU Vienna
1040 Wien, Karlsplatz 13
Hauptgebäude HS 7, Ground Floor, Stiege VII
download the lecture presentation
Ubiquitous Augmented Reality in AR-ready Environments
o: 
o
SEO Level: 
h3
Header Style: 
h3 (Sub section level header)
Invert colors: 
Off
Ubiquitous Augmented Reality in AR-ready Environments
Content: 

In this talk, I will present some of our recent work as well as our vision towards providing ubiquitous Augmented Reality services in AR-ready environments. I will elaborate on the concepts of ubiquitous tracking, ubiquitous information presentation and ubiquitous manipulation leading to the vision that users will use AR as one of their means to experience and manipulate a mixed physical and virtual reality. I will report on some observations we made when we tried these concepts in real applications in which users need to keep a keen eye on primary tasks in their real environment while also using/exploring an associated virtual information space.

Prof. Gudrun Klinker Ph.D
Technische Universität München, Fachgebiet Augmented Reality (FAR)
Date: 30-05-11
Time: 14:15 -15:45
School: Technische Universität München, Fachgebiet Augmented Reality (FAR)
Location: TU Vienna
1040 Wien, Karlsplatz 13
Hauptgebäude HS 7, Ground Floor, Stiege VII
download the lecture presentation
Real-Time Monocular SLAM
o: 
o
SEO Level: 
h3
Header Style: 
h3 (Sub section level header)
Invert colors: 
Off
Real-Time Monocular SLAM
Content: 

Recent advances in probabilistic Simultaneous Localisation and Mapping (SLAM) algorithms, together with modern computer power, have made it possible to create practical systems able to perform real-time estimation of the motion of a single camera in 3D purely from the image stream it acquires. This is of interest in robotics, but also in other fields like wearable computing and augmented reality. I will review my work on visual SLAM over the past few years, and present recent work which is now turning towards not just estimating camera motion for very rapid or large scale motion, but also recovering dense scene models and mosaics in real-time.

Dr. Andrew Davison
Imperial College London
Date: 29-03-11
Time: 14:15 -15:45
School: Imperial College London
Location: TU Vienna
1040 Wien, Wiedner Hauptstraße 8-10
Freihaus HS1, Tower C (red), 1. Flo
download the lecture presentation
Computer Vision for Augmented Reality
o: 
o
SEO Level: 
h3
Header Style: 
h3 (Sub section level header)
Invert colors: 
Off
Computer Vision for Augmented Reality
Content: 
Vincent Lepetit
Senior Researcher at the Computer Vision Laboratory, EPFL
Date: 22-02-11
Time: 14:15-15:45
Format: 1 hour talk + 30 minutes discussion
School: The University is École Polytechnique Fédérale de Lausanne (EPFL), Switzerland
Location: Seminarroom Zemanek TU Vienna
1040 Wien, Favoritenstraße 9-11, Stiege III,
ground floor, light green area
download the lecture presentation
Content: 
Program
Committee: 		Michael Gervautz - Qualcomm Austria Research Center
Oliver Bimber – Johannes Kepler University Linz
Eduard Gröller – Vienna University of Technology
Hannes Kaufmann – Vienna University of Technology
Walter Kropatsch – Vienna University of Technology
Gerhard Reitmayr – Graz University of Technology
Dieter Schmalstieg – Graz University of Technology
Werner Purgathofer – Vienna University of Technology
Sponsors