The core idea of the project is the enhancement of current state-of-the art navigation systems by visual information obtained from geo-referenced photographs. The aim is to establish a suite of tools together with algorithmic foundations that will be essential for any large scale image-based guidance project.

The main hypothesis of this project is that in the case of guidance, especially for pedestrians, the first-person perspective is intuitive and leads to natural orientation. In the project we will research how to generate first-person views on top of databases of simple ground-based photographs and classical overview maps. The ultimate idea is a system which allows the user to navigate through a city and even through interiors of buildings guided by the aid of annotated first-person views. Furthermore, the actual creation of the routes shall happen automatically on demand.

Examples of fields that can benefit from the proposed approach are tourism and general entertainment industries, city planners, local governments, simulation and security training, emergency management, civil protection and disaster control, as well as driving simulation to name but a few. Ultimately, the following scientific fields can profit from the proposed basic research results: computer graphics with image processing, computer vision, computational photography, pattern recognition, photogrammetry and remote sensing, cartography, computer aided design, geo-sciences and mobile-technology.

Funding

  • FWF P23237-N23

Research Areas

  • In this area, we focus on researching methods and algorithms that facilitate creation, representation, analysis and processing of 3D models.

Publications

24 Publications found:
Image Bib Reference Publication Type
2018
Michael Birsak
Discrete Optimization on Graphs and Grids for the Creation of Navigational and Artistic Imagery
Supervisor: Michael WimmerORCID iD
Duration: August 2012 — September 2018
PhD-Thesis
thumbnail Michael Birsak, Przemyslaw Musialski, Peter WonkaORCID iD, Michael WimmerORCID iD
Dynamic Path Exploration on Mobile Devices
IEEE Transactions on Visualization and Computer Graphics, 24(5):1784-1798, May 2018. [preprint]
Journal Paper (without talk)
2016
Overview Felix Kendlbacher
Introduction Of OpenStreetMap For The Automatic Generation Of Destination Maps
[thesis]
Bachelor Thesis
2015
image Christoph Kollmann
Depth of Field: Point Splatting on Per-Pixel Layers
[thesis]
Bachelor Thesis
Matthias Adorjan
The OpenSFM Database
[thesis]
Master Thesis
2014
image Lubin Fan, Przemyslaw Musialski, Ligang Liu, Peter WonkaORCID iD
Structure Completion for Facade Layouts
ACM Transactions on Graphics (ACM SIGGRAPH Asia 2014), 33(6):210:1-210:11, November 2014. [preprint-highres] [preprint]
Journal Paper with Conference Talk
Bernhard Steiner
Structure-aware shape manipulation
[poster] [thesis]
Master Thesis
image Victor Charpenay, Bernhard Steiner, Przemyslaw Musialski
Sampling Gabor Noise in the Spatial Domain
In Proceedings of the 30th Spring Conference on Computer Graphics - SCCG , pages 79-82. May 2014.
Conference Paper
image Michael Birsak, Przemyslaw Musialski, Peter WonkaORCID iD, Michael WimmerORCID iD
Automatic Generation of Tourist Brochures
Computer Graphics Forum (Proceedings of EUROGRAPHICS 2014), 33(2):449-458, April 2014. [preprint] [video]
Journal Paper with Conference Talk
2013
thumb Michael Birsak, Przemyslaw Musialski, Murat Arikan, Michael WimmerORCID iD
Seamless Texturing of Archaeological Data
In Digital Heritage International Congress (DigitalHeritage), 2013, pages 265-272 . October 2013.
[preprint]
Conference Paper
image Florian Schaukowitsch
Pano.NET - An interactive application for camera calibration, image stitching and projective operations
[Thesis]
Bachelor Thesis
image Georg Sperl
Procedural Textures for Architectural Models
[thesis]
Bachelor Thesis
overview Przemyslaw Musialski, Peter WonkaORCID iD, Daniel G. Aliaga, Michael WimmerORCID iD, Luc van Gool, Werner PurgathoferORCID iD
A Survey of Urban Reconstruction
Computer Graphics Forum, 32(6):146-177, September 2013. [draft]
Journal Paper (without talk)
ipm-pipeline scheme Przemyslaw Musialski, Michael WimmerORCID iD
Inverse-Procedural Methods for Urban Models
In Proceedings of Eurographics Workshop on Urban Data Modelling and Visualisation (UDMV 2013), pages 31-32. May 2013.
[paper-draft]
Conference Paper
Przemyslaw Musialski
Facade Reconstruction: An Interactive Image-Based Approach, 6. June 2013, Czech Technical University in Prague, Department of Computer Graphics and Interaction, Prague
Invited Talk
collage Victor Charpenay
Adaptive Garbor Noise Sampling
Student Project
image Christian Kößler
Feature-Adaptive Catmull-Clark Subdivision on the GPU
[thesis]
Bachelor Thesis
Image Stephan Zapotocky
Image-Based Modeling with Polyhedral Primitives
[image] [thesis]
Master Thesis
2012
Przemyslaw Musialski, Ming Cui, Jieping Ye, Anshuman Razdan, Peter WonkaORCID iD
A Framework for Interactive Image Color Editing
The Visual Computer, 29(11):1173-1186, November 2012. [draft]
Journal Paper (without talk)
Overview Przemyslaw Musialski, Peter WonkaORCID iD, Daniel G. Aliaga, Michael WimmerORCID iD, Luc van Gool, Werner PurgathoferORCID iD
A Survey of Urban Reconstruction
In EUROGRAPHICS 2012 State of the Art Reports, pages 1-28. May 2012.
[draft-hires] [draft-lowres]
Other Reviewed Publication
Przemyslaw Musialski, Michael WimmerORCID iD, Peter WonkaORCID iD
Interactive Coherence-Based Façade Modeling
Computer Graphics Forum (Proceedings of EUROGRAPHICS 2012), 31(2):661-670, May 2012. [draft-hires] [draft-lowres]
Journal Paper with Conference Talk
Ji Liu, Przemyslaw Musialski, Peter WonkaORCID iD, Jieping Ye
Tensor Completion for Estimating Missing Values in Visual Data
IEEE Transactions on Pattern Analysis & Machine Intelligence (PAMI), 35(1):208-220, January 2012.
Journal Paper (without talk)
Manpreet Kainth
Rendering of Urban Scenes
Student Project
Przemyslaw Musialski
Image-Based Approaches for Facade Reconstruction, 22. August 2012, RWTH Aachen, Germany
[slides]
Invited Talk
Download list as Bibtex, HTML (Advanced, Expert), JSON (with referenced objects), CSV, Permalink

Details

Project Leader

Start Date

End Date