Vision: reconstruct a model of the world that permits online level-of-detail extraction. The core idea in this project is to interactively integrate sensed 3D data of varying sources and scales into a topologically clean surface. Our varying-scale model then permits online extraction of seamless levels of detail for rendering with minimal aliasing and popping artifacts. For this, we develop new topological guarantees to minimize the needed geometry. By exploiting the inherent redundancy of 2D surfaces in 3D, we design a fast way to robustly detect changes that let users better control the scan acquisition process. The topologically clean output surface and the change detection permit easy processing of the geometry for common use cases such as autonomous navigation, environment learning, augmented reality displays of georeferenced semantic information. An example application is fusing and distributing scans from the built-in sensors of multiple autonomous vehicles (ground, air), for incidental map updating as well as guaranteed efficient collision detection and tracking changes for path planning.

Funding

  • WWTF Wiener Wissenschafts-, Forschungs- und Technologiefonds ICT19-009

Team

Research Areas

  • Uses concepts from applied mathematics and computer science to design efficient algorithms for the reconstruction, analysis, manipulation, simulation and transmission of complex 3D models. Example applications are collision detection, reconstruction, compression, occlusion-aware surface handling and improved sampling conditions.

Publications

10 Publications found:
Image Bib Reference Publication Type
2023
Michael Rubik
CycleSafely Acquire Data
[image]
Bachelor Thesis
2022
Diana MarinORCID iD, Stefan Ohrhallinger, Michael WimmerORCID iD
SIGDT: 2D Curve Reconstruction
Computer Graphics Forum, 41(7):25-36, October 2022. [Paper] [Paper]
Journal Paper with Conference Talk
Ahmed El Agrod
Immersive Redesign
[thesis]
Bachelor Thesis
Stefan Ohrhallinger
Curve/Surface Reconstruction and Occlusion-enabled Applications, 2. May 2022, LiX Polytechnique, Saclay-Paris, France
Invited Talk
Diana MarinORCID iD, Stefan Ohrhallinger, Michael WimmerORCID iD
SIG-based Curve Reconstruction
Poster shown at Eurographics 2022 - 43rd Annual Conference of the European Association for Computer Graphics (25. April 2022-29. April 2022) In Eurographics 2022 - Posters .
[paper] [poster] [Paper]
Poster
Stefan Ohrhallinger, Amal Dev Parakkat, Jiju Peethambaran
Shape Reconstruction: From Theory to Practice
In Eurographics 2022 - Tutorials. April 2022.
[website]
Other Reviewed Publication
Thomas Steinschauer
Change Detection using the InfiniTAM framework
[bachelor thesis] [image]
Bachelor Thesis
Stefan Ohrhallinger, Amal Dev Parakkat, Jiju Peethambaran
ECCV 2022 Tutorial on Outline and Shape Reconstruction in 2D, 22-10-23-22-10-27, Tel Aviv
Invited Talk
2021
Stefan Ohrhallinger, Jiju Peethambaran, Amal Dev Parakkat, Tamal K Dey, Ramanathan Muthuganapathy
2D Points Curve Reconstruction Survey and Benchmark
Computer Graphics Forum, 1:611-632, March 2021. [paper] [Website]
Journal Paper with Conference Talk
Dennis Depner
3D Scan Integration
[paper] [source]
Bachelor Thesis
Download list as Bibtex, HTML (Advanced, Expert), JSON (with referenced objects), CSV, Permalink

Details

Project Leader

Start Date

End Date