Projektass. PhD
  • Scientist







ohrhallinger [at]



  • Senior Researcher, located in room HD 05 23, see map

Acquired Projects

2020 - 2026: Modeling the World at Scale (WWTF): €578k.
2020 - 2022: Participation in Photogrammetry made easy (IPA): €50k.
2019 - 2023: Superhumans: Walking Through Walls (FWF): €333k.
2016 - 2020: Real-Time Shape Acquisition with Sensor-Specific Precision (FWF): €318k.
2014 - 2016: Participation and co-organization in Harvest4D (EU, 7th Framework Programme).

Job Offers

  • Please contact me if you are interested in one of my topics (see below, paid up to €1000, contact me for details) or want to propose your own



  • Point-based Graphics
  • Surface Reconstruction
  • Mesh Resampling
  • Virtual/Augmented Reality
  • Using Depth from Sensors


Stefan Ohrhallinger is a senior researcher at the Institute of Visual Computing and Human-Centered Technology at TU Wien, Austria. He graduated with a Master of Business Informatics (Wirtschaftsinformatik) in 1997 from Johannes-Kepler University Linz, Austria. From 1990 to 2009 he developed software for various projects in Austria, the United States and Canada, e.g. as the software architect for the Zentrales Melderegister (Central Population Register) for the Ministery of Interior, Austria.

In 2013 he obtained his PhD from Concordia University, Montréal, Canada. Since October 2012 he is a research associate at TU Wien, working mainly on surface reconstruction, geometry processing and point-based graphics. He has reviewed for major conferences and journals in Computer Graphics, including TOG, TVCG, SGP, CAG, EGPGV, GI, Sensors, and SIGGR PH, and served on the IPCs of GCH'18, Eurographics'21, '22, Pacific Graphics'22, '23, and SMI'24. He co-coordinated Eurographics'21 in Vienna.

Topics for Projects and Theses

Research Projects

Courses in the current semester


23 Publications found:
Image Bib Reference Publication Type
Stefan Ohrhallinger, Amal Dev Parakkat, Pooran Memari
Feature-Sized Sampling for Vector Line Art
In Proceedings of the 31th Pacific Conference on Computer Graphics and Applications, pages 1-2. October 2023.
[paper] [talk]
Conference Paper
Diana MarinORCID iD, Stefan Ohrhallinger, Michael WimmerORCID iD
Parameter-Free and Improved Connectivity for Point Clouds
Poster shown at Eurographics 2023 ( 8. May 2023-12. May 2023) In Eurographics 2023 - Posters , pages 5-6.
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
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]
Stefan Ohrhallinger, Amal Dev Parakkat, Jiju Peethambaran
Shape Reconstruction: From Theory to Practice
In Eurographics 2022 - Tutorials. April 2022.
Other Reviewed Publication
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
Mohamed Radwan, Stefan Ohrhallinger, Michael WimmerORCID iD
Fast occlusion-based point cloud exploration
The Visual Computer Journal, 37:2769-2781, September 2021. [paper]
Journal Paper with Conference Talk
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
Markus Schütz, Stefan Ohrhallinger, Michael WimmerORCID iD
Fast Out-of-Core Octree Generation for Massive Point Clouds
Computer Graphics Forum, 39(7):1-13, November 2020. [paper]
Journal Paper with Conference Talk
We present Points2Surf, a method to reconstruct an accurate implicit surface from a noisy point cloud. Unlike current data-driven surface reconstruction methods like DeepSDF and AtlasNet, it is patch-based, improves detail reconstruction, and unlike Screened Poisson Reconstruction (SPR), a learned prior of low-level patch shapes improves reconstruction accuracy. 
Note the quality of reconstructions, both geometric and topological, against the original surfaces. The ability of Points2Surf to generalize to new shapes makes it the first learning-based approach with significant generalization ability under both geometric and topological variations. Philipp ErlerORCID iD, Paul Guerrero, Stefan Ohrhallinger, Michael WimmerORCID iD, Niloy Mitra
Points2Surf: Learning Implicit Surfaces from Point Clouds
In Computer Vision -- ECCV 2020, pages 108-124. October 2020.
[points2surf_paper] [short video]
Conference Paper
Kurt Leimer, Andreas Winkler, Stefan Ohrhallinger, Przemyslaw Musialski
Pose to Seat: Automated design of body-supporting surfaces
Computer Aided Geometric Design, 79:1-1, April 2020. [image] [Paper] [paper]
Journal Paper (without talk)
Manifold curve fitted samples with highly varying noise Stefan Ohrhallinger, Michael WimmerORCID iD
FitConnect: Connecting Noisy 2D Samples by Fitted Neighborhoods
Computer Graphics Forum, 38(1):126-137, February 2019. [paper] [Replicability Source Code]
Journal Paper with Conference Talk
Stefan Ohrhallinger, Adam Celarek
X-Mas Card 2019
[image] [pdf]
X-Mas Card
Stefan Ohrhallinger, Michael WimmerORCID iD
StretchDenoise: Parametric Curve Reconstruction with Guarantees by Separating Connectivity from Residual Uncertainty of Samples
In Proceedings of Pacific Graphics 2018, pages 1-4. August 2018.
[image] [paper] [Extended version] [source]
Conference Paper
Occlusion-aware generation of a cutaway illustration. Mohamed Radwan, Stefan Ohrhallinger, Elmar Eisemann, Michael WimmerORCID iD
Cut and Paint: Occlusion-Aware Subset Selection for Surface Processing
In Proceedings of Graphics Interface 2017, pages 82-89. May 2017.
Conference Paper
Stefan Ohrhallinger, Scott A. Mitchell, Michael WimmerORCID iD
Curve Reconstruction with Many Fewer Samples
Computer Graphics Forum, 35(5):167-176, 2016. [paper] [slides] [Reproducibility Source Code]
Journal Paper with Conference Talk
Mohamed Radwan, Stefan Ohrhallinger, Michael WimmerORCID iD
Efficient Collision Detection While Rendering Dynamic Point Clouds
In Proceedings of the 2014 Graphics Interface Conference, pages 25-33. May 2014.
[paper] [slides]
Conference Paper
Stefan Ohrhallinger, Sudhir Mudur
An Efficient Algorithm for Determining an Aesthetic Shape Connecting Unorganised 2D Points
Computer Graphics Forum, 32(8):72-88, December 2013. [paper] [slides-ODP] [slides-PDF] [source code]
Journal Paper with Conference Talk
Stefan Ohrhallinger, Sudhir Mudur, Michael WimmerORCID iD
Minimizing Edge Length to Connect Sparsely Sampled Unorganized Point Sets
Computers & Graphics (Proceedings of Shape Modeling International 2013), 37(6):645-658, October 2013. [paper] [slides] [source and binaries]
Journal Paper with Conference Talk
2D and 3D Reconstruction Stefan Ohrhallinger
The Intrinsic Shape of Point Clouds
Supervisor: Sudhir Mudur
Duration: September 2006 — July 2012
3D Reconstruction Stefan Ohrhallinger, Sudhir Mudur
Minimising Longest Edge for Closed Surface Construction from Unorganised 3D Point Sets
Poster shown at Eurographics 2012 (Best Poster Award) (13. May 2012-18. May 2012) In Poster Proceedings , pages 25-26.
[paper] [poster]
Stefan Ohrhallinger, Sudhir Mudur
Interpolating an unorganized 2D point cloud with a single closed shape
Computer-Aided Design, 43(1):1629-1638, January 2011. [paper]
Journal Paper (without talk)
Download list as Bibtex, HTML (Advanced, Expert), JSON (with referenced objects), CSV, Permalink