I’m a Research Engineer at Reactive Reality. Prior to that I did a PhD and Postdoc at Graz University of Technology supervised by Prof. Horst Bischof (at the Institute for Computer Graphics and Vision (ICG), now Institute of Visual Computing (IVC). This page is to keep links to publications and corresponding material (mainly from those affiliations) accessible from a single place.

Publications

Thesis icon showing a square academic cap and the text 'PhD Thesis' Learning without Labeling for 3D Hand Pose Estimation
Georg Poier
PhD Thesis, 2020.
[Thesis (TU Graz diglib)]
Qualitative hand pose estimation results of the method presented in the WACV 2019 paper MURAUER: Mapping Unlabeled Real Data for Label AUstERity
Georg Poier, Michael Opitz, David Schinagl and Horst Bischof
In Proc. WACV, 2019.
[Paper (arXiv)]      [Project]
Method sketch of the CVPR 2018 paper showing the view prediction and feedback propagation Learning Pose Specific Representations by Predicting Different Views
Georg Poier, David Schinagl and Horst Bischof
In Proc. CVPR, 2018. (selected for spotlight presentation)
[Paper]      [Project]
Being lazy at labelling for pose estimation
Georg Poier, David Schinagl and Horst Bischof
In Proc. AAPR, 2018. (featured presentation)
[Paper]
Samples from the 3D-Pitoti dataset presented in the CBMI 2017 paper, showing depth maps and corresponding segmentations of rock art The 3D-Pitoti Dataset: A Dataset for high-resolution 3D Surface Segmentation
Georg Poier, Markus Seidl, Matthias Zeppelzauer, Christian Reinbacher, Martin Schaich, Giovanna Bellandi, Alberto Marretta and Horst Bischof
In Proc. CBMI, 2017. (selected for oral presentation)
[Paper (ACM DL)]      [More detailed Tech. Report (pdf)]      [Slides]      [Project]
Part of the motivation figure from the CVWW 2017 paper showing a comparision of the methods' result with the ground truth Loss-Specific Training of Random Forests for Super-Resolution
Alexander Grabner, Georg Poier, Michael Opitz, Samuel Schulter and Peter M. Roth
In Proc. CVWW, 2017. (selected for oral presentation)
[Paper (pdf)]
Part of the motivation figure for the ECCV 2016 paper illustrating different relevant grid cells used training and a sample result including a largely occluded face Grid Loss: Detecting Occluded Faces
Michael Opitz, Georg Waltner, Georg Poier, Horst Possegger and Horst Bischof
In Proc. ECCV, 2016.
[Paper (arXiv)]
The 3D-PITOTI Project with a Focus on Multi-Scale 3D Reconstruction using Semi-Autonomous UAVs
Christian Mostegel, Georg Poier, Christian Reinbacher, Manuel Hofer, Friedrich Fraundorfer, Horst Bischof, Thomas Höll, Gert Holler and Axel Pinz
In Proc. OAGM-ARW Joint Workshop, 2016.
Interactive 3D Segmentation of Rock-Art by Enhanced Depth Maps and Gradient Preserving Regularization
Matthias Zeppelzauer, Georg Poier, Markus Seidl, Christian Reinbacher, Samuel Schulter, Christian Breiteneder and Horst Bischof
ACM Journal on Computing and Cultural Heritage, 9(4):19:1-19:30, 2016.
[Paper (ACM DL)]      [Project]
Illustration of the method presented in the BMVC 2015 paper showing images of the input, distribution of joint predictions, a result only considering the modes of the distributions and the result of the presented hybrid method Hybrid One-Shot 3D Hand Pose Estimation by Exploiting Uncertainties
Georg Poier, Konstantinos Roditakis, Samuel Schulter, Damien Michel, Horst Bischof and Antonis A. Argyros
In Proc. BMVC, 2015. (selected for oral presentation)
[Paper (arXiv)]      [Ext. Abstract]      [Slides]      [Project]
A screenshot of a segmentation tool, illustrating scribbles used during an interactive segmentation process Interactive Segmentation of Rock-Art in High-Resolution 3D Reconstructions
Matthias Zeppelzauer, Georg Poier, Markus Seidl, Christian Reinbacher, Christian Breiteneder, Horst Bischof and Samuel Schulter
In Proc. Digital Heritage, 2015. (selected for oral presentation; Best Paper Award)
[Paper]      [Project]      [Video (vimeo)]
Sample images from the ISR 2015 paper showing a prototype of the walker and anomaly/hazard detection and visualization Navigation Assistance and Guidance of Older Adults across Complex Public Spaces: the DALi Approach
Luigi Palopoli, Antonis A. Argyros, Josef A. Birchbauer, Alessio Colombo, Daniele Fontanelli, Axel Legay, Andrea Garulli, Antonello Giannitrapani, David Macii, Federico Moro, Payam Nazemzadeh, Pashalis Padeleris, Roberto Passerone, Georg Poier, Domenico Prattichizzo, Tizar Rizano, Luca Rizzon, Stefano Scheggi and Sean Sedwards
Intelligent Service Robotics 8(2):77-92, 2015.
[Paper (pdf)]      [Video (YouTube)]
Example results from the GCPR 2014 paper on different camera views and on the ground plane Hough Forests Revisited: An Approach to Multiple Instance Tracking from Multiple Cameras
Georg Poier, Samuel Schulter, Sabine Sternig, Peter M. Roth and Horst Bischof
In Proc. GCPR, 2014.
[Paper (pdf)]
Illustration of an input sample, two intermediate and the final text localization result of the method presented in the CVWW 2012 paper Text Localization in Unconstrained Images
Georg Poier, Jürgen Hatzl, Stefan Kluckner, Peter M. Roth and Horst Bischof
In Proc. CVWW, 2012.
[Paper (pdf)]
AVSS 2011 Demo Session: OUTLIER – Online Learning and Visualization of Unusual Events
Josef A. Birchbauer, Samuel Schulter, René Schuster, Georg Poier, Martin Winter, Peter Schallauer, Peter M. Roth and Horst Bischof
In Proc. AVSS, 2011.
[Ext. Abstract (IEEE Digital Library)]
Multi-Cue Learning and Visualization of Unusual Events
René Schuster, Samuel Schulter, Georg Poier, Martin Hirzer, Josef A. Birchbauer, Peter M. Roth, Horst Bischof, Martin Winter and Peter Schallauer
In Proc. ICCV Workshops, 2011.
[Paper (IEEE Xplore)]