Christian Unger

Dr. rer. nat. Christian Unger BMW Group Max-Diamand-Str. 5 D-80788 München tel: +49 89 382 79974 room: 01.41/088.0-2-302

Previous Work

Master's Thesis

Master's Thesis: Motion Compensation from Three Views: Applying the Trifocal Tensor to Angiographic Studies (supervison: Prof. Nassir Navab and Martin Groher)

Ph.D. Thesis

Ph.D. Thesis: Contributions to Stereo Vision can be downloaded here

Supervision: Dr. Slobodan Ilic and Dr. Eric Wahl

Abstract: This work presents camera-based methods for dense scene reconstruction. In the context of binocular stereo vision, we introduce a novel algorithm for the efficient computation of dense disparity maps and a precise stereo method that is based on simulated random walks. Further, we present a novel method for the robust and efficient reconstruction from multiple views using a probabilistic formulation. In practice, we use these methods to realize various automotive parking assistance functionalities including an automatic parking slot detection, a collision detector for the pivoting ranges of the doors, and novel image based rendering techniques for visualization. The influence of reconstruction quality on application reliability is showcased with extensive experiments.

Current Work

I am affiliated with the BMW Group and in my work I focus on driving autonomous vehicles with the power of computer vision. My former and current topics include:

• Binocular stereo and motion-stereo.
• Multi-view stereo and structure from motion.
• Semantic segmentation.
• Camera-based driving and parking assistance, for example Parking Assistance.
• Computer vision for autonomous vehicles.
• Computer vision in general.

Please contact me if you are interested in a Master's or PhD Thesis at BMW in the area of computer vision.

Research Projects

Stereo Vision Contact Person(s): Christian Unger In industrial collaboration with: BMW Group

Publications

2019
	J. Mayr, C. Giracoglu, C. Unger, F. Tombari Headlight Range Estimation for Autonomous Driving using Deep Neural Networks. IEEE Intelligent Vehicles Symposium (IV) 2019, Paris, France, June 2019, Pages 2251-2258
	R. Schuster, O. Wasenmüller, C. Unger, D. Stricker An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching. Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Safe Artificial Intelligence for Automated Driving Workshop (SAIAD-2019), June 2019, Long Beach, CA, United States.
	A. Frickenstein, C. Unger, W. Stechele Resource-Aware Optimization of DNNs for Embedded Applications. 16th Conference on Computer and Robot Vision (CRV), May 2019, Pages 17-24
	R. Schuster, O. Wasenmüller, C. Unger, G. Kuschk, D. Stricker SceneFlowFields++: Multi-frame Matching, Visibility Prediction, and Robust Interpolation for Scene Flow Estimation. arXiv preprint 2019
	R. Schuster, O. Wasenmüller, C. Unger, D. Stricker SDC - Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks. Conference on Computer Vision and Pattern Recognition (CVPR), June 2019, Long Beach, CA, United States
2018
	J. Mayr, C. Unger, F. Tombari Self-Supervised Learning of the Drivable Area for Autonomous Vehicles. IEEE International Conference on Intelligent Robots and Systems (IROS), October 2018, Pages 362-369 (bib)
2016
	V. Haltakov , C. Unger, S. Ilic Geodesic pixel neighborhoods for 2D and 3D scene understanding. Computer Vision and Image Understanding, Volume 148, July 2016, Pages 164-180 (bib)
2015
	V. Haltakov , J. Mayr, C. Unger, S. Ilic Semantic segmentation based traffic light detection at day and at night. German Conference on Pattern Recognition, 7.-10. October 2015 (bib)
2014
	V. Haltakov , C. Unger, S. Ilic Geodesic pixel neighborhoods for multi-class image segmentation British Machine Vision Conference, 1.-5. September 2014 (bib)
	C. Unger, S. Ilic A Stochastic Cost Function for Stereo Vision. British Machine Vision Conference, 1.-5. September 2014 (bib)
2013
	V. Haltakov , C. Unger, S. Ilic Framework for generation of synthetic ground truth data for driver assistance applications 35th German Conference on Pattern Recognition, 3.-6. September 2013 (bib)
2012
	C. Unger, E. Wahl, P. Sturm, S. Ilic Stereo Fusion from Multiple Viewpoints Joint 34th DAGM and 36th OAGM Symposium, Graz, Austria, August 28-31, 2012 (bib)
2011
	C. Unger, E. Wahl, S. Ilic Parking assistance using dense motion-stereo Journal of Machine Vision and Applications, Special Issue, December 1st 2011 (bib)
	C. Unger, E. Wahl, S. Ilic Efficient Stereo Matching for Moving Cameras and Decalibrated Rigs Intelligent Vehicles (IV), 6 - 8 June, Baden-Baden, Germany 2011 (bib)
	C. Unger, E. Wahl, S. Ilic Efficient Stereo and Optical Flow with Robust Similarity Measures 33rd Annual Symposium of the German Association for Pattern Recognition, Frankfurt am Main, Germany, August 30th - September 2nd 2011 (bib)
2010
	E. Wahl, C. Unger, A. Zeller, D. Rossberg 3D-Environment Modeling as an Enabler for Autonomous Vehicles ATZ Automobiltechnische Zeitschrift, Ausgabe 02/2010. (bib)
2009
	C. Unger, S. Benhimane, E. Wahl, N. Navab Efficient Disparity Computation without Maximum Disparity for Real-Time Stereo Vision British Machine Vision Conference (BMVC), London (UK), September 7-10, 2009 (bib)
2008
	C. Unger, M. Groher, N. Navab Image Based Rendering for Motion Compensation in Angiographic Roadmapping IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska (USA), June 24-26, 2008 (bib)

Other interests

I am also interested in

• mathematics (numerical analysis, algebra, elementary number theory)
• image processing
• 3D rendering and computer graphics
• programming in general (C++)
• music
• ...