Uwe Schmidt

Uwe Schmidt

TU Darmstadt
Graphisch-Interaktive Systeme
Fraunhoferstr. 5
64283 Darmstadt, Germany
Office: S3|05-316
Phone: +49-6151-155 629
Fax: +49-6151-155 669
E-Mail: uwe.schmidt AT gris.tu-darmstadt DOT de

I am a PhD student at TU Darmstadt, affiliated with the GRIS group and supervised by Stefan Roth. My research interests are in Machine Learning and Computer Vision. Here's my CV and Google scholar profile.

Publications

Uwe Schmidt and Stefan Roth. Shrinkage Fields for Effective Image Restoration. In Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, June 2014. Oral presentation.
PaperSupplemental materialSlidesConference videoTeaser videoMATLAB code (GitHub)

Uwe Schmidt, Carsten Rother, Sebastian Nowozin, Jeremy Jancsary, and Stefan Roth. Discriminative Non-blind Deblurring. In Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, June 2013. Oral presentation. Best Student Paper Award.
PaperSlidesPosterC++ code

Thorsten Franzel, Uwe Schmidt, and Stefan Roth. Object Detection in Multi-View X-Ray Images. In Joint Pattern Recognition Symposium (34th DAGM, 36th OAGM), Graz, Austria, August 2012. Oral presentation.
Paper

Uwe Schmidt and Stefan Roth. Learning Rotation-Aware Features: From Invariant Priors to Equivariant Descriptors. In Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Providence, Rhode Island, June 2012. Oral presentation.
PaperSupplemental materialSlidesConference videoMATLAB code

Uwe Schmidt, Kevin Schelten, and Stefan Roth. Bayesian Deblurring with Integrated Noise Estimation. In Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, Colorado, June 2011.
PaperPosterMATLAB code

Uwe Schmidt, Qi Gao, and Stefan Roth. A Generative Perspective on MRFs in Low-Level Vision. In Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, California, June 2010. Oral presentation.
PaperSupplemental materialSlidesPosterConference videoMATLAB code

Jussi Kangasharju, Uwe Schmidt, Dirk Bradler, and Julian Schröder-Bernhardi. ChunkSim: Simulating Peer-to-Peer Content Distribution. In Communications and Networking Simulation Symposium, 2007.

Master’s Thesis

Learning and Evaluating Markov Random Fields for Natural Images. Supervisor: Stefan Roth
Thesis

Copyright Notice

All materials are presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors and other holders (publishers). These works may not be reposted without the explicit permission of the copyright holder.