Home
Uni-Logo
 

Thomas Brox

Professor for Pattern Recognition and Image Processing
Head of the Computer Vision Group

Department of Computer Science
University of Freiburg
Germany

Office location:
Georges-Köhler-Allee, Building 052, room 01-29/30
79110 Freiburg

Contact and consultation: make an appointment

 Thomas Brox

Personal Contact Publications Curriculum Vitae
All Selected Journals Conferences

Selected Publications

Deep Learning
Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction   Paperpaper-multimodal-future-prediction.pdf
Osama Makansi, Eddy Ilg, Özgün Çiçek, Thomas Brox
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Anomaly Detection With Multiple-Hypotheses Predictions   Papernguyen_icml19.pdf
Tam Nguyen, Z. Lou, M. Klar, Thomas Brox
IEEE International Conference on Machine Learning (ICML), 2019
Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs   Paperpaper-ogn.pdf
Maxim Tatarchenko, Alexey Dosovitskiy, Thomas Brox
IEEE International Conference on Computer Vision (ICCV), 2017
Generating Images with Perceptual Similarity Metrics based on Deep Networks   Code/data
Alexey Dosovitskiy, Thomas Brox
Advances in Neural Information Processing Systems (NIPS), 2016
Learning to Generate Chairs, Tables and Cars with Convolutional Networks   PaperChairs_PAMI.pdf doi>
Alexey Dosovitskiy, J. Springenberg, Maxim Tatarchenko, Thomas Brox
IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4): 692-705, Apr 2017

Optical Flow and Disparity
What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?   Paperpaper-1801.06397.pdf doi> Project
Nikolaus Mayer, Eddy Ilg, Philipp Fischer, C. Hazirbas, D. Cremers, Alexey Dosovitskiy, Thomas Brox
International Journal of Computer Vision, 126(9): 942-960, 2018
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks   Paperpaper-FlowNet_2_0__CVPR_old_version.pdf doi>
Eddy Ilg, Nikolaus Mayer, Tonmoy Saikia, Margret Keuper, Alexey Dosovitskiy, Thomas Brox
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
FlowNet: Learning Optical Flow with Convolutional Networks   Paperflownet.pdf Code/data
Alexey Dosovitskiy, Philipp Fischer, Eddy Ilg, P. Häusser, C. Hazırbaş, V. Golkov, P. Smagt, D. Cremers, Thomas Brox
IEEE International Conference on Computer Vision (ICCV), 2015
Large displacement optical flow: descriptor matching in variational motion estimation   Paperbrox_tpami10_ldof.pdf doi> Code/data
Thomas Brox, J. Malik
IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(3): 500-513, 2011
High accuracy optical flow estimation based on a theory for warping   Paperbrox_eccv04_of.pdf Code/data
Thomas Brox, A. Bruhn, N. Papenberg, J. Weickert
European Conference on Computer Vision (ECCV), Springer, LNCS, Vol.3024: 25-36, May 2004

3D Vision
DeepTAM: Deep Tracking and Mapping   Paperpaper-deeptam.pdf Project
Huizhong Zhou, Benjamin Ummenhofer, Thomas Brox
European Conference on Computer Vision (ECCV), 2018
Learning to Estimate 3D Hand Pose from Single RGB Images   Paperpaper-HandPose-from-SingleImages.pdf Project
Christian Zimmermann, Thomas Brox
IEEE International Conference on Computer Vision (ICCV), 2017
DeMoN: Depth and Motion Network for Learning Monocular Stereo   doi> Project
Benjamin Ummenhofer, Huizhong Zhou, Jonas Uhrig, Nikolaus Mayer, Eddy Ilg, Alexey Dosovitskiy, Thomas Brox
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
Global, Dense Multiscale Reconstruction for a Billion Points   Paperummenhofer2017Global.pdf doi> Project
Benjamin Ummenhofer, Thomas Brox
International Journal of Computer Vision, 125(1-3): 82-94, 2017

Biomedical Image Analysis
U-Net – Deep Learning for Cell Counting, Detection, and Morphometry   Paperpaper-U-Net.pdf doi> Project
Thorsten Falk, Dominic Mai, Robert Bensch, Özgün Çiçek, Ahmed Abdulkadir, Yassine Marrakchi, Anton Böhm, J. Deubner, Z. Jäckel, K. Seiwald, A. Dovzhenko, O. Tietz, C. Dal Bosco, S. Walsh, D. Saltukoglu, T. Tay, M. Prinz, K. Palme, M. Simons, I. Diester, Thomas Brox, Olaf Ronneberger
Nature Methods, 16: 67-70, 2019
An objective comparison of cell-tracking algorithms   doi>
V. Ulman, M. Maška, K. Magnusson, Olaf Ronneberger, C. Haubold, N. Harder, P. Matula, P. Matula, D. Svoboda, M. Radojevic, I. Smal, K. Rohr, J. Jaldén, H. Blau, O. Dzyubachyk, B. Lelieveldt, P. Xiao, Y. Li, S. Cho, A. Dufour, J. Olivo-Marin, C. Reyes-Aldasoro, J. Solis-Lemus, Robert Bensch, Thomas Brox, J. Stegmaier, R. Mikut, S. Wolf, F. Hamprecht, T. Esteves, P. Quelhas, Ö. Demirel, L. Malmström, F. Jug, P. Tomancák, E. Meijering, A. Muñoz-Barrutia, M. Kozubek, C. Ortiz-de-Solor
Nature Methods, 14: 1141-1152, 2017
ViBE-Z: A Framework for 3D Virtual Colocalization Analysis in Zebrafish Larval Brains   doi>
Olaf Ronneberger, Kun Liu, M. Rath, D. Rueß, T. Mueller, Henrik Skibbe, Benjamin Drayer, Thorsten Schmidt, A. Filippi, R. Nitschke, Thomas Brox, Hans Burkhardt, W. Driever
Nature Methods, 9(7): 735-742, 2012
Deep Reinforcement Learning
Motion Perception in Reinforcement Learning with Dynamic Objects   Paperpaper-flowrl.pdf Project
Artemij Amiranashvili, A. Dosovitskiy, V. Koltun, Thomas Brox
Conference on Robot Learning (CoRL), 2018
TD or not TD: Analyzing the Role of Temporal Differencing in Deep Reinforcement Learning   Paperpaper-tdornottd.pdf Project
Artemij Amiranashvili, A. Dosovitskiy, V. Koltun, Thomas Brox
International Conference on Learning Representations (ICLR), 2018
Video Segmentation
Motion Trajectory Segmentation via Minimum Cost Multicuts   PapermotionSeg.pdf Code/data
Margret Keuper, B. Andres, Thomas Brox
IEEE International Conference on Computer Vision (ICCV), 2015
Segmentation of moving objects by long term video analysis   Paperpami_moseg.pdf doi> Code/data
Peter Ochs, J. Malik, Thomas Brox
IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(6): 1187 - 1200, Jun 2014