| Image guided depth upsampling using anisotropic total generalized variation D Ferstl, C Reinbacher, R Ranftl, M Rüther, H Bischof Proceedings of the IEEE International Conference on Computer Vision, 993-1000, 2013 | 342 | 2013 |
| Pushing the limits of stereo using variational stereo estimation R Ranftl, S Gehrig, T Pock, H Bischof 2012 IEEE Intelligent Vehicles Symposium, 401-407, 2012 | 120 | 2012 |
| Non-local total generalized variation for optical flow estimation R Ranftl, K Bredies, T Pock European Conference on Computer Vision, 439-454, 2014 | 104 | 2014 |
| Dense Monocular Depth Estimation in Complex Dynamic Scenes R Ranftl, V Vineet, Q Chen, V Koltun CVPR, 2016 | 78 | 2016 |
| Insights into analysis operator learning: From patch-based sparse models to higher order MRFs Y Chen, R Ranftl, T Pock IEEE Transactions on Image Processing 23 (3), 1060-1072, 2014 | 78 | 2014 |
| Accurate optical flow via direct cost volume processing J Xu, R Ranftl, V Koltun Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2017 | 77 | 2017 |
| Revisiting loss-specific training of filter-based MRFs for image restoration Y Chen, T Pock, R Ranftl, H Bischof German Conference on Pattern Recognition, 271-281, 2013 | 55 | 2013 |
| Variational shape from light field S Heber, R Ranftl, T Pock International Workshop on Energy Minimization Methods in Computer Vision and …, 2013 | 41 | 2013 |
| Bilevel optimization with nonsmooth lower level problems P Ochs, R Ranftl, T Brox, T Pock International Conference on Scale Space and Variational Methods in Computer …, 2015 | 34 | 2015 |
| A bi-level view of inpainting-based image compression Y Chen, R Ranftl, T Pock arXiv preprint arXiv:1401.4112, 2014 | 31 | 2014 |
| A Deep Variational Model for Image Segmentation R Ranftl, T Pock | 28 | 2014 |
| Deep drone racing: Learning agile flight in dynamic environments E Kaufmann, A Loquercio, R Ranftl, A Dosovitskiy, V Koltun, ... arXiv preprint arXiv:1806.08548, 2018 | 26 | 2018 |
| Minimizing TGV-based variational models with non-convex data terms R Ranftl, T Pock, H Bischof International Conference on Scale Space and Variational Methods in Computer …, 2013 | 25 | 2013 |
| Deep fundamental matrix estimation R Ranftl, V Koltun Proceedings of the European Conference on Computer Vision (ECCV), 284-299, 2018 | 21 | 2018 |
| A higher-order MRF based variational model for multiplicative noise reduction Y Chen, W Feng, R Ranftl, H Qiao, T Pock IEEE signal processing letters 21 (11), 1370-1374, 2014 | 21 | 2014 |
| Techniques for gradient-based bilevel optimization with non-smooth lower level problems P Ochs, R Ranftl, T Brox, T Pock Journal of Mathematical Imaging and Vision 56 (2), 175-194, 2016 | 14 | 2016 |
| Beauty and the beast: Optimal methods meet learning for drone racing E Kaufmann, M Gehrig, P Foehn, R Ranftl, A Dosovitskiy, V Koltun, ... 2019 International Conference on Robotics and Automation (ICRA), 690-696, 2019 | 13 | 2019 |
| What Do Single-view 3D Reconstruction Networks Learn? M Tatarchenko, SR Richter, R Ranftl, Z Li, V Koltun, T Brox Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2019 | 10 | 2019 |
| Trajectory optimization with implicit hard contacts J Carius, R Ranftl, V Koltun, M Hutter IEEE Robotics and Automation Letters 3 (4), 3316-3323, 2018 | 9 | 2018 |
| Insights into analysis operator learning: A view from higher-order filter-based mrf model Y Chen, R Ranftl, T Pock IEEE Trans. Image Process 23 (3), 1060-1072, 2014 | 9 | 2014 |
Thomas PockProfessor of Computer Science, TU GrazBestätigte E-Mail-Adresse bei icg.tugraz.at
