Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Patrick Knöbelreiter"'
Autor:
Anna Pukaluk, Anna-Sophie Wittgenstein, Gerd Leitinger, Dagmar Kolb, Dominique Pernitsch, Sarah A. Schneider, Patrick Knöbelreiter, Verena Horak, Kristian Bredies, Gerhard A. Holzapfel, Thomas Pock, Gerhard Sommer
Publikováno v:
Acta Biomaterialia. 141:300-314
An insight into changes of soft biological tissue ultrastructures under loading conditions is essential to understand their response to mechanical stimuli. Therefore, this study offers an approach to investigate the arrangement of collagen fibrils an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7bb88e23a63957b92581373640834552
https://doi.org/10.1016/j.actbio.2022.01.036
https://doi.org/10.1016/j.actbio.2022.01.036
Autor:
Patrick Knöbelreiter, Thomas Pock
Publikováno v:
International Journal of Computer Vision. 129:2565-2582
In this work, we propose a learning-based method to denoise and refine disparity maps of a given stereo method. The proposed variational network arises naturally from unrolling the iterates of a proximal gradient method applied to a variational energ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bed660974d88c0a00061eb77e9015fc8
https://doi.org/10.1007/s11263-021-01485-5
https://doi.org/10.1007/s11263-021-01485-5
Autor:
Robert Harb, Patrick Knöbelreiter
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030926588
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc5131935be09fc95b4ee0d5e99aeef2
https://doi.org/10.1007/978-3-030-92659-5_2
https://doi.org/10.1007/978-3-030-92659-5_2
Autor:
Christian Sormann, Friedrich Fraundorfer, Patrick Knöbelreiter, Alexander Shekhovtsov, Thomas Pock
Publikováno v:
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
CVPR
CVPR
It has been proposed by many researchers that combining deep neural networks with graphical models can create more efficient and better regularized composite models. The main difficulties in implementing this in practice are associated with a discrep
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be5e4b0aa5fd2f0541980c81fb340d84
Autor:
Friedrich Fraundorfer, Mattia Rossi, Thomas Pock, Andreas Kuhn, Patrick Knöbelreiter, Christian Sormann
Publikováno v:
3DV
In this work, we propose BP-MVSNet, a convolutional neural network (CNN)-based Multi-View-Stereo (MVS) method that uses a differentiable Conditional Random Field (CRF) layer for regularization. To this end, we propose to extend the BP layer and add w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9f72ceb8186a4d328530641e7016e24b
Publikováno v:
IGARSS
Recent developments established deep learning as an inevitable tool to boost the performance of dense matching and stereo estimation. On the downside, learning these networks requires a substantial amount of training data to be successful. Consequent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d7ee24a51a17124b8081bd66235e1b88
Autor:
Patrick Knöbelreiter, Thomas Pock
Publikováno v:
Pattern Recognition-41st DAGM German Conference, DAGM GCPR 2019, Dortmund, Germany, September 10–13, 2019, Proceedings
Lecture Notes in Computer Science ISBN: 9783030336752
GCPR
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Pattern Recognition
Lecture Notes in Computer Science ISBN: 9783030336752
GCPR
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Pattern Recognition
In this work, we propose a learning-based method to denoise and refine disparity maps of a given stereo method. The proposed variational network arises naturally from unrolling the iterates of a proximal gradient method applied to a variational energ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b63a26f44487c67ed4bd51b9412a5d5d
Autor:
Inka Brijacak, Ole Jakob Elle, Saeed Yahyanejad, Kyrre Glette, Patrick Knöbelreiter, Jim Torresen, Justinas Miseikis
Publikováno v:
AIM
Many works in collaborative robotics and human-robot interaction focuses on identifying and predicting human behaviour while considering the information about the robot itself as given. This can be the case when sensors and the robot are calibrated i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dee1749c6f4cadebca999f7eac473c01
http://hdl.handle.net/10852/67770
http://hdl.handle.net/10852/67770
Publikováno v:
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
CVPR
CVPR
We propose a novel and principled hybrid CNN+CRF model for stereo estimation. Our model allows to exploit the advantages of both, convolutional neural networks (CNNs) and conditional random fields (CRFs) in an unified approach. The CNNs compute expre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a969fbda8919024de1a8c37a56671b76
Publikováno v:
German Conference on Pattern Recognition
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Pattern Recognition
Lecture Notes in Computer Science ISBN: 9783319667089
GCPR
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Pattern Recognition
Lecture Notes in Computer Science ISBN: 9783319667089
GCPR
We propose a method for large displacement optical flow in which local matching costs are learned by a convolutional neural network (CNN) and a smoothness prior is imposed by a conditional random field (CRF). We tackle the computation- and memory-int
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4c2cfb903fb256fcfefa73dccaf6716a