Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Mayer, Nikolaus"'
Autor:
Mayer, Nikolaus, Ilg, Eddy, Fischer, Philipp, Hazirbas, Caner, Cremers, Daniel, Dosovitskiy, Alexey, Brox, Thomas
The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations. As a result, the research challenge shifts from devising algorithms to cre
Externí odkaz:
http://arxiv.org/abs/1801.06397
Autor:
van Marrewijk, Bart M., Vroegindeweij, Bastiaan A., Gené-Mola, Jordi, Mencarelli, Angelo, Hemming, Jochen, Mayer, Nikolaus, Wenger, Maximilian, Kootstra, Gert
Publikováno v:
In Biosystems Engineering February 2022 214:11-27
Autor:
Ummenhofer, Benjamin, Zhou, Huizhong, Uhrig, Jonas, Mayer, Nikolaus, Ilg, Eddy, Dosovitskiy, Alexey, Brox, Thomas
In this paper we formulate structure from motion as a learning problem. We train a convolutional network end-to-end to compute depth and camera motion from successive, unconstrained image pairs. The architecture is composed of multiple stacked encode
Externí odkaz:
http://arxiv.org/abs/1612.02401
Autor:
Ilg, Eddy, Mayer, Nikolaus, Saikia, Tonmoy, Keuper, Margret, Dosovitskiy, Alexey, Brox, Thomas
The FlowNet demonstrated that optical flow estimation can be cast as a learning problem. However, the state of the art with regard to the quality of the flow has still been defined by traditional methods. Particularly on small displacements and real-
Externí odkaz:
http://arxiv.org/abs/1612.01925
Autor:
Mayer, Nikolaus, Ilg, Eddy, Häusser, Philip, Fischer, Philipp, Cremers, Daniel, Dosovitskiy, Alexey, Brox, Thomas
Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated dataset. T
Externí odkaz:
http://arxiv.org/abs/1512.02134
Autor:
Marhofer, Peter, Faryniak, Barbara, Oismüller, Christiane, Koinig, Herbert, Kapral, Stefan, Mayer, Nikolaus
Publikováno v:
In Regional Anesthesia and Pain Medicine 1999 24(5):399-404
Autor:
Mayer, Nikolaus, Ilg, Eddy, Hausser, Philip, Fischer, Philipp, Cremers, Daniel, Dosovitskiy, Alexey, Brox, Thomas
Publikováno v:
2016 IEEE Conference on Computer Vision & Pattern Recognition (CVPR); 2016, p4040-4048, 9p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Canadian Journal of Anaesthesia / Journal Canadien d'Anesthésie; Jun2006, Vol. 53 Issue 6, p595-601, 7p