Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Janai, Joel"'
Monocular 3D lane detection has become a fundamental problem in the context of autonomous driving, which comprises the tasks of finding the road surface and locating lane markings. One major challenge lies in a flexible but robust line representation
Externí odkaz:
http://arxiv.org/abs/2406.08381
Motion blurry images challenge many computer vision algorithms, e.g, feature detection, motion estimation, or object recognition. Deep convolutional neural networks are state-of-the-art for image deblurring. However, obtaining training data with corr
Externí odkaz:
http://arxiv.org/abs/2002.04070
Deep neural nets achieve state-of-the-art performance on the problem of optical flow estimation. Since optical flow is used in several safety-critical applications like self-driving cars, it is important to gain insights into the robustness of those
Externí odkaz:
http://arxiv.org/abs/1910.10053
Recent years have witnessed enormous progress in AI-related fields such as computer vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it becomes increasingly difficult to stay up-to-date or enter the field as a beg
Externí odkaz:
http://arxiv.org/abs/1704.05519
Autor:
Janai, Joel
Tiefe neuronale Netze ermöglichen das Erlernen von komplexeren hierarchischen Repräsentationen und machen somit das Ende-zu-Ende Lernen des optischen Flusses attraktiv. Jedoch erfordert das Trainieren solcher Modelle große Datensätzen und die Erz
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______707::46aef9e51311777b030fd73868b593c7
https://hdl.handle.net/10900/103400
https://hdl.handle.net/10900/103400
Publikováno v:
Foundations & Trends in Computer Graphics & Vision; 2020, Vol. 12 Issue 1-3, p1-308, 308p
