A Lightweight Optical Flow CNN -Revisiting Data Fidelity and Regularization

Over four decades, the majority addresses the problem of optical flow estimation using variational methods. With the advance of machine learning, some recent works have attempted to address the problem using convolutional neural network (CNN) and have showed promising results. FlowNet2 [1] , the sta...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2021-08, Vol.43 (8), p.2555-2569
Hauptverfasser:	Hui, Tak-Wai, Tang, Xiaoou, Loy, Chen Change
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Adaptive optics and warping Artificial neural networks Convolutional codes Convolutional neural network cost volume deep learning Estimation Feature extraction Image warping Lightweight Machine learning Optical computing optical flow Optical flow (image analysis) Optical imaging Optical network units Outliers (statistics) Parameter estimation Regularization spatial pyramid Variational methods
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!