Image Reflection Removal via Contextual Feature Fusion Pyramid and Task-Driven Regularization

In this paper, we propose a deep neural network for single image reflection removal. More specifically, we design a convolutional-grid module and take it as the building block of a feature fusion pyramid. The module leverages the combination effect of the grid topology to create a rich ensemble of r...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on circuits and systems for video technology 2022-02, Vol.32 (2), p.553-565
Hauptverfasser:	Li, Yuenan, Yan, Qixin, Zhang, Kuangshi, Xu, Haoyu
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial neural networks Computer architecture Feature extraction feature fusion Haze Image restoration Image segmentation Inference algorithms Modules multi-scale feature extraction Neural networks Reflection Reflection removal Regularization Semantic segmentation Semantics Separation Task analysis task-driven regularization Topology Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!