BaMBNet: A Blur-Aware Multi-Branch Network for Dual-Pixel Defocus Deblurring

Reducing the defocus blur that arises from the finite aperture size and short exposure time is an essential problem in computational photography. It is very challenging because the blur kernel is spatially varying and difficult to estimate by traditional methods. Due to its great breakthrough in low...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE/CAA journal of automatica sinica Jg. 9; H. 5; S. 878 - 892
Hauptverfasser:	Liang, Pengwei, Jiang, Junjun, Liu, Xianming, Ma, Jiayi
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway Chinese Association of Automation (CAA) 01.05.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE) School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001,China%Electronic Information School,Wuhan University,Wuhan 430072,China
Schlagworte:	Algorithms Artificial neural networks Blur kernel Complexity theory Convolutional neural networks convolutional neural networks (CNNs) Datasets defocus deblurring dual-pixel (DP) data Geometric constraints Image edge detection Kernels Machine learning meta-learning Neural networks Particle measurements Photography Pixels PSNR Signal to noise ratio convolutional neural networks (CNNs) dual-pixel (DP) data defocus deblurring meta-learning Blur kernel
ISSN:	2329-9266, 2329-9274
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!