AIFNet: All-in-Focus Image Restoration Network Using a Light Field-Based Dataset

Defocus blur often degrades the performance of image understanding, such as object recognition and image segmentation. Restoring an all-in-focus image from its defocused version is highly beneficial to visual information processing and many photographic applications, despite being a severely ill-pos...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on computational imaging Jg. 7; S. 675 - 688
Hauptverfasser: Ruan, Lingyan, Chen, Bin, Li, Jizhou, Lam, Miu-Ling
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Apertures
Artificial neural networks
Cameras
Computer architecture
Data processing
Datasets
deep learning
defocus deblurring
Estimation
Ill posed problems
Image deblurring
Image edge detection
Image restoration
Image segmentation
Kernel
Lenses
light field
Object recognition
Performance degradation
Synthetic apertures
ISSN:2573-0436, 2333-9403
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Defocus blur often degrades the performance of image understanding, such as object recognition and image segmentation. Restoring an all-in-focus image from its defocused version is highly beneficial to visual information processing and many photographic applications, despite being a severely ill-posed problem. We propose a novel convolutional neural network architecture AIFNet for removing spatially-varying defocus blur from a single defocused image. We leverage light field synthetic aperture and refocusing techniques to generate a large set of realistic defocused and all-in-focus image pairs depicting a variety of natural scenes for network training. AIFNet consists of three modules: defocus map estimation, deblurring and domain adaptation. The effects and performance of various network components are extensively evaluated. We also compare our method with existing solutions using several publicly available datasets. Quantitative and qualitative evaluations demonstrate that AIFNet shows the state-of-the-art performance.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2573-0436
2333-9403
DOI:10.1109/TCI.2021.3092891