Accurate and Fast Blur Detection Using a Pyramid M-Shaped Deep Neural Network

Accurate and Fast Blur Detection Using a Pyramid M-Shaped Deep Neural Network

Blur detection is aimed at estimating the probability of each pixel being blurred or non-blurred in an image affected by motion or defocus blur. This task has gained considerable attention due to its promising application fields in computer vision. Accurate differentiation of anomalous regions (incl...

Full description

Bibliographic Details
Main Authors: Xuewei Wang, Shulin Zhang, Xiao Liang, Hongjun Zhou, Jinjin Zheng, Mingzhai Sun
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Motion and defocus blur detection
M-shaped network
scale ambiguity
pyramid ensemble model
Online Access:https://ieeexplore.ieee.org/document/8755854/

Internet

https://ieeexplore.ieee.org/document/8755854/

Similar Items