TY - GEN
T1 - Deep Image Deblurring Using Local Correlation Block
AU - Su, Wei
AU - Yuan, Yuan
AU - Wang, Qi
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/5
Y1 - 2020/5
N2 - Dynamic scene deblurring is a challenging problem due to the various blurry source. Many deep learning based approaches try to train end-to-end deblurring networks, and achieve successful performance. However, the architectures and parameters of these methods are unchanged after training, so they need deeper network architectures and more parameters to adapt different blurry images, which increase the computational complexity. In this paper, we propose a local correlation block (LCBlock), which can adjust the weights of features adaptively according to the blurry inputs. And we use it to construct a dynamic scene deblurring network named LCNet. Experimental results show that the proposed LC-Net produces compariable performance with shorter running time and smaller network size, compared to state-of-the-art learning-based methods.
AB - Dynamic scene deblurring is a challenging problem due to the various blurry source. Many deep learning based approaches try to train end-to-end deblurring networks, and achieve successful performance. However, the architectures and parameters of these methods are unchanged after training, so they need deeper network architectures and more parameters to adapt different blurry images, which increase the computational complexity. In this paper, we propose a local correlation block (LCBlock), which can adjust the weights of features adaptively according to the blurry inputs. And we use it to construct a dynamic scene deblurring network named LCNet. Experimental results show that the proposed LC-Net produces compariable performance with shorter running time and smaller network size, compared to state-of-the-art learning-based methods.
KW - Dynamic scene deblurring
KW - Encoder-Decoder network
KW - Local correlation block
UR - http://www.scopus.com/inward/record.url?scp=85089245003&partnerID=8YFLogxK
U2 - 10.1109/ICASSP40776.2020.9053350
DO - 10.1109/ICASSP40776.2020.9053350
M3 - 会议稿件
AN - SCOPUS:85089245003
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 1908
EP - 1912
BT - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
Y2 - 4 May 2020 through 8 May 2020
ER -