TY - GEN
T1 - Attention-based adaptive selection of operations for image restoration in the presence of unknown combined distortions
AU - Suganuma, Masanori
AU - Liu, Xing
AU - Okatani, Takayuki
N1 - Funding Information:
This work was partly supported by JSPS KAKENHI Grant Number JP15H05919 and JST CREST Grant Number JPMJCR14D1.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - Many studies have been conducted so far on image restoration, the problem of restoring a clean image from its distorted version. There are many different types of distortion affecting image quality. Previous studies have focused on single types of distortion, proposing methods for removing them. However, image quality degrades due to multiple factors in the real world. Thus, depending on applications, e.g., vision for autonomous cars or surveillance cameras, we need to be able to deal with multiple combined distortions with unknown mixture ratios. For this purpose, we propose a simple yet effective layer architecture of neural networks. It performs multiple operations in parallel, which are weighted by an attention mechanism to enable selection of proper operations depending on the input. The layer can be stacked to form a deep network, which is differentiable and thus can be trained in an end-to-end fashion by gradient descent. The experimental results show that the proposed method works better than previous methods by a good margin on tasks of restoring images with multiple combined distortions.
AB - Many studies have been conducted so far on image restoration, the problem of restoring a clean image from its distorted version. There are many different types of distortion affecting image quality. Previous studies have focused on single types of distortion, proposing methods for removing them. However, image quality degrades due to multiple factors in the real world. Thus, depending on applications, e.g., vision for autonomous cars or surveillance cameras, we need to be able to deal with multiple combined distortions with unknown mixture ratios. For this purpose, we propose a simple yet effective layer architecture of neural networks. It performs multiple operations in parallel, which are weighted by an attention mechanism to enable selection of proper operations depending on the input. The layer can be stacked to form a deep network, which is differentiable and thus can be trained in an end-to-end fashion by gradient descent. The experimental results show that the proposed method works better than previous methods by a good margin on tasks of restoring images with multiple combined distortions.
KW - Computational Photography
KW - Deep Learning
KW - Image and Video Synthesis
KW - Low-level Vision
KW - Vision Applications and Syst
UR - http://www.scopus.com/inward/record.url?scp=85078301543&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078301543&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2019.00925
DO - 10.1109/CVPR.2019.00925
M3 - Conference contribution
AN - SCOPUS:85078301543
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 9031
EP - 9040
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PB - IEEE Computer Society
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Y2 - 16 June 2019 through 20 June 2019
ER -