TY - JOUR
T1 - LNNet : Lightweight Nested Network for motion deblurring
AU - GUO, Cai
AU - WANG, Qian
AU - DAI, Hong-Ning
AU - WANG, Hao
AU - LI, Ping
N1 - Publisher Copyright:
© 2022 Elsevier B.V.
PY - 2022/8
Y1 - 2022/8
N2 - Motion deblurring methods based on convolutional neural networks (CNN) have recently demonstrated their advantages over conventional methods. However, repetitions of scaling or slicing operations of these methods on the input images inevitably lead to spatial information loss. Meanwhile, some recent methods based on complex models inevitably bring a large model size and huge computing cost. It is still challenging to balance the deblurring performance and the cost. To this end, we propose a lightweight nested network (LNNet) for the motion-deblurring task. Our LNNet leverages several simple yet efficient sub-networks to process motion deblurring features at each stage. We design a nested connection, which is conducive to the model size reduction when connecting sub-networks so as to reuse deblurring information and facilitate deblurring information diversity. Meanwhile, we introduce the feature-fusion module to improve deblurring performance further. We perform extensive experiments on a workstation platform and an embedded mobile edge computing (MEC) platform to evaluate our LNNet as well as other existing methods. Extensive experimental results demonstrate that our LNNet achieves superior deblurring performance than state-of-the-art methods with a small model size within a short running time. Moreover, experimental results also show that our model is quite suitable for other embedded devices.
AB - Motion deblurring methods based on convolutional neural networks (CNN) have recently demonstrated their advantages over conventional methods. However, repetitions of scaling or slicing operations of these methods on the input images inevitably lead to spatial information loss. Meanwhile, some recent methods based on complex models inevitably bring a large model size and huge computing cost. It is still challenging to balance the deblurring performance and the cost. To this end, we propose a lightweight nested network (LNNet) for the motion-deblurring task. Our LNNet leverages several simple yet efficient sub-networks to process motion deblurring features at each stage. We design a nested connection, which is conducive to the model size reduction when connecting sub-networks so as to reuse deblurring information and facilitate deblurring information diversity. Meanwhile, we introduce the feature-fusion module to improve deblurring performance further. We perform extensive experiments on a workstation platform and an embedded mobile edge computing (MEC) platform to evaluate our LNNet as well as other existing methods. Extensive experimental results demonstrate that our LNNet achieves superior deblurring performance than state-of-the-art methods with a small model size within a short running time. Moreover, experimental results also show that our model is quite suitable for other embedded devices.
KW - Lightweight AI model
KW - Nested neural network
KW - Motion deblurring
KW - Mobile edge computing
UR - http://www.scopus.com/inward/record.url?scp=85131915834&partnerID=8YFLogxK
U2 - 10.1016/j.sysarc.2022.102584
DO - 10.1016/j.sysarc.2022.102584
M3 - Journal Article (refereed)
SN - 1383-7621
VL - 129
SP - 102584
JO - Journal of Systems Architecture
JF - Journal of Systems Architecture
M1 - 102584
ER -