Image deblurring based on lightweight multi-information fusion network

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Yanni, Liu, Yiming, Li, Qiang, Qi, Miao, Xu, Dahong, Kong, Jun, Wang, Jianzhong
Formato: Preprint
Publicado: 2021
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915756505038848
author Zhang, Yanni
Liu, Yiming
Li, Qiang
Qi, Miao
Xu, Dahong
Kong, Jun
Wang, Jianzhong
author_facet Zhang, Yanni
Liu, Yiming
Li, Qiang
Qi, Miao
Xu, Dahong
Kong, Jun
Wang, Jianzhong
contents Recently, deep learning based image deblurring has been well developed. However, exploiting the detailed image features in a deep learning framework always requires a mass of parameters, which inevitably makes the network suffer from high computational burden. To solve this problem, we propose a lightweight multiinformation fusion network (LMFN) for image deblurring. The proposed LMFN is designed as an encoder-decoder architecture. In the encoding stage, the image feature is reduced to various smallscale spaces for multi-scale information extraction and fusion without a large amount of information loss. Then, a distillation network is used in the decoding stage, which allows the network benefit the most from residual learning while remaining sufficiently lightweight. Meanwhile, an information fusion strategy between distillation modules and feature channels is also carried out by attention mechanism. Through fusing different information in the proposed approach, our network can achieve state-of-the-art image deblurring result with smaller number of parameters and outperforms existing methods in model complexity.
format Preprint
id arxiv_https___arxiv_org_abs_2101_05403
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Image deblurring based on lightweight multi-information fusion network
Zhang, Yanni
Liu, Yiming
Li, Qiang
Qi, Miao
Xu, Dahong
Kong, Jun
Wang, Jianzhong
Computer Vision and Pattern Recognition
Machine Learning
Recently, deep learning based image deblurring has been well developed. However, exploiting the detailed image features in a deep learning framework always requires a mass of parameters, which inevitably makes the network suffer from high computational burden. To solve this problem, we propose a lightweight multiinformation fusion network (LMFN) for image deblurring. The proposed LMFN is designed as an encoder-decoder architecture. In the encoding stage, the image feature is reduced to various smallscale spaces for multi-scale information extraction and fusion without a large amount of information loss. Then, a distillation network is used in the decoding stage, which allows the network benefit the most from residual learning while remaining sufficiently lightweight. Meanwhile, an information fusion strategy between distillation modules and feature channels is also carried out by attention mechanism. Through fusing different information in the proposed approach, our network can achieve state-of-the-art image deblurring result with smaller number of parameters and outperforms existing methods in model complexity.
title Image deblurring based on lightweight multi-information fusion network
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2101.05403