Image Restoration Using Multi-Stage Progressive Encoder-Decoder Network With Attention and Transfer Learning (MSP-ATL)
Open Access
- 21 October 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1517-1525
Abstract
Convolutional neural network (CNN) is widely used in the field of image restoration, however, most existing CNN based image restoration methods only focus on a part of image restoration without considering the relationship between image deblurring, image de-raining and image denoising. In addition, training a neural network model for different image restoration tasks requires a large amount of training data, plenty of hardware overheads and a great deal of time. In order to reduce resource consumption and improve the generality of the model, this paper proposes an image restoration algorithm using multistage progressive encoder-decoder network with attention and transfer learning (MSP-ATL). First of all, we design a multi-stage progressive encoder-decoder network with attention mechanisms, which does not require down-sampling or fragmentation of the input, and can retain the overall information of the image. Secondly, following the idea of coarse-to-fine which is widely used in the field of image restoration, we propose a multistage progressive loss function to recover images from coarse to fine by cooperating with the multi-stage network structure. Finally, using transfer learning, the obtained deblurring model can be transferred to image de-raining and image denoising tasks with less training data and simple training process. Extensive experimental results on commonly used datasets demonstrate the efficiency and effectiveness of the proposed method.Keywords
Funding Information
- Shandong Provincial Natural Science Foundation (ZR2019BF022)
- Natural Science Excellent Youth Foundation of Shandong Province (ZR2021YQ45)
- Youth Innovation Science and Technology Team Foundation of Shandong Higher School (2021KJ031)
- Taishan Scholars Program of Shandong Province (tsqn201909109)
- National Natural Science Foundation of China (62001272)
This publication has 51 references indexed in Scilit:
- Learning a convolutional neural network for non-uniform motion blur removal2015
- The Noise Clinic: a Blind Image Denoising AlgorithmImage Processing On Line, 2015
- Weighted Nuclear Norm Minimization with Application to Image Denoising2014
- Unnatural L0 Sparse Representation for Natural Image Deblurring2013
- Single-Image-Based Rain and Snow Removal Using Multi-guided Filter2013
- Context-Aware Single Image Rain Removal2012
- Image denoising: Can plain neural networks compete with BM3D?2012
- Fields of ExpertsInternational Journal of Computer Vision, 2009
- Image Denoising by Sparse 3-D Transform-Domain Collaborative FilteringIEEE Transactions on Image Processing, 2007
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse RepresentationIEEE Transactions on Signal Processing, 2006