Iterative multi‐scale residual network for deblurring
Authors:
Open Access
- 18 January 2021
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 15 (8) , 1583-1595
Abstract
In dynamic scene deblurring, recent neural network–based methods have been very successful. But with the improvement of deep deblurring performance, network structure and learning become more complicated. Compared with large‐scale network parameters and complex network structures, an iterative multi‐scale residual network to achieve a more effective parameter sharing scheme is proposed. In each iterative unit, fast multi‐scale residual blocks to replace superimposed convolutional layers or classic residual blocks are used. On the basis of preventing model overfitting, the receptive field of the network is increased. At the same time, the gated recurrent unit is introduced to connect modules of different stages. The model does not rely on the estimation of the blur kernel and directly generates sharp images in an end‐to‐end manner. The experimental structure on the benchmark dataset and real‐world images showed that this method has better quality than the existing methods in terms of large‐scale blur and subjective perception effects, both in quantitative and qualitative terms.Keywords
Funding Information
- National Natural Science Foundation of China (61772319, 62002200, 61976125, 61976124)
This publication has 36 references indexed in Scilit:
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- Recording and Playback of Camera Shake: Benchmarking Blind Deconvolution with a Real-World Database2012
- Bayesian Blind Deconvolution with General Sparse Image Priors2012
- Blur-Kernel Estimation from Spectral Irregularities2012
- Non-uniform Deblurring for Shaken ImagesInternational Journal of Computer Vision, 2011
- Two-Phase Kernel Estimation for Robust Motion Deblurring2010
- High-quality motion deblurring from a single imageACM Transactions on Graphics, 2008
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Total variation blind deconvolutionIEEE Transactions on Image Processing, 1998
- Long Short-Term MemoryNeural Computation, 1997