A Deep Convolutional Encoder–Decoder–Restorer Architecture for Image Deblurring
Open Access
- 11 February 2024
- journal article
- research article
- Published by Springer Nature in Neural Processing Letters
- Vol. 56 (1) , 1-20
Abstract
The accuracy of many computer vision tasks is reduced by blurred images, so deblur is important. More details of the image can be captured by a common multi-stage network, but the computational complexity of this method is higher compared with a single-stage network. However, a single-stage network cannot capture multi-scale information well. To tackle the problem, a novel convolutional encoder–decoder–restorer architecture is proposed. In this architecture, a multi-scale input structure is used in the encoder. Improved supervised attention module is inserted into the encoder for enhanced feature acquisition. In decoder, information supplement block is proposed to fuse multi-scale features. Finally, the fused features are used for image recovery in the restorer. In order to optimise the model in multiple domains, the loss function is calculated separately in the spatial and frequency domains. Our method is compared with existing methods on the GOPRO dataset. In addition, to verify the applications of our proposed method, we conduct experiments on the Real image dataset, the VOC2007 dataset and the LFW dataset. Experimental results show that our proposed method outperforms state-of-the-art deblurring methods and improves the accuracy of different vision tasks.Keywords
Funding Information
- National Natural Science Foundation of China (No. 62173285, No. 62103345)
- Fujian Provincial Natural Science Foundation of China (No. 2021J011181, No. 2020J02160)
- Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University (No. VRLAB2021C01)
- Xiamen Youth Innovation Fund Project (No. 3502Z20206072, No. 3502Z20206076)
This publication has 36 references indexed in Scilit:
- Learning a convolutional neural network for non-uniform motion blur removal2015
- FaceNet: A unified embedding for face recognition and clustering2015
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- Deblurring Shaken and Partially Saturated ImagesInternational Journal of Computer Vision, 2014
- Learning to Estimate and Remove Non-uniform Image Blur2013
- Bayesian Blind Deconvolution with General Sparse Image Priors2012
- Efficient marginal likelihood optimization in blind deconvolution2011
- Progressive inter-scale and intra-scale non-blind image deconvolutionACM Transactions on Graphics, 2008
- Massively parallel spatially variant maximum-likelihood restoration of Hubble Space Telescope imageryJournal of the Optical Society of America A, 1996
- Bayesian-Based Iterative Method of Image Restoration*Journal of the Optical Society of America, 1972