Multi-Scale Neural Network With Dilated Convolutions for Image Deblurring
Authors:
Open Access
- 16 March 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 53942-53952
Abstract
In image deblurring, information from the regions where the blur was propagated is needed for effective deblurring. For example, large blurs, such as those caused by fast-moving objects leaving a trail of afterimages, need spatial context from a large region, while small blurs, such as those caused by slight camera shake, need spatial context from a smaller scope. In this paper, we used multi-scale features to provide the spatial dependencies needed to deblur non-uniform blurs. Compared to previous works, we efficiently extract multi-scale features using two approaches: (1) coarse-to-fine scheme that can extract multi-scale features by applying the network to different scales of the images, and (2) dilated convolutions that can extract multi-scale features by using different dilation rates. Combining both methods has a multiplicative effect since multi-scale features from dilated convolutions are extracted from the input images at different scales (i.e. coarse-to-fine scheme). Furthermore, we optimized our network architecture by using parallel convolutions to decrease the execution time of the deblurring process. We show that our proposed method has better results than state-of-the-art methods in terms of image quality and execution time.Keywords
Funding Information
- Ministry of Science and Technology, Taiwan (MOST108-2218-E-011-026, MOST108-2221-E-011-116, MOST108-2622-E-011-016-CC3)
This publication has 21 references indexed in Scilit:
- Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring2017
- Deep Residual Learning for Image Recognition2016
- A Comparative Study for Single Image Blind Deblurring2016
- Blind Image Deblurring Using Dark Channel Prior2016
- Learning to DeblurIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Learning a convolutional neural network for non-uniform motion blur removal2015
- Segmentation-Free Dynamic Scene Deblurring2014
- Unnatural L0 Sparse Representation for Natural Image Deblurring2013
- Non-uniform Deblurring for Shaken ImagesInternational Journal of Computer Vision, 2011
- Single Image Deblurring Using Motion Density Functions2010