Contiguous Loss for Motion-Based, Non-Aligned Image Deblurring
In general dynamic scenes, blurring is the result of the motion of multiple objects, camera shaking or scene depth variations. As an inverse process, deblurring extracts a sharp video sequence from the information contained in one single blurry image—it is itself an ill-posed computer vision problem...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/13/4/630 |
_version_ | 1797538285164167168 |
---|---|
author | Wenjia Niu Kewen Xia Yongke Pan |
author_facet | Wenjia Niu Kewen Xia Yongke Pan |
author_sort | Wenjia Niu |
collection | DOAJ |
description | In general dynamic scenes, blurring is the result of the motion of multiple objects, camera shaking or scene depth variations. As an inverse process, deblurring extracts a sharp video sequence from the information contained in one single blurry image—it is itself an ill-posed computer vision problem. To reconstruct these sharp frames, traditional methods aim to build several convolutional neural networks (CNN) to generate different frames, resulting in expensive computation. To vanquish this problem, an innovative framework which can generate several sharp frames based on one CNN model is proposed. The motion-based image is put into our framework and the spatio-temporal information is encoded via several convolutional and pooling layers, and the output of our model is several sharp frames. Moreover, a blurry image does not have one-to-one correspondence with any sharp video sequence, since different video sequences can create similar blurry images, so neither the traditional pixel2pixel nor perceptual loss is suitable for focusing on non-aligned data. To alleviate this problem and model the blurring process, a novel contiguous blurry loss function is proposed which focuses on measuring the loss of non-aligned data. Experimental results show that the proposed model combined with the contiguous blurry loss can generate sharp video sequences efficiently and perform better than state-of-the-art methods. |
first_indexed | 2024-03-10T12:28:24Z |
format | Article |
id | doaj.art-d245b431ecb04ae5bf9134afcecff9f6 |
institution | Directory Open Access Journal |
issn | 2073-8994 |
language | English |
last_indexed | 2024-03-10T12:28:24Z |
publishDate | 2021-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Symmetry |
spelling | doaj.art-d245b431ecb04ae5bf9134afcecff9f62023-11-21T14:52:49ZengMDPI AGSymmetry2073-89942021-04-0113463010.3390/sym13040630Contiguous Loss for Motion-Based, Non-Aligned Image DeblurringWenjia Niu0Kewen Xia1Yongke Pan2School of Electronic and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaSchool of Electronic and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaSchool of Electronic and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaIn general dynamic scenes, blurring is the result of the motion of multiple objects, camera shaking or scene depth variations. As an inverse process, deblurring extracts a sharp video sequence from the information contained in one single blurry image—it is itself an ill-posed computer vision problem. To reconstruct these sharp frames, traditional methods aim to build several convolutional neural networks (CNN) to generate different frames, resulting in expensive computation. To vanquish this problem, an innovative framework which can generate several sharp frames based on one CNN model is proposed. The motion-based image is put into our framework and the spatio-temporal information is encoded via several convolutional and pooling layers, and the output of our model is several sharp frames. Moreover, a blurry image does not have one-to-one correspondence with any sharp video sequence, since different video sequences can create similar blurry images, so neither the traditional pixel2pixel nor perceptual loss is suitable for focusing on non-aligned data. To alleviate this problem and model the blurring process, a novel contiguous blurry loss function is proposed which focuses on measuring the loss of non-aligned data. Experimental results show that the proposed model combined with the contiguous blurry loss can generate sharp video sequences efficiently and perform better than state-of-the-art methods.https://www.mdpi.com/2073-8994/13/4/630motion based imageimage deblurringconventional neural networkscontiguous blurry lossspatio-temporal framework |
spellingShingle | Wenjia Niu Kewen Xia Yongke Pan Contiguous Loss for Motion-Based, Non-Aligned Image Deblurring Symmetry motion based image image deblurring conventional neural networks contiguous blurry loss spatio-temporal framework |
title | Contiguous Loss for Motion-Based, Non-Aligned Image Deblurring |
title_full | Contiguous Loss for Motion-Based, Non-Aligned Image Deblurring |
title_fullStr | Contiguous Loss for Motion-Based, Non-Aligned Image Deblurring |
title_full_unstemmed | Contiguous Loss for Motion-Based, Non-Aligned Image Deblurring |
title_short | Contiguous Loss for Motion-Based, Non-Aligned Image Deblurring |
title_sort | contiguous loss for motion based non aligned image deblurring |
topic | motion based image image deblurring conventional neural networks contiguous blurry loss spatio-temporal framework |
url | https://www.mdpi.com/2073-8994/13/4/630 |
work_keys_str_mv | AT wenjianiu contiguouslossformotionbasednonalignedimagedeblurring AT kewenxia contiguouslossformotionbasednonalignedimagedeblurring AT yongkepan contiguouslossformotionbasednonalignedimagedeblurring |