<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Blind deblurring is a basic subject of computer vision and image processing. Motion image deblurring is divided into non blind deblurring and blind deblurring by whether to estimate the blur kernel. Blind deblurring is easy to produce motion artifacts because of the inaccurate estimation of the blur kernel. Non blind deblurring is the best choice for the current blurred image processing. The purpose of this paper is to further improve the definition of blurred image, restore the edge information of contour, and strengthen the repair of texture details. Based on the multi-scale convolution neural network, a multi-scale residual network is proposed, which can comprehensively extract image features, enhance image feature fusion, and constrain image generation by combining multi-scale loss function with anti loss function. The performance of the algorithm is evaluated by testing the peak signal to noise ratio (PSNR) structure similarity and restoration time of the generated image relative to the clear image. This algorithm improves the average PSNR on GOPRO testset, and reduces the recovery time accordingly. It can successfully recover the detail information lost due to motion blur. This algorithm has simple network structure, strong robustness and good restoration effect, and is suitable for dealing with various image degradation problems caused by motion blur.</p>
</abstract>

Blind deblurring is a basic subject of computer vision and image processing. Motion image deblurring is divided into non blind deblurring and blind deblurring by whether to estimate the blur kernel. Blind deblurring is easy to produce motion artifacts because of the inaccurate estimation of the blur kernel. Non blind deblurring is the best choice for the current blurred image processing. The purpose of this paper is to further improve the definition of blurred image, restore the edge information of contour, and strengthen the repair of texture details. Based on the multi-scale convolution neural network, a multi-scale residual network is proposed, which can comprehensively extract image features, enhance image feature fusion, and constrain image generation by combining multi-scale loss function with anti loss function. The performance of the algorithm is evaluated by testing the peak signal to noise ratio (PSNR) structure similarity and restoration time of the generated image relative to the clear image. This algorithm improves the average PSNR on GOPRO testset, and reduces the recovery time accordingly. It can successfully recover the detail information lost due to motion blur. This algorithm has simple network structure, strong robustness and good restoration effect, and is suitable for dealing with various image degradation problems caused by motion blur.

Motion Blur Image Restoration by Multi-Scale Residual Neural Network

International Journal of Advanced Network, Monitoring and Controls

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"Motion Blur Image Restoration by Multi-Scale Residual Neural Network"}

Blind deblurring is a basic subject of computer vision and image processing. Motion image deblurring is divided into non blind deblurring and blind deblurring...

#	Layer	Weight demension	stride
1	conv	32×32×5×5	2
2	conv	64×32×5×5	1
3	conv	64 × 64 × 5 × 5	2
4	conv	128×64×5×5	1
5	conv	128×128×5×5	4
6	conv	256×128×5×5	1
7	conv	256×256×5×5	4
8	conv	512×256×5×5	1
9	conv	512×512×4×4	4
10	fc	512×1 ×1 ×1	-
11	sigmoid		-

	PSNR	SSIM	Runtime
Nah et al.	26.64	0.9142	0.93s
ours	27.33	0.9324	0.72s

Motion Blur Image Restoration by Multi-Scale Residual Neural Network

Pubblicato online: 19 apr 2021

Pagine: 57 - 67

DOI: https://doi.org/10.21307/ijanmc-2021-009

Parole chiave
Image Deblur, Motion Deblur, Multi-Scale Residual Network, Deep Learning

© 2021 Xu Hexin et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

DISCRIMINATOR NETWORK STRUCTURE DIAGRAM

QUANTITATIVE COMPARISON OF FUZZY PERFORMANCE OF GOPRO DATASET

Motion Blur Image Restoration by Multi-Scale Residual Neural Network

Pubblicato online: 19 apr 2021

Pagine: 57 - 67

DOI: https://doi.org/10.21307/ijanmc-2021-009

Parole chiaveImage Deblur, Motion Deblur, Multi-Scale Residual Network, Deep Learning

© 2021 Xu Hexin et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

DISCRIMINATOR NETWORK STRUCTURE DIAGRAM

QUANTITATIVE COMPARISON OF FUZZY PERFORMANCE OF GOPRO DATASET

Parole chiave
Image Deblur, Motion Deblur, Multi-Scale Residual Network, Deep Learning