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

<p>By learning nonlinear mapping functions from low resolution (LR) images to high resolution (HR) images, deep neural networks show good performance in image super-resolution (SR). However, the existing SR approach has two potential limitations. First, learning the mapping function from LR to HR images is usually an ill-conditioned problem, since there exist an infinite number of HR images that can be down-sampled to the same LR image. Thus, the space of possible functions can be very large, making it difficult to find a good solution. Second, paired LR-HR data may not be available in real-world applications, and the underlying degradation method is often unknown. For this more general case, existing SR models tend to generate adaptive problems and produce poor performance. To solve the above problem, we propose a dual regression scheme that reduces the space of possible functions by introducing additional constraints on LR data.</p>
</abstract>

By learning nonlinear mapping functions from low resolution (LR) images to high resolution (HR) images, deep neural networks show good performance in image super-resolution (SR). However, the existing SR approach has two potential limitations. First, learning the mapping function from LR to HR images is usually an ill-conditioned problem, since there exist an infinite number of HR images that can be down-sampled to the same LR image. Thus, the space of possible functions can be very large, making it difficult to find a good solution. Second, paired LR-HR data may not be available in real-world applications, and the underlying degradation method is often unknown. For this more general case, existing SR models tend to generate adaptive problems and produce poor performance. To solve the above problem, we propose a dual regression scheme that reduces the space of possible functions by introducing additional constraints on LR data.

Super-resolution Image Reconstruction Based on Double Regression Network Model

School of Computer Science and Engineering

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":"Super-resolution Image Reconstruction Based on Double Regression Network Model"}

By learning nonlinear mapping functions from low resolution (LR) images to high resolution (HR) images, deep neural networks show good performance in image...

Datasets	FSRCNN	SRGAN	ESRGAN	Ours
Set5	32.40	33.19	33.46	34.68
Set14	29.52	29.56	29.47	30.56
Bsd100	26.74	29.47	29.78	29.78

Datasets	FSRCNN	SRGAN	ESRGAN	Ours
Set5	0.8657	0.8657	0.8569	0.6895
Set14	0.7564	0.7369	0.8697	0.7698
Bsd100	0.7156	0.6689	0.6783	0.6856

Super-resolution Image Reconstruction Based on Double Regression Network Model

Online veröffentlicht: 26. Mai 2023

Seitenbereich: 82 - 88

DOI: https://doi.org/10.2478/ijanmc-2022-0039

Schlüsselwörter
Super Resolution, Mapping Function, Deep Neural Network, Double Regression Model

© 2022 Jieyi Lv 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.

Figure 5.

Comparison of the results of PSNR reconstruction by two times of each algorithm

Comparison of SSIM results of four times reconstruction of each algorithm

Super-resolution Image Reconstruction Based on Double Regression Network Model

Online veröffentlicht: 26. Mai 2023

Seitenbereich: 82 - 88

DOI: https://doi.org/10.2478/ijanmc-2022-0039

SchlüsselwörterSuper Resolution, Mapping Function, Deep Neural Network, Double Regression Model

© 2022 Jieyi Lv 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.

Figure 5.

Comparison of the results of PSNR reconstruction by two times of each algorithm

Comparison of SSIM results of four times reconstruction of each algorithm

Schlüsselwörter
Super Resolution, Mapping Function, Deep Neural Network, Double Regression Model