Research on Image Super-Resolution Using Attention Mechanisms based on Super-Resolution Generative Adversarial Network

Zhouli Wu

doi:10.54097/fcis.v5i2.13142

Authors

Zhouli Wu

DOI:

https://doi.org/10.54097/fcis.v5i2.13142

Keywords:

SRGAN, Attention Mechanism, Residual Blocks

Abstract

With the continuous advancement of technology, Super-Resolution Generative Adversarial Networks (SRGAN) have played a significant role in the field of image super-resolution, significantly enhancing the resolution of images. However, while SRGAN excels in generating details, sometimes the restored details do not always meet people's expectations. To further enhance the quality of images and make image details clearer, this paper introduces improvements to the architecture and loss functions of the SRGAN network. Specifically, this research draws inspiration from the architecture of ESRGAN, removing the original Batch Normalization layers and introducing a newly designed Residual Block. Leveraging insights from attention mechanisms, we incorporate three layers of convolutional operations and introduce attention mechanisms into these new Residual Blocks. Furthermore, to simplify the computational complexity of the model, this paper simplifies the original loss functions, consolidating the previous four losses into two. These enhancements result in a significantly improved model in capturing visual elements, making key objects in the images more prominent compared to SRGAN. Detailed experimental results demonstrate that this model, while maintaining the clarity of details, provides higher visual quality. These achievements provide valuable insights and inspiration for further research and applications in the field of image super-resolution.

Downloads

Download data is not yet available.

References

Han, W., Dong, X., Dong, W. (2021). Application research of neural network models in the field of image super-resolution. Journal of Information Engineering University, 22(02), 159-163.

Zhang, Y., Li, K., Li, K., et al. (2018). Image super-resolution using very deep residual channel attention networks. https:// arxiv.org/abs/1807.02758.

Dong, C., Loy, C. C., He, K., et al. (2015). Image super-resolution using deep convolutional networks. https://arxiv. org/ abs/1501.00092.

Shi, W., Caballero, J., Huszár, F., et al. (2016). Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. https://arxiv. org/abs/ 1609. 05158.

Ledig, C., Theis, L., Huszar, F., et al. (2017). Photo-realistic single image super-resolution using a generative adversarial network. https://arxiv.org/abs/1609.04802.

Wang, X., Yu, K., Wu, S., et al. (2018). Esrgan: Enhanced super-resolution generative adversarial networks. https://arxiv. org/abs/ 1809.00219.

Ioffe, S., Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. https://arxiv.org/abs/1502.03167.

Wu, Y., He, K. (2018). Group normalization. https://arxiv. org/ abs/ 1803.08494.

Timofte, R., Agustsson, E., Gool, L.V., et al.. (2017). NTIRE 2017 challenge on single image super-resolution: methods and results. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 1110-1121.

D. Martin, C. Fowlkes, D. Tal, et al.. (2002). A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. Proceedings Eighth IEEE International Conference on Computer Vision (ICCV 2001), Vancouver, Canada, pp. 416-423.