Lightweight Single Image Super-Resolution by Channel Split Residual Convolution


Buzhong Liu, Journal of Information Processing Systems Vol. 18, No. 1, pp. 12-25, Feb. 2022  

10.3745/JIPS.02.0168
Keywords: Channel Split Residual, Double-Upsampling, Lightweight, super-resolution
Fulltext:

Abstract

In recent years, deep convolutional neural networks have made significant progress in the research of single image super-resolution. However, it is difficult to be applied in practical computing terminals or embedded devices due to a large number of parameters and computational effort. To balance these problems, we propose CSRNet, a lightweight neural network based on channel split residual learning structure, to reconstruct high- resolution images from low-resolution images. Lightweight refers to designing a neural network with fewer parameters and a simplified structure for lower memory consumption and faster inference speed. At the same time, it is ensured that the performance of recovering high-resolution images is not degraded. In CSRNet, we reduce the parameters and computation by channel split residual learning. Simultaneously, we propose a double-upsampling network structure to improve the performance of the lightweight super-resolution network and make it easy to train. Finally, we propose a new evaluation metric for the lightweight approaches named 100_FPS. Experiments show that our proposed CSRNet not only speeds up the inference of the neural network and reduces memory consumption, but also performs well on single image super-resolution.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.




Cite this article
[APA Style]
Buzhong Liu (2022). Lightweight Single Image Super-Resolution by Channel Split Residual Convolution. Journal of Information Processing Systems, 18(1), 12-25. DOI: 10.3745/JIPS.02.0168.

[IEEE Style]
B. Liu, "Lightweight Single Image Super-Resolution by Channel Split Residual Convolution," Journal of Information Processing Systems, vol. 18, no. 1, pp. 12-25, 2022. DOI: 10.3745/JIPS.02.0168.

[ACM Style]
Buzhong Liu. 2022. Lightweight Single Image Super-Resolution by Channel Split Residual Convolution. Journal of Information Processing Systems, 18, 1, (2022), 12-25. DOI: 10.3745/JIPS.02.0168.