GRFN: A Group Residual Feature Network for Lightweight Image Super-Resolution.
Saved in:
| Title: | GRFN: A Group Residual Feature Network for Lightweight Image Super-Resolution. |
|---|---|
| Authors: | Yang, Xin1 (AUTHOR) yangxin@nuaa.edu.cn, Hong, Chaming1 (AUTHOR) hcm0531@nuaa.edu.cn, Zhang, Panpan1 (AUTHOR) zhangpanpan@nuaa.edu.cn |
| Source: | Circuits, Systems & Signal Processing. May2025, Vol. 44 Issue 5, p3513-3533. 21p. |
| Subjects: | High resolution imaging, Pixels, Speed |
| Abstract: | In recent years, image super-resolution (SR) research has made remarkable progress. However, the complexity of the models, such as increased network depth, attention mechanisms, and Transformer structures, has resulted in high computational costs, making it challenging to deploy these models on mobile devices. To address this issue, we propose a lightweight SR model based on the group residual feature network (GRFN). Our model features an efficient Group Residual Feature Block (GRFB), composed mainly of Feature Pixel Convolution Units (FPUs) combined with local residual connection stacking. This design simplifies feature fusion and strikes a balance between model performance and inference time. With a scale factor of 4, the number of parameters of GRFN is only 554 K, and PSNR/SSIM is able to reach 32.30 dB/0.8965, which balances the inference speed and quality and outperforms the state-of-the-art methods. Furthermore, our model achieves excellent reconstruction results in subjective visual evaluations. [ABSTRACT FROM AUTHOR] |
| Copyright of Circuits, Systems & Signal Processing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | In recent years, image super-resolution (SR) research has made remarkable progress. However, the complexity of the models, such as increased network depth, attention mechanisms, and Transformer structures, has resulted in high computational costs, making it challenging to deploy these models on mobile devices. To address this issue, we propose a lightweight SR model based on the group residual feature network (GRFN). Our model features an efficient Group Residual Feature Block (GRFB), composed mainly of Feature Pixel Convolution Units (FPUs) combined with local residual connection stacking. This design simplifies feature fusion and strikes a balance between model performance and inference time. With a scale factor of 4, the number of parameters of GRFN is only 554 K, and PSNR/SSIM is able to reach 32.30 dB/0.8965, which balances the inference speed and quality and outperforms the state-of-the-art methods. Furthermore, our model achieves excellent reconstruction results in subjective visual evaluations. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 0278081X |
| DOI: | 10.1007/s00034-024-02975-w |
