Image super-resolution method using a generative adversarial network incorporating attention and residual density
Qiong Zhang, Yiliu Hang, Hui Zhang, Xi Lu, Jianlin Qiu · 2025
Read Image super-resolution method using a generative adversarial network incorporating attention and residual density by Qiong Zhang, Yiliu Hang, Hui Zhang, Xi Lu, Jianlin Qiu (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12756245.txt.
Description
Qiong Zhang and co-authors sharpen blurry images with a generative network that watches where it looks in a 2025 paper. Enlarging low-resolution photos often loses fine detail and adds noise. Their adversarial network fuses features from many layers through dense residual blocks that keep training signals alive.
An attention gate then mutes noisy channels and lifts the signal quality. Against rival methods, the design scored better on both peak signal-to-noise ratio and structural similarity, the two standard image quality yardsticks. The authors present the network as a step toward cleaner upscaling for photos and video.
Catalog record
| CREATOR | Qiong Zhang, Yiliu Hang, Hui Zhang, Xi Lu, Jianlin Qiu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 22 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |