Lightweight super-resolution reconstruction architecture of remote sensing images using a residual hierarchical transformer network
Bo Huang, Jian Lin, Qingtang Chen, Yiqing Cao, Liaoni Wu · 2025
Read Lightweight super-resolution reconstruction architecture of remote sensing images using a residual hierarchical transformer network by Bo Huang, Jian Lin, Qingtang Chen, Yiqing Cao, Liaoni Wu (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-12727879.txt.
Description
Bo Huang and co-authors present a light model to sharpen satellite images in a 2025 paper. Clearer images help people read land, crops, and cities from space. Transformer models do this well, but fixed small windows limit their view, and full attention costs too much compute for large images.
Their design stacks blocks that look at windows at several scales at once. A new attention step mixes space and channel cues while keeping cost in line with window size. A gated step then adds more spatial detail. Tests on several standard sets beat top prior methods on both scores and how the images look.
Catalog record
| CREATOR | Bo Huang, Jian Lin, Qingtang Chen, Yiqing Cao, Liaoni Wu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |