Pixel-Based Long-Wave Infrared Spectral Image Reconstruction Using a Hierarchical Spectral Transformer
Zi Wang, Yang Yang, Liyin Yuan, Chunlai Li, Jianyu Wang, Pierre-Jean Lapray, Jean-Baptiste Thomas, Yusuke Monno · 2024
Read Pixel-Based Long-Wave Infrared Spectral Image Reconstruction Using a Hierarchical Spectral Transformer by Zi Wang, Yang Yang, Liyin Yuan, Chunlai Li, Jianyu Wang, Pierre-Jean Lapray, Jean-Baptiste Thomas, Yusuke Monno (2024) 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-11644978.txt.
Description
Wang and co-authors build a neural net to sharpen long-wave infrared spectral images. Such imaging aids gas checks, mineral hunts, and fire spotting. A snapshot device now captures these images in real time. Its output has low spectral detail and heavy noise. Training data for this band are also scarce.
Their Hierarchical Spectral Transformer learns from single-pixel spectral records. Pixel-level learning sidesteps the lack of full image sets. The design aims to catch both local and global spectral links. Past nets based on convolution or attention missed one of those scales. The authors claim finer spectral rebuilds for noisy long-wave input.
Catalog record
| CREATOR | Zi Wang, Yang Yang, Liyin Yuan, Chunlai Li, Jianyu Wang, Pierre-Jean Lapray, Jean-Baptiste Thomas, Yusuke Monno |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |