A lightweight multimodal image fusion and enhancement method for smoke scenes
Jie Ma, Ming Yang, Xianli Jin, Yangyang Zhao · 2026
Read A lightweight multimodal image fusion and enhancement method for smoke scenes by Jie Ma, Ming Yang, Xianli Jin, Yangyang Zhao (2026) 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/PMC13542177.txt.
Description
Jie Ma and colleagues propose an image method in 2026. The method merges visible and infrared pictures. It also clears smoke in a single pass. Older pipelines de-smoke first and fuse later. That order stacks errors and heavy computation. The new design is lightweight by intent.
Convolutional layers read local detail in each picture. Transformer blocks read global context across the scene. Both sit inside an encoder-decoder frame. Training ran in two stages. A small internal network suppresses smoke within the features. Tests spanned several smoke densities. The method beat mainstream fusion rivals on sharpness and error scores. The authors pitch it for surveillance use.
Catalog record
| CREATOR | Jie Ma, Ming Yang, Xianli Jin, Yangyang Zhao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44337 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |