HDCTfusion: Hybrid Dual-Branch Network Based on CNN and Transformer for Infrared and Visible Image Fusion
Wenqing Wang, Lingzhou Li, Yifei Yang, Han Liu, Runyuan Guo · 2024
Read HDCTfusion: Hybrid Dual-Branch Network Based on CNN and Transformer for Infrared and Visible Image Fusion by Wenqing Wang, Lingzhou Li, Yifei Yang, Han Liu, Runyuan Guo (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-11644922.txt.
Description
Wenqing Wang and co-authors present in 2024 HDCTfusion, a two branch network that merges heat and light images into one rich shot. Heat shots show hot targets well, while light shots hold fine detail. Past merge tools oft stress one scale and lose key traits from the other.
One branch uses a classic fold net to pull local traits, with slope and link tricks to keep texture sharp. The twin branch uses a shift based net to read the whole scene at once. On split test sets the fused shots beat most top merge tools on detail and contrast.
Catalog record
| CREATOR | Wenqing Wang, Lingzhou Li, Yifei Yang, Han Liu, Runyuan Guo |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |