CL-ODGAN: an unpaired attention-guided GAN framework for remote sensing image dehazing
Hongwei Zhang, Xin Mu, Bin Yin · 2026
Read CL-ODGAN: an unpaired attention-guided GAN framework for remote sensing image dehazing by Hongwei Zhang, Xin Mu, Bin Yin (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/pmc-13434088.txt.
Description
Hongwei Zhang and colleagues propose CL-ODGAN, an unpaired learning framework for clearing haze from remote-sensing images. Haze degrades image quality and interpretation, yet deep-learning dehazers usually need large paired clean-and-hazy datasets that remote sensing rarely offers.
Their design centres on a generator with residual blocks using omni-dimensional dynamic convolution for multi-scale perception, plus hybrid normalisation for training stability, enabling adaptive detail recovery under uneven haze. A dual-level contrastive constraint, at feature and pixel levels, supplies unsupervised guidance. Satellite analysts get a dehazer that learns from unpaired images, matching how remote-sensing data actually arrives.
Catalog record
| CREATOR | Hongwei Zhang, Xin Mu, Bin Yin |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |