Physics-Inspired Frequency-Decoupled Network for Remote Sensing Image Dehazing

Hao Yang, Xiaohan Chen, Gang Xu · 2026

Read Physics-Inspired Frequency-Decoupled Network for Remote Sensing Image Dehazing by Hao Yang, Xiaohan Chen, Gang Xu (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-13211142.txt.

Description

Hao Yang, Xiaohan Chen, and Gang Xu present a haze removal network in a 2026 paper. Satellite and aerial images often come veiled by uneven haze. The haze dulls contrast, blurs detail, and skews color. Bright land cover, like sand or roofs, is easy to damage in cleanup.

Their network, PhysWave-SSN, splits the image by frequency bands. One gate picks which channels to keep for each band. A state space module adjusts its span based on local haze density. That design ties the math to how light scatters in air. A fusion step then guards bright areas from color shifts. The authors say the system restores detail with truer color than rivals. It targets high fidelity cleanup for remote sensing work.

Catalog record

CREATORHao Yang, Xiaohan Chen, Gang Xu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE85 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13211142

Browse the full library · About the Tower of Babel