The paper derives a composite atmospheric scattering model for non-ideal clean data and uses a four-loss committee to train a dehazing network, claiming state-of-the-art results on real-world haze benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Synthetic-to-Real Dehazing Method based on Domain Unification
The paper derives a composite atmospheric scattering model for non-ideal clean data and uses a four-loss committee to train a dehazing network, claiming state-of-the-art results on real-world haze benchmarks.