A joint neural network trained with atmospheric-scattering and brightness-consistency losses simultaneously dehazes real driving video and estimates depth, reporting state-of-the-art results on four hazy benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video
A joint neural network trained with atmospheric-scattering and brightness-consistency losses simultaneously dehazes real driving video and estimates depth, reporting state-of-the-art results on four hazy benchmarks.