An unpaired dehazing network combining shared Retinex priors, wavelet separable convolutions, and adaptive color correction reports modest benchmark gains, but its state-of-the-art claim is contradicted by its own tables on HSTS and I-HAZE.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
UR2P-Dehaze: Learning a Simple Image Dehaze Enhancer via Unpaired Rich Physical Prior
An unpaired dehazing network combining shared Retinex priors, wavelet separable convolutions, and adaptive color correction reports modest benchmark gains, but its state-of-the-art claim is contradicted by its own tables on HSTS and I-HAZE.