PSG-UIENet fuses Retinex physics with CLIP-derived text semantics and a new multimodal dataset to enhance underwater images, claiming better results than fifteen prior methods.
Single image haze removal using dark channel prior,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
UDehaze-iT is a lightweight deep network that enhances underwater images by implicitly estimating depth and deriving transmission via learnable Beer-Lambert attenuation coefficients, achieving competitive results on UIEB and UFO-120 with 0.9M parameters.
citing papers explorer
-
Retinex Meets Language: A Physics-Semantics-Guided Underwater Image Enhancement Network
PSG-UIENet fuses Retinex physics with CLIP-derived text semantics and a new multimodal dataset to enhance underwater images, claiming better results than fifteen prior methods.
-
An Underwater Dehazing Network with Implicit Transmission Estimation
UDehaze-iT is a lightweight deep network that enhances underwater images by implicitly estimating depth and deriving transmission via learnable Beer-Lambert attenuation coefficients, achieving competitive results on UIEB and UFO-120 with 0.9M parameters.