Mar 17, 2021 · This paper elaborates on a novel method that achieves state-of-the-art results for underwater image restoration based on the unsupervised image-to-image ...
We design our method by leveraging from contrastive learning and generative adversarial networks to maximize mutual information between raw and restored images.
JunlinHan/CWR: Code and dataset for Single Underwater Image ... - GitHub
github.com › JunlinHan › CWR
CWR is designed for underwater image restoration, but not limited to it. It performs style-transfer to certain kinds of low-level vision tasks.
Sep 7, 2024 · This paper elaborates on a novel method that achieves state-of-the-art results for underwater image restoration based on the unsupervised image- ...
We design our method by leveraging from contrastive learning and generative adversarial networks to maximize mutual information between raw and restored images.
We present a novel method for underwater image restoration based on an unsupervised image-to-image translation framework.
Our method adopts an unpaired image-to-image translation network to learn the characteristics of underwater haze images. To enhance restoration, we propose ...
Jun 20, 2021 · We present a novel method for underwater image restoration based on unsupervised image-to-image translation framework.
Missing: Single | Show results with:Single
The contrastive learning of positive and negative samples makes the generated image closer to the clear underwater image and deviates from the real underwater ...
Underwater image restoration aims to rectify the distorted colors and present the true colors of the underwater scene.