Underwater Image Restoration

11 papers with code • 1 benchmarks • 2 datasets

Underwater image restoration aims to rectify the distorted colors and present the true colors of the underwater scene.


Most implemented papers

Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding

Li-Chongyi/Ucolor 27 Apr 2021

As a result, our network can effectively improve the visual quality of underwater images by exploiting multiple color spaces embedding and the advantages of both physical model-based and learning-based methods.

Enhancing Underwater Imagery using Generative Adversarial Networks

cameronfabbri/Underwater-Color-Correction 11 Jan 2018

Autonomous underwater vehicles (AUVs) rely on a variety of sensors - acoustic, inertial and visual - for intelligent decision making.

Fast Underwater Image Enhancement for Improved Visual Perception

xahidbuffon/funie-gan 23 Mar 2019

In this paper, we present a conditional generative adversarial network-based model for real-time underwater image enhancement.

U-shape Transformer for Underwater Image Enhancement

LintaoPeng/U-shape_Transformer 23 Nov 2021

In this work, we constructed a large-scale underwater image (LSUI) dataset including 5004 image pairs, and reported an U-shape Transformer network where the transformer model is for the first time introduced to the UIE task.

An Underwater Image Enhancement Benchmark Dataset and Beyond

tnwei/waternet 11 Jan 2019

In this paper, we construct an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images.

Restoration of Non-rigidly Distorted Underwater Images using a Combination of Compressive Sensing and Local Polynomial Image Representations

jeringeo/CompressiveFlows ICCV 2019

Surprisingly, we demonstrate that PEOF is more efficient and often outperforms all the state of the art methods in terms of numerical measures.

Single Underwater Image Restoration by Contrastive Learning

JunlinHan/CWR 17 Mar 2021

Underwater image restoration attracts significant attention due to its importance in unveiling the underwater world.

Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration

pksvision/Deep-WaveNet-Underwater-Image-Restoration 15 Jun 2021

Background: Underwater images, in general, suffer from low contrast and high color distortions due to the non-uniform attenuation of the light as it propagates through the water.

Underwater Image Restoration via Contrastive Learning and a Real-world Dataset

JunlinHan/CWR 20 Jun 2021

There are 2000 reference restored images and 6003 original underwater images in the unpaired training set.

MetaUE: Model-based Meta-learning for Underwater Image Enhancement

duanlab123/metaue 12 Mar 2023

The meta-learning strategy is used to obtain a pre-trained model on the synthetic underwater dataset, which contains different types of degradation to cover the various underwater environments.