computer-vision-10

Underwater Image Restoration

3260 papers • 126 benchmarks • 313 datasets

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

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in underwater-image-restoration-10

Trend

Dataset

Best Model

Actions

LSUI

Libraries

i

Use these libraries to find underwater-image-restoration-10 models and implementations

Datasets

LSUI

MVK

Subtasks

No subtasks available.

Most implemented papers

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

Wenqi Ren, Runmin Cong, Chongyi Li, Chunle Guo, Junhui Hou, Saeed Anwar•Mon Apr 26 2021

This work proposes a multi-color space encoder network, which enriches the diversity of feature representations by incorporating the characteristics of different color spaces into a unified structure, and designs a medium transmission-guided decoder network to enhance the response of network towards quality-degraded regions.

763

Content

0

Paper Graph

Fast Underwater Image Enhancement for Improved Visual Perception

M. Islam, Junaed Sattar, Youya Xia•Fri Mar 22 2019

The proposed conditional generative adversarial network-based model is suitable for real-time preprocessing in the autonomy pipeline by visually-guided underwater robots and provides improved performances of standard models for underwater object detection, human pose estimation, and saliency prediction.

1234 0

Paper Graph

Enhancing Underwater Imagery Using Generative Adversarial Networks

M. Islam, Junaed Sattar, C. Fabbri•Wed Jan 10 2018

A method to improve the quality of visual underwater scenes using Generative Adversarial Networks (GANs), with the goal of improving input to vision-driven behaviors further down the autonomy pipeline is proposed.

681 0

Paper Graph

U-Shape Transformer for Underwater Image Enhancement

Lintao Peng, Chunli Zhu, Liheng Bian•Mon Nov 22 2021

A large scale underwater image (LSUI) dataset is built, which covers more abundant underwater scenes and better visual quality reference images than existing underwater datasets and a novel loss function combining RGB, LAB and LCH color spaces is designed following the human vision principle.

591 0

Paper Graph

An Underwater Image Enhancement Benchmark Dataset and Beyond

D. Tao, Wenqi Ren, Runmin Cong, Chongyi Li, S. Kwong, Chunle Guo, Junhui Hou•Thu Jan 10 2019

This paper constructs an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images and proposes an underwater image enhancement network (called Water-Net) trained on this benchmark as a baseline, which indicates the generalization of the proposed UIEB for training Convolutional Neural Networks (CNNs).

1713 0

Paper Graph

Single Underwater Image Restoration by Contrastive Learning

L. Petersson, M. Shoeiby, Saeed Anwar, Junlin Han, T. Malthus, J. Anstee, Ran Wei, M. Armin, Elizabeth Botha•Tue Mar 16 2021

A novel method that achieves state-of-the-art results for underwater image restoration based on the unsupervised image-to-image translation framework is elaborates on by leveraging from contrastive learning and generative adversarial networks to maximize mutual information between raw and restored images.

56 0

Paper Graph

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

Pranay Agrawal, Jerin Geo James, Ajit V. Rajwade•Mon Aug 05 2019

It is demonstrated that a two-stage approach consisting of the CS step followed by PEOF much more accurately preserves the image structure and improves the (visual as well as numerical) video quality as compared to just the PEOf stage.

21 0

Paper Graph

Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration

P. Sharma, Ira Bisht, A. Sur•Mon Jun 14 2021

It is shown that attributing the right receptive field size (context) based on the traversing range of the color channel may lead to a substantial performance gain for the task of UIR and an attentive skip mechanism is incorporated to adaptively refine the learned multi-contextual features.

160 0

Paper Graph

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

Hongdong Li, L. Petersson, M. Shoeiby, Saeed Anwar, Junlin Han, T. Malthus, E. Botha, J. Anstee, Ran Wei, M. Armin•Sat Jun 19 2021

This work constructed a large-scale real underwater image dataset, dubbed Heron Island Coral Reef Dataset (`HICRD’), for the purpose of benchmarking existing methods and supporting the development of new deep-learning based methods.

94 0

Paper Graph

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

Zhenwei Zhang, Haorui Yan, K. Tang, Yuping Duan•Sat Mar 11 2023

A model-based deep learning method for restoring clean images under various underwater scenarios, which exhibits good interpretability and generalization ability and outperform the state-of-the-art underwater image restoration methods.

11 0

Paper Graph

Adding a benchmark result helps the community track progress.