Twice Mixing: A Rank Learning based Quality Assessment Approach for Underwater Image Enhancement (2021-02-01T00:00:00.000000Z)

TL;DR

This paper proposes a novel rank learning guided no-reference quality assessment method for UIE, trained based on an elaborately formulated self-supervision mechanism to train a Siamese Network to learn their quality rankings.

Authors

Xueyang Fu

3 papers

Xinghao Ding

4 papers

Zhenqi Fu

2 papers

Yue Huang

3 papers

TL;DR

Authors

References55 items

Underwater image enhancement with global-local networks and compressed-histogram equalization

Underwater Image Enhancement Using a Multiscale Dense Generative Adversarial Network

MLFcGAN: Multilevel Feature Fusion-Based Conditional GAN for Underwater Image Color Correction

Underwater scene prior inspired deep underwater image and video enhancement

RankSRGAN: Generative Adversarial Networks With Ranker for Image Super-Resolution

Enhancement of Underwater Images With Statistical Model of Background Light and Optimization of Transmission Map

Underwater Image Enhancement Using Adaptive Retinal Mechanisms

Sea-Thru: A Method for Removing Water From Underwater Images

All-In-One Underwater Image Enhancement using Domain-Adversarial Learning

Fast Underwater Image Enhancement for Improved Visual Perception

Real-World Underwater Enhancement: Challenges, Benchmarks, and Solutions Under Natural Light

An Underwater Image Enhancement Benchmark Dataset and Beyond

Joint Residual Learning for Underwater Image Enhancement

A Rapid Scene Depth Estimation Model Based on Underwater Light Attenuation Prior for Underwater Image Restoration

Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data

Generalization of the Dark Channel Prior for Single Image Restoration

Single Underwater Image Restoration Using Adaptive Attenuation-Curve Prior

End-to-End Blind Image Quality Assessment Using Deep Neural Networks

Two-step approach for single underwater image enhancement

mixup: Beyond Empirical Risk Minimization

Emerging From Water: Underwater Image Color Correction Based on Weakly Supervised Color Transfer

RankIQA: Learning from Rankings for No-Reference Image Quality Assessment

Underwater Image Restoration Based on Image Blurriness and Light Absorption

WaterGAN: Unsupervised Generative Network to Enable Real-Time Color Correction of Monocular Underwater Images

Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior

Human-Visual-System-Inspired Underwater Image Quality Measures

An Underwater Color Image Quality Evaluation Metric

Underwater image quality enhancement through integrated color model with Rayleigh distribution

Deriving inherent optical properties from background color and underwater image enhancement

A retinex-based enhancing approach for single underwater image

Very Deep Convolutional Networks for Large-Scale Image Recognition

Quality Assessment for Comparing Image Enhancement Algorithms

New Image Quality Evaluation Metric for Underwater Video

Making a “Completely Blind” Image Quality Analyzer

Enhancing underwater images and videos by fusion

Underwater Image Enhancement by Wavelength Compensation and Dehazing

Single Image Haze Removal Using Dark Channel Prior

Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality

Initial results in underwater single image dehazing

A comparative study of image retargeting

Enhancing the low quality images using Unsupervised Colour Correction Method

No-reference quality assessment using natural scene statistics: JPEG2000

Visual inspection of sea bottom structures by an autonomous underwater vehicle

Automatic white balance for digital still camera

Contrast-limited adaptive histogram equalization: speed and effectiveness

Image Enhancement by Histogram transformation

CA-GAN: Class-Condition Attention GAN for Underwater Image Enhancement

Exemplar-based Underwater Image Enhancement Augmented by Wavelet Corrected Transforms

Color Balance and Fusion for Underwater Image Enhancement

Diving into Haze-Lines: Color Restoration of Underwater Images

Unpaired image-to-image translation using cycle-consistent adversarial networks

Visual Computing and the Progress of Developing Countries Underwater Depth Estimation and Image Restoration Based on Single Images

Automatic Red-Channel underwater image restoration

Compared with three competitors

hand-crafted low-level features for quality evaluation, their performance

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names