Attenuation Coefficient Guided Two-Stage Network for Underwater Image Restoration

Lin, Yufei; Shen, Liquan; Wang, Zhengyong; Wang, Kun; Zhang, Xi

doi:10.1109/lsp.2020.3048619

Cited by 33 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of a global-local network greatly simplifies the learning problem, allowing a lightweight network architecture to be used to process underwater images. Lin et al [53] proposed a new two-stage network for underwater images, which divides the recovery process into two stages, horizontal and vertical distortion recovery, so that the network can effectively solve the scattering and absorption problems. In the first phase, they propose a model-based network that embeds underwater physical models directly into the network to deal with horizontal distortion.…”

Section: Learning-based Underwater Image Enhancement Methodsmentioning

confidence: 99%

Two-Branch Underwater Image Enhancement and Original Resolution Information Optimization Strategy in Ocean Observation

Zhang

Cao

Zhou

et al. 2023

JMSE

View full text Add to dashboard Cite

In complex marine environments, underwater images often suffer from color distortion, blur, and poor visibility. Existing underwater image enhancement methods predominantly rely on the U-net structure, which assigns the same weight to different resolution information. However, this approach lacks the ability to extract sufficient detailed information, resulting in problems such as blurred details and color distortion. We propose a two-branch underwater image enhancement method with an optimized original resolution information strategy to address this limitation. Our method comprises a feature enhancement subnetwork (FEnet) and an original resolution subnetwork (ORSnet). FEnet extracts multi-resolution information and utilizes an adaptive feature selection module to enhance global features in different dimensions. The enhanced features are then fed into ORSnet as complementary features, which extract local enhancement features at the original image scale to achieve semantically consistent and visually superior enhancement effects. Experimental results on the UIEB dataset demonstrate that our method achieves the best performance compared to the state-of-the-art methods. Furthermore, through comprehensive application testing, we have validated the superiority of our proposed method in feature extraction and enhancement compared to other end-to-end underwater image enhancement methods.

show abstract

Section: Learning-based Underwater Image Enhancement Methodsmentioning

confidence: 99%

Two-Branch Underwater Image Enhancement and Original Resolution Information Optimization Strategy in Ocean Observation

Zhang

Cao

Zhou

et al. 2023

JMSE

View full text Add to dashboard Cite

show abstract

“…As shown in Fig. 4 (a), the depth map D ∈ R 1×H×W of the input underwater image I ∈ R 3×H×W is first estimated using the depth estimation network proposed in our previous work [16]. Then, the obtained depth map is clustered at the pixel level using the K-means [41] algorithm and classified into three region masks, denoted as M k ∈ R 1×H×W , k = 1, 2, 3, representing three different quality degradation patterns.…”

Section: B Internal Representation Learning Stagementioning

confidence: 99%

Domain Adaptation for Underwater Image Enhancement

Wang

Shen

et al. 2023

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

“…The paper [2]- [7] explains some of the popular conventional underwater image enhancement and restoration techniques. The documents [8]- [10] and [12]- [27] describe machine learning algorithms in which convolutional neural networks (CNN) based methods are presented in [8]- [10] and [12]- [19] and generative adversarial network (GAN) models are described in [20]- [26]. The paper [27] introduced a realtime and unsupervised advancement scheme (RUAS) for underwater computer visuals in natural light situations.…”

Section: Underwater Image Enhancement and Restoration Techniquesmentioning

confidence: 99%

A Review on Underwater Image Enhancement Techniques

Amala,

Alex Raj

2023

2023 International Conference on Control, Communication and Computing (ICCC)

View full text Add to dashboard Cite

Underwater imaging is an innovative research area that has more benefits to researchers and scholars for mine detection, navigation, autonomous underwater imaging devices, etc. Underwater photos suffer greatly from scattering, light absorption, color cast, and the presence of artifacts, which causes the image to become increasingly blurry. At this juncture, color correction and image enhancement are highly recommended for getting a precise image with the right information. This paper summarizes the recent algorithms and their approaches in the area of underwater imaging enhancement techniques. An outline of the developing applications of underwater image processing is also presented.

show abstract

Attenuation Coefficient Guided Two-Stage Network for Underwater Image Restoration

Cited by 33 publications

References 22 publications

Two-Branch Underwater Image Enhancement and Original Resolution Information Optimization Strategy in Ocean Observation

Two-Branch Underwater Image Enhancement and Original Resolution Information Optimization Strategy in Ocean Observation

Domain Adaptation for Underwater Image Enhancement

A Review on Underwater Image Enhancement Techniques

Contact Info

Product

Resources

About