Model-Based Underwater Image Simulation and Learning-Based Underwater Image Enhancement Method

Liu, Yidan; Xu, Huiping; Zhang, Bing; Sun, Keyan; Yang, Jingchuan; Li, Bo; Li, Chen; Quan, Xiangqian

doi:10.3390/info13040187

Cited by 14 publications

(7 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Guo et al [9] divided images into illumination maps and restored clear images, capturing global information with a transform module. Liu et al [21] designed a multi-expert encoder to extract and fuse features for the R, G, and B channels separately, utilizing a multi-expert discriminator to handle different color channels individually. Li et al [22] developed the Ucolor multi-color space encoder network, integrating RGB, HSV, and Lab color spaces with parameters estimated by GDCP, enhancing feature diversity and highlighting important features through attention mechanisms.…”

Section: Learning-based Methodsmentioning

confidence: 99%

Dual-Branch Underwater Image Enhancement Utilizing Bidirectional Supervision Loss, Contrast Loss, and Style Transfer Loss

Qiao,

Fan,

et al. 2024

Preprint

View full text Add to dashboard Cite

Due to the complexity of underwater environments, underwater images often exhibit multiple forms of degradation. Despite recent notable advancements in underwater image restoration, the scarcity of paired datasets poses significant challenges for future progress in this field. This paper introduces a dual-branch underwater image enhancement network that includes an image restoration branch and an illumination estimation branch, trained using both paired and unpaired datasets to mitigate the scarcity of paired data. The network is jointly trained through supervised and unsupervised methods: in the supervised phase, it uses paired datasets guided by contrast loss, perceptual loss, and bidirectional supervision loss to learn the mapping from underwater to clear images, in the unsupervised phase, it employs unpaired datasets with bidirectional supervision loss and style transfer loss to learn the style of natural images and enhance network generalizability. Experimental results demonstrate that our proposed method performs comparably or better than other methods across multiple datasets, providing valuable insights and techniques for underwater image restoration.

show abstract

Section: Learning-based Methodsmentioning

confidence: 99%

Dual-Branch Underwater Image Enhancement Utilizing Bidirectional Supervision Loss, Contrast Loss, and Style Transfer Loss

Qiao,

Fan,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Solar radiation faces a change in medium from air to water, thus varying the refraction index according to specific physical and chemical water properties. Light absorption and scattering are the two main underwater issues [ 31 ]. Figure 8 illustrates how the presence of suspended underwater particles generates scattering light components.…”

Section: Critical Issues In Auv Underwater Imagingmentioning

confidence: 99%

Autonomous Underwater Vehicles: Identifying Critical Issues and Future Perspectives in Image Acquisition

Monterroso Muñoz,

Moron-Fernández,

Cascado-Caballero

et al. 2023

Sensors

View full text Add to dashboard Cite

Underwater imaging has been present for many decades due to its relevance in vision and navigation systems. In recent years, advances in robotics have led to the availability of autonomous or unmanned underwater vehicles (AUVs, UUVs). Despite the rapid development of new studies and promising algorithms in this field, there is currently a lack of research toward standardized, general-approach proposals. This issue has been stated in the literature as a limiting factor to be addressed in the future. The key starting point of this work is to identify a synergistic effect between professional photography and scientific fields by analyzing image acquisition issues. Subsequently, we discuss underwater image enhancement and quality assessment, image mosaicking and algorithmic concerns as the last processing step. In this line, statistics about 120 AUV articles fro recent decades have been analyzed, with a special focus on state-of-the-art papers from recent years. Therefore, the aim of this paper is to identify critical issues in autonomous underwater vehicles encompassing the entire process, starting from optical issues in image sensing and ending with some issues related to algorithmic processing. In addition, a global underwater workflow is proposed, extracting future requirements, outcome effects and new perspectives in this context.

show abstract

“…The underwater image suffers from low contrast and resolution due to poor visibility conditions Poor visibility in water. [18] Underwater images suffer from color casts and low contrast due to wavelength-and distance-dependent and scattering. Underwater image enhancement is a field of image processing that aims to improve the visual quality of images taken underwater.…”

Section: Literature Surveymentioning

confidence: 99%

Image Enhancement of Underwater Images using Deep Learning Techniques

Sravani¹,

Sai²,

Noomika³

et al. 2023

Int. J. Res. Publ. Rev.

View full text Add to dashboard Cite

The quality of underwater images is very important for research purpose and ocean exploration. The market for high-quality underwater images is expanding exponentially. Despite this, there are a number of issues including blurriness, dim lighting, poor contrast and color fidelity. Light attenuation, absorption and scattering lower the quality. As a result, it is essential to enhance underwater images, and different image processing techniques are used for enhancement .The deep learning methodology used in this study improves image quality and produce the best outcomes when compared to conventional image enhancing techniques. The architecture used is GAN with the combination of Image processing algorithms as a preprocessing step for implementing deep learning models .The algorithms include Histogram Equalization and Dark Channel Prior. These methods normalizes the contrast of images and removes the hazing or dark parts of the images. The dataset used in this study is EUVP (Paired) which contains about 2186 real-world underwater images. Three parameters, UICM, MSE and PSNR are used to assess quality of enhanced images. The optimum technique for improving the images is determined by comparing the performance of the models after the dataset has been trained through them.

show abstract

Model-Based Underwater Image Simulation and Learning-Based Underwater Image Enhancement Method

Cited by 14 publications

References 43 publications

Dual-Branch Underwater Image Enhancement Utilizing Bidirectional Supervision Loss, Contrast Loss, and Style Transfer Loss

Dual-Branch Underwater Image Enhancement Utilizing Bidirectional Supervision Loss, Contrast Loss, and Style Transfer Loss

Autonomous Underwater Vehicles: Identifying Critical Issues and Future Perspectives in Image Acquisition

Image Enhancement of Underwater Images using Deep Learning Techniques

Contact Info

Product

Resources

About