We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
A Review of Underwater Image Enhancement and Restoration Techniques Based on Gan
Summary
This review examines underwater image enhancement and restoration technologies based on generative adversarial networks (GANs), assessing challenges arising from the underwater imaging environment and evaluating GAN-based methods for improving image quality in support of marine operations and seabed resource development.
In recent years, underwater image enhancement and restoration technology have significantly contributed to the efficiency of marine operations and the advancement of seabed resource development, which carries substantial academic significance and practical value. This study initially investigates and assesses the underwater imaging model based on the principles of underwater imaging, emphasizing the challenges and issues faced by current technology. Secondly, it thoroughly presents the pertinent research on underwater image enhancement and restoration technologies utilizing generative adversarial networks, and provides an in-depth classification and analysis of the prevailing underwater image enhancement and restoration techniques based on GAN. The study of experimental findings highlights the peculiarities of various classification methods. Thirdly, it summarizes the commonly used datasets and evaluation indicators. Finally, it forecasts and examines the viable development pathways for underwater image enhancement and restoration technology moving forward, particularly emphasizing the significant potential and application value of generative adversarial networks within this domain.
Sign in to start a discussion.
More Papers Like This
A Survey of Seafloor Characterization and Mapping Techniques
This survey reviews the main techniques used to map and characterize the deep seafloor, including optical and acoustic sensing methods. The paper covers approaches ranging from traditional statistics to deep learning, highlighting current limitations in underwater imaging and pointing to future research directions for better understanding seabed ecosystems.
Underwater Image Detection for Cleaning Purposes; Techniques Used for Detection Based on Machine Learning
Researchers reviewed machine learning techniques for underwater image detection to support water pollution cleanup, focusing on convolutional neural networks and region-based CNN methods for identifying surface mucilage and debris. The study evaluated supervised classification algorithms as the most effective approach for automated aquatic waste detection systems.
Robust and Fair Undersea Target Detection with Automated Underwater Vehicles for Biodiversity Data Collection
Researchers developed a robust and fair underwater target detection system for automated underwater vehicles (AUVs) to support marine biodiversity data collection, addressing unique challenges of subsea imaging compared to above-ground remote sensing.
Microplastic Identification in Seawater using Generative Adversarial Networks
Researchers trained a generative adversarial network (GAN) on microscope images of seawater samples and achieved 92.5% accuracy in automatically distinguishing microplastic particles from natural particulates. This AI-based detection approach could dramatically speed up the analysis of water samples, making routine monitoring of marine microplastic pollution faster and more scalable.
Improving YOLOv11 for marine water quality monitoring and pollution source identification
Researchers improved the YOLOv11 computer vision model to better detect and identify marine pollution sources, including oil spills, debris, and turbid water, in complex underwater environments. The enhanced model achieved higher detection accuracy and faster processing speeds compared to the standard version. The study demonstrates that advanced AI-based monitoring tools can meaningfully improve our ability to track and respond to marine pollution in real time.