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

Underwater images suffer degradation from light propagates through water. The degradation by light propagation not only affects the quality of underwater images but limits the ability of object detection. In this paper, we propose a color correction method by cycle-consistent adversarial networks (CycleGAN) for an improvement of underwater object detection. The proposed CycleGAN is implemented with a polynomial loss function including adversarial loss, cycle-consistency loss, and structural similarity index measure (SSIM) loss. Thereby, underwater images are generated as output images including the content and structure of the input images. Simulation results show that our method achieves an improved 7% mean average precision in underwater object detection, compared with a conventional method.

Underwater optical images face various limitations that degrade the image quality compared with optical images taken in our atmosphere. Attenuation according to the wavelength of light and reflection by very small floating objects cause low contrast, blurry clarity, and color degradation in underwater images. We constructed an image data of the Korean sea and enhanced it by learning the characteristics of underwater images using the deep learning techniques of CycleGAN (cycle-consistent adversarial network), UGAN (underwater GAN), FUnIE-GAN (fast underwater image enhancement GAN). In addition, the underwater optical image was enhanced using the image processing technique of Image Fusion. For a quantitative performance comparison, UIQM (underwater image quality measure), which evaluates the performance of the enhancement in terms of colorfulness, sharpness, and contrast, and UCIQE (underwater color image quality evaluation), which evaluates the performance in terms of chroma, luminance, and saturation were calculated. For 100 underwater images taken in Korean seas, the average UIQMs of CycleGAN, UGAN, and FUnIE-GAN were 3.91, 3.42, and 2.66, respectively, and the average UCIQEs were measured to be 29.9, 26.77, and 22.88, respectively. The average UIQM and UCIQE of Image Fusion were 3.63 and 23.59, respectively. CycleGAN and UGAN qualitatively and quantitatively improved the image quality in various underwater environments, and FUnIE-GAN had performance differences depending on the underwater environment. Image Fusion showed good performance in terms of color correction and sharpness enhancement. It is expected that this method can be used for monitoring underwater works and the autonomous operation of unmanned vehicles by improving the visibility of underwater situations more accurately.

Fusion of multiscale gradient domain enhancement and gamma correction for underwater image/video enhancement and restoration

Images captured by underwater robots often suffer from issues such as blurring and colour distortion, which hinder effective feature extraction and target recognition in underwater environments. To address these challenges, this paper proposes a novel underwater image enhancement method based on generative adversarial networks (GANs), termed multiple colour space underwater generative adversarial network (MCS‐UGAN). The proposed method is built upon a GAN framework, consisting of a generator and a discriminator. The generator comprises two main modules: a deblurring module and a colour correction module. The deblurring module innovatively incorporates an efficient multi‐scale feature extraction technique and an attention mechanism, which enhances object contours while preserving fine image details. The colour correction module integrates residual blocks into the U‐Net architecture, effectively mitigating the problems of gradient vanishing and explosion during backpropagation in underwater image enhancement networks, thereby enhancing the network's feature learning capability. This design corrects colour distortions while preserving edge information in the image. The discriminator adopts the PatchGAN structure, which focuses on the local regions of the image, significantly improving the generator's ability to restore high‐frequency details and thus enhancing the quality of the generated images. Experimental results on benchmark datasets demonstrate that, compared to existing methods, MCS‐UGAN achieves superior performance in terms of peak signal‐to‐noise ratio, structural similarity index measure, underwater image quality measure, and underwater colour image quality evaluation, with average values of 26.24, 0.91, 3.13, and 0.64, respectively. Results from real‐world applications further show that MCS‐UGAN effectively increases the number of extracted corner points, validating its practicality and effectiveness. The code is available at https://github.com/invincibility6/MCS‐UGAN.git

Multi-scale adversarial network for underwater image restoration

Underwater images play a critical role in underwater exploration and related tasks. However, due to light attenuation and other underwater factors, underwater images often suffer from color distortion and low contrast, which to some extent limit the efficiency and safety of underwater exploration. To meticulously address these issues and enhance the accuracy and reliability of underwater exploration, this paper proposes a multi-task underwater image enhancement method based on Retinex theory. This method divides the underwater image enhancement task into several sub-tasks, including image decomposition, color correction, detail reconstruction, and illumination adjustment. Specialized sub-networks— DecomNet, DecolorNet, and DelightNet—are designed to specifically address these problems, thereby alleviating color distortion, enhancing image details, and improving contrast. Experiments conducted on several publicly underwater image datasets indicate that the quality of underwater images is significantly improved after enhancement with the proposed method, compared to other representative underwater image processing techniques. For example, on the real-world dataset Underwater Image Enhancement Benchmark, the MSE, Structural Similarity Index Measure, and Peak signal-to-noise ratio scores achieved were 453.480, 0.901, and 25.145, respectively. This study holds significant implications for underwater exploration, with potential applications in the fields of marine research and underwater archaeology.OPEN ACCESS Received: 03/11/2024 Accepted: 27/12/2024 Published: 20/04/2025

Underwater images typically suffer from poor visibility, low contrast, and severe color distortion caused by wavelength-dependent absorption and scattering of light. These degradations not only reduce visual quality but also affect subsequent analysis and interpretation in marine and robotic imaging applications. To address these challenges, this study presents an efficient underwater image enhancement (UIE) framework that integrates color balancing, morphological residual processing, and gamma correction to achieve natural color restoration and structural enhancement. Initially, an adaptive color compensation strategy corrects the imbalance in red and blue channels, followed by morphological residual processing that refines fine textures while suppressing unwanted noise. The enhanced outputs are then fused through an adaptive multiscale fusion process guided by optimized weight maps to preserve both global illumination and local detail. A final gamma correction step ensures perceptually balanced contrast and brightness. The proposed method requires no training data or prior depth estimation making it computationally efficient and robust for real-time applications. Extensive experiments conducted on multiple benchmark underwater datasets demonstrate that the proposed approach consistently outperforms 22 state-of-the-art UIE techniques in both qualitative and quantitative assessments. The method achieves superior results in terms of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), underwater image quality measure (UIQM), and underwater color image quality evaluation (UCIQE) metrics, confirming its capability to restore realistic colors, enhance visibility, and preserve fine details. The proposed framework provides an effective and lightweight solution for practical underwater imaging enhancement. This work supports SDG 14 (Life Below Water) by enhancing underwater imagery for marine monitoring, SDG 9 (Industry, Innovation and Infrastructure) through an efficient real-time imaging framework, and SDG 12 (Responsible Consumption and Production) by enabling accurate underwater inspection that promotes sustainable resource use.

Underwater Image Enhancement (UIE) aims to restore degraded images by addressing light absorption, scattering, and color attenuation in aquatic environments. Achieving accurate visibility and natural color remains challenging due to uneven illumination and suspended particles. Traditional techniques improve contrast but often cause artifacts, noise amplification, or unnatural colors in difficult conditions. This paper presents URST-Net, an integrated deep learning framework combining an attention-augmented U-Net encoder-decoder, residual modules, and a Swin Transformer to effectively capture fine details and long-range context, delivering improved underwater image restoration. The model was trained on the Underwater Fisheye Object (UFO 120) dataset of 1620 paired images with 1500 used for training and 120 for testing. On quantitative evaluation URST-Net attains a Structural Similarity Index Measure (SSIM) of 0.96, Peak Signal to Noise Ratio (PSNR) of $\mathbf{4 5. 2 6 ~ d B}$, an Underwater Image Quality Measure (UIQM) of 4.12 and an Underwater Color Image Quality Evaluation Index (UCIQE) of 0.75, outperforming UGAN with PSNR 38.00 dB, SSIM 0.93 and Contrast Limited Adaptive Histogram Equalization (CLAHE) with SSIM 0.80 PSNR 30.00 dB. Visual results show URST-Net effectively restores textures, suppresses noise and preserves natural colors without artifacts. These findings pave the way for real time deployment on embedded platforms, adaptation to diverse aquatic environments and development of lightweight variants for onsite underwater imaging.

Single underwater image enhancement using integrated variational model

Underwater images can be captured either with the help of light waves or sound waves. Images that are taken underwater typically are not of optimum quality as they suffer from issues such as low contrast, blurring of detail, colour distortion, and greenish tones. Several physical processes that take place in the aquatic environment, such as light absorption, refraction, and scattering, are responsible for the existence of such degradation in underwater images. To address these challenges, numerous researchers have put forth a range of cutting-edge techniques for enhancing and restoring such degraded underwater images, with the aim of addressing these issues. These techniques primarily focus on improving visibility and enhancing the level of detail. To achieve this, we propose a method that performs White Balancing in the LAB colour space to remove the bluish-greenish tones present in the image. Next, we enhance the contrast by first converting the RGB image into HSV and HLS colour spaces and then by using the S & V channels in HSV and L & S colour channels in HLS, we apply Contrast Limited Adaptive Histogram Equalization (CLAHE). To control the brightness of the enhanced image, we apply Gamma Correction. Lastly, by using the method Dark Channel Prior (DCP), we separate the image’s red channel from the RGB colour space and perform the dehazing operation to get the final enhanced image. We have conducted a comprehensive qualitative analysis of our proposed approach as well as existing techniques, evaluating them objectively and subjectively through metrics such as peak signal-to-noise ratio (PSNR), root-mean-square error (RMSE), structural similarity (SSIM), and the underwater colour image quality evaluation metric (UCIQE) and underwater image quality measure (UIQM). Since our proposed approach uses traditional image processing methods, it is computationally less expensive and quicker as compared to deep learning or frequency domain-based methods. With this, it can be adapted for using in real-time applications such as underwater navigation, examination of the behavior of marine ecosystems and other scientific research.

Taking underwater concrete images with an optical camera is an important measure for underwater defect detection. However, the underwater low-light environment and light refraction on the surface of different media result in poor image quality. In order to make the collected underwater images effectively reflect the real situation of underwater concrete defects, we propose an image conversion algorithm combining underwater image color enhancement and refraction distortion correction, which can convert underwater images into aerial equivalent images. In this paper, two conversion models of underwater image to air conversion are proposed, one of which models the refractive distortion of the underwater multilayered media through the ray projection method to correct the refractive distortion of underwater images and image field of view (FOV) conversion. The other is that by analyzing the problem of low image-imaging quality and loss of edge information due to the uneven illumination environment underwater, we process the dark channel priority adaptive enhancement algorithm to improve underwater image quality. The experimental results from real scenes show that the imaging quality of underwater images is improved by converting underwater images to air. The pixel error of images converted into the air is ⩽1 pixel, and the FOV error of images is ⩽8.5%. The high-precision underwater image conversion provides strong support for subsequent underwater measurement.

The significant growth in technology advancement leads to underwater videos and images capturing for different purposes. However, the captured underwater images or videos suffer from the low contrast, color distortion, and haziness, thus it is required to enhance the quality of such images or videos for further analysis. The image enhancement techniques already proposed, however such methods are not applicable for the underwater images with the different physical properties. It is challenging research problem to optimize the underwater image quality. In this paper, first attempt towards the restoration of underwater image using the fusion based approach proposed. Previously, the weight maps are computed and fused to enhance the quality of images, but the weight maps introduces the artefacts while performing the fusion, hence to overcome that problem, the optimized fusion technique of weight maps for underwater image enhancement designed. The multi-step fusion approach works independently on two derived images from the original image. Then to optimize the visibility of underwater image, the three weight maps such as saliency, luminance, and chromaticity computed. These weight maps are fused in multi-step manner to overcome the challenge of artefacts and generate the final restored underwater image. The results prove the effectiveness of proposed model compared to single step fusion technique.

Objective: Due to the problems of light propagation underwater, such as scattering and absorption, which leads to low contrast, color distortion and blurring of details in the images obtained underwater, this phenomenon is more serious in the deep sea, and most undersea map images collected by manned submersibles during deep-sea exploration exhibit these issues. To address these problems, an underwater image fusion enhancement algorithm based on color correction and image sharpening is proposed for image enhancement and restoration. Methods: The automatic color enhancement algorithm is used to correct and enhance the color of the underwater image. Subsequently, the RGB three channels are corrected by gamma filtering. The RGB space is then converted to the Lab space, and the L channel is processed by the Contrast Limited Adaptive Histogram Equalization algorithm to enhance the luminance. At the same time, the color-corrected image is image-sharpened by using unsharpened mask algorithms. Finally, image fusion is performed by using the algorithm based on the fusion of guided filters. Results: The experimental results on several underwater images under different scenarios show that the enhancement effect achieved by this algorithm is better than the comparison algorithm. In the subjective aspect, the color and details of the images are better balanced and enhanced. In the objective aspect, quantitative evaluations are carried out in three aspects: Information entropy (IE), underwater image quality measure (UIQM), and underwater color image quality evaluation (UCIQE), in which the IE is quantitatively evaluated. Regarding the UCIQE, the proposed algorithm has a better effect than other algorithms in terms of IE, UIQM, and UCIQE. Specifically, compared to the original image, the proposed algorithm shows improvements of 33.4%, 1.45 times, and 54.4% or more in mean value. Conclusion: The results show that the algorithm has good results in image processing for underwater environments, with enhancement and restoration of images acquired through manned submersibles.

Underwater image enhancement method with light scattering characteristics

Quality evaluation of underwater images is a key goal of underwater video image retrieval and intelligent processing. To date, no metric has been proposed for underwater color image quality evaluation (UCIQE). The special absorption and scattering characteristics of the water medium do not allow direct application of natural color image quality metrics especially to different underwater environments. In this paper, subjective testing for underwater image quality has been organized. The statistical distribution of the underwater image pixels in the CIELab color space related to subjective evaluation indicates the sharpness and colorful factors correlate well with subjective image quality perception. Based on these, a new UCIQE metric, which is a linear combination of chroma, saturation, and contrast, is proposed to quantify the non-uniform color cast, blurring, and low-contrast that characterize underwater engineering and monitoring images. Experiments are conducted to illustrate the performance of the proposed UCIQE metric and its capability to measure the underwater image enhancement results. They show that the proposed metric has comparable performance to the leading natural color image quality metrics and the underwater grayscale image quality metrics available in the literature, and can predict with higher accuracy the relative amount of degradation with similar image content in underwater environments. Importantly, UCIQE is a simple and fast solution for real-time underwater video processing. The effectiveness of the presented measure is also demonstrated by subjective evaluation. The results show better correlation between the UCIQE and the subjective mean opinion score.