Underwater image enhancement based on conditional generative adversarial network

Clear and high-quality underwater images are essential for marine applications, including autonomous navigation, ecological monitoring, and infrastructure inspection. However, underwater images typically suffer from severe colour distortion, low contrast, and diminished structural visibility due to wavelength-dependent attenuation, scattering, and uneven illumination conditions. Recent deep learning-based underwater image enhancement (UIE) methods primarily adopt end-to-end frameworks, directly regressing enhanced images from degraded inputs. While these approaches have achieved significant progress, they often lack explicit modeling of the degradation process, leading to limited interpretability and suboptimal recovery of fine-grained details. To address these limitations, we propose DRM-Net, an explicit residual learning framework for UIE. Rather than estimating the enhanced image directly, DRM-Net first predicts a pixel-wise Degradation Residual Map (DRM) in the perceptually uniform CIELab colour space. This map explicitly quantifies local colour, contrast, and structural degradations, thereby enabling the network to precisely reconstruct missing visual information. Furthermore, we design a lightweight Subaquatic Multi-Scale Context Fusion module, which utilizes parallel atrous convolutions with softmax-weighted feature aggregation, significantly enhancing robustness against spatially heterogeneous scattering. Trained jointly with pixel-wise DRM and VGG-based perceptual losses, DRM-Net achieves superior colour fidelity, perceptual realism, and structural detail recovery. Comprehensive experiments conducted on multiple benchmarks demonstrate that our proposed approach attains competitive quantitative results and superior qualitative visual performance compared to state-of-the-art UIE methods, while maintaining low computational overhead, making it particularly suitable for resource-constrained underwater robotic systems.

The underwater color disparity is an important cue for enhancing an underwater image. Applying the underwater color disparity indiscriminately to the entire underwater image tends to give rise to foreground-background crosstalk with either excessive foreground or insufficient background enhancement. To address the discriminativeness between underwater color disparities in foreground and background regions, we develop a discriminative underwater image enhancement method empowered by large foundation model technology. We first utilize the Segment Anything Model to generate segmentation masks, dividing the underwater image into foreground and background regions. This enables accurate foreground-background separation. Then, we conduct adaptive color compensation and fusion to improve the color histogram similarity for foreground and background regions separately. This corrects color deviations and improves contrasts in a discriminative manner that avoids the foreground-background crosstalk. Finally, we propose high-frequency edge fusion to extract high-frequency components from both the original underwater image and the fused image, and then fuse these components to obtain the final enhanced image. This eliminates blurred details arising from the discriminative processing of foreground and background regions. Our method represents the pioneering application of large foundation model technology to empower underwater image enhancement. Experimental results indicate that our method outperforms nine state-of-the-art underwater image enhancement methods in visual quality, achieves superior results across five underwater image quality evaluation metrics on three underwater image datasets, and is beneficial for practical applications such as underwater feature matching. We release our code at https://gitee.com/wanghaoupc/UIE SAM.

Underwater images often have severe quality degradation and distortion due to light absorption and scattering in the water medium. A hazy image formation model is widely used to restore the image quality. It depends on two optical parameters: the background light (BL) and the transmission map (TM). Underwater images can also be enhanced by color and contrast correction from the perspective of image processing. In this paper, we propose an effective underwater image enhancement method for underwater images in composition of underwater image restoration and color correction. Firstly, a manually annotated background lights (MABLs) database is developed. With reference to the relationship between MABLs and the histogram distributions of various underwater images, robust statistical models of BLs estimation are provided. Next, the TM of R channel is roughly estimated based on the new underwater dark channel prior (NUDCP) via the statistic of clear and high resolution (HD) underwater images, then a scene depth map based on the underwater light attenuation prior (ULAP) and an adjusted reversed saturation map (ARSM) are applied to compensate and modify the coarse TM of R channel. Next, TMs of G-B channels are estimated based on the difference of attenuation ratios between R and G-B channels. Finally, to improve the color and contrast of the restored image with a dehazed and natural appearance, a variation of white balance is introduced as post-processing. In order to guide the priority of underwater image enhancement, sufficient evaluations are conducted to discuss the impacts of the key parameters including BL and TM, and the importance of the color correction. Comparisons with other state-of-the-art methods demonstrate that our proposed underwater image enhancement method can achieve higher accuracy of estimated BLs, lower computation time, overall superior performance, and better information retention.

In response to the challenges of blur distortion, low contrast and color fading in underwater images, caused by complex environmental factors and light attenuation, this study presents a novel underwater image enhancement method that leverages the U-Net architecture and channel attention mechanism fusion generative adversarial network (GAN), named UAEGAN. UAEGAN is built on the framework of GAN, combining the U-Net structure with a channel attention mechanism to construct a generator network, reducing the loss of low-level information during feature extraction and enhancing image details. Additionally, the algorithm employs a PatchGAN discriminator, which improves image resolution and detail representation by performing fine-grained true/false judgments on local image patches. Finally, the visual quality of the enhanced image is further optimized through the weighted fusion of multiple loss functions. Experimental results on the UIEB dataset indicate that UAEGAN outperforms the latest methods in terms of both visual quality and numerical metrics. The algorithm effectively enhances the clarity and visual quality of underwater images, providing strong support for subsequent underwater image processing tasks and applications.

Vision-based underwater exploration is crucial for marine research. However, the degradation of underwater images due to light attenuation and scattering poses a significant challenge. This results in the poor visual quality of underwater images and impedes the development of vision-based underwater exploration systems. Recent popular learning-based Underwater Image Enhancement (UIE) methods address this challenge by training enhancement networks with annotated image pairs, where the label image is manually selected from the reference images of existing UIE methods since the groundtruth of underwater images do not exist. Nevertheless, these methods encounter uncertainty issues stemming from ambiguous multiple-candidate references. Moreover, they often suffer from local perception and color perception limitations, which hinder the effective mitigation of wide-range underwater degradation. This paper proposes a novel NUAM-Net (Novel Underwater Image Enhancement Attention Mechanism Network) that addresses these limitations. NUAM-Net leverages a probabilistic training framework, measuring enhancement uncertainty to learn the UIE mapping from a set of ambiguous reference images. By extracting features from both the RGB and LAB color spaces, our method fully exploits the fine-grained color degradation clues of underwater images. Additionally, we enhance underwater feature extraction by incorporating a novel Adaptive Underwater Image Enhancement Module (AUEM) that incorporates both local and long-range receptive fields. Experimental results on the well-known UIEBD benchmark demonstrate that our method significantly outperforms popular UIE methods in terms of PSNR while maintaining a favorable Mean Opinion Score. The ablation study also validates the effectiveness of our proposed method.

The complexity of underwater environments combined with light attenuation and scattering in water often leads to quality degradation in underwater images, including color distortion and blurred details. To eliminate obstacles in underwater imaging, we propose an underwater image enhancement method based on a cascaded attention network called MSCA-Net. Specifically, this method designs an attention-guided module that connects channel and pixel attention in both serial and parallel ways to simultaneously achieve channel feature refinement and feature representation enhancement. Afterward, we propose a multi-scale feature integration module to capture information and details at different scales within the image. Meanwhile, residual connections are introduced to assist in deep feature learning via acquiring more detailed information from shallow features. We conducted extensive experiments on various underwater datasets, and the results demonstrate that our method still holds an advantage when compared to the latest underwater image enhancement methods.

Underwater images generally suffer from low contrast, serious noise and color distortion. The main challenges of underwater image enhancement are to preserve details in dark regions while avoiding oversaturetion in bright regions. This paper proposes a novel underwater image enhancement method based on image decomposition. By decomposing the high-frequency texture and noise into the texture layer, the transmission map is estimated from the noise-free structure layer to avoid the noise amplification problem in underwater image enhancement. Both the structure layer and texture layer are descattered with the estimated transmission map. After denoising by gradient residual minimizition, the texture layer is enhanced and added back into the structure layer to recover the final enhanced image. Experimental results verify that the proposed approach can recover the high-quality images with fine details and edges while improving contrast and color naturalness, especially for images taken in the high turbidity environment.

Aimed at the two problems of color deviation and poor visibility of the underwater image, this paper proposes an underwater image enhancement method based on the multi-scale fusion and global stretching of dual-model (MFGS), which does not rely on the underwater optical imaging model. The proposed method consists of three stages: Compared with other color correction algorithms, white-balancing can effectively eliminate the undesirable color deviation caused by medium attenuation, so it is selected to correct the color deviation in the first stage. Then, aimed at the problem of the poor performance of the saliency weight map in the traditional fusion processing, this paper proposed an updated strategy of saliency weight coefficient combining contrast and spatial cues to achieve high-quality fusion. Finally, by analyzing the characteristics of the results of the above steps, it is found that the brightness and clarity need to be further improved. The global stretching of the full channel in the red, green, blue (RGB) model is applied to enhance the color contrast, and the selective stretching of the L channel in the Commission International Eclairage-Lab (CIE-Lab) model is implemented to achieve a better de-hazing effect. Quantitative and qualitative assessments on the underwater image enhancement benchmark dataset (UIEBD) show that the enhanced images of the proposed approach achieve significant and sufficient improvements in color and visibility.

Region-specialized underwater image restoration in inhomogeneous optical environments

A multi-angle image enhancement method based on underwater imaging was proposed to solve the problems of color bias, geometric distortion and low contrast of the observed object in the complex and changeable underwater environment. Firstly, the gray world algorithm is used to preprocess the underwater image. Then an image optimization denoising algorithm based on K-SVD dictionary learning is used to keep the structure and texture information of the original image. Finally, combining with the underwater optical imaging model, the blue-green channel enhancement algorithm is used to realize the underwater imaging defog processing, which makes the restored image closer to the reality. The results show that this method can solve the problems of noise interference, fuzzy underwater image and low contrast.

Underwater polarimetric imaging for visibility enhancement utilizing active unpolarized illumination

Vision graph convolutional network for underwater image enhancement

Underwater images suffer from severe color distortion, due to the wavelength-dependent light attenuation and scattering. Various underwater image enhancement methods have been developed to improve the quality of degraded underwater images. However, contemporary approaches often overlook the impact of different scene colors on the overall process, potentially leading to undesired outcomes, such as enhanced images exhibiting excessive redness. In this paper, we observe that the color tones of degraded underwater images exhibit variability under the influence of different underwater targets and scenes. Each degraded color channel can be utilized to guide the color correction of other channels. Given this, a light-weight underwater color correction network, dubbed UCCNet, is presented to alleviate the issue of color corruption. In UCCNet, three parallel branches are designed to excavate the residual information within each color channel, subsequently leveraging these features to improve the quality of underwater images. Moreover, facing the challenge of effectively enhancing underwater images in diverse and complex scenes, the model UCCNet-KT is established based on UCCNet. In UCCNet-KT, the technology of knowledge transfer is designed to improve the generalization ability by enriching the dataset and constructing the loss function. Extensive experiments on various underwater datasets indicate the impressive performance of the UCCNet and UCCNet-KT qualitatively and quantitatively.

In order to solve the image blurring and distortion problem caused by underwater non-uniform and low illumination, this paper proposes an underwater image enhancement algorithm based on the Retinex theory and the Alternating Direction Method of Multipliers (ADMM). Firstly, the L component of the original image in the Lab space is extracted as the initial illumination map, and an Augmented Lagrange Multiplier (ALM) framework is constructed based on the ADMM to optimize the initial illumination map in order to obtain an accurate illumination image. In addition, the illumination map is further corrected in the luminance region with the Gamma Correction. Secondly, combined with the color constancy characteristics in the Retinex theory, the reflected image of the object is obtained. Finally, the bilateral filter is picked to suppress the underwater noise and obtain a more detailed enhanced image. The experimental results show that the underwater image enhancement algorithm can effectively solve the non-uniform illumination problem caused by natural light or artificial light source and improve the underwater image quality, thus having a better performance than other algorithms.

In either situation, underwater vision is affected by low light, diffraction, and color aberrations that lead to image distortion. To prevent this, we implemented a Texture Distribution Mapping Approach for undersea image improvement using MATLAB. Under this framework, we will enhance texture distribution, contrast, and visibility in general by controlling the most relevant properties of texture in the underwater environment. The TDM process is incremental: it involves pre-processing to eliminate noise and color distortion, followed by enhancement using another method for texture improvement. By enhancing texture mapping onto the image, we achieve a balance of visibility in high-texture regions, resulting in low-texture regions and better clarity and coloring. The method was compared against real underwater image data sets and tested for performance using quality measures like UCIQE (Underwater Color Image Quality Evaluation) and UIQM (Underwater Image Quality Measure). Experimental results and MATLAB implementation of the proposed algorithm exhibited stunning improvements in image quality and luminosity enhancements in texture compared to baseline methods, especially in challenging water conditions.