Underwater Image Enhancement Based on Multi-Scale Spatial and Channel Attention Fusion

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.

Underwater optical imaging can intuitively reflect internal state of the ocean. However, due to absorption and scattering of light, the degree of attenuation of different wavelengths of light in seawater is different, and underwater images suffer from low contrast and color distortion. To address the problems, a novel network based on U-Net is proposed for underwater image enhancement in this paper. The network consists of two branches namely Branch1 and Branch2: Branch 1 contains a channel attention module and a recurrent residual convolutional neural network based on spatial attention termed AttR2U-Net that is capable of extracting multiscale features. Branch 2 contains three residual groups, embedded in the residual dense block of the channel attention model, by re-weighting the features of different channels to enhance useful features. Furthermore, through dense cascading and residual learning, convolutional enhancement branches extract high-frequency information such as edges in the corrected image to maintain original structure and edges. Finally, results of the outputs of the two branches are fused. Comparable studies demonstrate that the proposed method is superior to state-of-art methods in color correction on underwater images in different scenes and enhancement of the clarity and contrast of images.

In ocean engineering, an underwater vehicle is widely used as an important equipment to explore the ocean. However, due to the reflection and attenuation of light when propagating in water, the images captured by the visual system of an underwater vehicle in the complex underwater environment usually suffer from low visibility, blurred details, and color distortion. To solve this problem, in this article, we present an underwater image enhancement framework based on transfer learning, which consists of a domain transformation module and an image enhancement module. The two modules, respectively, perform color correction and image enhancement, effectively transferring in-air image dehazing to underwater image enhancement. To maintain the physical properties of an underwater image, we embed the physical model into the domain transformation module which ensures that the transformed image complies with the physical model. To effectively remove the color deviation, a coarse-grained similarity calculation is added to the domain transformation module to improve the model performance. The experimental results on real-world underwater images of different scenes show that the presented method is superior to some advanced underwater image enhancement algorithms both qualitatively and quantitatively. Furthermore, we conduct ablation experiments to indicate the contribution of each component and further validate the effectiveness of the presented method through application tests.

Due to complex underwater environments characterized by severe scattering, absorption, and color distortion, accurate restoration remains challenging. This paper proposes a hybrid approach combining dual transmission estimation, adaptive ambient light estimation with color correction, and a U-Net Transformer (Uformer) for underwater image enhancement. Our method estimates transmission maps by integrating boundary constraints and local contrast, which effectively address visibility degradation. An adaptive ambient light estimation and color correction strategy are further developed to correct color distortion robustly. Subsequently, a Uformer network enhances the restored image by capturing global and local contextual features effectively. Experiments conducted on publicly available underwater image datasets validate our approach. Performance is quantitatively evaluated using widely adopted non-reference image quality metrics, especially Underwater Image Quality Measure (UIQM) and Underwater Color Image Quality Evaluation (UCIQE). The results demonstrate that our proposed method achieves superior enhancement performance over several state-of-the-art methods.

Bayesian retinex underwater image enhancement

Underwater images often suffer from color distortion and detail loss due to light absorption and scattering, which degrades visual quality and limits practical applications. To address these issues, a novel adaptive algorithm for underwater image color correction and detail enhancement is proposed. The algorithm first applies threshold stretching to adjust the grayscale range, enhancing contrast while mitigating the risk of localized overcompensation. Based on the color distribution, images are categorized into bluish and greenish tones, providing the foundation for the adaptive color compensation method (ACCM). The ACCM is designed to separately compensate different color channels, using the green channel as a reference to restore the most degraded channels while maintaining overall color balance. The compensation process is further constrained by the minimum color loss criterion to ensure consistent color fidelity. Furthermore, an edge detail enhancement method is formulated to recover fine details by amplifying intensity differences between the original image and its smoothed version. Extensive experiments on multiple underwater image data sets demonstrate that the proposed algorithm consistently outperforms state-of-the-art methods, achieving average improvements of 0.0021, 0.0646, 0.3677, and 0.0800 in underwater color image quality evaluation, underwater image quality metric, fog aware density evaluator, and colorfulness contrast fog density index metrics, respectively, underscoring its effectiveness and robustness across diverse underwater environments.

Underwater image enhancement has drawn much attention due to the significance of underwater vision. Although considerable progress has been made in this field, a key problem remains unsolved: how can we extract and enhance minutiae while trying to remove the noise caused by scattering and attenuation? To address this limitation, we propose a new underwater image enhancement technique with a novel spiral generative adversarial framework, named Spiral-GAN, which can effectivelly recover real-world underwater images with more details, vivid colors and better contrast. For steady training and color correction, we include the pixelwise losses that consist of a mean squared error and an angle error in our objective function. In addition, we design our generator with several deconv-conv blocks to preserve the details from the original distorted images. Furthermore, we present a spiral learning strategy for generalizing the enhancing model to effectively recover the real-world underwater images. Finally, we perform a number of qualitative and quantitative evaluations that suggest that our proposed approach can efficiently enhance the quality of underwater images, which can be further used for underwater object detection.

Underwater imaging posts a challenge due to the degradation by the absorption and scattering occurred during light propagation as well as poor lighting conditions in water medium. Although image filtering techniques are utilized to improve image quality effectively, problems of the distortion of image details and the bias of color correction still exist in output images due to the complexity of image texture distribution. This paper proposes a new underwater image enhancement method based on image structural decomposition. By introducing a curvature factor into the Mumford_Shah_G decomposition algorithm, image details and structure components are better preserved without the gradient effect. Thus, histogram equalization and Retinex algorithms are applied in the decomposed structure component for global image enhancement and non-uniform brightness correction for gray level and the color images, then the optical absorption spectrum in water medium is incorporate to improve the color correction. Finally, the enhanced structure and preserved detail component are recomposed to generate the output. Experiments with real underwater images verify the image improvement by the proposed method in image contrast, brightness and color fidelity.

Underwater images suffer from the quality degradation caused by the light scattering and absorption in the water. Recent deep-learning based underwater image enhancement methods achieve limited performance due to the lack of proper training datasets. In this paper, we provide a realistic underwater image dataset reflecting the diverse characteristics of turbidity and color distortion in underwater environments. We also design an underwater image enhancement network to exploit the local and global features of the turbid underwater images with color distortion. The experimental results show that the proposed dataset is more effective than existing datasets to train deep neural networks, and the proposed underwater image enhancement network successfully removes the haze and color distortion from real underwater images while outperforming the existing methods.

Underwater image enhancement has been widely used and received increasing attention. However, visual perception is affected by environmental factors, which reduces the visual quality. These images often suffer from color distortion, low contrast, and lack of detail, and the color of the image turns green or blue. This paper proposes an underwater image enhancement method based on deep learning and establishes a neural network based on dilated convolution and parameter correction. Firstly, multi-scale features are extracted, and then global features are used to enhance local features at each scale. In addition, the innovative CBAM attention mechanism is introduced. The algorithm is significantly faster than ICM, RGHS, UCM, CLAHE, HE, etc., in terms of operation speed. Besides, better computational performance, color correction, and detail retention are obtained.

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

Light of long wavelengths is absorbed almost immediately with depth, while remaining photons are scattered by suspended particles, producing images that are bright, color‑distorted, and structurally blurred. Underwater imaging is therefore a grand challenge across diverse marine environments. Existing enhancement methods fail to balance image fidelity and speed or depend on large, environment‑specific training sets that lack generalization. We propose a frequency‑based quantum‑classical pipeline that uses the Quantum Fourier Transform (QFT) to optimize underwater images without extensive data. The luminance and chroma channels are encoded into quantum states; QFT reveals the spectral content. In the quantum frequency domain, we suppress low‑frequency illumination artifacts and enhance high‑frequency edges and fine details. The modified spectrum is decoded back into classical space in a manner compatible with Noisy Intermediate‑Scale Quantum (NISQ) devices. Experiments on standard underwater datasets show significant improvements in visibility, color balance, and edge sharpness compared to traditional Fourier methods and deep‑learning models. This work demonstrates that quantum spectral processing is an efficient, multi‑productive tool for underwater image enhancement, providing substantial gains in underwater visual perception notably, and for marine navigation and research, in challenging visibility conditions for autonomous underwater vehicles.

Underwater image enhancement and object recognition are crucial in multiple fields, like marine biology, archeology, and environmental monitoring, but face severe challenges due to low light, color distortion, and reduced contrast in underwater environments. DeepSeaNet re-evaluates the model guidance strategy from multiple dimensions, enhances color recovery using the MCOLE score, and addresses the problem of inconsistent attenuation across different regions of underwater images by integrating a feature extraction method guided by a global attention mechanism by ViT. Comprehensive tests on diverse underwater datasets show that DeepSeaNet achieves a maximum PSNR of 28.96 dB and an average SSIM of 0.901, representing a 20–40% improvement over baseline methods. These results highlight DeepSeaNet’s superior performance in enhancing image clarity, color richness, and contrast, making it a remarkably effective instrument for underwater image processing and analysis.

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.

In the computer vision field, underwater object detection has been a challenging task. Due to the attenuation of light in a medium and the scattering of light by suspended particles in water, underwater optical images often face the problems of color distortion and target feature blurring, which greatly affect the detection accuracy of underwater object detection. Although deep learning-based algorithms have achieved state-of-the-art results in the field of object detection, most of them cannot be applied to practice because of the limited computing capacity of a low-power processor embedded in unmanned underwater vehicles. This paper proposes a lightweight underwater object detection network based on the YOLOX model called LUO-YOLOX. A novel weighted ghost-CSPDarknet and simplified PANet were used in LUO-YOLOX to reduce the parameters of the whole model. Moreover, aiming to solve the problems of color distortion and unclear features of targets in underwater images, this paper proposes an efficient self-supervised pre-training joint framework based on underwater auto-encoder transformation (UAET). After the end-to-end pre-training process with the self-supervised pre-training joint framework, the backbone of the object detection network can extract more essential and robust features from degradation images when retrained on underwater datasets. Numerous experiments on the URPC2021 and detecting underwater objects (DUO) datasets verify the performance of our proposed method. Our work can assist unmanned underwater vehicles to perform underwater object detection tasks more accurately.