Towards Effective Noise Removal and Visual Enhancement Using CILA-SegNet for Color Casting and Illumination Distortions in Underwater Images

Deep Learning based Underwater Image Enhancement: A Review of Trends, Challenges, and Task Relevance

Underwater images often suffer from significant quality degradation due to light absorption, scattering, suspended particles, low illumination, and color distortion, which limit their usability in marine applications. To address these challenges, deep learning-based methods, including Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), transformer-based architectures, and hybrid models, have been extensively developed to enhance visual quality by improving color consistency, contrast, and structural details. In this paper, we present a comprehensive review of these approaches and propose a unified taxonomy that systematically categorizes existing methods while highlighting recent advancements. In addition, we emphasize the emerging concept of task-aware enhancement, where image quality is evaluated based on its effectiveness in downstream tasks such as object detection, segmentation, and marine monitoring. This perspective is important as it bridges the gap between visual enhancement and practical application performance. Furthermore, we demonstrate that integrating multiple learning paradigms and adopting application-driven evaluation strategies can improve robustness and generalization. The findings suggest that hybrid and task-aware approaches are promising directions for developing efficient and reliable underwater image enhancement systems.

Deep white balance and dark channel prior fusion: Toward efficient and natural low-light image restoration

Image enhancement in low-light conditions is a challenging problem within the field of computer vision, since underexposed images generally lead to poor visibility, low contrast, noise amplification, and color distortion. Recent deep learning approaches have indeed shown promising performance, yet most of them adopt computation-heavy architectures and do not treat the luminance enhancement and color restoration separately; as a result cause unnatural restorations. To this end, in this paper, we present an efficient low-light image enhancement framework based on the Deep White-Balance (DWB) with Dark Channel Prior guidance in the YCbCr color space. The proposed framework separates luminance and chrominance components, making it easier to manage brightness enhancement and color restoration separately. This method aims to generate visually consistent enhanced images while preserving color fidelity and avoiding common enhancement artifacts. We evaluate the performance of the proposed method on reference benchmark datasets (LOL, LOLv2-Synthetic, and LIME) as well as a no-reference benchmark dataset (DICM). The experimental results demonstrate that, although state-of-the-art deep learning methods achieve higher numerical scores, qualitatively, the framework produces enhanced images with consistent contrast and illumination, while retaining color fidelity, all requiring less computational resources. Moreover, it does not require any further training or fine-tuning since the proposed approach is based on a pretrained Deep White Balance model and only uses inference. Experimental results show that the proposed method provides a convincing quality-efficiency compromise for low-light image enhancement.

EG-RetinexNet: entropy-guided illumination enhancement using Retinex theory and Swish-based CNN

Experimental results show that the proposed approach achieves better contrast enhancement, noise suppression, and color preservation compared with other methods, and the lightweight architecture and low computational complexity make the method suitable for practical low-light image enhancement applications.

Bidirectional Convolutional-GRU Integrated GAN for Unpaired Low-Light Image Enhancement

Image enhancement is a widely researched area in the domain of computer vision, particularly image processing. Among the subdomains, low-light image enhancement (LLIE) receives considerable attention due to problems and challenges imposed by poor lighting conditions. As such, low-light images suffer from poor visibility, distorted colors, and loss of details, which limits their usability in many applications. The traditional methods have struggled to preserve such details and make the images susceptible to over-enhancement. Whereas, the learning-based techniques rely heavily on paired datasets for training. Therefore, we propose a Bidirectional Conv-GRU integrated GAN framework. Involving bidirectional Conv-GRU modules in our use-case enables the model to capture both local textures and long-range feature dependencies. Also, the use of unpaired datasets allows it to learn flexible and realistic mappings without the strict need for aligned image pairs. The results demonstrate the potency of our proposed work as compared to state-of-the-art methods.

Not All Pixels Sink: Phase-Guided Representation Learning For Underwater Image Restoration

Enhancing low-light images with MSHCDI-Net: A multi-scale hybrid cross-domain interaction approach

Low-light image enhancement aims to improve visual visibility and perceptual quality under challenging illumination conditions. However, conventional convolutional neural networks (CNNs) are inherently limited in modeling long-range dependencies due to their restricted receptive fields, which often leads to insufficient global context modeling and suboptimal restoration results. To address this limitation, we propose MSHCDI-Net, a Multi-Scale Hybrid Cross-Domain Interaction Network that effectively integrates CNN and Transformer branches to jointly capture local texture details and global contextual relationships. Specifically, the proposed framework adopts a hierarchical encoder–decoder architecture to perform multi-scale feature extraction and progressive reconstruction. A cross-domain interaction mechanism is introduced to facilitate effective information exchange between convolutional and Transformer representations across multiple resolutions, enabling complementary modeling of fine-grained structures and long-range dependencies. Through adaptive feature fusion and multi-scale guidance, the network achieves improved structural consistency and detail restoration in low-light scenes. Extensive experiments on several public benchmarks demonstrate the effectiveness of the proposed method. MSHCDI-Net achieves 23.45 dB PSNR / 0.848 SSIM on LOL-v1, 23.74 dB / 0.910 SSIM on LOL-v2-synthetic, and 22.24 dB / 0.868 SSIM on LOL-v2-real, demonstrating competitive performance in both quantitative metrics and visual quality.