Current methods for underwater image enhancement primarily focus on single-frame processing. While these approaches achieve impressive results for static images, they often fail to maintain temporal coherence across frames in underwater videos, which leads to temporal artifacts and frame flickering. Furthermore, existing enhancement methods struggle to accurately capture features in underwater scenes. This makes it difficult to handle challenges such as uneven lighting and edge blurring in complex underwater environments. To address these issues, this paper presents a dual-branch underwater video enhancement network. The network synthesizes short-range video sequences by learning and inferring optical flow from individual frames. It effectively enhances temporal consistency across video frames through predicted optical flow information, thereby mitigating temporal instability within frame sequences. In addition, to address the limitations of traditional U-Net models in handling complex multiscale feature fusion, this study proposes a novel underwater feature fusion module. By applying both max pooling and average pooling, this module separately extracts local and global features. It utilizes an attention mechanism to adaptively adjust the weights of different regions in the feature map, thereby effectively enhancing key regions within underwater video frames. Experimental results indicate that when compared with the existing underwater image enhancement baseline method and the consistency enhancement baseline method, the proposed model improves the consistency index by 30% and shows a marginal decrease of only 0.6% in enhancement quality index, demonstrating its superiority in underwater video enhancement tasks.

The coexistence of cloud and snow is very common in remote sensing images. It presents persistent challenges for automated interpretation systems, primarily due to their highly similar visible light spectral characteristic in optical remote sensing images. This intrinsic spectral ambiguity significantly impedes accurate cloud and snow segmentation tasks, particularly in delineating fine boundary features between cloud and snow regions. Much research on cloud and snow segmentation based on deep learning models has been conducted, but there are still deficiencies in the extraction of fine boundaries between cloud and snow regions. In addition, existing segmentation models often misjudge the body of clouds and snow with similar features. This work proposes a Multi-scale Feature Mixed Attention Network (MFMANet). The framework integrates three key components: (1) a Multi-scale Pooling Feature Perception Module to capture multi-level structural features, (2) a Bilateral Feature Mixed Attention Module that enhances boundary detection through spatial-channel attention, and (3) a Multi-scale Feature Convolution Fusion Module to reduce edge blurring. We opted to test the model using a high-resolution cloud and snow dataset based on WorldView2 (CSWV). This dataset contains high-resolution images of cloud and snow, which can meet the training and testing requirements of cloud and snow segmentation tasks. Based on this dataset, we compare MFMANet with other classical deep learning segmentation algorithms. The experimental results show that the MFMANet network has better segmentation accuracy and robustness. Specifically, the average MIoU of the MFMANet network is 89.17%, and the accuracy is about 0.9% higher than CSDNet and about 0.7% higher than UNet. Further verification on the HRC_WHU dataset shows that the MIoU of the proposed model can reach 91.03%, and the performance is also superior to other compared segmentation methods.

High-resolution meteorological satellite cloud imagery plays a crucial role in diagnosing and forecasting severe convective weather phenomena characterized by suddenness and locality, such as tropical cyclones. However, constrained by imaging principles and various internal/external interferences during satellite data acquisition, current satellite imagery often fails to meet the spatiotemporal resolution requirements for fine-scale monitoring of these weather systems. Particularly for real-time tracking of tropical cyclone genesis-evolution dynamics and capturing detailed cloud structure variations within cyclone cores, existing spatial resolutions remain insufficient. Therefore, developing super-resolution techniques for meteorological satellite cloud imagery through software-based approaches holds significant application potential. This paper proposes a Multi-scale Residual Deformable Attention Model (MRDAM) based on Generative Adversarial Networks (GANs), specifically designed for satellite cloud image super-resolution tasks considering their morphological diversity and non-rigid deformation characteristics. The generator architecture incorporates two key components: a Multi-scale Feature Progressive Fusion Module (MFPFM), which enhances texture detail preservation and spectral consistency in reconstructed images, and a Deformable Attention Additive Fusion Module (DAAFM), which captures irregular cloud pattern features through adaptive spatial-attention mechanisms. Comparative experiments against multiple GAN-based super-resolution baselines demonstrate that MRDAM achieves superior performance in both objective evaluation metrics (PSNR/SSIM) and subjective visual quality, proving its superior performance for satellite cloud image super-resolution tasks.