An integrated multi-scale context-aware network for efficient desnowing

Adverse snow conditions, significantly degrade visual data quality, resulting in substantial performance drops in computer vision systems. We propose an advanced neural network architecture designed for desnowing tasks, leveraging multi-scale features and context-aware attention mechanisms. Our novel network integrates a series of enhancements including ghost encoders for efficient feature representation and extraction through the utilization of linear transformations, and the multi-scale transformer bottleneck which combines the atrous spatial pyramid pooling with a vision transformer in the bottleneck to strengthen multi-scale feature extraction and captures local and global dependencies. Additionally, the SimGC attention module combines the simple parameter-free attention and global context attention, to enhance local and global spatial features. Lastly, the feature enhancement module is used to refine the final reconstruction. Our experimental results demonstrate that the proposed network significantly outperforms state-of-the-art methods on certain metrics and confirms the robustness and accuracy of our approach.