Remote sensing image denoising algorithm based on improved Transformer network

In the current optical remote sensing field, it has continuously evolved into a multi-layered and multi-perspective observation system. Faced with the complexities of observation tasks, diverse observation methods, and the refinement of observation targets, there is a need for more in-depth research on denoising of remote sensing images. Traditional denoising algorithms often produce denoised images with overly smooth edge textures, leading to the loss of small targets within the images. Therefore, addressing the aforementioned issues, this paper proposes an improved denoising algorithm based on the Transformer network structure. This algorithm employs attention operations across channel dimensions and utilizes feature recalibration. This allows the model to determine the importance of various feature channels, thereby avoiding the significant computational overhead brought about by the traditional Transformer's self-attention enhancement in spatial dimensions. Moreover, the algorithm utilizes a U-shaped denoising module, which effectively reduces the semantic gap between image feature mappings, resulting in the restoration of better image features. The experiments indicate that when tested on remote sensing image datasets, the proposed algorithm outperforms current representative algorithms in both subjective and objective evaluation metrics. While effectively removing image noise, it also better preserves edge details and texture features, achieving superior visual results.