Remote Sensing Image Denoising Algorithm Based on Improved Transformer Network
2024 International Conference on Optoelectronic Information and Optical Engineering (OIOE 2024)(2024)
Abstract
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.
MoreTranslated text
求助PDF
上传PDF
View via Publisher
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example

Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
Summary is being generated by the instructions you defined