A Method for Remote Sensing Image Restoration Based on the System Degradation Model
Results in Physics(2023)
Harbin Inst Technol
Abstract
High-definition remote sensing images have been widely used in many fields such as urban planning and resource exploration. Due to the impact of imaging links, the quality of images produced by remote sensing platforms often deteriorates. Therefore, high-performance remote sensing image restoration processing methods are of great significance for improving their application efficiency. However, existing deep learning methods have not been matched and adjusted based on the imaging characteristics and degradation mechanism of remote sensing systems, and lack representation and constraints on various prior information of remote sensing platforms, which leads to false information easily and is not conducive to interpretation application. To overcome these problems, in this work, we conduct research on a multi-stage remote sensing image restoration network. First, we propose a multi-stage network framework of "denoising deblurring detail enhancement", in which structures at different stages are designed to address the multi-scale characteristics of remote sensing images. Secondly, in order to avoid the degradation of the multi-stage network, we design a differentiated intermediate supervision module and an adaptive structural adjustment module. Finally, based on the degradation characteristics of the remote sensing platform imaging system, we propose a loss function from the prior term of the modulation transfer function. We verify our method by conducting comprehensive comparisons on a new dataset by the full-link imaging simulation. Experiments show that our method is superior to other comparison methods in remote sensing image restoration, and shows competitive performance in terms of restoration performance and speed. Compared with the basic network, the proposed modules improve PSNR and SSIM by 7.18% and 4.74% respectively.
MoreTranslated text
Key words
Optical remote sensing,Image restoration,Deep learning,Multi-stage network,Loss function design
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