Remote Sensing Image Denoising Based on Feature Interaction Complementary Learning

被引:2
作者
Zhao, Shaobo [1 ]
Dong, Youqiang [1 ]
Cheng, Xi [1 ]
Huo, Yu [1 ]
Zhang, Min [1 ]
Wang, Hai [1 ]
机构
[1] Xidian Univ, Sch Aerosp Sci & Technol, Xian 710126, Peoples R China
关键词
remote sensing image denoising; deep learning; feature interaction; complementary learning;
D O I
10.3390/rs16203820
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Optical remote sensing images are of considerable significance in a plethora of applications, including feature recognition and scene semantic segmentation. However, the quality of remote sensing images is compromised by the influence of various types of noise, which has a detrimental impact on their practical applications in the aforementioned fields. Furthermore, the intricate texture characteristics inherent to remote sensing images present a significant hurdle in the removal of noise and the restoration of image texture details. In order to address these challenges, we propose a feature interaction complementary learning (FICL) strategy for remote sensing image denoising. In practical terms, the network is comprised of four main components: noise predictor (NP), reconstructed image predictor (RIP), feature interaction module (FIM), and fusion module. The combination of these modules serves to not only complete the fusion of the prediction results of NP and RIP, but also to achieve a deep coupling of the characteristics of the two predictors. Consequently, the advantages of noise prediction and reconstructed image prediction can be combined, thereby enhancing the denoising capability of the model. Furthermore, comprehensive experimentation on both synthetic Gaussian noise datasets and real-world denoising datasets has demonstrated that FICL has achieved favorable outcomes, emphasizing the efficacy and robustness of the proposed framework.
引用
收藏
页数:20
相关论文
共 65 条
[1]   Real Image Denoising with Feature Attention [J].
Anwar, Saeed ;
Barnes, Nick .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :3155-3164
[2]   Category-Specific Object Image Denoising [J].
Anwar, Saeed ;
Porikli, Fatih ;
Cong Phuoc Huynh .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (11) :5506-5518
[3]   Spatial-Adaptive Network for Single Image Denoising [J].
Chang, Meng ;
Li, Qi ;
Feng, Huajun ;
Xu, Zhihai .
COMPUTER VISION - ECCV 2020, PT XXX, 2020, 12375 :171-187
[4]   Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network [J].
Chen, Hu ;
Zhang, Yi ;
Kalra, Mannudeep K. ;
Lin, Feng ;
Chen, Yang ;
Liao, Peixi ;
Zhou, Jiliu ;
Wang, Ge .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2017, 36 (12) :2524-2535
[5]   Image Denoising With Generative Adversarial Networks and its Application to Cell Image Enhancement [J].
Chen, Songkui ;
Shi, Daming ;
Sadiq, Muhammad ;
Cheng, Xiaochun .
IEEE ACCESS, 2020, 8 :82819-82831
[6]   Memory-Oriented Unpaired Learning for Single Remote Sensing Image Dehazing [J].
Chen, Xiang ;
Huang, Yufeng .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
[7]   Remote Sensing Image Scene Classification: Benchmark and State of the Art [J].
Cheng, Gong ;
Han, Junwei ;
Lu, Xiaoqiang .
PROCEEDINGS OF THE IEEE, 2017, 105 (10) :1865-1883
[8]   Deep Feature Aggregation Network for Hyperspectral Anomaly Detection [J].
Cheng, Xi ;
Huo, Yu ;
Lin, Sheng ;
Dong, Youqiang ;
Zhao, Shaobo ;
Zhang, Min ;
Wang, Hai .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2024, 73
[9]  
Cheng X, 2024, IEEE T INSTRUM MEAS, V73, DOI [10.1109/TIM.2023.3330225, 10.1109/TIM.2024.3373087]
[10]   Two-Stream Isolation Forest Based on Deep Features for Hyperspectral Anomaly Detection [J].
Cheng, Xi ;
Zhang, Min ;
Lin, Sheng ;
Zhou, Kexue ;
Zhao, Shaobo ;
Wang, Hai .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2023, 20