A Unified Remote Sensing Image Restoration Framework Integrating Frequency-Domain Physical Perception and Higher-Order Semantic Fusion

DONG Zhe; SUN Yuzhe; LIU Tianzhu; GU Yanfeng

doi:10.12263/DZXB.20251152

您当前的位置：

首页 >

文章列表页 >

A Unified Remote Sensing Image Restoration Framework Integrating Frequency-Domain Physical Perception and Higher-Order Semantic Fusion

PAPERS | 更新时间：2026-05-28

- A Unified Remote Sensing Image Restoration Framework Integrating Frequency-Domain Physical Perception and Higher-Order Semantic Fusion
- ACTA ELECTRONICA SINICA Vol. 54, Issue 2, Pages: 799-817(2026)
- 作者机构：
  
  哈尔滨工业大学电子与信息工程学院，黑龙江哈尔滨 150001
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(624B2051)
- DOI：10.12263/DZXB.20251152
  CLC： TP391.41;TP751
- Received：29 December 2025，
  
  Accepted：02 February 2026，
  
  Published：25 February 2026
- 稿件说明：
移动端阅览
董喆, 孙钰哲, 刘天竹, 等. 结合频域物理感知与高阶语义融合的一体化遥感图像复原框架[J]. 电子学报, 2026, 54(02): 799-817.

DONG Zhe, SUN Yuzhe, LIU Tianzhu, et al. A Unified Remote Sensing Image Restoration Framework Integrating Frequency-Domain Physical Perception and Higher-Order Semantic Fusion[J]. Acta Electronica Sinica, 2026, 54(02): 799-817.
董喆, 孙钰哲, 刘天竹, 等. 结合频域物理感知与高阶语义融合的一体化遥感图像复原框架[J]. 电子学报, 2026, 54(02): 799-817. DOI：10.12263/DZXB.20251152

DONG Zhe, SUN Yuzhe, LIU Tianzhu, et al. A Unified Remote Sensing Image Restoration Framework Integrating Frequency-Domain Physical Perception and Higher-Order Semantic Fusion[J]. Acta Electronica Sinica, 2026, 54(02): 799-817. DOI：10.12263/DZXB.20251152

摘要

遥感图像在成像链路中常受大气散射、传感器噪声及极端光照等多种异质退化因素的严重影响，现有一体化复原方法主要依赖隐式特征学习，缺乏对退化物理频域特性的显式建模及高阶语义交互能力。为此，本文提出一种结合频域物理感知与高阶语义融合的一体化遥感图像复原框架Aether。该框架构建频域自适应退化解析器（Harmonic-Adaptive Degradation Analyzer，HADA），利用数据驱动的可学习谐波滤波器组替代固定基底变换，实现对不同退化类型频谱指纹的自适应解析与精准提取。此外，设计基于Kolmogorov-Arnold表示定理的高阶非线性交互融合模块（Higher-Order Nonlinear Interaction Fusion，HONIF），通过样条函数网络构建高维映射空间，突破传统线性注意力的表达瓶颈，实现退化先验与图像特征的深度语义对齐。在MD-RSID、MD-RRSHID及MDRS-Landsat三个基准数据集上的实验表明，Aether在处理雾霾、噪声、模糊及低光等退化问题时均取得最优性能。特别是在MDRS-Landsat数据集上，该方法在去雾任务中的峰值信噪比（Peak Signal-to-Noise Ratio，PSNR）较次优方法提升3.63 dB，在低光增强任务中PSNR提升1.60 dB，且可学习感知图像块相似度（Learned Perceptual Image Patch Similarity，LPIPS）改善了75.2%，有效解决了复杂遥感场景下的一体化通用复原难题。

Abstract

Remote sensing imagery is often severely degraded along the imaging chain by heterogeneous factors such as atmospheric scattering

sensor noise

and extreme illumination conditions. Existing all-in-one restoration approaches predominantly rely on implicit feature learning

lacking explicit modeling of the physical frequency-domain properties of degradation and the ability to capture higher-order semantic interactions. To address these limitations

we present Aether

a unified remote sensing image restoration framework that integrates frequency-domain physical perception with higher-order semantic fusion. Aether introduces a harmonic-adaptive degradation analyzer (HADA)

which replaces fixed-basis transforms with a data-driven learnable harmonic filter bank. This enables adaptive parsing and precise extraction of spectral fingerprints associated with diverse degradation types. In addition

we design a higher-order nonlinear interaction fusion module (HONIF) grounded in the Kolmogorov-Arnold representation theorem. HONIF constructs a high-dimensional mapping space via spline-based function networks

overcoming the representational bottleneck of conventional linear attention and facilitating deep semantic alignment between degradation priors and image features. Experiments on three benchmark datasets—MD-RSID

MD-RRSHID

and MDRS-Landsat—demonstrate that Aether achieves state-of-the-art performance across haze removal

denoising

deblurring

and low-light enhancement tasks. Notably

on the MDRS-Landsat dataset

Aether surpasses the second-best method by 3.63 dB in peak signal-to-noise ratio (PSNR) for dehazing and by 1.60 dB for low-light enhancement

while improving learned perceptual image patch similarity (LPIPS) by 75.2%

effectively addressing the long-standing challenge of unified and generalizable restoration in complex remote sensing scenarios.

关键词

Keywords

references

Wang Peijuan , Bayram B , Sertel E . A comprehensive review on deep learning based remote sensing image super-resolution methods [J ] . Earth-Science Reviews , 2022 , 232 : 104110 . DOI: 10.1016/j.earscirev.2022.104110 http://dx.doi.org/10.1016/j.earscirev.2022.104110

Liu Baodi , Zhao Lifei , Shao Shuai , et al . RAN: Region-aware network for remote sensing image super-resolution [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2023 , 61 : 5408113 . DOI: 10.1109/tgrs.2023.3330876 http://dx.doi.org/10.1109/tgrs.2023.3330876

Lei Sen , Shi Zhenwei , Mo Wenjie . Transformer-based multistage enhancement for remote sensing image super-resolution [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2022 , 60 : 5615611 . DOI: 10.1109/tgrs.2021.3136190 http://dx.doi.org/10.1109/tgrs.2021.3136190

Dong Runmin , Mou Lichao , Zhang Lexing , et al . Real-world remote sensing image super-resolution via a practical degradation model and a kernel-aware network [J ] . ISPRS Journal of Photogrammetry and Remote Sensing , 2022 , 191 : 155 - 170 . DOI: 10.1016/j.isprsjprs.2022.07.010 http://dx.doi.org/10.1016/j.isprsjprs.2022.07.010

Chen Hao , Yokoya N , Chini M . Fourier domain structural relationship analysis for unsupervised multimodal change detection [J ] . ISPRS Journal of Photogrammetry and Remote Sensing , 2023 , 198 : 99 - 114 . DOI: 10.1016/j.isprsjprs.2023.03.004 http://dx.doi.org/10.1016/j.isprsjprs.2023.03.004

Roy S K , Deria A , Hong Danfeng , et al . Multimodal fusion transformer for remote sensing image classification [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2023 , 61 : 5515620 . DOI: 10.1109/tgrs.2023.3286826 http://dx.doi.org/10.1109/tgrs.2023.3286826

Kar A , Dhara S K , Sen D , et al . Zero-shot single image restoration through controlled perturbation of koschmieder’s model [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 16200 - 16210 . DOI: 10.1109/cvpr46437.2021.01594 http://dx.doi.org/10.1109/cvpr46437.2021.01594

Zamir S W , Arora A , Khan S , et al . Restormer: Efficient transformer for high-resolution image restoration [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 5718 - 5729 . DOI: 10.1109/cvpr52688.2022.00564 http://dx.doi.org/10.1109/cvpr52688.2022.00564

Chen Liangyu , Chu Xiaojian , Zhang Xiangyu , et al . Simple baselines for image restoration [C ] // Computer Vision-ECCV 2022 . Cham : Springer , 2022 : 17 - 33 . DOI: 10.1007/978-3-031-20071-7_2 http://dx.doi.org/10.1007/978-3-031-20071-7_2

Li Yawei , Fan Yuchen , Xiang Xiaoyu , et al . Efficient and explicit modelling of image hierarchies for image restoration [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2023 : 18278 - 18289 . DOI: 10.1109/cvpr52729.2023.01753 http://dx.doi.org/10.1109/cvpr52729.2023.01753

Khan S , Potlapalli V , Khan F S , et al . PromptIR: Prompting for all-in-one image restoration [C ] // Advances in Neural Information Processing Systems 36 . Neural Information Processing Systems Foundation, Inc. (NeurIPS) , 2023 : 71275 - 71293 . DOI: 10.52202/075280-3121 http://dx.doi.org/10.52202/075280-3121

Li Boyun , Liu Xiao , Hu Peng , et al . All-In-one image restoration for unknown corruption [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 17431 - 17441 . DOI: 10.1109/cvpr52688.2022.01693 http://dx.doi.org/10.1109/cvpr52688.2022.01693

Zhang Jianhai , Huang Jian , Yao Mingda , et al . Ingredient-oriented multi-degradation learning for image restoration [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2023 : 5825 - 5835 . DOI: 10.1109/cvpr52729.2023.00564 http://dx.doi.org/10.1109/cvpr52729.2023.00564

Zhao Chen , Cai Wenli , Dong Chengyu , et al . Wavelet-based Fourier information interaction with frequency diffusion adjustment for underwater image restoration [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 8281 - 8291 . DOI: 10.1109/cvpr52733.2024.00791 http://dx.doi.org/10.1109/cvpr52733.2024.00791

Cui Yuning , Ren Wenqi , Cao Xiaochun , et al . Image restoration via frequency selection [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2024 , 46 ( 2 ): 1093 - 1108 . DOI: 10.1109/tpami.2023.3330416 http://dx.doi.org/10.1109/tpami.2023.3330416

Cui Yuning , Tao Yi , Bing Zhenshan , et al . Selective frequency network for image restoration [C/OL ] // The 11th International Conference on Learning Representations . ICLR , 2023 . https://openreview.net/forum?id=tyZ1ChGZIKO https://openreview.net/forum?id=tyZ1ChGZIKO . DOI: 10.1109/iccv51070.2023.01195 http://dx.doi.org/10.1109/iccv51070.2023.01195

Tu Zhengzhong , Talebi H , Zhang Han , et al . MAXIM: Multi-axis MLP for image processing [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 5759 - 5770 . DOI: 10.1109/cvpr52688.2022.00568 http://dx.doi.org/10.1109/cvpr52688.2022.00568

Wang Zhendong , Cun Xiaodong , Bao Jianmin , et al . Uformer: A general U-shaped transformer for image restoration [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 17662 - 17672 . DOI: 10.1109/cvpr52688.2022.01716 http://dx.doi.org/10.1109/cvpr52688.2022.01716

Liang Jingyun , Cao Jiezhang , Sun Guolin , et al . SwinIR: Image restoration using swin transformer [C ] // 2021 IEEE/CVF International Conference on Computer Vision Workshops . Piscataway : IEEE , 2021 : 1833 - 1844 . DOI: 10.1109/iccvw54120.2021.00210 http://dx.doi.org/10.1109/iccvw54120.2021.00210

Song Tianyu , Fan Suming , Jin Jianyu , et al . Exploring an efficient frequency-guidance transformer for single image deraining [J ] . Signal, Image and Video Processing , 2024 , 18 ( 3 ): 2429 - 2438 . DOI: 10.1007/s11760-023-02918-z http://dx.doi.org/10.1007/s11760-023-02918-z

Fuoli D , Van Gool L , Timofte R . Fourier space losses for efficient perceptual image super-resolution [C ] // 2021 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2021 : 2340 - 2349 . DOI: 10.1109/iccv48922.2021.00236 http://dx.doi.org/10.1109/iccv48922.2021.00236

Huang Jing , Liu Yanjun , Zhao Feng , et al . Deep Fourier-based exposure correction network with spatial-frequency interaction [C ] // Computer Vision-ECCV 2022 . Cham : Springer , 2022 : 163 - 180 . DOI: 10.1007/978-3-031-19800-7_10 http://dx.doi.org/10.1007/978-3-031-19800-7_10

Valanarasu J M J , Yasarla R , Patel V M . TransWeather: Transformer-based restoration of images degraded by adverse weather conditions [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 2343 - 2353 . DOI: 10.1109/cvpr52688.2022.00239 http://dx.doi.org/10.1109/cvpr52688.2022.00239

Guo Hang , Li Jianmin , Dai Tao , et al . MambaIR: A simple baseline for image restoration with state-space model [C ] // Computer Vision - ECCV 2024 . Cham : Springer , 2025 : 222 - 241 . DOI: 10.1007/978-3-031-72649-1_13 http://dx.doi.org/10.1007/978-3-031-72649-1_13

Luo Ziwei , Gustafsson F K , Zhao Zheng , et al . Controlling vision-language models for multi-task image restoration [PP/OL ] . V2. arXiV ( 2024-02-28 ) [ 2025-12-29 ] . https://doi.org/10.48550/arXiv.2310.01018 https://doi.org/10.48550/arXiv.2310.01018 .

Zhang Xin , Ma Jianqi , Wang Guoli , et al . Perceive-IR: Learning to perceive degradation better for all-in-one image restoration [J ] . IEEE Transactions on Image Processing , 2026 , 35 : 2018 - 2033 . DOI: 10.1109/tip.2025.3566300 http://dx.doi.org/10.1109/tip.2025.3566300

Cao Shen , Liu Yuhuan , Zhang Weilong , et al . GRIDS: Grouped multiple-degradation restoration with image degradation similarity [C ] // Computer Vision - ECCV 2024 . Cham : Springer , 2025 : 70 - 87 . DOI: 10.1007/978-3-031-72897-6_5 http://dx.doi.org/10.1007/978-3-031-72897-6_5

Wu Gang , Jiang Junjun , Wang Yujie , et al . Debiased all-in-one image restoration with task uncertainty regularization [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2025 , 39 ( 8 ): 8386 - 8394 . DOI: 10.1609/aaai.v39i8.32905 http://dx.doi.org/10.1609/aaai.v39i8.32905

Xia Bin , Zhang Yulun , Wang Shiyin , et al . DiffIR: Efficient diffusion model for image restoration [C ] // 2023 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2023 : 13049 - 13059 . DOI: 10.1109/iccv51070.2023.01204 http://dx.doi.org/10.1109/iccv51070.2023.01204

Jiang Yuntian , Zhang Zeyu , Xue Tianfan , et al . AutoDIR: Automatic all-in-one image restoration with latent diffusion [C ] // Computer Vision - ECCV 2024 . Cham : Springer , 2025 : 340 - 359 . DOI: 10.1007/978-3-031-73661-2_19 http://dx.doi.org/10.1007/978-3-031-73661-2_19

Chen Haoyu , Li Wenbo , Gu Jinjin , et al . RestoreAgent: Autonomous image restoration agent via multimodal large language models [C ] // Advances in Neural Information Processing Systems 37 . Neural Information Processing Systems Foundation , Inc. , 2024 : 110643 - 110666 . DOI: 10.52202/079017-3512 http://dx.doi.org/10.52202/079017-3512

Jiang Junjun , Zuo Zhenyu , Wu Gang , et al . A survey on all-in-one image restoration: Taxonomy, evaluation and future trends [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2025 , 47 ( 12 ): 11892 - 11911 . DOI: 10.1109/tpami.2025.3598132 http://dx.doi.org/10.1109/tpami.2025.3598132

Feng Yujie , Yang Yu , Fan Xiaohui , et al . A progressive image restoration network for high-order degradation imaging in remote sensing [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2025 , 63 : 5633816 . DOI: 10.1109/tgrs.2025.3590753 http://dx.doi.org/10.1109/tgrs.2025.3590753

Li Hezhe , Yuan Qiangqiang , He Jiang , et al . Ada4DIR: An adaptive model-driven all-in-one image restoration network for remote sensing images [J ] . Information Fusion , 2025 , 118 : 102930 . DOI: 10.1016/j.inffus.2025.102930 http://dx.doi.org/10.1016/j.inffus.2025.102930

Dong Zhe , Sun Yuzhe , Jiang Haochen , et al . PhyDAE: Physics-guided degradation-adaptive experts for all-in-one remote sensing image restoration [PP/OL ] . V1. arXiV ( 2025-10-09 ) [ 2025-12-29 ] . https://doi.org/10.48550/arXiv.2510.08653 https://doi.org/10.48550/arXiv.2510.08653 .

Wang Shuo , Zhang Libo . A unified framework for double-degradation remote sensing image restoration through saliency-guided interaction learning [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2024 , 62 : 5607719 . DOI: 10.1109/tgrs.2024.3357730 http://dx.doi.org/10.1109/tgrs.2024.3357730

Dian Renwei , Li Shutao . Hyperspectral image super-resolution via subspace-based low tensor multi-rank regularization [J ] . IEEE Transactions on Image Processing , 2019 , 28 ( 10 ): 5135 - 5146 . DOI: 10.1109/tip.2019.2916734 http://dx.doi.org/10.1109/tip.2019.2916734

Chi Kancheng , Yuan Yuan , Wang Qi . Trinity-net: Gradient-guided swin transformer-based remote sensing image dehazing and beyond [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2023 , 61 : 4702914 . DOI: 10.1109/tgrs.2023.3285228 http://dx.doi.org/10.1109/tgrs.2023.3285228

Zhu Zhihui , Lu Wei , Chen Shibin , et al . Real-world remote sensing image dehazing: Benchmark and baseline [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2025 , 63 : 4705014 . DOI: 10.1109/tgrs.2025.3584234 http://dx.doi.org/10.1109/tgrs.2025.3584234

Song Yudong , He Zhiqiang , Qian Hao , et al . Vision transformers for single image dehazing [J ] . IEEE Transactions on Image Processing , 2023 , 32 : 1927 - 1941 . DOI: 10.1109/tip.2023.3256763 http://dx.doi.org/10.1109/tip.2023.3256763

Wen Yubo , Gao Tian , Zhang Jian , et al . Multi-axis prompt and multi-dimension fusion network for all-in-one weather-degraded image restoration [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2025 , 39 ( 8 ): 8323 - 8331 . DOI: 10.1609/aaai.v39i8.32898 http://dx.doi.org/10.1609/aaai.v39i8.32898

Zhu Ruixing , Tu Zhengzhong , Liu Jianmin , et al . MW-Former: Multi-weather image restoration using degradation-aware transformers [J ] . IEEE Transactions on Image Processing , 2024 , 33 : 6790 - 6805 . DOI: 10.1109/tip.2024.3501855 http://dx.doi.org/10.1109/tip.2024.3501855

Cui Yuning , Zamir S W , Khan S , et al . AdaIR: Adaptive all-in-one image restoration via frequency mining and modulation [C ] // 13th International Conference on Learning Representations . ICLR , 2025 : 57335 - 57356 . DOI: 10.1109/indin64977.2025.11279637 http://dx.doi.org/10.1109/indin64977.2025.11279637

Guo Yan , Gao Yu , Lu Yuxin , et al . OneRestore: A universal restoration framework for composite degradation [C ] // Computer Vision - ECCV 2024 . Cham : Springer Nature Switzerland , 2024 : 255 - 272 . DOI: 10.1007/978-3-031-72655-2_15 http://dx.doi.org/10.1007/978-3-031-72655-2_15

Wang Ting , Zhang Kehai , Shao Zhiqiang , et al . GridFormer: Residual dense transformer with grid structure for image restoration in adverse weather conditions [J ] . International Journal of Computer Vision , 2024 , 132 ( 10 ): 4541 - 4563 . DOI: 10.1007/s11263-024-02056-0 http://dx.doi.org/10.1007/s11263-024-02056-0

Tang Xiaolin , Gu Xin , He Xiaoyun , et al . Degradation-aware residual-conditioned optimal transport for unified image restoration [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2025 , 47 ( 8 ): 6764 - 6779 . DOI: 10.1109/tpami.2025.3562211 http://dx.doi.org/10.1109/tpami.2025.3562211

Zamfir E , Wu Ziwei , Mehta N , et al . Complexity experts are task-discriminative learners for any image restoration [C ] // 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2025 : 12753 - 12763 . DOI: 10.1109/cvpr52734.2025.01190 http://dx.doi.org/10.1109/cvpr52734.2025.01190

Mou Chong , Wang Qi , Zhang Jian . Deep generalized unfolding networks for image restoration [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 17378 - 17389 . DOI: 10.1109/cvpr52688.2022.01688 http://dx.doi.org/10.1109/cvpr52688.2022.01688

Kong Xiangtao , Dong Chao , Zhang Lei . Towards effective multiple-in-one image restoration: A sequential and prompt learning strategy [PP/OL ] . V3. arXiV ( 2024-03-20 ) [ 2025-12-29 ] . https://doi.org/10.48550/arXiv.2401.03379 https://doi.org/10.48550/arXiv.2401.03379 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Compact Microstrip Second-Order Frequency-Variant Coupled Bandpass Filter with Simplified Composite Right-/Left-Handed Zeroth-Order Resonator

Multimodal Smart Contract Vulnerability Detection Enhanced by Large Language Model Semantics

Encrypted Traffic Detection Based on Gradient Collaboration and Feature Fusion

A Priority-Weighted and Packet Arrival Time Based Scheduling Algorithm for MP-QUIC

Identification and Migration of Silent Security Patches in Blockchain Systems via Information Fusion

Related Author

No data

Related Institution

No data

⁰