合成孔径雷达图像去噪算法研究进展

doi:10.12305/j.issn.1001-506X.2026.01.10

摘要/Abstract

摘要：

合成孔径雷达（synthetic aperture radar, SAR）成像过程中相干斑噪声的影响显著降低图像的质量和准确性，给图像的后续解译带来挑战。简要概述SAR图像相干斑的形成机理，列举常用SAR数据集及在相干斑噪声建模中的应用，比较传统去噪算法和基于深度学习的去噪算法的研究进展。在总结国内外学者研究的基础上，介绍空域滤波、非局部均值和变换域滤波等传统去噪方法的原理及优缺点，分析这些方法在保留图像细节与抑制噪声方面的局限性。概括包括卷积神经网络、生成对抗网络等在内的深度学习去噪算法的最新发展，探讨不同模型的优势与改进策略。最后，通过实验对比分析各算法的性能和不足，探讨当前SAR图像去噪面临的挑战及未来的发展趋势。

关键词: 合成孔径雷达, 图像去噪, 相干斑抑制, 人工智能, 深度学习

Abstract:

The imaging process of synthetic aperture radar （SAR） is significantly affected by speckle noise, which degrades the quality and accuracy of the images, posing challenges for subsequent image interpretation. This paper briefly summarizes the formation mechanism of SAR image speckle and compares the research progress of traditional denoising algorithms with deep learning-based denoising algorithms. Firstly, it introduces the principles and advantages/disadvantages of traditional denoising methods such as spatial filtering, non-local means, and transform domain filtering, analyzing their limitations in preserving image details and suppressing noise to clarify their application constraints. Subsequently, it summarizes the latest developments of deep learning denoising algorithms, including convolutional neural networks （CNN） and generative adversarial networks （GAN）, discussing the advantages and improvement strategies of different models. Finally, through experimental comparisons, it analyzes the performance and shortcomings of each algorithm, exploring the challenges faced by current SAR image denoising and future development trends.

Key words: synthetic aperture radar, image denoising, coherent speckle suppression, artificial intelligence, deep learning

中图分类号:

TN 957

陈海青, 汪刘应, 刘顾, 王龙, 葛超群, 陈孟州. 合成孔径雷达图像去噪算法研究进展[J]. 系统工程与电子技术, 2026, 48(1): 94-105.

Haiqing CHEN, Liuying WANG, Gu LIU, Long WANG, Chaoqun GE, Mengzhou CHEN. Research progress on denoising algorithms for synthetic aperture radar images[J]. Systems Engineering and Electronics, 2026, 48(1): 94-105.

图/表 10

图1

图2

表1

图3

表2

图4

图5

图6

表3

图7

参考文献 80

1	LI J, CHEN J, CHENG P, et al. A survey on deep-learning-based real-time SAR ship detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, 16, 3218- 3247. doi: 10.1109/JSTARS.2023.3244616
2	SHEN H F, ZHOU C X, LI J, et al. SAR image despeckling employing a recursive deep CNN prior[J]. IEEE Trans. on Geoscience and Remote Sensing, 2021, 59 (1): 273- 286.
3	朱磊, 姚同钰, 车晨洁, 等. 边缘引导的双分支网络SAR图像相干斑抑制方法[J]. 北京航空航天大学学报, 2025, 51(6): 1852−1862.
	ZHU L, YAO T Y, CHE C J, et al. Edge-guided dual-branch network for SAR image speckle suppression[J]. Journal of Beijing University of Aeronautics and Astronautics, 2025, 51(6): 1852−1862.
4	王俊杰. 成像雷达目标特征电磁调控技术研究[D]. 长沙: 国防科技大学, 2020.
	WANG J J. Research on electromagnetic regulation technology of imaging radar target characteristics [D]. Changsha: National University of Defense Technology, 2020.
5	邢孟道, 谢意远, 高悦欣, 等. 电磁散射特征提取与成像识别算法综述[J]. 雷达学报, 2022, 11 (6): 921- 942.
	XING M D, XIE Y Y, GAO Y X, et al. Electromagnetic scattering characteristic extraction and imaging recognition algorithm: a review[J]. Journal of Radars, 2022, 11 (6): 921- 942.
6	PAN Y C, ZHONG L H, CHEN J D, et al. SAR image despeckling based on denoising diffusion probabilistic model and Swin transformer[J]. Remote Sensing, 2024, 16 (17): 3222. doi: 10.3390/rs16173222
7	KEYDEL E R, LEE S W, MOORE J T. MSTAR extended operating conditions: a tutorial[C]// Proc. of SPIE, 1996, 2757: 228−242.
8	HUANG L Q, LIU B, LI B Y, et al. OpenSARShip: a dataset dedicated to Sentinel-1 ship interpretation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11 (1): 195- 208. doi: 10.1109/JSTARS.2017.2755672
9	HOU X Y, AO W, SONG Q, et al. FUSAR-Ship: building a high-resolution SAR-AIS matchup dataset of Gaofen-3 for ship detection and recognition[J]. Science China Information Sciences, 2020, 63 (4): 140303. doi: 10.1007/s11432-019-2772-5
10	ZHAO J P, ZHANG Z H, YAO W, et al. OpenSARUrban: a Sentinel-1 SAR image dataset for urban interpretation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13, 187- 203. doi: 10.1109/JSTARS.2019.2954850
11	SUN X, LV Y X, WANG Z R, et al. SCAN: scattering characteristics analysis network for few-shot aircraft classification in high-resolution SAR images[J]. IEEE Trans. on Geoscience and Remote Sensing, 2022, 60, 5226- 5517.
12	LEE J S. Refined filtering of image noise using local statistics[J]. Computer Graphics and Image Processing, 1983, 22 (2): 197- 206.
13	FROST V S, HAYES M H, WILSON A F, et al. A model for radar images and its application to adaptive digital filtering of multiplicative noise[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1982, 4 (2): 175- 186.
14	KUAN D T, HANSEN E R, JONES P A, et al. Adaptive noise smoothing filter for images with signal-dependent noise[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1985, 7 (2): 221- 229.
15	曹国金. 基于多尺度注意力与域自适应的遥感SAR图像变化检测[D]. 西安: 西安电子科技大学, 2023.
	CAO G J. Change detection of remote sensing SAR images based on multi-scale attention and domain adaptation[D]. Xi’an: Xi’an University of Electronic Science and Technology, 2023.
16	XU B, CUI Y, LI Z H, et al. Patch ordering-based SAR image despeckling via transform-domain filtering[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8 (4): 1682- 1695. doi: 10.1109/JSTARS.2014.2375359
17	WEI Z, BO L W, GONG Z, et al. SAR image denoising algorithm based on adaptive shrinkage in nonsubsampled contourlet domain[J]. Journal of Image and Graphics, 2009, 11 (2): 782- 795.
18	范旭. 基于Contourlet变换的SAR图像去噪研究[D]. 西安: 西安电子科技大学, 2015.
	FAN X. A study of SAR image denoising based on contourlet transform[D]. Xi’an: Xidian University, 2015.
19	刘帅奇, 胡绍海, 肖扬. 基于局部混合滤波的SAR图像去噪[J]. 系统工程与电子技术, 2012, 34 (2): 396- 402. doi: 10.3969/j.issn.1001-506X.2012.02.34
	LIU S Q, HU S H, XIAO Y. SAR image de-noise base on local hybrid filter[J]. Systems Engineering and Electronics, 2012, 34 (2): 396- 402. doi: 10.3969/j.issn.1001-506X.2012.02.34
20	刘帅奇, 胡绍海, 肖扬. 基于稀疏表示的Shearlet域SAR图像去噪[J]. 电子与信息学报, 2012, 34 (9): 2110- 2115.
	LIU S Q, HU S H, XIAO Y. Shearlet domain SAR image de-noising via sparse representation[J]. Journal of Electronics & Information Technology, 2012, 34 (9): 2110- 2115.
21	刘帅奇, 胡绍海, 肖扬. 基于复Shearlet域高斯混合模型的SAR图像去噪[J]. 航空学报, 2013, 34 (1): 173- 180.
	LIU S Q, HU S H, XIAO Y. SAR image denoising based on complex Shearlet transform domain Gaussian mixture model[J]. Acta Aeronautica, 2013, 34 (1): 173- 180.
22	PARRILLI S, PODERICO M, ANGELINO C V, et al. A nonlocal SAR image denoising algorithm based on LLMMSE wavelet shrinkage[J]. IEEE Trans. on Geoscience and Remote Sensing, 2012, 50 (2): 606- 616. doi: 10.1109/TGRS.2011.2161586
23	DELEDALE C A, DENIS L, TUPIN F. Iterative weighted maximum likelihood denoising with probabilistic patch-based weights[J]. IEEE Trans. on Image Processing, 2009, 18 (12): 2661- 2672. doi: 10.1109/TIP.2009.2029593
24	GUAN D D, XIANG D L, TANG X A, et al. SAR image despeckling based on nonlocal low-rank regularization[J]. IEEE Trans. on Geoscience and Remote Sensing, 2019, 57 (6): 3472- 3489. doi: 10.1109/TGRS.2018.2885089
25	LIU S Q, HU Q, LI P F, et al. Speckle suppression based on weighted nuclear norm minimization and grey theory[J]. IEEE Trans. on Geoscience and Remote Sensing, 2019, 57 (5): 2700- 2708. doi: 10.1109/TGRS.2018.2876339
26	ZHANG Q, YUAN Q Q, LI J, et al. Learning a dilated residual network for SAR image despeckling[J]. Remote Sensing, 2018, 10 (2): 196. doi: 10.3390/rs10020196
27	ZHAO W Y, DELEDALE C, DENIS L, et al. Ratio-based multitemporal SAR images denoising: RABASAR[J]. IEEE Trans. on Geoscience and Remote Sensing, 2019, 57 (6): 3552- 3565. doi: 10.1109/TGRS.2018.2885683
28	SALEEM A, ALVER M B, ÇETIN M. SAR image despeckling with CNN using a novel logarithmic discrete cosine transform-based loss[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17 (8): 1234- 1245.
29	CHIERCHIA G, COZZOLINO D, POGGI G, et al. SAR image despeckling through convolutional neural networks[C]// Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2017, 11: 23−28.
30	WANG P Y, ZHANG H, PATEL V M. SAR image despeckling using a convolutional neural network[J]. IEEE Signal Processing Letters, 2017, 24 (12): 1763- 1767. doi: 10.1109/LSP.2017.2758203
31	WANG J, ZHENG T, LEI P, et al. Ground target classification in noisy SAR images using convolutional neural networks[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11 (11): 163- 167.
32	SHI H Y, YANG X Y, ZHOU Q X, et al. SAR slow moving target imaging based on over-sampling smooth algorithm[J]. Chinese Journal of Electronics, 2017, 26 (4): 876- 882. doi: 10.1049/cje.2017.06.005
33	ZHANG T W, ZHANG X L. A polarization fusion network with geometric feature embedding for SAR ship classification[J]. Pattern Recognition, 2022, 123, 108365. doi: 10.1016/j.patcog.2021.108365
34	刘彤. 基于卷积神经网络的SAR图像去噪算法研究[D]. 保定: 河北大学, 2020.
	LIU T. Research on SAR image denoising algorithm based on convolutional neural network[D]. Baoding: Hebei University, 2020.
35	YANG T, SHI H Y, QIAO Z J. Enhanced SAR imaging using multiple plane spiral orbital angular momentum beams[J]. Measurement, 2022, 202, 111784. doi: 10.1016/j.measurement.2022.111784
36	张云, 穆慧琳, 姜义成, 等. 基于深度学习的雷达成像技术研究进展[J]. 雷达科学与技术, 2021, 19 (5): 467- 478.
	ZHANG Y, MU H L, JIANG Y C, et al. Overview of radar imaging techniques based on deep learning[J]. Radar Science and Technology, 2021, 19 (5): 467- 478.
37	ANKUSH M, YASIR A. Optical and SAR images-based image translation for change detection using generative adversarial network （GAN）[J]. Multimedia Tools and Applications, 2023, 82 (17): 26289- 26315. doi: 10.1007/s11042-023-14331-2
38	ZHANG Z W, LIU Y J, LIU T, et al. Edge detection algorithm of a symmetric difference kernel SAR image based on the GAN network model[J]. Symmetry, 2019, 11 (4): 557. doi: 10.3390/sym11040557
39	DING Z G, WANG Z W, WEI Y K, et al. SPA-GAN: SAR parametric autofocusing method with generative adversarial network[J]. Remote Sensing, 2022, 14 (20): 5159.
40	周驿枰. 基于生成对抗网络的SAR图像生成与数据扩充研究[D]. 西安: 西安电子科技大学, 2020.
	ZHOU Y P. The research of SAR image generation and data expansion based on generative adversarial network[D]. Xi’an: Xidian University, 2020.
41	GU F, ZHANG H, WANG C, et al. Residual encoder-decoder network introduced for multisource SAR image despeckling[J]. IEEE Access, 2017, 7 (4): 73- 78.
42	解涛, 郭建胜, 张晓丰, 等. 基于生成对抗网络的 SAR 图像降噪模型[J]. 电光与控制, 2022, 29 (9): 48- 52.
	XIE T, GUO J S, ZHANG X F, et al. SAR image noise reduction model based on GAN[J]. Electronics Optics & Control, 2022, 29 (9): 48- 52.
43	SHI H, ZHANG B C, WANG Y P, et al. SAR-to-optical image translation through generate-validate adversarial networks[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19
44	刘帅奇, 雷钰, 庞姣, 等. 基于生成对抗网络的SAR图像去噪[J]. 河北大学学报（自然科学版）, 2022, 42 (3): 306- 313.
	LIU S Q, LEI Y, PANG J, et al. SAR image denoising based on generative adversarial networks[J]. Journal of Hebei University （Natural Science Edition）, 2022, 42 (3): 306- 313.
45	WEI J, ZOU H X, SUN L, et al. CFRWD-GAN for SAR-to-optical image translation[J]. Remote Sensing, 2023, 15 (10): 2547.
46	ZHANG M, YANG L Y, YU D J, et al. Synthetic aperture radar image despeckling with a residual learning of convolutional neural network[J]. Optik, 2021, 228, 165876. doi: 10.1016/j.ijleo.2020.165876
47	DONG Y S, JIANG Z Q, TAO F Z, et al. Multiple spatial residual network for object detection[J]. Complex & Intelligent Systems, 2023, 9 (2): 1347- 1362.
48	GU F, ZHANG H, WANG C. A two-component deep learning network for SAR image denoising[J]. IEEE Access, 2020, 8, 17792- 17803. doi: 10.1109/ACCESS.2020.2965173
49	VITALE S, FERRAIOLI G, PASCAZIO V. Multi-objective CNN-based algorithm for SAR despeckling[J]. IEEE Trans. on Geoscience and Remote Sensing, 2021, 59 (11): 9336- 9349. doi: 10.1109/TGRS.2020.3034852
50	VITALE S, FERRAIOLI G, PASCAZIO V. A new ratio image based CNN algorithm for SAR despeckling[J]. Ithaca: Cornell University Library, 2019, 57 (12): 180- 190.
51	倪水平, 王仕杰, 李慧芳, 等. 多尺度残差密集注意力网络图像超分辨率重建[J]. 河南理工大学学报（自然科学版）, 2024, 43 (1): 140- 148. doi: 10.16186/j.cnki.1673-9787.2021110080
	NI S P, WANG S J, LI H F, et al. Image super-resolution reconstruction of multi-scale residual dense attention network[J]. Journal of Henan Polytechnic University （Natural Science）, 2024, 43 (1): 140- 148. doi: 10.16186/j.cnki.1673-9787.2021110080
52	LUO R, CHEN L F, XING J, et al. A fast aircraft detection method for SAR images based on efficient bidirectional path aggregated attention network[J]. Remote Sensing, 2021, 13 (15): 2940. doi: 10.3390/rs13152940
53	雷钰. 基于注意力卷积神经网络的SAR图像去噪算法研究[D]. 保定: 河北大学, 2022.
	LEI Y. Research on SAR image denoising algorithm based on attention convolutional neural network[D]. Baoding: Hebei University, 2022.
54	SHAN H L, FU X W, LV Z K, et al. Synthetic aperture radar images denoising based on multi-scale attention cascade convolutional neural network[J]. Measurement Science and Technology, 2023, 34, 085403.
55	LI L. Target detection network for SAR images based on semi-supervised learning and attention mechanism[J]. Remote Sensing, 2021, 13 (21): 4369- 4379. doi: 10.3390/rs13214369
56	LIU S Q, LEI Y, ZHANG L Y, et al. MRDDANet: a multiscale residual dense dual attention network for SAR image denoising[J]. IEEE Trans. on Geoscience and Remote Sensing, 2022, 60
57	XU S P, XIAO N, LUO J, et al. Multi-channel deep image prior for image denoising[J]. Signal, Image and Video Processing, 2023, 17 (8): 4395- 4404. doi: 10.1007/s11760-023-02673-1
58	LIU B, WU L, SONG X, et al. InDeandCoE: a framework based on multi-scale feature fusion and residual learning for interferometric SAR remote sensing image denoising and coherence estimation[J]. Displays, 2023, 79, 102496. doi: 10.1016/j.displa.2023.102496
59	LEI Y, LIU S Q, ZHANG L Y. Multi-level residual attention network for speckle suppression[C]//Proc. of the Pattern Recognition and Computer Vision, 2021.
60	SHAN H L, FU X W, LV Z K, et al. Synthetic aperture radar images denoising based on multi-scale attention cascade convolutional neural network[J]. Measurement Science & Technology, 2023, 34 (8): 85403.
61	赵琰, 赵凌君, 匡纲要. 基于注意力机制特征融合网络的SAR图像飞机目标快速检测[J]. 电子学报, 2021, 49 (9): 1665- 1674.
	ZHAO Y, ZHAO L J, KUANG G Y. Attention feature fusion network for rapid aircraft detection in SAR images[J]. Acta Electronica Sinica, 2021, 49 (9): 1665- 1674.
62	YUAN Y X, LUO Y, NI J C, et al. Inverse synthetic aperture radar imaging using an attention generative adversarial network[J]. Remote Sensing, 2022, 14 (15): 3509. doi: 10.3390/rs14153509
63	ZHENG P G, ZHOU Y, WANG W, et al. Target recognition in SAR images via multi-scale perception and denoising representation[J]. IEEE Signal Processing Letters, 2023, 30, 1352- 1356. doi: 10.1109/LSP.2023.3311956
64	LIU S Q, LIU M, LI P F, et al. SAR image denoising via sparse representation in shearlet domain based on continuous cycle spinning[J]. IEEE Trans. on Geoscience and Remote Sensing, 2017, 55 (5): 2985- 2992. doi: 10.1109/TGRS.2017.2657602
65	JING R, DUAN F Z, LU F X, et al. Denoising diffusion probabilistic feature-based network for cloud removal in Sentinel-2 imagery[J]. Remote Sensing, 2023, 15 (9): 2217. doi: 10.3390/rs15092217
66	HUANG T, LI S J, JIA X, et al. Neighbor2Neighbor: a self-supervised framework for deep image denoising[J]. IEEE Trans. on Image Processing, 2022, 31, 4023- 4038. doi: 10.1109/TIP.2022.3176533
67	WANG Z J, LIU J Z, LI G Q, et al. Blind2Unblind: self-supervised image denoising with visible blind spots[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022.
68	YUAN Y, WU Y X, FENG P M, et al. Segmentation-guided semantic-aware self-supervised denoising for SAR image[J]. IEEE Trans. on Geoscience and Remote Sensing, 2023, 61
69	PERERA M V, NAIR N G, BANDARA W G C, et al. SAR despeckling using a denoising diffusion probabilistic model[J]. IEEE Geoscience and Remote Sensing Letters, 2023, 20
70	ZHANG T W, ZHANG X L. A polarization fusion network with geometric feature embedding for SAR ship classification[J]. Pattern Recognition, 2022, 123: 108365.
71	CHEN S W. SAR image speckle filtering with context covariance matrix formulation and similarity test[J]. IEEE Trans. on Image Processing, 2020, 29, 6641- 6654. doi: 10.1109/TIP.2020.2992883
72	KO J, LEE S. SAR image despeckling using continuous attention module[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15, 3- 19. doi: 10.1109/JSTARS.2021.3132027
73	刘颖, 庞羽良, 张伟东, 等. 基于主动学习的图像分类技术: 现状与未来[J]. 电子学报, 2023, 51 (10): 2960- 2984.
	LIU Y, PANG Y L, ZHANG W D, et al. Active learning-based image classification technology: status and future[J]. Acta Electronica Sinica, 2023, 51 (10): 2960- 2984.
74	ZHU Y T, CHEN M R, WANG X Q, et al. Synthetic aperture radar image despeckling neural network based on maximum a posteriori probability estimation[J]. International Journal of Remote Sensing, 2023, 44 (2): 609- 630. doi: 10.1080/01431161.2023.2169594
75	PU X Y, JIA H C, XIN Y, et al. Ship detection in low-quality SAR images via an unsupervised domain adaptation method[J]. Remote Sensing, 2023, 15 (13): 3326. doi: 10.3390/rs15133326
76	MORADI M, AMINDAVAR H. A novel Bayesian image despeckling method using 2D CGARCH-M model in 2D dost framework[J]. Digital Signal Processing, 2023, 140, 104134. doi: 10.1016/j.dsp.2023.104134
77	SHEN P, WANG C C. HoMeNL: a homogeneity measure-based nonlocal filtering framework for detail-enhanced （pol）（in）SAR image denoising[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 197, 212- 227. doi: 10.1016/j.isprsjprs.2023.01.026
78	LI J, XU Z Q, LI Z Y, et al. An unsupervised CNN-based multichannel interferometric phase denoising method applied to TomoSAR imaging[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, 16, 3784- 3796. doi: 10.1109/JSTARS.2023.3263964
79	ZHAO C X, FU X J, DONG J, et al. LPDNet: a lightweight network for SAR ship detection based on multi-level Laplacian denoising[J]. Sensors, 2023, 23 (13): 6084. doi: 10.3390/s23136084
80	WANG C, ZHENG R Y, ZHU J Z, et al. Unsupervised SAR despeckling by combining online speckle generation and unpaired training[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, 16, 10175- 10190. doi: 10.1109/JSTARS.2023.3327180

数据集名称	图像数量	极化方式	样本分辨率	主要目标对象	采集工具
MSTAR^[7]	超20 000	HH	128 × 128	SAR车辆	聚束式SAR
OpenSARShip^[8]	11 346	VV、VH	100 × 100	SAR船舶	Sentinel-1卫星
FuSAR-Ship^[9]	16 144	DH、DV	512 × 512	SAR船舶	高分三号卫星
OpenSARUrban^[10]	33 358	VV、VH	100 × 100	SAR城市	Sentinel-1卫星
SAR-ACD^[11]	4 322	HH	未公开	SAR飞机	高分三号卫星

算法类型	优点	缺点
经典空域滤波	简单易实现；可用于抑制噪声，改善图像质量；特定滤波器（如均值滤波）对高斯噪声具有较好效果	对复杂噪声和低信噪比图像的处理效果有限；性能受到滤波器窗口大小的影响较大，可能导致细节模糊化，对目标信号边缘保护性能相对较差
基于小波变换	能够较好保留图像的细节特征；对高斯噪声和脉冲噪声具有较好效果	对复杂噪声和非线性噪声处理能力有限；边缘保护能力相对较差，可能引入新的伪影
基于Contourlet变换	能更好地捕捉图像纹理和结构信息；对复杂噪声类型有较好效果	对计算资源要求较高；处理过程中可能引入新的伪影，不符合MRA理论
基于Shearlet变换	能够更好地处理图像的纹理和微观结构信息；对相干斑噪声和高斯噪声有较好效果	计算复杂度较高；处理过程中可能引入新的伪影
基于非局部均值	能够保留图像细节；对脉冲噪声和斑点噪声具有较好效果	计算复杂度较高；需要提前估计噪声水平；在处理低信噪比图像时效果有限

Method	PPB	SAR-BM3D	SAR-DRN	SAR-RDCP	MONet	MRDDANet	NB2NB	B2UB	SARDeseg
PSNR	17.38	17.94	21.35	21.3	21.22	21.51	21.2	21.32	21.41
ENL	310.2648	208.6316	69.8153	74.1399	61.0177	110.8038	104.1671	36.1941	167.714 0
FOM	0.9158	0.9454	0.9361	0.9445	0.9357	0.9454	0.9507	0.9436	0.9555
RGPI	−0.2432	0.0264	0.0842	0.0977	0.0925	0.0927	0.0571	0.1083	0.1049

[1]	包玉刚, 贾皓翔, 赵旦峰. 基于高阶递归网络的单幅图像去雨滴模型[J]. 系统工程与电子技术, 2026, 48(1): 12-21.
[2]	张彬, 许高添, 张廷豪, 李志辉, 何宏强. 分布式合成孔径雷达前视高分辨成像算法[J]. 系统工程与电子技术, 2026, 48(1): 119-131.
[3]	蒋明煜, 张顺生, 肖思瑶. 面向轻量级交叉注意力卷积网络的SAR目标识别[J]. 系统工程与电子技术, 2025, 47(9): 2853-2861.
[4]	李开明, 张袁鹏, 罗迎, 代肖楠. 弹道导弹雷达目标识别研究进展[J]. 系统工程与电子技术, 2025, 47(9): 2870-2889.
[5]	李响, 曾顶, 殷君君, 国贤玉, 杨健. 基于梯度融合的极化SAR图像引导滤波[J]. 系统工程与电子技术, 2025, 47(9): 2890-2904.
[6]	朱国辉, 杨琳, 汪洋, 郑陶冶. 一种高速机动平台SAR成像PRF改进设计方法[J]. 系统工程与电子技术, 2025, 47(9): 2905-2912.
[7]	季策, 马相宇, 牟晓宇, 赵家毅. TS-GRU-VTA：基于深度学习的车辆信道估计方案[J]. 系统工程与电子技术, 2025, 47(9): 3093-3098.
[8]	陈凯柏, 高博, 高敏, 余道杰, 周晓东, 宋燕燕, 王越. 电子系统高功率微波效应研究进展[J]. 系统工程与电子技术, 2025, 47(8): 2429-2443.
[9]	付卫红, 彭文洪, 刘乃安. 混合注意力优化的SAR图像小目标检测方法[J]. 系统工程与电子技术, 2025, 47(8): 2519-2526.
[10]	倪康, 贾文杰, 邹旻瑞, 郑志忠. 基于动态聚合网络的SAR目标检测[J]. 系统工程与电子技术, 2025, 47(8): 2527-2539.
[11]	王纪凯, 豆亚杰, 李婧, 董奕君, 姜江, 谭跃进. 智能决策在军事体系工程的研究综述[J]. 系统工程与电子技术, 2025, 47(8): 2581-2599.
[12]	闫小伟, 凌冲, 石胜斌. 地表未爆子弹药快速检测系统设计与实现[J]. 系统工程与电子技术, 2025, 47(8): 2639-2645.
[13]	张琬滢, 高由兵, 李泽一, 李鹏飞, 张伟. 基于双路径特征融合网络的背景信号抑制算法[J]. 系统工程与电子技术, 2025, 47(7): 2406-2413.
[14]	黄丰卓, 冯东, 华洋晟, 黄晓涛. 一种改进的全息SAR相位梯度自聚焦算法[J]. 系统工程与电子技术, 2025, 47(6): 1786-1795.
[15]	张新征, 闫梦可, 朱晓林. 噪声伪标签容忍的半监督SAR目标识别[J]. 系统工程与电子技术, 2025, 47(6): 1796-1805.