Conditional diffusion model for arbitrary-size synthetic aperture radar image despeckling with multi-scale and dual attention mechanism

被引:0
作者
Zhang, Dongxu [1 ,2 ]
Li, Qing [1 ,2 ]
机构
[1] Chinese Acad Sci, Inst Microelect, Beijing, Peoples R China
[2] Univ Chinese Acad Sci, Beijing, Peoples R China
关键词
synthetic aperture radar; image; despeckling; diffusion; multi-scale; attention; SAR IMAGES; ENHANCEMENT; FRAMEWORK; NOISE;
D O I
10.1117/1.JRS.18.046503
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Synthetic aperture radar (SAR) inherently encounters speckle noise as a characteristic challenge, which degrades image quality significantly. In recent years, learning-based methods have achieved remarkable success in SAR despeckling. However, these methods are often limited by complex speckle-noise patterns and the size of SAR images. To further improve despeckling quality and adapt arbitrary-size SAR images, we propose a novel method based on a conditional diffusion model coupled with a multi-scale and dual attention mechanism. During despeckling, the strong modeling capability of the diffusion model enables more accurate original clear scene restoration. Multi-scale features encompassing low-frequency large structure information and high-frequency details in SAR images are aggregated and input to position and channel dual attention mechanism, which effectively extracts global context information and establishes long-range dependencies, ensuring a broader perspective and more accurate distinction between structure textures and speckle noise. Using smooth noise estimation across overlapping patches to guide the sampling process, the proposed method is capable of handling arbitrary-size SAR images. Extensive experiment demonstrates that the proposed method has outstanding despeckling performance and flexible adaptability for arbitrary-size SAR images. (c) 2024 Society of Photo- Optical Instrumentation Engineers (SPIE)
引用
收藏
页数:20
相关论文
共 57 条
  • [1] Truncated-statistics-based bilateral filter for speckle reduction in synthetic aperture radar imagery
    Ai, Jiaqiu
    Yang, Hang
    Yang, Xuezhi
    Liu, Ruiming
    Luo, Qiwu
    Zhang, Xiaohui
    [J]. JOURNAL OF APPLIED REMOTE SENSING, 2019, 13 (02)
  • [2] Speckle removal from SAR images in the undecimated wavelet domain
    Argenti, F
    Alparone, L
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2002, 40 (11): : 2363 - 2374
  • [3] Chierchia G, 2017, INT GEOSCI REMOTE SE, P5438, DOI 10.1109/IGARSS.2017.8128234
  • [4] Dabhi Shrey, 2020, IEEE DataPort, DOI 10.21227/ASTH-RA98
  • [5] MuLoG, or How to Apply Gaussian Denoisers to Multi-Channel SAR Speckle Reduction?
    Deledalle, Charles-Alban
    Denis, Loic
    Tabti, Sonia
    Tupin, Florence
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (09) : 4389 - 4403
  • [6] NL-SAR: A Unified Nonlocal Framework for Resolution-Preserving (Pol)(In)SAR Denoising
    Deledalle, Charles-Alban
    Denis, Loic
    Tupin, Florence
    Reigber, Andreas
    Jaeger, Marc
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2015, 53 (04): : 2021 - 2038
  • [7] Iterative Weighted Maximum Likelihood Denoising With Probabilistic Patch-Based Weights
    Deledalle, Charles-Alban
    Denis, Loic
    Tupin, Florence
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2009, 18 (12) : 2661 - 2672
  • [8] Benchmarking Framework for SAR Despeckling
    Di Martino, Gerardo
    Poderico, Mariana
    Poggi, Giovanni
    Riccio, Daniele
    Verdoliva, Luisa
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (03): : 1596 - 1615
  • [9] Spaceborne Bistatic SAR Processing Using the EETF4 Algorithm
    Eldhuset, Knut
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2009, 6 (02) : 194 - 198
  • [10] Multitask GANs for Oil Spill Classification and Semantic Segmentation Based on SAR Images
    Fan, Jianchao
    Liu, Chuan
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 : 2532 - 2546