SAR Despeckling via Regional Denoising Diffusion Probabilistic Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Xuran, Xu, Ziqiang, Chen, Zhihan, Feng, Zhengpeng, Zhu, Mingzhe, Stankovic, LJubisa
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916081851957248
author Hu, Xuran
Xu, Ziqiang
Chen, Zhihan
Feng, Zhengpeng
Zhu, Mingzhe
Stankovic, LJubisa
author_facet Hu, Xuran
Xu, Ziqiang
Chen, Zhihan
Feng, Zhengpeng
Zhu, Mingzhe
Stankovic, LJubisa
contents Speckle noise poses a significant challenge in maintaining the quality of synthetic aperture radar (SAR) images, so SAR despeckling techniques have drawn increasing attention. Despite the tremendous advancements of deep learning in fixed-scale SAR image despeckling, these methods still struggle to deal with large-scale SAR images. To address this problem, this paper introduces a novel despeckling approach termed Region Denoising Diffusion Probabilistic Model (R-DDPM) based on generative models. R-DDPM enables versatile despeckling of SAR images across various scales, accomplished within a single training session. Moreover, The artifacts in the fused SAR images can be avoided effectively with the utilization of region-guided inverse sampling. Experiments of our proposed R-DDPM on Sentinel-1 data demonstrates superior performance to existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03122
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SAR Despeckling via Regional Denoising Diffusion Probabilistic Model
Hu, Xuran
Xu, Ziqiang
Chen, Zhihan
Feng, Zhengpeng
Zhu, Mingzhe
Stankovic, LJubisa
Computer Vision and Pattern Recognition
Image and Video Processing
I.4.4
Speckle noise poses a significant challenge in maintaining the quality of synthetic aperture radar (SAR) images, so SAR despeckling techniques have drawn increasing attention. Despite the tremendous advancements of deep learning in fixed-scale SAR image despeckling, these methods still struggle to deal with large-scale SAR images. To address this problem, this paper introduces a novel despeckling approach termed Region Denoising Diffusion Probabilistic Model (R-DDPM) based on generative models. R-DDPM enables versatile despeckling of SAR images across various scales, accomplished within a single training session. Moreover, The artifacts in the fused SAR images can be avoided effectively with the utilization of region-guided inverse sampling. Experiments of our proposed R-DDPM on Sentinel-1 data demonstrates superior performance to existing methods.
title SAR Despeckling via Regional Denoising Diffusion Probabilistic Model
topic Computer Vision and Pattern Recognition
Image and Video Processing
I.4.4
url https://arxiv.org/abs/2401.03122