SAR Despeckling Via Regional Denoising Diffusion Probabilistic Model
Xuran Hu, Ziqiang Xu, Zhihan Chen, Zhenpeng Feng, Mingzhe Zhu, Ljubiša Stanković
Abstract
Speckle noise poses a significant challenge in maintaining the quality of synthetic aperture radar (SAR) images. SAR despeckling techniques have drawn increasing attention. Despite the tremendous advancements of deep learning in 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 diffusion 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.