SAR Despeckling via Regional Denoising Diffusion Probabilistic Model

TL;DR

This paper introduces R-DDPM, a novel generative model-based approach for SAR image despeckling that effectively handles large-scale images and reduces artifacts, outperforming existing methods.

Contribution

The paper presents a region-guided diffusion probabilistic model that enables versatile, large-scale SAR despeckling within a single training, improving over prior deep learning methods.

Findings

R-DDPM outperforms existing despeckling methods on Sentinel-1 data.

The approach effectively handles large-scale SAR images.

Artifacts in fused images are significantly reduced.

Abstract

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.