SAR-DeCR: Latent Diffusion for SAR-Fused Thick Cloud Removal

The current methods for removing thick clouds from remote-sensing images face significant limitations, including the integration of thick cloud images with synthetic aperture radar (SAR) ground information, the provision of meaningful guidance for SAR ground data, and the accurate reconstruction of...

Full description

Saved in:
Bibliographic Details
Main Authors: Meilin Wang, Shihao Hu, Yexing Song, Yukai Shi
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/13/2241
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704663938498560
author Meilin Wang
Shihao Hu
Yexing Song
Yukai Shi
author_facet Meilin Wang
Shihao Hu
Yexing Song
Yukai Shi
author_sort Meilin Wang
collection DOAJ
description The current methods for removing thick clouds from remote-sensing images face significant limitations, including the integration of thick cloud images with synthetic aperture radar (SAR) ground information, the provision of meaningful guidance for SAR ground data, and the accurate reconstruction of textures in cloud-covered regions. To overcome these challenges, we introduce SAR-DeCR, a novel method for thick cloud removal in satellite remote-sensing images. SAR-DeCR utilizes a diffusion model combined with the transformer architecture to synthesize accurate texture details guided by SAR ground information. The method is structured into three distinct phases: coarse cloud removal (CCR), SAR-Fusion (SAR-F) and cloud-free diffusion (CF-D), aimed at enhancing the effectiveness of the thick cloud removal. In CCR, we significantly employ the transformer’s capability for long-range information interaction, which significantly strengthens the cloud removal process. In order to overcome the problem of missing ground information after cloud removal and ensure that the ground information produced is consistent with SAR data, we introduced SAR-F, a module designed to incorporate the rich ground information in synthetic aperture radar (SAR) into the output of CCR. Additionally, to achieve superior texture reconstruction, we introduce prior supervision based on the output of the coarse cloud removal, using a pre-trained visual-text diffusion model named cloud-free diffusion (CF-D). This diffusion model is encouraged to follow the visual prompts, thus producing a visually appealing, high-quality result. The effectiveness and superiority of SAR-DeCR are demonstrated through qualitative and quantitative experiments, comparing it with other state-of-the-art (SOTA) thick cloud removal methods on the large-scale SEN12MS-CR dataset.
format Article
id doaj-art-c64d68efecaf4fb58fee32e80189bf6b
institution DOAJ
issn 2072-4292
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-c64d68efecaf4fb58fee32e80189bf6b2025-08-20T03:16:42ZengMDPI AGRemote Sensing2072-42922025-06-011713224110.3390/rs17132241SAR-DeCR: Latent Diffusion for SAR-Fused Thick Cloud RemovalMeilin Wang0Shihao Hu1Yexing Song2Yukai Shi3School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Information Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Information Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Information Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaThe current methods for removing thick clouds from remote-sensing images face significant limitations, including the integration of thick cloud images with synthetic aperture radar (SAR) ground information, the provision of meaningful guidance for SAR ground data, and the accurate reconstruction of textures in cloud-covered regions. To overcome these challenges, we introduce SAR-DeCR, a novel method for thick cloud removal in satellite remote-sensing images. SAR-DeCR utilizes a diffusion model combined with the transformer architecture to synthesize accurate texture details guided by SAR ground information. The method is structured into three distinct phases: coarse cloud removal (CCR), SAR-Fusion (SAR-F) and cloud-free diffusion (CF-D), aimed at enhancing the effectiveness of the thick cloud removal. In CCR, we significantly employ the transformer’s capability for long-range information interaction, which significantly strengthens the cloud removal process. In order to overcome the problem of missing ground information after cloud removal and ensure that the ground information produced is consistent with SAR data, we introduced SAR-F, a module designed to incorporate the rich ground information in synthetic aperture radar (SAR) into the output of CCR. Additionally, to achieve superior texture reconstruction, we introduce prior supervision based on the output of the coarse cloud removal, using a pre-trained visual-text diffusion model named cloud-free diffusion (CF-D). This diffusion model is encouraged to follow the visual prompts, thus producing a visually appealing, high-quality result. The effectiveness and superiority of SAR-DeCR are demonstrated through qualitative and quantitative experiments, comparing it with other state-of-the-art (SOTA) thick cloud removal methods on the large-scale SEN12MS-CR dataset.https://www.mdpi.com/2072-4292/17/13/2241remote-sensing imagethick cloud removaldiffusion modelSAR data fusion
spellingShingle Meilin Wang
Shihao Hu
Yexing Song
Yukai Shi
SAR-DeCR: Latent Diffusion for SAR-Fused Thick Cloud Removal
Remote Sensing
remote-sensing image
thick cloud removal
diffusion model
SAR data fusion
title SAR-DeCR: Latent Diffusion for SAR-Fused Thick Cloud Removal
title_full SAR-DeCR: Latent Diffusion for SAR-Fused Thick Cloud Removal
title_fullStr SAR-DeCR: Latent Diffusion for SAR-Fused Thick Cloud Removal
title_full_unstemmed SAR-DeCR: Latent Diffusion for SAR-Fused Thick Cloud Removal
title_short SAR-DeCR: Latent Diffusion for SAR-Fused Thick Cloud Removal
title_sort sar decr latent diffusion for sar fused thick cloud removal
topic remote-sensing image
thick cloud removal
diffusion model
SAR data fusion
url https://www.mdpi.com/2072-4292/17/13/2241
work_keys_str_mv AT meilinwang sardecrlatentdiffusionforsarfusedthickcloudremoval
AT shihaohu sardecrlatentdiffusionforsarfusedthickcloudremoval
AT yexingsong sardecrlatentdiffusionforsarfusedthickcloudremoval
AT yukaishi sardecrlatentdiffusionforsarfusedthickcloudremoval