SADER: Structure-Aware Diffusion Framework with DEterministic Resampling for Multi-Temporal Remote Sensing Cloud Removal

TL;DR

SADER is a novel structure-aware diffusion framework that effectively removes clouds from multi-temporal remote sensing images by leveraging structural and temporal priors, and introduces a deterministic resampling strategy for improved sample refinement.

Contribution

The paper introduces SADER, which combines a multi-temporal conditional diffusion network with a cloud-aware attention loss and a deterministic resampling strategy, advancing remote sensing cloud removal techniques.

Findings

Outperforms state-of-the-art methods across multiple datasets

Effectively captures multi-temporal and multimodal correlations

Improves sample quality with deterministic resampling

Abstract

Cloud contamination severely degrades the usability of remote sensing imagery and poses a fundamental challenge for downstream Earth observation tasks. Recently, diffusion-based models have emerged as a dominant paradigm for remote sensing cloud removal due to their strong generative capability and stable optimization. However, existing diffusion-based approaches often suffer from limited sampling efficiency and insufficient exploitation of structural and temporal priors in multi-temporal remote sensing scenarios. In this work, we propose SADER, a structure-aware diffusion framework for multi-temporal remote sensing cloud removal. SADER first develops a scalable Multi-Temporal Conditional Diffusion Network (MTCDN) to fully capture multi-temporal and multimodal correlations via temporal fusion and hybrid attention. Then, a cloud-aware attention loss is introduced to emphasize cloud-dominated regions by accounting for cloud thickness and brightness discrepancies. In addition, a deterministic resampling strategy is designed for continuous diffusion models to iteratively refine samples under fixed sampling steps by replacing outliers through guided correction. Extensive experiments on multiple multi-temporal datasets demonstrate that SADER consistently outperforms state-of-the-art cloud removal methods across all evaluation metrics. The code of SADER is publicly available at https://github.com/zyfzs0/SADER.