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

2026-01-31

AI Summary

This work proposes a structure-aware conditional diffusion framework for cloud removal in multi-temporal remote sensing imagery, addressing the degradation in image quality caused by cloud contamination. The method leverages a multi-temporal conditional diffusion network to integrate spatiotemporal and multimodal information, introduces a cloud-aware attention loss to enhance reconstruction of thick cloud regions, and incorporates a deterministic resampling mechanism to improve sampling efficiency and structural fidelity. Extensive experiments demonstrate that the proposed approach consistently outperforms existing cloud removal methods across multiple multi-temporal remote sensing datasets, achieving state-of-the-art performance on all evaluation metrics and significantly enhancing data usability for downstream Earth observation tasks.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web

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.

Problem

• cloud removal
• multi-temporal remote sensing
• diffusion models
• structural priors
• temporal priors

Innovation

• diffusion model
• multi-temporal remote sensing
• cloud removal
• deterministic resampling
• structure-aware attention