🤖 AI Summary
This work addresses the challenge of cloud removal in multimodal remote sensing imagery, where existing SAR-optical fusion methods often introduce speckle noise and cause excessive smoothing. To overcome these limitations, the authors propose the IB-HFN network, which employs a dual-stream backbone to preserve modality-specific features. Channel-wise variational information bottleneck is applied to compress SAR features and suppress noise, while a local-global gating mechanism safeguards optical details. A spatial information bottleneck fusion module, coupled with Dirac-initialized skip connections, enables decoupled optimization of noise suppression and texture preservation. The framework further integrates feature-level regularization with image-level multi-constraint objectives for joint optimization. Evaluated on the SEN12MS-CR dataset, the proposed method significantly outperforms state-of-the-art approaches in both structural integrity and spectral fidelity.
📝 Abstract
Synthetic aperture radar (SAR)-assisted optical cloud removal aims to recover surface information obscured by clouds in optical remote sensing images by exploiting complementary SAR observations. Existing multimodal fusion methods typically rely on direct spatial concatenation and pixel-wise supervision, which can propagate SAR speckle noise into optical reconstruction and lead to over-smoothed results. To address these limitations, we propose an Information Bottleneck-driven High-Fidelity Network (IB-HFN) for SAR-assisted optical cloud removal. IB-HFN employs a dual-stream backbone to preserve modality-specific representations before deep semantic fusion, thereby mitigating premature cross-modal contamination. At the fusion stage, we introduce a Spatial Information Bottleneck Fusion module that compresses SAR features through a channel-wise variational information bottleneck to suppress unstructured speckle noise. In parallel, a local-global gating mechanism predicts clear-sky regions and routes reliable optical details through a Dirac-initialized skip connection, decoupling noise suppression from texture preservation. We further develop a joint optimization strategy that integrates feature-level bottleneck regularization with image-level constraints on reconstruction accuracy, structural consistency, spectral fidelity, and contrastive sharpness. A dynamic weighting schedule balances these objectives to stabilize training and reduce hazy artifacts. Experiments on the SEN12MS-CR dataset under challenging spatio-temporal splits demonstrate that IB-HFN achieves superior structural preservation and spectral fidelity over existing methods.