AeroDeshadow: Physics-Guided Shadow Synthesis and Penumbra-Aware Deshadowing for Aerospace Imagery

2026-04-17

AI Summary

This work addresses the pervasive challenge of shadows in high-resolution aerospace imagery, which induce spectral distortion and information loss while lacking paired training data and posing difficulties in modeling penumbral transition regions. To tackle these issues, the authors propose a two-stage unified shadow removal framework: first, they construct a physically grounded synthetic dataset with soft shadow boundaries based on a light attenuation model (PDSS-Net); then, they design a cascaded penumbra-aware de-shadowing network (PCDS-Net) to progressively restore umbra and penumbra regions. This approach is the first to integrate physics-guided degradation modeling into shadow synthesis and achieves cross-domain generalization without real paired data through unsupervised domain translation. Extensive experiments demonstrate superior performance over state-of-the-art methods on both synthetic and real-world imagery in terms of quantitative accuracy and visual fidelity. The code and dataset are publicly released.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Hardware-aware ML

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Shadows are prevalent in high-resolution aerospace imagery (ASI). They often cause spectral distortion and information loss, which degrade downstream interpretation tasks. While deep learning methods have advanced natural-image shadow removal, their direct application to ASI faces two primary challenges. First, strictly paired training data are severely lacking. Second, homogeneous shadow assumptions fail to handle the broad penumbra transition zones inherent in aerospace scenes. To address these issues, we propose AeroDeshadow, a unified two-stage framework integrating physics-guided shadow synthesis and penumbra-aware restoration. In the first stage, a Physics-aware Degradation Shadow Synthesis Network (PDSS-Net) explicitly models illumination decay and spatial attenuation. This process constructs AeroDS-Syn, a large-scale paired dataset featuring soft boundary transitions. Constrained by this physical formulation, a Penumbra-aware Cascaded DeShadowing Network (PCDS-Net) then decouples the input into umbra and penumbra components. By restoring these regions progressively, PCDS-Net alleviates boundary artifacts and over-correction. Trained solely on the synthetic AeroDS-Syn, the network generalizes to real-world ASI without requiring paired real annotations. Experimental results indicate that AeroDeshadow achieves state-of-the-art quantitative accuracy and visual fidelity across synthetic and real-world datasets. The datasets and code will be made publicly available at: https://github.com/AeroVILab-AHU/AeroDeshadow.

Problem

• aerospace imagery
• shadow removal
• penumbra
• paired training data
• spectral distortion

Innovation

• Physics-guided shadow synthesis
• Penumbra-aware deshadowing
• Aerospace imagery
• Shadow removal
• Synthetic dataset generation