deSEO: Physics-Aware Dataset Creation for High-Resolution Satellite Image Shadow Removal

2026-05-05

AI Summary

This work addresses the challenge of shadow interference in high-resolution satellite imagery, which severely degrades downstream visual tasks. Existing methods are hindered by the scarcity of geometrically consistent paired shadow/shadow-free data. To overcome this, the authors propose deSEO, a novel approach that constructs the first geometry-aware, physics-driven paired dataset for satellite shadow removal based on the S-EO dataset. Their method integrates a digital surface model (DSM) into a dedicated deshadowing network. Geometric consistency in the paired data is ensured through temporal and geometric filtering, LoFTR-RANSAC registration, and per-pixel validity masks. The model’s generalization capability is enhanced via adversarial training incorporating residual transfer, perceptual loss, and mask-based constraints. Experiments demonstrate that deSEO significantly mitigates shadow effects across diverse illumination and viewing conditions, outperforming existing UAV-transfer-based methods in both structural fidelity and perceptual quality, with superior performance on held-out scenes.

Abstract

Shadows cast by terrain and tall structures remain a major obstacle for high-resolution satellite image analysis, degrading classification, detection, and 3D reconstruction performance. Public resources offering geometry-consistent paired shadow/shadow-free satellite imagery are essentially missing, and most Earth-observation datasets are designed for shadow detection or 3D modelling rather than removal. Existing deep shadow-removal datasets either target ground-level or aerial scenes or rely on unpaired and weakly supervised formulations rather than explicit satellite pairs. We address this gap with deSEO, a geometry-aware and physics-informed methodology that, to the best of our knowledge, is the first to derive paired supervision for satellite shadow removal from the S-EO shadow detection dataset through a fully replicable pipeline. For each tile, deSEO selects a minimally shadowed acquisition as a weak reference and pairs it with shadowed counterparts using temporal and geometric filtering, Jacobian-based orientation normalisation, and LoFTR-RANSAC registration. A per-pixel validity mask restricts learning to reliably aligned regions, enabling supervision despite residual off-nadir parallax. In addition to this paired dataset, we develop a DSM-aware deshadowing model that combines residual translation, perceptual objectives, and mask-constrained adversarial learning. In contrast, a direct adaptation of a UAV-based SRNet/pix2pix architecture fails to converge under satellite viewpoint variability. Our model consistently reduces the visual impact of cast shadows across diverse illumination and viewing conditions, achieving improved structural and perceptual fidelity on held-out scenes. deSEO therefore provides the first reproducible, geometry-aware paired dataset and baseline for shadow removal in satellite Earth observation.

Problem

• shadow removal
• satellite imagery
• paired dataset
• high-resolution
• Earth observation

Innovation

• paired dataset
• physics-aware
• satellite shadow removal
• geometry-consistent
• DSM-aware