PulseAugur
LIVE 15:27:45
research · [2 sources] ·
0
research

deSEO dataset and model tackle satellite image shadow removal challenges

Researchers have introduced deSEO, a novel methodology for creating paired datasets to address shadow removal in high-resolution satellite imagery. This approach leverages physics-informed techniques and temporal/geometric filtering to derive shadow-free and shadowed image pairs from existing datasets. The developed deSEO model demonstrates improved shadow reduction and structural fidelity, offering a new baseline for satellite Earth observation tasks. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Provides a new dataset and baseline model for improving satellite image analysis by removing shadows.

RANK_REASON This is a research paper detailing a new methodology and dataset for a specific computer vision task.

Read on arXiv cs.CV →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 · Lorenzo Beltrame, Jules Salzinger, Filip Svoboda, Phillipp Fanta-Jende, Jasmin Lampert, Radu Timofte, Marco K\"orner ·

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

    arXiv:2605.03610v1 Announce Type: new 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 …

  2. arXiv cs.CV TIER_1 · Marco Körner ·

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

    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 …