BRIC-Net: Boundary-Reliable Illumination-Color Interaction for Remote Sensing Image Deshadowing

2026-08-01

AI Summary

This work addresses the challenge of shadow removal in remote sensing imagery, where shadows obscure surface details and disrupt radiometric continuity, and existing methods often introduce artifacts such as ghosting, halos, or color distortion. To achieve high-fidelity shadow removal, the authors propose BRIC-Net, a novel framework that decouples illumination recovery and color reconstruction across multiple scales. The method introduces three key components: a Luminance Reliability Prior (LRP), Boundary-Adaptive Gated Mixing (BAGM), and Spatial-Channel Mutual Modulation (SCMM), which collectively enable accurate handling of penumbral transitions while preserving consistency in non-shadowed regions. Extensive experiments demonstrate that BRIC-Net achieves state-of-the-art performance, yielding PSNR values of 29.46 dB and 27.96 dB on AeroDS-Syn and SRGTA, respectively, and obtaining the lowest PIQE scores on AISD and AeroDS-Real, significantly outperforming current approaches.

Abstract

Shadows in remote sensing images obscure surface appearance and disrupt radiometric continuity, reducing the reliability of visual interpretation and downstream analysis. Remote sensing image deshadowing is an ill-posed inverse problem that requires spatially varying illumination recovery while preserving chromatic and radiometric consistency in non-shadow regions. Existing methods commonly rely on hard shadow masks for compensation or directly regress RGB intensities. Hard masks may inadequately model gradual penumbra variations and are sensitive to localization errors, often producing residual shadows or halo artifacts; direct RGB regression entangles illumination recovery with chromatic reconstruction and can introduce color casts. To this end, we propose the Boundary-Reliable Illumination-Color Interaction Network (BRIC-Net), which decouples these failures at different representation levels. A Lightness Reliability Prior (LRP) derives reliability-aware guidance from CIELAB statistics. Boundary-Adaptive Gated Mixing (BAGM) performs gated interpolation between shallow RGB and lightness features around uncertain transitions, while Spatial-Channel Mutual Modulation (SCMM) coordinates deeper spatial and channel responses for appearance-preserving illumination recovery. BRIC-Net achieves 29.46~dB full-image peak signal-to-noise ratio (PSNR) on AeroDS-Syn and 27.96~dB on SRGTA. It also obtains the lowest Perception-based Image Quality Evaluator (PIQE) scores on AISD and AeroDS-Real. Region-wise evaluations and component ablations further support its effectiveness in shadow recovery and non-shadow preservation.

Problem

• remote sensing image deshadowing
• illumination recovery
• radiometric consistency
• chromatic consistency
• shadow removal

Innovation

• deshadowing
• illumination-color decoupling
• boundary-adaptive gating
• reliability prior
• remote sensing