ShadowHack: Hacking Shadows via Luminance-Color Divide and Conquer

TL;DR

ShadowHack introduces a divide-and-conquer approach to shadow removal by separately enhancing luminance and color, utilizing specialized neural networks to improve image quality in shadowed regions.

Contribution

The paper proposes a novel divide-and-conquer framework with customized neural networks for luminance recovery and color correction, advancing shadow removal techniques.

Findings

Outperforms existing methods quantitatively

Produces visually compelling shadow removal results

Validated on multiple datasets

Abstract

Shadows introduce challenges such as reduced brightness, texture deterioration, and color distortion in images, complicating a holistic solution. This study presents \textbf{ShadowHack}, a divide-and-conquer strategy that tackles these complexities by decomposing the original task into luminance recovery and color remedy. To brighten shadow regions and repair the corrupted textures in the luminance space, we customize LRNet, a U-shaped network with a rectified attention module, to enhance information interaction and recalibrate contaminated attention maps. With luminance recovered, CRNet then leverages cross-attention mechanisms to revive vibrant colors, producing visually compelling results. Extensive experiments on multiple datasets are conducted to demonstrate the superiority of ShadowHack over existing state-of-the-art solutions both quantitatively and qualitatively, highlighting the effectiveness of our design. Our code will be made publicly available.