ShadowHack: Hacking Shadows via Luminance-Color Divide and Conquer
This addresses image quality issues for computer vision applications, but it is incremental as it builds on existing shadow removal techniques with a novel decomposition approach.
The paper tackles the problem of shadows in images causing brightness reduction, texture deterioration, and color distortion by proposing ShadowHack, a divide-and-conquer method that separates luminance recovery and color remedy, achieving superior results over state-of-the-art solutions in experiments on multiple datasets.
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.