Shadow Removal by a Lightness-Guided Network With Training on Unpaired Data

Shadow removal can significantly improve the image visual quality and has many applications in computer vision. Deep learning methods based on CNNs have become most effective approach for shadow by training either paired data, where both underlying shadow-free versions of an are known, or unpaired images totally different with no correspondence. In practice, CNN data is more preferred given easiness collection. this paper, we present a new Lightness-Guided Removal Network (LG-ShadowNet) data. method, first train module to compensate lightness then second guidance information from final removal. We also introduce loss function further utilise colour prior existing Extensive experiments widely used ISTD, adjusted ISTD USR datasets demonstrate that proposed method outperforms state-of-the-art