UnShadowNet: Illumination Critic Guided Contrastive Learning For Shadow Removal
This addresses shadow removal for computer vision applications, but it is incremental as it builds on existing contrastive learning and adversarial training approaches.
The paper tackles the problem of shadow removal in images, which hinders computer vision systems like autonomous driving, by introducing UnShadowNet, a weakly supervised framework using contrastive learning that outperforms state-of-the-art methods on three public datasets.
Shadows are frequently encountered natural phenomena that significantly hinder the performance of computer vision perception systems in practical settings, e.g., autonomous driving. A solution to this would be to eliminate shadow regions from the images before the processing of the perception system. Yet, training such a solution requires pairs of aligned shadowed and non-shadowed images which are difficult to obtain. We introduce a novel weakly supervised shadow removal framework UnShadowNet trained using contrastive learning. It is composed of a DeShadower network responsible for the removal of the extracted shadow under the guidance of an Illumination network which is trained adversarially by the illumination critic and a Refinement network to further remove artefacts. We show that UnShadowNet can be easily extended to a fully-supervised set-up to exploit the ground-truth when available. UnShadowNet outperforms existing state-of-the-art approaches on three publicly available shadow datasets (ISTD, adjusted ISTD, SRD) in both the weakly and fully supervised setups.