RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removal
This addresses the problem of improving image quality by removing shadows for applications in computer vision, though it appears incremental as it builds on existing GAN and residual/illumination techniques.
The paper tackles shadow removal in images by proposing RIS-GAN, a framework that uses generative adversarial networks to explore residual images and illumination estimation, achieving superior performance on benchmark datasets SRD and ISTD compared to state-of-the-art methods.
Residual images and illumination estimation have been proved very helpful in image enhancement. In this paper, we propose a general and novel framework RIS-GAN which explores residual and illumination with Generative Adversarial Networks for shadow removal. Combined with the coarse shadow-removal image, the estimated negative residual images and inverse illumination maps can be used to generate indirect shadow-removal images to refine the coarse shadow-removal result to the fine shadow-free image in a coarse-to-fine fashion. Three discriminators are designed to distinguish whether the predicted negative residual images, shadow-removal images, and the inverse illumination maps are real or fake jointly compared with the corresponding ground-truth information. To our best knowledge, we are the first one to explore residual and illumination for shadow removal. We evaluate our proposed method on two benchmark datasets, i.e., SRD and ISTD, and the extensive experiments demonstrate that our proposed method achieves the superior performance to state-of-the-arts, although we have no particular shadow-aware components designed in our generators.