GR-GAN: A unified adversarial framework for single image glare removal and denoising

Cong Niu, Ke Li, Di Wang, Wenxuan Zhu, Haojie Xu, Jinhui Dong

Abstract: Highlights•A new image denoising task is introduced, focusing on single image glare removal, and a corresponding dataset is constructed.•A novel adversarial generative network is proposed for single image glare removal.•It aggregates multiscale spatial and semantic visual features, enhancing the quality of the generated images.•Extensive qualitative and quantitative experiments on four types image denoising benchmark datasets demonstrate the superiority of the proposed method over state-of-the-art methods.