Pyramid Ensemble Structure for High Resolution Image Shadow Removal

Shuhao Cui, Junshi Huang, Shuman Tian, Mingyuan Fan, Jiaqi Zhang, Li Zhu, Xiaoming Wei, Xiaolin Wei; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 1311-1319

Existing methods for shadow removal in high-resolution images may not be effective due to challenges such as the time-consuming nature of training and the loss of visual data during image cropping or resizing, highlighting the necessity for the development of more efficient methods. In this paper, we propose a novel Pyramid Ensemble Structure (PES) for High Resolution Image Shadow Removal. Our approach takes advantage of multiple scales by constructing pyramid inputs that allow for the capturing of a wide range of shadow sizes and shapes. We then train the network in pyramid stages to enhance global information processing. Furthermore, an ensemble of different shadow removal models is employed, and the maximum value is chosen to indicate the least amount of remaining shadow in the output. Experiments on both validation and testing data sets confirm the effectiveness of our method. In the Image Shadow Removal Challenge competition, our method obtained 22.36 PSNR score (1st place) and 0.70 SSIM score (2nd place) on the test sets.