HirFormer: Dynamic High Resolution Transformer for Large-Scale Image Shadow Removal

Xin Lu, Yurui Zhu, Xi Wang, Dong Li, Jie Xiao, Yunpeng Zhang, Xueyang Fu, Zheng-Jun Zha; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 6513-6523

Existing image restoration models have limited performance in high-resolution image shadow removal tasks particularly in handling complex background information and unevenly distributed shadows. To address this challenge we propose a novel two-stage approach called HirFormer for high-resolution image shadow removal. The first stage Dynamic High Resolution Transformer reconstructs the high-resolution background information and removes a significant portion of the shadows based on the Transformer architecture. The second stage Large-scale Image Refinement incorporates the NAFNet model to further eliminate residual shadows and address block artifacts introduced by the first stage. Experimental results on official datasets validate the superiority of our method compared to existing approaches and our approach emerged as the winner in the fidelity track of the NTIRE 2024 Shadow Removal Challenge during the final testing competition (1st place).