GoLDFormer: A global-local deformable window transformer for efficient image restoration

Quan Chen, Bolun Zheng, Chenggang Yan, Zunjie Zhu, Tingyu Wang, Gregory G. Slabaugh, Shanxin Yuan

Abstract: Highlights•We propose GoLDFormer, including two blocks, to enhance W-MSA globally and locally.•Globally-enhanced attention block captures global dependencies between all windows.•Deformable filtering block captures local dependencies by modifying filter size.•Our GoLDFormer achieves competitive results against recent lightweight methods.