Edge-aware Laplacian Pyramid Network for Efficient Image Deblurring

Image deblurring is dedicated to restoring blurry images resulting from camera shake or target motion into high-quality sharp images. Recent work has made notable progress in image deblurring, but few studies have focused on the role of high-frequency information in this task. Hence, an efficient Edge-aware Laplacian Pyramid Network (ELPNet) is proposed for image deblurring. Specifically, we introduce a reversible Laplacian pyramid decomposition and reconstruction mechanism within the deblurring network, guiding the reconstruction of high-frequency information. Additionally, we present a novel Large-Kernel convolution Hybrid Attention Block (LKHAB) that leverages re-parameterization to effectively integrate channel-wise and spatial-invariant features with a larger receptive field. We also introduce an Edge-Aware Merge Block (EAMB) that combines Laplacian and Scharr operators with difference convolutions to create various learnable edge gradient convolutions. The EAMB can elegantly capture the edge information of features, and through re-parameterization, enables to merging of different edge gradient convolutions into a vanilla convolution during inference. Experimental results show that the proposed method achieves state-of-the-art performance with significantly reduced parameters and computation.