IFGLT: Information fusion guided lightweight Transformer for image denoising

Abstract

Image denoising is a low-level computer vision task that aims to reconstruct high-quality images from noisy ones. However, large networks with a high computational burden have been employed in existing works in pursuit of high-quality images. This paper introduces an Information Fusion Guided Lightweight Transformer (IFGLT) that can lessen the computational burden and achieve superior restoration results. The Feature Enhancement Module (FEM) optimizes the computing cost of the Transformer layer by layer using various techniques such as group mapping, channel generation, fusion convolution, and window rearrangement. The Information Compensation Module (ICM) gradually compensates for missing information by leveraging the original image. The Lightweight Sample Module (LSM) performs up-sampling and down-sampling with the minimal computing cost by altering the order of feature transformation. The experimental results demonstrate that our proposed IFGLT attains higher objective indices and achieves better visual effects with reduced computing cost in comparison to conventional methods.