Recently, transformer based deep neural networks have been found useful in solving various image restoration tasks like image denoising, deblurring, deraining etc., producing significant improvement in PSNR and SSIM over CNN based techniques on benchmark datasets. These networks have effectively addressed quadratic computational complexity issue with increasing image resolution by making use of novel self attention strategies on local image windows. In this paper, we propose a fast and efficient UNet based architecture using transformer modules for the image demoireing task. The proposed architecture is computationally very efficient as the transformer blocks perform non-overlapping window-based self-attention instead of global self attention. We further improve upon the computational complexity by using decreasing window sizes across scales under the proposed U-Net multi resolution framework. To the best of our knowledge, ours is the first deep network architecture using transformer blocks for the image demoireing problem producing comparable results with state of the art techniques both visually and quantitatively on the CFAMoire challenge dataset.
