SUNet: Swin Transformer UNet for Image Denoising
This work addresses image restoration for computer vision applications, representing an incremental advancement by combining transformer and CNN-based approaches.
The paper tackles image denoising by proposing SUNet, a model that integrates Swin Transformer layers into a UNet architecture, achieving state-of-the-art performance with concrete improvements over existing methods.
Image restoration is a challenging ill-posed problem which also has been a long-standing issue. In the past few years, the convolution neural networks (CNNs) almost dominated the computer vision and had achieved considerable success in different levels of vision tasks including image restoration. However, recently the Swin Transformer-based model also shows impressive performance, even surpasses the CNN-based methods to become the state-of-the-art on high-level vision tasks. In this paper, we proposed a restoration model called SUNet which uses the Swin Transformer layer as our basic block and then is applied to UNet architecture for image denoising. The source code and pre-trained models are available at https://github.com/FanChiMao/SUNet.