SUNet: Swin Transformer UNet for Image Denoising

Abstract

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.

References in corpus (6)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
• Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
• Fully Dense UNet for 2D Sparse Photoacoustic Tomography Artifact Removal
• RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans

Cited by in corpus (4)

• Advances in Artificial Intelligence: A Review for the Creative Industries
• MS-DCANet: A Novel Segmentation Network For Multi-Modality COVID-19 Medical Images
• Swap-Net: A Memory-Efficient 2.5D Network for Sparse-View 3D Cone Beam CT Reconstruction
• A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping