论文标题
Sunet：Swin Transformer UNET用于图像Denoising
SUNet: Swin Transformer UNet for Image Denoising
论文作者
论文摘要
图像恢复是一个具有挑战性的问题，这也是一个长期存在的问题。在过去的几年中，卷积神经网络（CNN）几乎统治了计算机视觉，并在包括图像恢复在内的不同视觉任务中取得了巨大的成功。但是，最近，基于Swin Transformer的模型也显示出令人印象深刻的性能，甚至超过了基于CNN的方法，成为高级视觉任务的最新方法。在本文中，我们提出了一种称为Sunet的修复模型，该模型使用Swin Transformer层作为我们的基本块，然后将其应用于UNET体系结构以进行图像Denoising。源代码和预培训模型可在https://github.com/fanchimao/sunet上找到。
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.
