Abstract: In order to solve the problem of limited receptive field of deraining methods based on convolution neural network, we propose a single image deraining method using swin transformer to fuse global and local features, which combines the advantages of swin transformer and convolution neural network. Firstly, the local features of the image is extracted by convolution neural network. Secondly, the global information in different feature spaces is learned by multi-branch network based on Swin Transformer. Finally, the extracted multi-branch global features and local features are fused to realize the restoration of clean image. Compared with several state-of-the-art single image deraining methods on multiple datasets, the results of the proposed network have competitive performance in terms of peak signal-to-noise ratio and structural similarity index, which verifies the effectiveness of the proposed method in single image deraining task.