RSTC: Residual Swin Transformer Cascade to approximate Taylor expansion for image denoising

• Published in: Computer vision and image understanding Vol. 248; p. 104132
• Main Authors: Liu, Jin, Yang, Yang, Xu, Biyun, Yu, Hao, Zhang, Yaozong, Li, Qian, Huang, Zhenghua
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.11.2024
• Subjects: Image denoising; Residual swin transformer cascade (RSTC); Swin transformer layer; Taylor expansion approximation; Swin transformer layer; Residual swin transformer cascade (RSTC); Taylor expansion approximation; Image denoising
• ISSN: 1077-3142
• DOI: 10.1016/j.cviu.2024.104132

Traditional denoising methods establish mathematical models by employing different priors, which can achieve preferable results but they are usually time-consuming and their outputs are not adaptive on regularization parameters. While the success of end-to-end deep learning denoising strategies depends on a large amount of data and lacks a theoretical interpretability. In order to address the above problems, this paper proposes a novel image denoising method, namely Residual Swin Transformer Cascade (RSTC), based on Taylor expansion. The key procedures of our RSTC are specified as follows: Firstly, we discuss the relationship between image denoising model and Taylor expansion, as well as its adjacent derivative parts. Secondly, we use a lightweight deformable convolutional neural network to estimate the basic layer of Taylor expansion and a residual network where swin transformer block is selected as a backbone for pursuing the solution of the derivative layer. Finally, the results of the two networks contribute to the approximation solution of Taylor expansion. In the experiments, we firstly test and discuss the selection of network parameters to verify its effectiveness. Then, we compare it with existing advanced methods in terms of visualization and quantification, and the results show that our method has a powerful generalization ability and performs better than state-of-the-art denoising methods on performance improvement and structure preservation. •A residual swin transformer cascade (RSTC) network for pursuing the solution of the Taylor expansion approximation.•A lightweight residual network, namely base layer network (BLNet), for the base layer estimation.•A residual swin transformer network for each derivative part of the Taylor expansion.