Image rain removal network based on checkerboard transformer and CNN hybrid mechanism.

Journal: PloS one
PMID:

Abstract

In this paper, a novel hybrid network called ChessFormer is proposed for the single image de-rain task. The network seamlessly integrates the advantages of Transformer and fitted neural network (CNN) in a checkerboard architecture, fully utilizing the global modeling capability of Transformer and the local feature extraction efficiency of CNN.ChessFormer adopts a multilevel feature extraction and progressive feature fusion strategy to efficiently achieve the rain line while preserving the We design a multidimensional transposed attention (MSTA), which enhances the network fusion for different rain patterns and mechanism image textures by combining self-attention with gated phase operation. In addition, the efficient architecture ensures full integration of features across dimensions and codecs. Experimental results show that ChessFormer outperforms existing methods in terms of quantitative metrics and visual quality on multiple benchmark datasets, achieving state-of-the-art performance with fewer parameters.

Authors

  • Yutian Yang
    College of Computer Science and Technolog, Civil Aviation University of China, Tianjin, China.
  • Jianyu Lin
    The Hamlyn Centre for Robotic Surgery, Imperial College London, London, UK; Department of Computing, Imperial College London, London, UK. Electronic address: xjtuljy@gmail.com.
  • Xinyue Dai
    Materdicine Lab, School of Life Sciences, Shanghai University, Shanghai, 200444, P. R. China.
  • Zhipei Zhang
    University of Electronic Science and Technology of China, Zhongshan Institute, Zhongshan, China.
  • Shuijin Zhang
    School of Computing, North China Institute of Science and Technology, Langfang, China.
  • Yingyu Chen
    College of Veterinary Medicine, Wuhan, China.
  • Guangxin Kong
    School of Electrical Engineering, Yanshan University, Qinhuangdao, China.
  • Xin Li
    Veterinary Diagnostic Center, Shanghai Animal Disease Control Center, Shanghai, China.