基于随机置换的红外图像超分辨率TransformerOA

Infrared image super-resolution has wide applications.Currently,the Visual Transformer has shown great potential in improving the performance of image super-resolution,but how to effectively balance system complexity has attracted the interest of many researchers.A random permutation based Transformer for infrared image super-resolution is proposed,which achieves further improvement in image reconstruction performance while controlling system complexity well.Specifically,a window self-attention module combining random permutation is designed to replace the original Swin Transformer's shifted window self-attention module,effectively improving the learning ability of global dependency relationships of window self-attention through random permutation operations in the spatial dimension of the feature map.Experimental comparison results based on multiple public infrared image datasets validate the effectiveness of this method.