基于维度感知注意力的无监督图像拼接网络OA

To address the common issues of structural deformation and misalignment in unsuper-vised image stitching,a dimension-aware images stitching network(DAISNet)based on dimen-sion aware attention was proposed.This network consists of two sub networks:homography esti-mation and reconstruction.The reconstruction sub network was further composed of two bran-ches:a low-resolution optimization branch and a high-resolution dual channel branch.We intro-duced the hollow space pyramid pooling module and dimension aware attention module to con-struct a low-resolution optimization branch,enhancing the perception ability of key areas such as structural features and stitching boundaries.Drawing on the idea of heterogeneous architecture,a high-resolution dual branch was constructed by adding lower-level subnetworks to extract more complementary structural information and improve local details in stitched images.The experi-mental results show that compared with advanced image stitching methods such as UDIS,the proposed DAISNet method effectively improves the structural deformation and misalignment phe-nomena in stitched images on the UDIS-D dataset,increases structural similarity by more than 0.63%,and improves peak signal-to-noise ratio by more than 0.30%.