红外技术2024，Vol.46Issue(7)：791-801,11.
全局-局部注意力引导的红外图像恢复算法
Global-Local Attention-Guided Reconstruction Network for Infrared Image
摘要
Abstract
To solve the problems of image blur smoothing,texture distortion,and excessively large parameters in real-world infrared-image recovery algorithms,a global-local attention-guided super-resolution reconstruction algorithm for infrared images is proposed.First,a cross-scale global-local feature fusion module utilizes multi-scale convolution and a transformer to fuse information at different scales in parallel and to guide the effective fusion of global and local information by learnable factors.Second,a novel domain randomization degradation model accommodates the degradation domain of real-world infrared images.Finally,a new hybrid loss based on weight learning and regularization penalty enhances the recovery capability of the network while speeding up convergence.Test results on classical degraded images and real-world infrared images show that,compared with existing methods,the images recovered by the proposed algorithm have more realistic textures and fewer boundary artifacts.Moreover,the total number of parameters can be reduced by up to 20%.关键词
域随机化退化算法/跨尺度融合/红外图像超分辨率/生成对抗网络Key words
domain randomization degradation algorithm/cross-scale fusion/infrared image super-resolution/generative adversarial network分类
计算机与自动化引用本文复制引用
刘晓朋,张涛..全局-局部注意力引导的红外图像恢复算法[J].红外技术,2024,46(7):791-801,11.基金项目
船舶总体性能创新研究开放基金项目(14422102). （14422102）
