This work presents a cascade residual learning based non-uniformity correction method. This method adopts multi-scale feature extraction unit to fuse the extracted features and employs residual learning strategy to deal with the over-fitting problem. 赖睿,官俊涛,徐昆然,熊皑,杨银堂.级联残差学习的红外图像非均匀性校正方法[J].西安电子科技大学学报,2019,46(01):14-19.

Roughnes is the subjective metric in NUC. Reference: M. M. Hayat, S. N. Torres, E. Armstrong, S. C. Cain, et al. Statistical algorithm for nonuniformity correction in focal-plane arrays. Applied Optics, 1999, 38:772-780