Super-resolution Image Reconstruction Based on Double Regression Network Model

International Journal of Advanced Network, Monitoring, and Controls

article

Jieyi Lv¹  Zhongsheng Wang¹ 

[1] School of Computer Science and Engineering Xi’an Technological University Xi’an

关键词: Super Resolution;    Mapping Function;    Deep Neural Network;    Double Regression Model;   

DOI  :  10.2478/ijanmc-2022-0039

学科分类：社会科学、人文和艺术（综合）

来源: Asociación Regional De Diálisis Y Trasplantes Renales

【 摘 要 】

By learning nonlinear mapping functions from low resolution (LR) images to high resolution (HR) images, deep neural networks show good performance in image super-resolution (SR). However, the existing SR approach has two potential limitations. First, learning the mapping function from LR to HR images is usually an ill-conditioned problem, since there exist an infinite number of HR images that can be down-sampled to the same LR image. Thus, the space of possible functions can be very large, making it difficult to find a good solution. Second, paired LR-HR data may not be available in real-world applications, and the underlying degradation method is often unknown. For this more general case, existing SR models tend to generate adaptive problems and produce poor performance. To solve the above problem, we propose a dual regression scheme that reduces the space of possible functions by introducing additional constraints on LR data.

【 授权许可】

CC BY-NC-ND