Abstract

This paper presents a regularized superresolution (SR) reconstruction method using locally adaptive multiple linear regression to overcome the limitation of spatial resolution of digital images. In order to make the SR problem better-posed, the proposed method incorporates the locally adaptive multiple linear regression into the regularization process as a local prior. The local regularization prior assumes that the target high-resolution (HR) pixel is generated by a linear combination of similar pixels in differently scaled patches and optimum weight parameters. In addition, we adapt a modified version of the nonlocal means filter as a smoothness prior to utilize the patch redundancy. Experimental results show that the proposed algorithm better restores HR images than existing state-of-the-art methods in the sense of the most objective measures in the literature.

© 2015 Optical Society of America

Continuous digital zooming using local self-similarity-based super-resolution for an asymmetric dual camera system

Byeongho Moon, Soohwan Yu, Seungyong Ko, Seonhee Park, and Joonki Paik
J. Opt. Soc. Am. A 34(6) 991-1003 (2017)

Multiframe image super-resolution adapted with local spatial information

Liangpei Zhang, Qiangqiang Yuan, Huanfeng Shen, and Pingxiang Li
J. Opt. Soc. Am. A 28(3) 381-390 (2011)

Simultaneous digital super-resolution and nonuniformity correction for infrared imaging systems

Pablo Meza, Guillermo Machuca, Sergio Torres, Cesar San Martin, and Esteban Vera
Appl. Opt. 54(21) 6508-6515 (2015)

Weighted-encoding-based image interpolation with the nonlocal linear regression model

Junchao Zhang
Appl. Opt. 59(28) 8588-8594 (2020)

Concentric circular trajectory sampling for super-resolution and image mosaicing

Xian Du, Nigel Kojimoto, and Brian W. Anthony
J. Opt. Soc. Am. A 32(2) 293-304 (2015)