Single image super resolution via neighbor reconstruction

Zhihong Zhang, Chen Xu, Zhonghao Zhang, Guo Chen, Yide Cai, Zeli Wang, Heng Li, Edwin R. Hancock

Research output: Journal article publicationJournal articleAcademic researchpeer-review

3 Citations (Scopus)

Abstract

Super Resolution (SR) is a complex, ill-posed problem where the aim is to construct the mapping between the low and high resolution manifolds of image patches. Anchored neighborhood regression for SR (namely A+ [27]) has shown promising results. In this paper we present a new regression-based SR algorithm that overcomes the limitations of A+ and benefits from an innovative and simple Neighbor Reconstruction Method (NRM). This is achieved by vector operations on an anchored point and its corresponding neighborhood. NRM reconstructs new patches which are closer to the anchor point in the manifold space. Our method is robust to NRM sparsely-sampled points: increasing PSNR by 0.5 dB compared to the next best method. We comprehensively validate our technique on standardised datasets and compare favourably with the state-of-the-art methods: we obtain PSNR improvement of up to 0.21 dB compared to previously-reported work.

Original languageEnglish
Pages (from-to)157-165
Number of pages9
JournalPattern Recognition Letters
Volume125
DOIs
Publication statusPublished - 1 Jul 2019

Keywords

  • Manifold learning
  • Neighbor reconstruction
  • Super resolution

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this