Gluing Reference Patches Together for Face Super-Resolution

Ji Soo Kim, Keunsoo Ko, Chang Su Kim

Research output: Contribution to journalArticlepeer-review

Abstract

Face super-resolution is a domain-specific super-resolution task to generate a high-resolution facial image from a low-resolution one. In this paper, we propose a novel face super-resolution network, called CollageNet, to super-resolve an input image by exploiting a reference image of an identical person at the patch level. First, we extract feature pyramids from input and reference images to exploit multi-scale information hierarchically. Next, we compute the patch-wise similarities between input and reference feature pyramids and select the $K$ most similar reference patches to each input patch. Then, we compose a collaged feature pyramid by gluing those selected patches together. Finally, we obtain a super-resolved image by blending the collaged feature pyramid and the input feature. Experimental results demonstrate that the proposed CollageNet yields state-of-the-art performances.

Original languageEnglish
Pages (from-to)169321-169334
Number of pages14
JournalIEEE Access
Volume9
DOIs
Publication statusPublished - 2021

Keywords

  • Face super-resolution
  • convolutional neural network
  • patch matching
  • reference-based super-resolution

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Fingerprint

Dive into the research topics of 'Gluing Reference Patches Together for Face Super-Resolution'. Together they form a unique fingerprint.

Cite this