Example-Based Super-Resolution

  • Authors:
  • William T. Freeman;Thouis R. Jones;Egon C Pasztor

  • Affiliations:
  • -;-;-

  • Venue:
  • IEEE Computer Graphics and Applications
  • Year:
  • 2002

Quantified Score

Hi-index 0.06

Visualization

Abstract

Image-based models for computer graphics lack resolution independence: they cannot be enlarged much beyond the pixel resolution they were sampled at without a degradation of quality. Interpolating images usually results in a blurring of edges and image details. We describe image interpolation algorithms which use a database of training images to create plausible high-frequency details in zoomed images. Image preprocessing steps allow the use of image detail from regions of the training images which may look quite different than the image to be processed. These methods preserve fine details, such as edges, generate believable textures, and can give good results even after enlarging multiple octaves.