Perceptually aware image inpainting

Ding Ding, Sundaresh Ram, Jeffrey J Rodriguez

Research output: Contribution to journalArticlepeer-review

17 Scopus citations

Abstract

Image inpainting is a process of reconstructing missing regions, or removing unwanted objects automatically by propagating intensity and texture information from surrounding parts of the image in a visually plausible manner. We propose a new exemplar-based image inpainting algorithm, which uses the recently developed metric called the perceptual-fidelity aware mean squared error (PAMSE). The PAMSE is a Gaussian-smoothed mean squared error (MSE) and approximates a weighted sum of the gradient of MSE, the Laplacian of MSE, and MSE itself. We show that, compared to MSE, PAMSE is a promising perceptual fidelity metric for application to image inpainting and leads to better performance in propagating texture and geometric structure simultaneously.

Original languageEnglish (US)
Pages (from-to)174-184
Number of pages11
JournalPattern Recognition
Volume83
DOIs
StatePublished - Nov 1 2018

Keywords

  • Exemplar-based image inpainting
  • Geometric structure propagation
  • Object removal
  • PAMSE
  • Texture synthesis

ASJC Scopus subject areas

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

Fingerprint Dive into the research topics of 'Perceptually aware image inpainting'. Together they form a unique fingerprint.

Cite this