Fragment-based image completion

Iddo Drori, Daniel Cohen-Or, Hezy Yeshurun

Research output: Contribution to journalConference articlepeer-review

Abstract

We present a new method for completing missing parts caused by the removal of foreground or background elements from an image. Our goal is to synthesize a complete, visually plausible and coherent image. The visible parts of the image serve as a training set to infer the unknown parts. Our method iteratively approximates the unknown regions and composites adaptive image fragments into the image. Values of an inverse matte are used to compute a confidence map and a level set that direct an incremental traversal within the unknown area from high to low confidence. In each step, guided by a fast smooth approximation, an image fragment is selected from the most similar and frequent examples. As the selected fragments are composited, their likelihood increases along with the mean confidence of the image, until reaching a complete image. We demonstrate our method by completion of photographs and paintings.

Original languageEnglish
Pages (from-to)303-312
Number of pages10
JournalACM Transactions on Graphics
Volume22
Issue number3
DOIs
StatePublished - Jul 2003
EventACM SIGGRAPH 2003 - San Diego, CA, United States
Duration: 27 Jul 200331 Jul 2003

Keywords

  • Compositing
  • Digital matting
  • Example-based synthesis
  • Image completion

Fingerprint

Dive into the research topics of 'Fragment-based image completion'. Together they form a unique fingerprint.

Cite this