Missing data correction in still images and image sequences

  • Authors:
  • Raphaël Bornard;Emmanuelle Lecan;Louis Laborelli;Jean-Hugues Chenot

  • Affiliations:
  • Institut National de l'Audiovisuel, Bry-sur-Marne Cedex, France and Ecole Centrale Paris, Applied Mathematics and Systems Laboratory, Châtenay-Malabry Cedex, France;Institut National de l'Audiovisuel, Bry-sur-Marne Cedex, France;Institut National de l'Audiovisuel, Bry-sur-Marne Cedex, France;Institut National de l'Audiovisuel, Bry-sur-Marne Cedex, France

  • Venue:
  • Proceedings of the tenth ACM international conference on Multimedia
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

The ability to replace missing data in images and video is of key importance to many application fields. The general-purpose algorithm presented here is inspired by texture synthesis techniques but is suited to any complex natural scene and not restricted to stationary patterns. It has the property to be adapted to both still images and image sequences and to incorporate temporal information when available while preserving the simplicity of the algorithm. This method gives very good results in various situations without user intervention. The resulting computational cost is relatively low and corrections are usually produced within seconds.