Image inpainting using LLE-LDNR and linear subspace mappings - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2013

Image inpainting using LLE-LDNR and linear subspace mappings

Résumé

The paper first describes an examplar-based image inpainting algorithm using a locally linear neighbor embedding technique with low-dimensional neighborhood representation (LLE-LDNR). The inpainting algorithm first searches the K nearest neighbors (K-NN) of the input patch to be filled-in and linearly combine them with LLE-LDNR to synthesize the missing pixels. Linear regression is then introduced for improving the K-NN search. The performance of the LLE-LDNR with the enhanced K-NN search method is assessed for two applications: loss concealment and object removal.
Fichier non déposé

Dates et versions

hal-00876130 , version 1 (23-10-2013)

Identifiants

  • HAL Id : hal-00876130 , version 1

Citer

Christine Guillemot, Mehmet Turkan, Olivier Le Meur, Mounira Ebdelli. Image inpainting using LLE-LDNR and linear subspace mappings. IEEE Intl. Conf. on Acoustics and Signal Processing (IEEE-ICASSP), May 2013, Vancouver, United States. ⟨hal-00876130⟩
148 Consultations
0 Téléchargements

Partager

More