Video enhancement with convex optimization methods

Benoit Boyadjis 1, 2 Andrei Purica 3 Béatrice Pesquet-Popescu 3 Frédéric Dufaux 4
1 THALES COMMUNICATIONS & SECURITY
2 LTCI - Laboratoire Traitement et Communication de l'Information
3 LTCI - Laboratoire Traitement et Communication de l'Information
4 L2S - Laboratoire des signaux et systèmes
Abstract : Video enhancement methods enable to optimize the viewing of video content at the end-user side. Most approaches do not consider the compressed nature of the available content. In the present work, we build upon a recently proposed video enhancement approach that explicitly models a compression stage. To apply the enhancement framework on compressed representations requires to extract specific syntax elements during their decoding. This additional information embeds the enhanced result in a domain that closely fits the observation. We evaluate the framework performance in a single source resolution enhancement scenario, and show the method efficiency with respect to state-of-the-art approaches.
Type de document :
Communication dans un congrès
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2018), Apr 2018, Calgary, Canada. 〈10.1109/icassp.2018.8462357 〉
Liste complète des métadonnées
https://hal.archives-ouvertes.fr/hal-01698173
Contributeur : Frédéric Dufaux <>
Soumis le : mercredi 31 janvier 2018 - 23:37:05
Dernière modification le : mercredi 23 janvier 2019 - 14:39:32

Identifiants

Collections

L2S | CENTRALESUPELEC | SUP_LSS | TELECOM-PARISTECH | SUP_TELECOMS | UNIV-PARIS-SACLAY | PARISTECH

Citation

Benoit Boyadjis, Andrei Purica, Béatrice Pesquet-Popescu, Frédéric Dufaux. Video enhancement with convex optimization methods. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2018), Apr 2018, Calgary, Canada. 〈10.1109/icassp.2018.8462357 〉. 〈hal-01698173〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

246

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD