Robust Face Hallucination Using Quantization-Adaptive Dictionaries

Reuben Farrugia 1 Christine Guillemot 2
2 Sirocco - Analysis representation, compression and communication of visual data
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : Existing face hallucination methods are optimized to super-resolve uncompressed images and are not able to handle the distortions caused by compression. This work presents a new dictionary construction method which jointly models both distortions caused by down-sampling and compression. The resulting dictionaries are then used to make three face super-resolution methods more robust to compression. Experimental results show that the proposed dictionary construction method generates dictionaries which are more representative of the low-quality face image being restored and makes the extended face hallucination methods more robust to compression. These experiments demonstrate that the proposed robust face hallucination methods can achieve Peak Signal-to-Noise Ratio (PSNR) gains between 2–4.48dB and recognition improvement between 2.9–8.1% compared with the low-quality image and outperforming traditional super-resolution methods in most cases.
Type de document :
Communication dans un congrès
IEEE International Conference on Image Processing, Sep 2016, Phoenix, United States. pp.5, 2016
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01388972
Contributeur : Christine Guillemot <>
Soumis le : mardi 15 novembre 2016 - 13:30:52
Dernière modification le : mercredi 16 mai 2018 - 11:23:38
Document(s) archivé(s) le : jeudi 16 mars 2017 - 16:42:25

Fichier

camera_UPLOAD_1551.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01388972, version 1

Citation

Reuben Farrugia, Christine Guillemot. Robust Face Hallucination Using Quantization-Adaptive Dictionaries. IEEE International Conference on Image Processing, Sep 2016, Phoenix, United States. pp.5, 2016. 〈hal-01388972〉

Partager

Métriques

Consultations de la notice

350

Téléchargements de fichiers

79