Robust Face Hallucination Using Quantization-Adaptive Dictionaries - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Robust Face Hallucination Using Quantization-Adaptive Dictionaries

Résumé

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.
Fichier principal
Vignette du fichier
camera_UPLOAD_1551.pdf (597.3 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01388972 , version 1 (15-11-2016)

Identifiants

  • HAL Id : hal-01388972 , version 1

Citer

Reuben Farrugia, Christine Guillemot. Robust Face Hallucination Using Quantization-Adaptive Dictionaries. IEEE International Conference on Image Processing, Sep 2016, Phoenix, United States. pp.5. ⟨hal-01388972⟩
223 Consultations
156 Téléchargements

Partager

Gmail Facebook X LinkedIn More