PARAMESWARAN, Shibin; ENMING, Luo; DELEDALLE, Charles; NGUYEN, Truong

Métadonnées

Afficher la notice complète

Licence d’utilisation du document

PARAMESWARAN, Shibin
University of California [San Diego] [UC San Diego]

ENMING, Luo

DELEDALLE, Charles
University of California [San Diego] [UC San Diego]
Institut de Mathématiques de Bordeaux [IMB]

Langue

Communication dans un congrès

Ce document a été publié dans

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 29-37, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 29-37, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017-07-22, Honolulu. 2017-08-01

Résumé en anglais

We introduce a new external denoising algorithm that utilizes pre-learned transformations to accelerate filter calculations during runtime. The proposed fast external denoising (FED) algorithm shares characteristics of the powerful Targeted Image Denoising (TID) and Expected Patch Log-Likelihood (EPLL) algorithms. By moving computationally demanding steps to an offline learning stage, the proposed approach aims to find a balance between processing speed and obtaining high quality denoising estimates. We evaluate FED on three datasets with targeted databases (text, face and license plates) and also on a set of generic images without a targeted database. We show that, like TID, the proposed approach is extremely effective when the transformations are learned using a targeted database. We also demonstrate that FED converges to competitive solutions faster than EPLL and is orders of magnitude faster than TID while providing comparable denoising performance.< Réduire

Métadonnées

Partager cette publication !

Licence d’utilisation du document

Fast External Denoising Using Pre-Learned Transformations

Langue

Ce document a été publié dans

Résumé en anglais

URI

Origine

Unités de recherche