Non Local Exposure Fusion - ANR - Agence nationale de la recherche Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Non Local Exposure Fusion

Résumé

—Exposure fusion is an efficient method to obtain a well exposed and detailed image from a scene with high dynamic range. However, this method fails when there is camera shake and/or object motions. In this work, we tackle this issue by replacing the pixel-based fusion by a fusion between pixels having similar neighborhood (patches) in images with different exposure settings. In order to achieve this, we compare patches in the luminance domain. We show through several experiments that this procedure yields comparable or better results than the state of the art, at a reasonable computing time.
Fichier principal
Vignette du fichier
NLEF_Published.pdf (2.87 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01334028 , version 1 (20-06-2016)
hal-01334028 , version 2 (15-07-2019)

Identifiants

  • HAL Id : hal-01334028 , version 2

Citer

Cristian Felipe Ocampo-Blandon, Yann Gousseau. Non Local Exposure Fusion. Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, Nov 2016, Lima, Peru. ⟨hal-01334028v2⟩
297 Consultations
489 Téléchargements

Partager

Gmail Facebook X LinkedIn More