Consistent Video Filtering for Camera Arrays

Abstract : Visual formats have advanced beyond single-view images and videos: 3D movies are commonplace, researchers have developed multi-view navigation systems, and VR is helping to push light field cameras to mass market. However, editing tools for these media are still nascent, and even simple filtering operations like color correction or stylization are problematic: naively applying image filters per frame or per view rarely produces satisfying results due to time and space inconsistencies. Our method preserves and stabilizes filter effects while being agnostic to the inner working of the filter. It captures filter effects in the gradient domain, then uses \emph{input} frame gradients as a reference to impose temporal and spatial consistency. Our least-squares formulation adds minimal overhead compared to naive data processing. Further, when filter cost is high, we introduce a filter transfer strategy that reduces the number of per-frame filtering computations by an order of magnitude, with only a small reduction in visual quality. We demonstrate our algorithm on several camera array formats including stereo videos, light fields, and wide baselines.
Type de document :
Article dans une revue
Computer Graphics Forum, Wiley, 2017, Proc. Eurographics 2017, 36 (2)
Liste complète des métadonnées

Littérature citée [44 références]  Voir  Masquer  Télécharger
Contributeur : Nicolas Bonneel <>
Soumis le : lundi 6 mars 2017 - 13:57:51
Dernière modification le : mercredi 28 février 2018 - 15:20:29
Document(s) archivé(s) le : mercredi 7 juin 2017 - 13:59:32


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01483753, version 1


Nicolas Bonneel, James Tompkin, Deqing Sun, Oliver Wang, Kalyan Sunkavalli, et al.. Consistent Video Filtering for Camera Arrays. Computer Graphics Forum, Wiley, 2017, Proc. Eurographics 2017, 36 (2). 〈hal-01483753〉



Consultations de la notice


Téléchargements de fichiers