Robust Image Filtering Using Joint Static and Dynamic Guidance

Bumsub Ham 1, 2 Minsu Cho 1, 2 Jean Ponce 1, 2
2 WILLOW - Models of visual object recognition and scene understanding
CNRS - Centre National de la Recherche Scientifique : UMR8548, Inria Paris-Rocquencourt, DI-ENS - Département d'informatique de l'École normale supérieure
Abstract : Regularizing images under a guidance signal has been used in various tasks in computer vision and computational photography, particularly for noise reduction and joint up-sampling. The aim is to transfer fine structures of guidance signals to input images, restoring noisy or altered structures. One of main drawbacks in such a data-dependent framework is that it does not handle differences in structure between guidance and input images. We address this problem by jointly leveraging structural information of guidance and input images. Image filtering is formulated as a nonconvex optimization problem, which is solved by the majorization-minimization algorithm. The proposed algorithm converges quickly while guaranteeing a local minimum. It effectively controls image structures at different scales and can handle a variety of types of data from different sensors. We demonstrate the flexibility and effectiveness of our model in several applications including depth super-resolution, scale-space filtering, texture removal, flash/non- flash denoising, and RGB/NIR denoising.
Type de document :
Communication dans un congrès
CVPR 2015, Jun 2015, BOSTON, United States
Liste complète des métadonnées
Contributeur : Bumsub Ham <>
Soumis le : mercredi 9 décembre 2015 - 00:24:01
Dernière modification le : jeudi 7 février 2019 - 15:49:27
Document(s) archivé(s) le : samedi 29 avril 2017 - 10:07:38


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


  • HAL Id : hal-01240280, version 1



Bumsub Ham, Minsu Cho, Jean Ponce. Robust Image Filtering Using Joint Static and Dynamic Guidance. CVPR 2015, Jun 2015, BOSTON, United States. 〈hal-01240280〉



Consultations de la notice


Téléchargements de fichiers