• xmlui.mirage2.page-structure.header.title
    • français
    • English
  • Help
  • Login
  • Language 
    • Français
    • English
View Item 
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

BIRDResearch centres & CollectionsBy Issue DateAuthorsTitlesTypeThis CollectionBy Issue DateAuthorsTitlesType

My Account

LoginRegister

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors
Thumbnail - No thumbnail

Wasserstein Regularization of Imaging Problem

Peyré, Gabriel; Rabin, Julien (2011), Wasserstein Regularization of Imaging Problem, 18th IEEE International Conference on Image Processing (ICIP), 2011 - Proceedings, IEEE, p. 1541-1544

Type
Communication / Conférence
External document link
http://hal.archives-ouvertes.fr/hal-00591279/fr/
Date
2011
Conference title
ICIP 2011 : 2011 IEEE International Conference on Image Processing
Conference date
2011-09
Conference city
Bruxelles
Conference country
Belgique
Book title
18th IEEE International Conference on Image Processing (ICIP), 2011 - Proceedings
Publisher
IEEE
ISBN
978-1-4577-1304-0
Pages
1541-1544
Publication identifier
http://dx.doi.org/10.1109/ICIP.2011.6115740
Metadata
Show full item record
Author(s)
Peyré, Gabriel
Rabin, Julien cc
Abstract (EN)
This paper introduces a novel and generic framework embedding statistical constraints for variational problems. We resort to the theory of Monge-Kantorovich optimal mass transport to define penalty terms depending on statistics from images. To cope with the computation time issue of the corresponding Wasserstein distances involved in this approach, we propose an approximate variational formulation for statistics represented as point clouds. We illustrate this framework on the problem of regularized color specification. This is achieved by combining the proposed approximate Wasserstein constraint on color statistics with a generic geometric-based regularization term in a unified variational minimization problem. We believe that this methodology may lead to some other interesting applications in image processing, such as medical imaging modification, texture synthesis, etc.
Subjects / Keywords
color and contrast modification; Gradient descent; Image regularization; Energy minimization; Variational model

Related items

Showing items related by title and author.

  • Thumbnail
    Sliced and Radon Wasserstein Barycenters of Measures 
    Pfister, Hanspeter; Peyré, Gabriel; Rabin, Julien; Bonneel, Nicolas (2015) Article accepté pour publication ou publié
  • Thumbnail
    Wasserstein Active Contours 
    Rabin, Julien; Fadili, Jalal; Peyré, Gabriel (2012) Communication / Conférence
  • Thumbnail
    Wasserstein Barycenter and its Application to Texture Mixing 
    Bernot, Marc; Rabin, Julien; Peyré, Gabriel; Delon, Julie (2012) Communication / Conférence
  • Thumbnail
    Régularisation de Wasserstein. Application au Transfert de Couleur 
    Julien, Rabin; Peyré, Gabriel (2011) Communication / Conférence
  • Thumbnail
    Low Complexity Regularization of Linear Inverse Problems 
    Vaiter, Samuel; Peyré, Gabriel; Fadili, Jalal (2015) Chapitre d'ouvrage
Dauphine PSL Bibliothèque logo
Place du Maréchal de Lattre de Tassigny 75775 Paris Cedex 16
Phone: 01 44 05 40 94
Contact
Dauphine PSL logoEQUIS logoCreative Commons logo