Wasserstein Regularization of Imaging Problems - Archive ouverte HAL Access content directly
Conference Papers Year : 2011

Wasserstein Regularization of Imaging Problems


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.
Fichier principal
Vignette du fichier
wasserstein_variational_prox.pdf (998.61 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00591279 , version 1 (08-05-2011)


  • HAL Id : hal-00591279 , version 1


Julien Rabin, Gabriel Peyré. Wasserstein Regularization of Imaging Problems. ICIP 2011 : 2011 IEEE International Conference on Image Processing, Sep 2011, Bruxelles, Belgium. ⟨hal-00591279⟩
473 View
681 Download


Gmail Facebook X LinkedIn More