Computer Vision – ECCV 2008

Volume 5304 of the series Lecture Notes in Computer Science pp 57-68

Non-local Regularization of Inverse Problems

  • Gabriel PeyréAffiliated withUniversité Paris-Dauphine, CEREMADE
  • , Sébastien BougleuxAffiliated withUniversité Paris-Dauphine, CEREMADE
  • , Laurent CohenAffiliated withUniversité Paris-Dauphine, CEREMADE

* Final gross prices may vary according to local VAT.

Get Access


This article proposes a new framework to regularize linear inverse problems using the total variation on non-local graphs. This non-local graph allows to adapt the penalization to the geometry of the underlying function to recover. A fast algorithm computes iteratively both the solution of the regularization process and the non-local graph adapted to this solution. We show numerical applications of this method to the resolution of image processing inverse problems such as inpainting, super-resolution and compressive sampling.