Accelerating GMM-based patch priors for image restoration: Three ingredients for a 100x speed-up

Abstract : Image restoration methods aim to recover the underlying clean image from corrupted observations. The Expected Patch Log-likelihood (EPLL) algorithm is a powerful image restoration method that uses a Gaussian mixture model (GMM) prior on the patches of natural images. Although it is very effective for restoring images, its high runtime complexity makes EPLL ill-suited for most practical applications. In this paper, we propose three approximations to the original EPLL algorithm. The resulting algorithm, which we call the fast-EPLL (FEPLL), attains a dramatic speed-up of two orders of magnitude over EPLL while incurring a negligible drop in the restored image quality (less than 0.5 dB). We demonstrate the efficacy and versatility of our algorithm on a number of inverse problems such as denoising, deblurring, super-resolution, inpainting and devignetting. To the best of our knowledge, FEPLL is the first algorithm that can competitively restore a 512x512 pixel image in under 0.5s for all the degradations mentioned above without specialized code optimizations such as CPU parallelization or GPU implementation.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01617722
Contributeur : Charles-Alban Deledalle <>
Soumis le : lundi 27 août 2018 - 14:06:32
Dernière modification le : jeudi 30 août 2018 - 01:08:37

Fichiers

fepll_arxiv.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01617722, version 2
  • ARXIV : 1710.08124

Citation

Shibin Parameswaran, Charles-Alban Deledalle, Loïc Denis, Truong Q. Nguyen, Truong Nguyen. Accelerating GMM-based patch priors for image restoration: Three ingredients for a 100x speed-up. 2017. 〈hal-01617722v2〉

Partager

Métriques

Consultations de la notice

63

Téléchargements de fichiers

40