Accelerating GMM-based patch priors for image restoration: Three ingredients for a 100x speed-up
DELEDALLE, Charles-Alban
Institut de Mathématiques de Bordeaux [IMB]
University of California [San Diego] [UC San Diego]
Institut de Mathématiques de Bordeaux [IMB]
University of California [San Diego] [UC San Diego]
DENIS, Loïc
Université Jean Monnet - Saint-Étienne [UJM]
Université de Lyon
Institut d'Optique Graduate School [IOGS]
Laboratoire Hubert Curien [LabHC]
See more >
Université Jean Monnet - Saint-Étienne [UJM]
Université de Lyon
Institut d'Optique Graduate School [IOGS]
Laboratoire Hubert Curien [LabHC]
DELEDALLE, Charles-Alban
Institut de Mathématiques de Bordeaux [IMB]
University of California [San Diego] [UC San Diego]
Institut de Mathématiques de Bordeaux [IMB]
University of California [San Diego] [UC San Diego]
DENIS, Loïc
Université Jean Monnet - Saint-Étienne [UJM]
Université de Lyon
Institut d'Optique Graduate School [IOGS]
Laboratoire Hubert Curien [LabHC]
< Reduce
Université Jean Monnet - Saint-Étienne [UJM]
Université de Lyon
Institut d'Optique Graduate School [IOGS]
Laboratoire Hubert Curien [LabHC]
Language
en
Document de travail - Pré-publication
English 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 ...Read more >
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.Read less <
English Keywords
Index Terms—Image restoration
Image restoration
efficient algorithms
Gaussian mix- ture model
image patch
Gaussian mixture model
Origin
Hal imported