Accelerating GMM-based patch priors for image restoration: Three ingredients for a 100x speed-up
| hal.structure.identifier | University of California [San Diego] [UC San Diego] | |
| dc.contributor.author | PARAMESWARAN, Shibin | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| hal.structure.identifier | University of California [San Diego] [UC San Diego] | |
| dc.contributor.author | DELEDALLE, Charles-Alban | |
| hal.structure.identifier | Université Jean Monnet - Saint-Étienne [UJM] | |
| hal.structure.identifier | Université de Lyon | |
| hal.structure.identifier | Institut d'Optique Graduate School [IOGS] | |
| hal.structure.identifier | Laboratoire Hubert Curien [LabHC] | |
| dc.contributor.author | DENIS, Loïc | |
| hal.structure.identifier | University of California [San Diego] [UC San Diego] | |
| dc.contributor.author | NGUYEN, Truong Q. | |
| hal.structure.identifier | Centre de Géosciences [GEOSCIENCES] | |
| dc.contributor.author | NGUYEN, Truong | |
| dc.date.accessioned | 2024-04-04T03:05:22Z | |
| dc.date.available | 2024-04-04T03:05:22Z | |
| dc.date.created | 2017-10-16 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/193239 | |
| dc.description.abstractEn | 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. | |
| dc.language.iso | en | |
| dc.subject.en | Index Terms—Image restoration | |
| dc.subject.en | Image restoration | |
| dc.subject.en | efficient algorithms | |
| dc.subject.en | Gaussian mix- ture model | |
| dc.subject.en | image patch | |
| dc.subject.en | Gaussian mixture model | |
| dc.title.en | Accelerating GMM-based patch priors for image restoration: Three ingredients for a 100x speed-up | |
| dc.type | Document de travail - Pré-publication | |
| dc.subject.hal | Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV] | |
| dc.subject.hal | Sciences de l'ingénieur [physics]/Traitement du signal et de l'image | |
| dc.subject.hal | Informatique [cs]/Traitement des images | |
| dc.subject.hal | Informatique [cs]/Traitement du signal et de l'image | |
| dc.identifier.arxiv | 1710.08124 | |
| bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| hal.identifier | hal-01617722 | |
| hal.version | 1 | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-01617722v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.au=PARAMESWARAN,%20Shibin&DELEDALLE,%20Charles-Alban&DENIS,%20Lo%C3%AFc&NGUYEN,%20Truong%20Q.&NGUYEN,%20Truong&rft.genre=preprint |
Files in this item
| Files | Size | Format | View |
|---|---|---|---|
|
There are no files associated with this item. |
|||