• Corpus ID: 25824916

Image restoration with generalized Gaussian mixture model patch priors

@article{Deledalle2018ImageRW,
  title={Image restoration with generalized Gaussian mixture model patch priors},
  author={Charles-Alban Deledalle and Shibin Parameswaran and Truong Q. Nguyen},
  journal={ArXiv},
  year={2018},
  volume={abs/1802.01458}
}
Patch priors have became an important component of image restoration. A powerful approach in this category of restoration algorithms is the popular Expected Patch Log-likelihood (EPLL) algorithm. EPLL uses a Gaussian mixture model (GMM) prior learned on clean image patches as a way to regularize degraded patches. In this paper, we show that a generalized Gaussian mixture model (GGMM) captures the underlying distribution of patches better than a GMM. Even though GGMM is a powerful prior to… 
View PDF on arXiv
View With Semantic Reader
5 Citations
Background Citations
1
Methods Citations
3

5 Citations

Citation Type

Citation Type

Image Restoration Using Conditional Random Fields and Scale Mixtures of Gaussians
TLDR
The results show that the proposed approach outperforms methods based on Gaussian mixture models for image denoising and state-of-the-art methods for image interpolation/inpainting.
Multivariate Statistical Approach to Image Quality Tasks
TLDR
A generalized Gaussian-based local contrast estimator is proposed as a way to implement non-linear local gain control, that facilitates the accurate modeling of both pristine and distorted images.
High-Dimensional Mixture Models for Unsupervised Image Denoising (HDMI)
TLDR
This work proposes a full modeling of the process that is supposed to have generated the noisy patches and proposes a blind denoising algorithm that demonstrates state-of-the-art performance, both when the noise level is known and unknown.
Patch-Based Nonlocal Adaptive Gradient Regularization for Image Restoration in Sensor Networks
TLDR
A novel patch-based adaptive nonlocal gradient regularization method for image restoration in sensor networks that formulates the hyper-Laplacian distribution to regularize the global gradient distribution.
MOVING OBJECT DETECTION METHOD OF VIDEO SATELLITE BASED ON TRACKING CORRECTION DETECTION
TLDR
It is proved by this work that the accuracy of the target detection of TCD method has reached 85%, which has a high engineering application value.

References

SHOWING 1-10 OF 88 REFERENCES
Expected Patch Log Likelihood with a Sparse Prior
TLDR
The derivation leads to a close yet extended variant of the popular K-SVD image denoising algorithm, where in order to effectively maximize the EPLL the Denoising process should be iterated.
Accelerating GMM-Based Patch Priors for Image Restoration: Three Ingredients for a $100{\times}$ Speed-Up
TLDR
The resulting algorithm, which is called 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).
The student-t mixture as a natural image patch prior with application to image compression
TLDR
This work demonstrates that the Student-t mixture model convincingly surpasses GMMs in terms of log likelihood, achieving performance competitive with the state of the art in image patch modeling, and proposes efficient coding schemes that can easily be extended to other unsupervised machine learning models.
From learning models of natural image patches to whole image restoration
TLDR
A generic framework which allows for whole image restoration using any patch based prior for which a MAP (or approximate MAP) estimate can be calculated is proposed and a generic, surprisingly simple Gaussian Mixture prior is presented, learned from a set of natural images.
Multi-Scale Patch-Based Image Restoration
TLDR
This scheme comes to alleviate another shortcoming existing in patch-based restoration algorithms-the fact that a local (patch-based) prior is serving as a model for a global stochastic phenomenon.
Fast Image Deconvolution using Hyper-Laplacian Priors
TLDR
This paper describes a deconvolution approach that is several orders of magnitude faster than existing techniques that use hyper-Laplacian priors and is able to deconvolve a 1 megapixel image in less than ~3 seconds, achieving comparable quality to existing methods that take ~20 minutes.
A Nonlocal Bayesian Image Denoising Algorithm
TLDR
A simple patch-based Bayesian method is proposed, which on the one hand keeps most interesting features of former methopping methods and on the other hand unites the transform thresholding method and a Markovian Bayesian estimation.
Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
TLDR
This work addresses the image denoising problem, where zero-mean white and homogeneous Gaussian additive noise is to be removed from a given image, and uses the K-SVD algorithm to obtain a dictionary that describes the image content effectively.
Analysis of Multiresolution Image Denoising Schemes Using Generalized Gaussian and Complexity Priors
TLDR
This paper investigates various connections between shrinkage methods and maximum a posteriori (MAP) estimation using such priors, and introduces a new family of complexity priors based upon Rissanen's universal prior on integers.
Fields of Experts: a framework for learning image priors
  • S. Roth, Michael J. Black
  • Computer Science
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
TLDR
A framework for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks, developed using a Products-of-Experts framework.
...
1
2
3
4
5
...