Charles Deledalle picture
 
[english][français]

Charles Deledalle's Homepage

CNRS Research associate in the Image team at IMB (Université Bordeaux, France)
charles-alban (dot) deledalle (at) math.u-bordeaux (dot) fr
+33 (0)5 40 00 21 14

 

Short bio

I received the engineer degree from EPITA and the Master of Science and Technology from Univ. Paris VI both in France, in 2008. In 2011, I defended my PhD, from Telecom ParisTech, France, in signal and image processing and supervised by Florence Tupin and Loïc Denis. I made a postdoctoral fellowship at Univ. Paris IX, France, in 2011-2012, under the supervision of Gabriel Peyré and Jalal Fadili. I am currently CNRS Researcher at IMB, Univ. Bordeaux, France. My research interests include image denoising and inverse-problems with a focus on parameter estimation. I received the IEEE ICIP Best Student Paper Award in 2010 and the ISIS/EEA/GRETSI Best PhD Award in 2012.


  [See my resume]
 

News


Events


Research

Algorithme NL means

Recent publications

Some of the publications below have appeared in an IEEE journal, Springer journal, Elsevier journal or conference record. By allowing you to download them, I am required to post the following copyright reminder: "This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder."


[See all my publications]  [See my publications on Scholar Google]
Some of my papers in refereed journals
NL-SAR: a unified Non-Local framework for resolution-preserving (Pol)(In)SAR denoising,
Charles-Alban Deledalle, Loïc Denis, Florence Tupin, Andreas Reigber and Marc Jäger
IEEE Trans. on Geoscience and Remote Sensing, vol. 53, no. 4, pp. 2021-2038, 2015 (IEEE Xplore, HAL)
 
Speckle noise is an inherent problem in coherent imaging systems like synthetic aperture radar. It creates strong intensity fluctuations and hampers the analysis of images and the estimation of local radiometric, polarimetric or interferometric properties. SAR processing chains thus often include a multi-looking (i.e., averaging) filter for speckle reduction, at the expense of a strong resolution loss. Preservation of point-like and fine structures and textures requires to locally adapt the estimation. Non-local means successfully adapt smoothing by deriving data-driven weights from the similarity between small image patches. The generalization of non-local approaches offers a flexible framework for resolution-preserving speckle reduction. We describe a general method, NL-SAR, that builds extended non-local neighborhoods for denoising amplitude, polarimetric and/or interferometric SAR images. These neighborhoods are defined on the basis of pixel similarity as evaluated by multi-channel comparison of patches. Several non-local estimations are performed and the best one is locally selected to form a single restored image with good preservation of radar structures and discontinuities. The proposed method is fully automatic and handles single and multi-look images, with or without interferometric or polarimetric channels. Efficient speckle reduction with very good resolution preservation is demonstrated both on numerical experiments using simulated data and airborne radar images. The source code of a parallel implementation of NL-SAR is released with the paper.
 
Stein Unbiased GrAdient estimator of the Risk (SUGAR) for multiple parameter selection,
C.-A. Deledalle, S. Vaiter, J.-M. Fadili, G. Peyré
SIAM Journal on Imaging Sciences, vol. 7., no. 4, pp. 2448-2487, 2014 (epubs SIAM, ArXiv)
 
Algorithms to solve variational regularization of ill-posed inverse problems usually involve operators that depend on a collection of continuous parameters. When these operators enjoy some (local) regularity, these parameters can be selected using the so-called Stein Unbiased Risk Estimate (SURE). While this selection is usually performed by exhaustive search, we address in this work the problem of using the SURE to efficiently optimize for a collection of continuous parameters of the model. When considering non-smooth regularizers, such as the popular l1-norm corresponding to soft-thresholding mapping, the SURE is a discontinuous function of the parameters preventing the use of gradient descent optimization techniques. Instead, we focus on an approximation of the SURE based on finite differences as proposed in (Ramani et al., 2008). Under mild assumptions on the estimation mapping, we show that this approximation is a weakly differentiable function of the parameters and its weak gradient, coined the Stein Unbiased GrAdient estimator of the Risk (SUGAR), provides an asymptotically (with respect to the data dimension) unbiased estimate of the gradient of the risk. Moreover, in the particular case of soft-thresholding, the SUGAR is proved to be also a consistent estimator. The SUGAR can then be used as a basis to perform a quasi-Newton optimization. The computation of the SUGAR relies on the closed-form (weak) differentiation of the non-smooth function. We provide its expression for a large class of iterative proximal splitting methods and apply our strategy to regularizations involving non-smooth convex structured penalties. Illustrations on various image restoration and matrix completion problems are given.
 
Adaptive regularization of the NL-means: Application to image and video denoising,
Camille Sutour, Charles-Alban Deledalle, Jean-François Aujol
IEEE Trans. on Image Processing, vol. 23, no. 8, pp. 3506-3521, 2014 (IEEE Xplore, HAL)
 
Image denoising is a central problem in image processing and it is often a necessary step prior to higher level analysis such as segmentation, reconstruction or super-resolution. The non-local means (NL-means) perform denoising by exploiting the natural redundancy of patterns inside an image; they perform a weighted average of pixels whose neighborhoods (patches) are close to each other. This reduces significantly the noise while preserving most of the image content. While it performs well on flat areas and textures, it suffers from two opposite drawbacks: it might over-smooth low-contrasted areas or leave a residual noise around edges and singular structures. Denoising can also be performed by total variation minimization -- the ROF model -- which leads to restore regular images, but it is prone to over-smooth textures, staircasing effects, and contrast losses. We introduce in this paper a variational approach that corrects the over-smoothing and reduces the residual noise of the NL-means by adaptively regularizing non-local methods with the total variation. The proposed regularized NL-means algorithm combines these methods and reduces both of their respective defaults by minimizing an adaptive total variation with a non-local data fidelity term. Besides, this model adapts to different noise statistics and a fast solution can be obtained in the general case of the exponential family. We develop this model for image denoising and we adapt it to video denoising with 3D patches.
 
Local Behavior of Sparse Analysis Regularization: Applications to Risk Estimation,
Samuel Vaiter, Charles-Alban Deledalle, Gabriel Peyré, Charles Dossal, Jalal Fadili
Applied and Computational Harmonic Analysis, vol. 35, no. 3, pp. 433-451, 2013 (HAL, Science Direct (Elsevier))
 
In this paper, we aim at recovering an unknown signal x0 from noisy L1measurements y=Phi*x0+w, where Phi is an ill-conditioned or singular linear operator and w accounts for some noise. To regularize such an ill-posed inverse problem, we impose an analysis sparsity prior. More precisely, the recovery is cast as a convex optimization program where the objective is the sum of a quadratic data fidelity term and a regularization term formed of the L1-norm of the correlations between the sought after signal and atoms in a given (generally overcomplete) dictionary. The L1-sparsity analysis prior is weighted by a regularization parameter lambda>0. In this paper, we prove that any minimizers of this problem is a piecewise-affine function of the observations y and the regularization parameter lambda. As a byproduct, we exploit these properties to get an objectively guided choice of lambda. In particular, we develop an extension of the Generalized Stein Unbiased Risk Estimator (GSURE) and show that it is an unbiased and reliable estimator of an appropriately defined risk. The latter encompasses special cases such as the prediction risk, the projection risk and the estimation risk. We apply these risk estimators to the special case of L1-sparsity analysis regularization. We also discuss implementation issues and propose fast algorithms to solve the L1 analysis minimization problem and to compute the associated GSURE. We finally illustrate the applicability of our framework to parameter(s) selection on several imaging problems.
 
Some of my conference papers
Stein COnsistent Risk Estimator (SCORE) for hard thresholding,
Charles-Alban Deledalle, Gabriel Peyré, Jalal Fadili
SPARS, Lausanne, Switzerland, July 2013 (HAL, poster)
 
In this work, we construct a risk estimator for hard thresholding which can be used as a basis to solve the difficult task of automatically selecting the threshold. As hard thresholding is not even continuous, Stein's lemma cannot be used to get an unbiased estimator of degrees of freedom, hence of the risk. We prove that under a mild condition, our estimator of the degrees of freedom, although biased, is consistent. Numerical evidence shows that our estimator outperforms another biased risk estimator.
 
Image denoising with patch based PCA: local versus global,
Charles-Alban Deledalle, Joseph Salmon, Arnak Dalalyan
In the proceedings of BMVC, University of Dundee, August-Septembre 2011 (pdf, slides)
 
In recent years, overcomplete dictionaries combined with sparse learning techniques became extremely popular in computer vision. While their usefulness is undeniable, the improvement they provide in specific tasks of computer vision is still poorly understood. The aim of the present work is to demonstrate that for the task of image denoising, nearly state-of-the-art results can be achieved using orthogonal dictionaries only, provided that they are learned directly from the noisy image. To this end, we introduce three patch-based denoising algorithms which perform hard thresholding on the coefficients of the patches in image-specific orthogonal dictionaries. The algorithms differ by the methodology of learning the dictionary: local PCA, hierarchical PCA and global PCA. We carry out a comprehensive empirical evaluation of the performance of these algorithms in terms of accuracy and running times. The results reveal that, despite its simplicity, PCA-based denoising appears to be competitive with the state-of-the-art denoising algorithms, especially for large images and moderate signal-to-noise ratios.
 
Poisson NL means: unsupervised non local means for Poisson noise,
Charles-Alban Deledalle, Florence Tupin and Loïc Denis
In the proceedings of ICIP, Hong Kong, September 2010 (pdf, slides)
Best student paper award IEEE ICIP 2010
 
An extension of the non local (NL) means is proposed for images damaged by Poisson noise. The proposed method is guided by the noisy image and a pre-filtered image and is adapted to the statistics of Poisson noise. The influence of both images can be tuned using two filtering parameters. We propose an automatic setting to select these parameters based on the minimization of the estimated risk (mean square error). This selection uses an estimator of the MSE for NL means with Poisson noise and Newton's method to find the optimal parameters in few iterations.
 
My PhD
Image denoising beyond additive Gaussian noise
Patch-based estimators and their application to SAR imagery
,
Charles-Alban Deledalle
In Telecom ParisTech, France, Nov 15, 2011 (HAL, slides)
 
Noise in images often limits visual and automatic interpretation of the scene. Speckle in synthetic aperture radar (SAR) imagery and shot noise in photon-limited imagery are two examples of strong corruptions that require the use of denoising techniques. Patches are small image parts that capture both textures and local structures. Though being crude low-level features (compared to higher level descriptors), they have led to very powerful image processing approaches by exploiting the natural redundancy of images. Patch-based methods achieve state-of-the-art denoising performance. The classical patch-based denoising technique non-local (NL) means is designed for images corrupted by an additive Gaussian noise (i.e., fluctuations being symmetrical, signal-independent without outliers). NL means cannot be applied directly on images corrupted by a non-Gaussian process especially with non-symmetrical distribution, signal-dependence and heavy-tail such as speckle and shot noise. The goal of this thesis is to bridge the gap between patch-based denoising methods restricted to Gaussian noise and techniques dedicated to SAR despeckling. After reviewing image denoising techniques for Gaussian noise and for non-Gaussian noise, we propose an extension of the NL means that adapts to a given noise distribution. Besides the problem of image denoising, we study the problem of patch comparison under non-Gaussian conditions. Many tasks in computer vision require matching image parts. We introduce a similarity criterion grounded on the generalized likelihood ratio test and illustrate its effectiveness on different applications including detection, stereo-vision and motion-tracking. This criterion is at the heart of the proposed patch-based estimator. An iterative scheme is proposed to deal with strong noise corruptions and we develop an unsupervised method for parameter setting. Our approach leads to state-of-the-art denoising results in SAR imagery for amplitude images, as well as interferometric or polarimetric data. The proposed technique is applied successfully to one of the latest aerial SAR sensor: F-SAR from the German Aerospace Center (DLR). Images with strong contrasts suffer from denoising artefacts known as noise halo due to the absence of similar patches in the vicinity of some structures. This residual noise can be reduced by considering patches with shapes of various scales and orientations. Local selection of relevant shapes leads to an improved denoising quality, especially close to edges.

[See all my publications]  [See my publications on Scholar Google]
 

Software

Inverse problems
SUGAR software
SUGAR (2014)
Matlab open-source software for the automatic selection of (multiple) parameters in inverse problems.
 
Algorithms to solve variational regularization of ill-posed inverse problems usually involve operators that depend on a collection of continuous parameters. When these operators enjoy some (local) regularity, these parameters can be selected using the so-called Stein Unbiased Risk Estimate (SURE). While this selection is usually performed by exhaustive search, we address in this work the problem of using the SURE to efficiently optimize for a collection of continuous parameters of the model. When considering non-smooth regularizers, such as the popular l1-norm corresponding to soft-thresholding mapping, the SURE is a discontinuous function of the parameters preventing the use of gradient descent optimization techniques. Instead, we focus on an approximation of the SURE based on finite differences as proposed in (Ramani et al., 2008). Under mild assumptions on the estimation mapping, we show that this approximation is a weakly differentiable function of the parameters and its weak gradient, coined the Stein Unbiased GrAdient estimator of the Risk (SUGAR), provides an asymptotically (with respect to the data dimension) unbiased estimate of the gradient of the risk. Moreover, in the particular case of soft-thresholding, the SUGAR is proved to be also a consistent estimator. The SUGAR can then be used as a basis to perform a quasi-Newton optimization. The computation of the SUGAR relies on the closed-form (weak) differentiation of the non-smooth function. We provide its expression for a large class of iterative proximal splitting methods and apply our strategy to regularizations involving non-smooth convex structured penalties. Illustrations on various image restoration and matrix completion problems are given.
 
Denoising
NL-SAR software
NL-SAR (2013-2014)
Open-source software distributed under CeCILL license to perform adaptive non-local (Pol)(In)SAR filtering.
Interface in command line, IDL, Matlab, Python and C dynamic library.
Plug in for PolSARpro.
 
Speckle noise is an inherent problem in coherent imaging systems like synthetic aperture radar. It creates strong intensity fluctuations and hampers the analysis of images and the estimation of local radiometric, polarimetric or interferometric properties. SAR processing chains thus often include a multi-looking (i.e., averaging) filter for speckle reduction, at the expense of a strong resolution loss. Preservation of point-like and fine structures and textures requires to locally adapt the estimation. Non-local means successfully adapt smoothing by deriving data-driven weights from the similarity between small image patches. The generalization of non-local approaches offers a flexible framework for resolution-preserving speckle reduction. NL-SAR is a general method that builds extended non-local neighborhoods for denoising amplitude, polarimetric and/or interferometric SAR images. These neighborhoods are defined on the basis of pixel similarity as evaluated by multi-channel comparison of patches. Several non-local estimations are performed and the best one is locally selected to form a single restored image with good preservation of radar structures and discontinuities. The proposed method is fully automatic and can handle single and multi-look images, with or without interferometric or polarimetric channels. Efficient speckle reduction with very good resolution preservation has been demonstrated both on numerical experiments using simulated data and airborne radar images.
 
NLSPCA software
Poisson NLSPCA (2012)
Matlab open-source software to perform non-local filtering in an extended PCA domain for Poisson noise.
 
Photon-limited imaging arises when the number of photons collected by a sensor array is small relative to the number of detector elements. Photon limitations are an important concern for many applications such as spectral imaging, night vision, nuclear medicine, and astronomy. Typically a Poisson distribution is used to model these observations, and the inherent heteroscedasticity of the data combined with standard noise removal methods yields significant artifacts. A novel denoising algorithm is implemented for photon-limited images which combines elements of dictionary learning and sparse patch-based representations of images. The method employs both an adaptation of Principal Component Analysis (PCA) for Poisson noise and recently developed sparsity-regularized convex optimization algorithms for photon-limited images. A comprehensive empirical evaluation of the proposed method helps characterize the performance of this approach relative to other state-of-the-art denois ing methods. The results reveal that, despite its conceptual simplicity, Poisson PCA-based denoising appears to be highly competitive in very low light regimes.
 
NL-PCA software
NLPCA (2011)
Matlab open-source software to perform non-local filtering in the PCA domain.
 
In recent years, overcomplete dictionaries combined with sparse learning techniques became extremely popular in computer vision. While their usefulness is undeniable, the improvement they provide in specific tasks of computer vision is still poorly understood. The aim of the present work is to demonstrate that for the task of image denoising, nearly state-of-the-art results can be achieved using orthogonal dictionaries only, provided that they are learned directly from the noisy image. To this end, we introduce three patch- based denoising algorithms which perform hard thresholding on the coefficients of the patches in image-specific orthogonal dictionaries. The algorithms differ by the method- ology of learning the dictionary: local PCA, hierarchical PCA and global PCA. We carry out a comprehensive empirical evaluation of the performance of these algorithms in terms of accuracy and running times. The results reveal that, despite its simplicity, PCA-based denoising appears to be competitive with the state-of-the-art denoising algorithms, espe- cially for large images and moderate signal-to-noise ratios.
 
NLMSAP software
NLMSAP (2011)
Matlab open-source software to perform non-local filtering with shape adaptive patches.
 
This implements an extension of the Non-Local Means (NL-Means) denoising algorithm. The idea is to replace the usual square patches used to compare pixel neighborhoods with various shapes that can take advantage of the local geometry of the image. We provide a fast algorithm to compute the NL-Means with arbitrary shapes thanks to the Fast Fourier Transform. We then consider local combinations of the estimators associated with various shapes by using Stein’s Unbiased Risk Estimate (SURE). Experimental results show that this algorithm improve the standard NL-Means performance and is close to state-of-the-art methods, both in terms of visual quality and numerical results. Moreover, common visual artifacts usually observed by denoising with NL-Means are reduced or suppressed thanks to our approach.
 
Poisson NL-means software
Poisson NL-means (2010)
Matlab/Mex software to perform non-local filtering for Poisson noise with automatic selection of the denoising parameters.
 
This work has been achieved by Charles Deledalle supervised by Florence Tupin and Loïc Denis. The aim was to adapt the Non-Local means (NL means) filter [1] to images sensed in low-light conditions. The Poisson NL means filter is based on the PPB filter [2] which ables to extend the NL means to deal with the Poisson distribution followed by the noise in such images. An efficient estimator has been designed, able to cope with the statistics and especially with the signal-dependent nature of such images. The Poisson NL means filter is an an extension of the non local (NL) [1] means for images damaged by Poisson noise. The proposed method is guided by the noisy image and a pre-filtered image and is adapted to the statistics of Poisson noise as recommended in [2]. The influence of both images can be tuned using two filtering parameters. These two parameters are automatically set to minimize an estimation of the mean square error (MSE). This selection uses an estimator of the MSE for NL means with Poisson noise and a Newton's method to find the optimal parameters in few iterations.
 
NL-InSAR software
Non-local InSAR (NL-InSAR) filter (2011)
Matlab/Mex software of the PPB version for SAR interferometry.
 
This work has been achieved by Charles Deledalle supervised by Florence Tupin and Loïc Denis. The aim was to adapt the Non-Local means (NL means) filter [7] to InSAR images. The NL-InSAR filter is based on the PPB filter [6] which is an extension of the NL means to non-gaussian noise and multivariate data. Then, an efficient estimator as been designed, able to cope with the statistical nature and the multi-dimensionnality of InSAR images. Interferometric synthetic aperture radar (InSAR) data provides reflectivity, interferometric phase and coherence images, which are paramount to scene interpretation or low-level processing tasks such as segmentation and 3D reconstruction. These images are estimated in practice from hermitian product on local windows. These windows lead to biases and resolution losses due to local heterogeneity caused by edges and textures. We propose a non-local approach for the joint estimation of the reflectivity, the interferometric phase and the coherence images from an interferometric pair of co-registered single-look complex (SLC) SAR images. Non-local techniques are known to efficiently reduce noise while preserving structures by performing a weighted averaging of similar pixels. Two pixels are considered similar if the surrounding image patches are "resembling". Patch- similarity is usually defined as the Euclidean distance between the vectors of graylevels. A statistically grounded patch-similarity criterion suitable to SLC images is derived. A weighted maximum likelihood estimation of the SAR interferogram is then computed with weights derived in a data-driven way. Weights are defined from intensity and interferometric phase, and are iteratively refined based both on the similarity between noisy patches and on the similarity of patches from the previous estimate..
 
PPB software
Probabilistic Patch Based (PPB) filter (2009)
Matlab/Mex software to perform iterative non-local filtering for reducing: additive white Gaussian noise or, multiplicative speckle noise, i.e Nakagami-Rayleigh distributions (NL-SAR).
 
This work has been achieved by Charles Deledalle supervised by Florence Tupin and Loïc Denis. The aim was to adapt the Non-Local means (NL means) filter [2] to SAR images. Then, an efficient filter as been designed, able to cope with non Gaussian noise, multi-dimensionnal images and especially to the various existing SAR images. Results on the extended filter for amplitude SAR images are given on this page. The NL-InSAR filter is also an extension of the non-local means based on the PPB filter for interferometric SAR images, as well as the Poisson NL means filter for images sensed in low-light conditions.
 
Edition
MooseTeX
MooseTeX (2012 - 2014)
Open-source software distributed under CeCILL license for UNIX-like systems (such as Linux and MacOS-X).
 
MooseTeX helps you generate high quality LaTeX documents of any kind such as articles, letters, reports, theses, presentations or posters. Based on the technology of Makefile(s), the purpose of MooseTeX is ``to determine automatically which pieces of a (large) LaTeX project need to be recompiled, and issue the commands to recompile them''. For doing so, MooseTeX also includes a suite of tools to recompile each of such pieces. Note that MooseTeX is non-intrusive. It does not change the way you use LaTeX and is, as a consequence, compatible with your older projects. You can also use MooseTeX within collaborative LaTeX projects without imposing the use of MooseTeX to other collaborators.
 

Charles Deledalle - charles-alban (dot) deledalle (at) math.u-bordeaux (dot) fr
Bureau 209
Institut de Mathématiques de Bordeaux
Université Bordeaux
351, cours de la Libération - F-33405 TALENCE cedex
FRANCE
+33 (0)5 40 00 21 14
 
Last modified: Thu Dec 4 08:39:46 Europe/Berlin 2014
This website uses Google Analytics [know more]