IPOLIPOLhttp://www.ipol.im/feed/IPOL Preprints — Latest public preprints from IPOL.ikiwiki2018-08-17T16:13:25ZAn Analysis and Implementation of the FFDNet Image Denoising Methodhttp://www.ipol.im/pub/pre/231/Matias Tassano,
Julie Delon,
Thomas Veit2018-08-17T16:13:25Z2018-08-17T15:40:09Z
FFDNet is a recent image denoising method based on a convolutional neural network
architecture. In contrast to other existing neural network denoisers, FFDNet exhibits several
desirable properties such as faster execution time and smaller memory footprint, and the ability
to handle a wide range of noise levels effectively with a single network model. The combination
between its denoising performance and lower computational load makes this algorithm attractive
for practical denoising applications. In this paper we propose an open-source implementation
of the method based on PyTorch, a popular machine learning library for Python. Code for the
training of the network is also provided. We also discuss the characteristics of the architecture
of this algorithm and we compare it to other similar methods.
Implementation of a Denoising Algorithm based on High-Order Singular Value Decomposition of Tensorshttp://www.ipol.im/pub/pre/226/Fabien Feschet2018-07-22T11:40:36Z2018-05-30T09:57:10Z
This article presents an implementation of a denoising algorithm based on High-Order Singular
Value Decomposition (HOSVD) of tensors. It belongs to the class of patch-based methods such
as BM3D and NL-Bayes. It exploits the grouping of similar patches in a local neighbourhood
into a 3D matrix also called a third order tensor. Instead of performing different processing
in different dimension, as in BM3D for instance, it is based on the decomposition of a tensor
simultaneously in all dimensions reducing it to a core tensor in a similar way as SVD does for
matrices in computing the diagonal matrix of singular values. The core tensor is filtered and
a tensor is reconstructed by inverting the HOSVD. As common in patch-based algorithms, all
tensors containing a pixel are then merged to produce an output image.
Improvements of the Inverse Compositional Algorithm for Parametric Motion Estimationhttp://www.ipol.im/pub/pre/222/Thibaud Briand,
Gabriele Facciolo,
Javier Sánchez2018-07-22T11:40:36Z2018-04-19T08:34:16Z
In this work, we propose several improvements of the inverse compositional algorithm for parametric registration. We propose an improved handling of boundary pixels, a different color handling and gradient estimation, and the possibility to skip scales in the multiscale coarse-to-fine scheme. In an experimental part, we analyze the influence of the modifications. The estimation accuracy is at least improved by a factor 1.3 while the computation time is at least reduced by a factor 2.2 for color images.
Numerical Simulation of Landscape Evolution Modelshttp://www.ipol.im/pub/pre/205/Marc Lebrun,
Jean-Michel Morel,
Miguel Colom,
Jérôme Darbon2018-07-22T11:40:36Z2017-12-21T23:52:15Z
This paper gives the complete numerical schemes implementing the main physical laws pro-
posed in landscape evolution (LEMs). These laws can be modeled by a system of three partial
differential equations governing water run-off, stream incision, hill slope evolution and sedimentation. The goal of the presented algorithm, code and online facility is to be able to test these
equations on digital elevation models (DEMs) of any resolution, and to illustrate its potential
to simulate the fine structure of the river network, and to understand the landscape
morphology and its causes. The equations simulate plausible evolutions. We illustrate experiments on
DEMs of several sites, including one site, La Réunion where the DEM is given at three different
resolutions: the SRTM resolution (90m), and then 12m and 4m on DEMs derived from several
Pléiades pairs. Other many DEM’s are proposed in the online demo, which allows to upload and tests other DEMs.
Comparison of Optical Flow Methods under Stereomatching with Short Baselineshttp://www.ipol.im/pub/pre/217/Tristan Dagobert,
Nelson Monzón,
Javier Sánchez2018-07-22T11:40:36Z2017-10-16T12:24:59Z
This article studies the effectiveness of optical flow methods employed in the case of short baselines and different noise levels. New metrics have been developed to analyze the evaluation results because the usual metrics are inadequate in a subpixel context. Experiments conducted on the adequate Middlebury and CMLA dataset pairs show that the Brox et al. method produces the best errors, with a 60% success rate in relative precision at 1/100 th of a pixel. On the other hand, our comparison shows that the Monzón et al. method also provides competitive results at the same time that it yields disparities with more details and correct contours.
An Affine Invariant Patch Similarityhttp://www.ipol.im/pub/pre/202/Vadim Fedorov,
Coloma Ballester2018-07-22T11:40:36Z2017-07-14T10:09:29Z
Image and video comparison is often approached by comparing patches of visual information. In this work we present a detailed description and implementation of an affine invariant patch similarity measure that performs an appropriate patch comparison by automatically and intrinsically adapting the size and shape of the patches. We also describe the complete implementation of the proposed iterative algorithm for computation of those shape-adaptive patches around each point in the image domain.
Recovering the Blur Kernel from Natural Image Statistics: An Analysis of the Goldstein-Fattal Methodhttp://www.ipol.im/pub/pre/211/Jérémy Anger,
Gabriele Facciolo,
Mauricio Delbracio2018-07-22T11:40:36Z2017-06-13T16:23:36Z
Despite the significant improvement in image quality mainly caused by the improvement in
optical sensors and general electronics, blur due to camera shake significantly undermines the
quality of hand-held photographs being one of the most active research topics. In this work,
we present a detailed description and implementation of the blurring kernel estimation algorithm
introduced by Goldstein and Fattal in 2012. Unlike most methods that attempt to solve
an inverse problem through a variational formulation (e.g., through a maximum a posteriori
estimation), this method directly estimates the blurring kernel by modeling statistical irregu-
larities in the power spectrum of blurred natural images. The adopted mathematical model
extends the well-known power-law by contemplating the presence of dominant strong edges in
particular directions. The blurring kernel is retrieved from an estimation of the blurring
kernel power spectrum, by solving a phase retrieval problem using additional constraints due to
the particular nature of camera shake blurring kernels (e.g., non-negativity and small spatial
support). Although the algorithm is conceptually simple, being based on several clean
mathematical/physical assumptions, the numerical implementation presents several challenges. This
work contributes to a detailed anatomy of the Goldstein and Fattal method, and the algorithms
that constitute it and its parameters.
Structural Similarity Metrics for Quality Image Fusion
Assessment: Algorithmshttp://www.ipol.im/pub/pre/196/Silvina Pistonesi,
Jorge Martinez,
Silvia Maria Ojeda,
Ronny Vallejos2018-07-22T11:40:36Z2017-04-13T22:43:08Z
The wide use of image fusion techniques in different fields such as medical diagnostics, digital
camera vision, military and surveillance applications, among others, has motivated the
development of various image quality fusion metrics, in order to evaluate them. In this paper, we
study and implement the algorithms of non-reference image structural similarity based metrics
for fusion assessment: Piella’s metric, Cvejic’s metric, Yang’s metric, and Codispersion Fusion
Quality metric. We conduct the comparative experiment of the selected image fusion metrics
over four multiresolution image fusion algorithms, performed on different pairs of images used
in different applications.
Joint Large-Scale Motion Estimation and Image Reconstructionhttp://www.ipol.im/pub/pre/193/Hendrik Dirks2018-07-22T11:40:36Z2016-11-24T13:13:55Z
This article describes the implementation of the joint motion estimation and image reconstruction framework presented by Burger, Dirks and Schönlieb and extends this framework to large-scale motion between consecutive image frames. The variational framework uses displacements between consecutive frames based on the optical
flow approach to improve the image reconstruction quality on the one hand and the motion estimation quality on the other. The energy functional consists of a
data-fidelity term with a general operator that connects the input sequence to the solution, it has a total variation term for the image sequence and is connected to the underlying flow using an optical flow term. Additional spatial regularity for the flow is modeled by a total variation regularizer for both components of the flow. The numerical minimization is performed in an alternating manner using
primal-dual techniques. The resulting schemes are presented as pseudo-code together with a short numerical evaluation.
Joint TV-L1 Optical Flow and Occlusion Estimationhttp://www.ipol.im/pub/pre/118/Juan Francisco Garamendi Bragado,
Coloma Ballester,
Lluís Garrido,
Vanel Lazcano,
Vicent Caselles2018-07-22T11:40:36Z2015-02-05T12:37:40Z
This document describes an implementation of the energy functional minimization proposed by Ballester, Garrido, Lazcano and Caselles for joint optical flow and occlusion estimation. The method is based on the TV-L1 approach introduced Zach, Pock and Bischof in 2007 but with the particularity of detecting occlusions. The energy functional is composed by a regularization term (over the optical flow and the occlusion fields) using the total variation, a data term using the L1 norm, and a term, which is based on the divergence of the flow, for dealing with the occlusions.
Study of the Principal Component Analysis Method for the Correction of Images Degraded by Turbulencehttp://www.ipol.im/pub/pre/47/Tristan Dagobert,
Yohann Tendero,
Stéphane Landeau2018-07-22T11:40:36Z2013-06-29T03:13:25Z
This article details the use of principal component analysis
in order to restore images degraded by atmospheric turbulence. It
analyzes and discusses a well-known paper and proposes a
generalization of the algorithm described in such article.
Examples using sequences of real atmospheric turbulence are
presented.
Real atmospheric turbulent image acquisition is described and
sequences are made accessible for downloading.