Proximity operators have become increasingly important tools as basic building blocks of proximal splitting algorithms, a class of algorithms that decompose complex composite convex optimization methods into simple steps involving one of the functions present in the model. This website provides formulas for efficiently computing the proximity operator of various functions, along with the associated codes.
The plugin FIGARO, for ImageJ software, helps tracking resolution of microscope systems by extracting dimensions and orientation of standardized microbeads images, acquired from test samples. In the develop- ment of optical microscopes for biomedical imaging, the evaluation of resolution is a fundamental parameter achieved by Point Spread Function (PSF) measurements. Sometimes, PSF measurement procedure is not easy or impossible in case of microspheres images presenting a high noise level. The current method proposed into the plugin FIGARO is based on a variational approach for PSF modeling through multivariate Gaussian fitting, adapted to images acquired in a high noise context.
The website shares the software Kymatio for Scattering Transform, that computes cascade of wavelets and modulus non-linearity. The codes have been optimized for GPUs and work on the open-source framework PyTorch.
The BiasedWalk network representation learning algorithm, computes latent node features on graphs based on biased random walks. The framework has been implemented in Python and has been built upon widely used modules, including networkx, numpy, gensim and scikit-learn.
The DiffuGreedy is an algorithm for influence maximization in complex networks, that is based on diffusion cascades. It has been implemented in Python and has been built upon widely used modules, including networkx, igraph, numpy and pandas.
Graph-based TC is a framework for text categorization that relies on a graph representation of documents. The framework uses various graph centrality criteria to determine the importance of a term within a document. It also makes use of word embeddings to further boost the performance of graph-based methods. It has been implemented in Python and has been built upon widely used modules, including networkx, igraph, numpy and scikit-learn.
KernelNE learns node representations on graphs based on a weighted matrix factorization model which encodes random walk-based information about the nodes.
EFGE learns node embeddings generalizing random walk-based network representation learning techniques to exponential family conditional distributions.
We propose a graph-based semi-supervised fake news detection method, based on graph neural networks.
The PINK image library is a general-purpose, open-source, portable image processing library specializing in discrete geometry and mathematical morphology. It is the result of several decades of research in these domains and features state-of-the art algorithmic implementation of both classical and leading edge DG and MM operators. These include nD parallel thinning and skeletonization methods and efficient hierarchical morphological transforms.
AngioTK is a toolkit supported by Kitware (the authors of VTK) for the filtering, segmentation, generation and simulation of blood vessels. It was started in the context of the Vivabrain ANR project in 2012, but continues with the same as well as new partners. Applications are numerous, from the simulation and understanding of perfusion (see associated theme) to the simulation of realistic blood flow MRI images with associated ground truth, via the generation of blood vessel atlases.
Quantitive Positron Emission Tomography is a new area for which software is not readily availble. With our partners from Toulouse and Beth Israel hospitals, we have proposed a free open-source plugin allowing clinicians to view, interact and perform automated and interactive lesion segmentation in the context of PET/CT.
Alternating Direction Graph Matching. An implementation of the methods introduced in the paper Alternating Direction Graph Matching, CVPR 2017.
An implementation of the algorithm described in the paper Fully Convolutional Dense Shape Regression In-the-Wild, CVPR 2017.
A software programme that registers images originating from one or more modes by quickly and efficiently calculating a non-rigid/deformable field of deformation. DROP is a new, quick, and effective registration tool based on new algorithms that do not require a cost function derivative.
A generic graph-based optimization platform written in C++ for the computer vision and medical imaging community developed at Ecole Centrale and University of Crete. This is the most efficient available platform in terms of a compromise of computational efficiency and ability to converge to a good minimum for the optimization of generic pair-wise MRFs.
Learning Based Symmetry Detection. LBSD implements the learning-based approach to symmetry detection. It includes code for running a detector, along with ground-truth symmetry annotations that we have introduced for the Berkeley Segmentation Dataset (BSD) benchmark.
Deep Gaussian CRFs. An implementation of the Potts type G-CRF caffe layer introduced in the paper Fast, Exact and Multi-Scale Inference For Semantic Image Segmentation with Deep Gaussian CRFs, ECCV 2016.
A generic image parsing library based on re-inforcement learning written in C++ developed at Ecole Centrale de Paris. It can handle grammars (binary-split, four-color, Hausmannian) and image-based rewards (Gaussian mixtures, Randomized Forests) of varying complexity while being modular and computationally efficient both in terms of grammar and image rewards.
This software provides a convenient API for learning to rank with high-order information. Samples are ranked according to a score that is proportional to the difference of max-marginals of the positive and negative classes. The parameters of the score function are computed by minimising an upper bound on the average precision loss. This software also provides an instantiation of the API for ranking samples according to their relevance to an action, using poselet features. The algorithms included in the API are Multiclass-SVM, AP-SVM, High-order Binary SVM, High-order AP-SVM, and M4 Learning.