Pierre Vandergheynst

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Limited data and low dose constraints are common problems in a variety of tomographic reconstruction paradigms which lead to noisy and incomplete data. Over the past few years sinogram denoising has become an essential pre-processing step for low dose Computed Tomographic (CT) reconstructions. We propose a novel sinogram denoising algorithm inspired by the modern field of signal processing on graphs. Graph based methods often perform better than standard filtering operations since they can exploit the signa

Radio interferometry probes astrophysical signals through incomplete and noisy Fourier measurements. The theory of compressed sensing demonstrates that such measurements may actually suffice for accurate reconstruction of the signals. We propose new generic imaging techniques based on convex optimization for global minimization problems defined in this context. The versatility of the framework notably allows introduction of prior information on the signals, which offers the possibility of significant improv

We introduce the Free Music Archive (FMA), an open and easily accessible dataset which can be used to evaluate several tasks in music information retrieval (MIR), a field concerned with browsing, searching, and organizing large music collections. The community's growing interest in feature and end-to-end learning is however restrained by the limited availability of large audio datasets. By releasing the FMA, we hope to foster research which will improve the state-of-the-art and hopefully surpass the perform

We consider the problem of designing spectral graph filters for the construction of dictionaries of atoms that can be used to efficiently represent signals residing on weighted graphs. While the filters used in previous spectral graph wavelet constructions ...

The construction of a meaningful graph plays a crucial role in the emerging field of signal processing on graphs. In this paper, we address the problem of learning graph Laplacians, which is similar to learning graph topologies, such that the input data fo ...

The prevalence of signals on weighted graphs is increasing; however, because of the irregular structure of weighted graphs, classical signal processing techniques cannot be directly applied to signals on graphs. In this paper, we define generalized translation and modulation operators for signals on graphs, and use these operators to adapt the classical windowed Fourier transform to the graph setting, enabling vertex-frequency analysis. When we apply this transform to a signal with frequency components that

Wireless body sensor networks (WBSN) hold the promise to enable next-generation patient-centric tele-cardiology systems. A WBSNenabled electrocardiogram (ECG) monitor consists of wearable, miniaturized and wireless sensors able to measure and wirelessly re ...

Spatial scalability of video signals can be achieved with critically sampled spatial wavelet schemes but also with an overcomplete spatial representation. Critically sampled schemes struggle with the problem that critically sampled high-bands are shift-variant. Therefore, efficient motion compensation is challenging. On the other hand, overcomplete representations can be shift-invariant, thus permitting efficient motion compensation in the spatial subbands, but they have to be designed carefully to achieve

A novel compressive sampling scheme suitable for highly scalable hardware implementations is presented. The scheme utilizes an identical pseudo-random sequence for every image column, therefore reducing in-pixel hardware complexity and allowing measurement ...

In this paper, we propose an analytical low-level representation of images, obtained by a decomposition process, here the matching pursuit (MP) algorithm, as a new way of describing objects through a general continuous description using an affine invariant dictionary of basis functions. This description is used to recognize objects in images. In the learning phase, a template object is decomposed, and the extracted subset of basis functions, called meta-atom, gives the description of our object. We then ext

We question the global universe isotropy by probing the alignment of local structures in the cosmic microwave background (CMB) radiation. The original method proposed relies on a steerable wavelet decomposition of the CMB signal on the sphere. The analysis ...

Gene interactions form complex networks underlying disease susceptibility and therapeutic response. While bulk transcriptomic datasets offer rich resources for studying these interactions, applying Graph Neural Networks (GNNs) to such data remains limited by a lack of methodological guidance, especially for constructing gene interaction graphs. We present REGEN (REconstruction of GEne Networks), a GNN-based framework that simultaneously learns latent gene interaction networks from bulk transcriptomic profil

A novel compressive sampling scheme suitable for highly scalable hardware implementation is presented. The prototype design is implemented in a 0.18um standard CMOS technology and utilizes compressed acquisition to achieve high frame rates and maintain low power consumption. Specialized pixels, convenient for Comparator-Based Switched Capacitor readout are developed for this purpose. A custom measurement matrix generation algorithm is implemented which reduces in-pixel hardware complexity and performs measu

Compressive Sampling (CS) offers bandwidth, power and memory size reduction compared to conventional (Nyquist) sampling. However, very few Integrated Circuit (IC) designs based on CS exist due to the missing link between the well-established CS theory on o ...

We review the construction of the continuous wavelet transform (CWT) on the two-sphere by two methods, the group-theoretical approach and the geometrical method based on conformal invariance. Then we discuss the discretization of the spherical CWT, obtaini ...

A novel framework for image inpainting is proposed, relying on graph-based diffusion processes. Depending on the construction of the graph, both flow-based and exemplar-based inpainting methods can be implemented by the same equations, hence providing a un ...

Using local morphological measures on the sphere defined through a steerable wavelet analysis, we examine the three-year WMAP and the NVSS data for correlation induced by the integrated Sachs-Wolfe (ISW) effect. The steerable wavelet constructed from the s ...

In general purpose computer vision systems, non-supervised image analysis is mandatory in order to achieve an automatic operation. In this paper a different approach to image segmentation for natural scenes is presented. Scale-Space representation is used to extract the structure from meaningful objects in the image. A hierarchical decomposition of the image is performed from the iso-intensity paths. The Scale-Space stack is generated using isotropic diffusion on the basis of linear Scale-Space theory. From

We study the multi-view imaging problem where one has to reconstruct a set of l images, representing a single scene, from a few measurements made at different viewpoints. We first express the solution of the problem as the minimizer of a non-convex objecti ...

This paper discusses distributed coding of two correlated video signals. The video signals are captured from a dynamic scene where each signal is temporally decorrelated by a motion-compensated Haar wavelet. The two cameras operate independently, however, the central decoder is able to exploit the coded information from all cameras to achieve the best reconstruction of the correlated video signals. The coding system utilizes nested lattice codes for the transform coefficients and exploits side information a

Pierre Vandergheynst

Chat with Graph Search

Graph Based Sinogram Denoising for Tomographic Reconstructions

Compressed sensing imaging techniques for aperture synthesis by radio interferometry

FMA: A Dataset For Music Analysis

Spectrum-Adapted Tight Graph Wavelet and Vertex-Frequency Frames

Laplacian Matrix Learning for Smooth Graph Signal Representation

A Windowed Graph Fourier Transform

Real-Time Compressed Sensing-Based Electrocardiogram Compression on Energy Constrained Wireless Body Sensors

Inter-Resolution Transform for Spatially Scalable Video Coding

Column-Separated Compressive Sampling Scheme for Low Power CMOS Image Sensors

Affine invariant Matching Pursuit-based shape representation and recognition using scale-space

Global universe anisotropy probed by the alignment of structures in the cosmic microwave background

Learning gene interactions from tabular gene expression data using Graph Neural Networks

High Frame-Rate Low-Power Compressive Sampling CMOS Image Sensor Architecture

Compressive Image Acquisition in Modern CMOS IC Design

Wavelets on the two-sphere and other conic sections

Towards unifying diffusion and exemplar-based inpainting

Probing dark energy with steerable wavelets through correlation of WMAP and NVSS local morphological measures

Segmentation of Natural Images Using Scale-Space Representation with Multi-Scale Edge Supervised Hierarchical Linking

Non-convex optimization for robust multi-view imaging

Distributed Coding of Dynamic Scenes with Motion-Compensated Wavelets