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.

A new plenoptic sensor inspired from the visual system of flying insects is introduced. This sensor is referred to as the Panoptic camera. This system has two distinguished features. First it is an omnidirectional camera capable of recording light information around it. Second it is a polydioptric system where each CMOS facet has a distinct focal plane; hence the full system is multiple aperture camera. An FPGA based solution is proposed for real time application deployment. The omnidirectional vision recon

A new formalism is derived for the analysis and exact reconstruction of band-limited signals on the sphere with directional wavelets. It represents an evolution of a previously developed wavelet formalism developed by Antoine & Vandergheynst and Wiaux et a ...

In this paper we exploit the Continuous Wavelet Transform (CWT) on the two dimensional sphere, introduced previously by two of us, to build associated Discrete Wavelet Frames. We first explore half-continuous frames, i.e., frames where the position remains ...

This paper presents a highly flexible video coding scheme (MP3D), based on the use of a redundant 3-D spatio-temporal dictionary of functions. Directionality and anisotropic scaling are key ingredients to the spatial components, that form a rich collection ...

The problem of finding a piecewise smooth approximation of an original image while preserving edges is closely related to the image segmentation problem. Indeed, if we know the cartoon version of the original image, it is easier to perform an image partition into homogeneous regions. From this point of view, we propose to simultaneously perform regularization and segmentation. By working in the space of functions of bounded total variation, we allow discontinuities in the result of the minimisation. Therefo

Modern data processing tasks frequently involve structured data, for example signals defined on the vertex set of a weighted graph. In this paper, we address the problem of inference of mobility patterns from data defined on geographical graphs based on sp ...

We propose an algorithm for the reconstruction of the signal induced by cosmic strings in the cosmic microwave background (CMB), from radio-interferometric data at arcminute resolution. Radio interferometry provides incomplete and noisy Fourier measurement ...

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 objective function where one needs to estimate one reference image, l foreground images modeling possible occlusions, and a set of l transformation parameters modeling the inter-correlation between the observations. Then, we propose an alternating descent method

This paper presents a new, highly flexible, scalable image coder based on a Matching Pursuit expansion. The dictionary of atoms is built by translation, rotation and anisotropic refinement of gaussian functions, in order to efficiently capture edges in natural images. In the same time, the dictionary is invariant under isotropic scaling, which interestingly leads to very simple spatial resizing operations. It is shown that the proposed scheme compares to state-of-the-art coders when the compressed image is

We present a general framework and an efficient algorithm for tracking relevant video structures. The structures to be tracked are implicitly defined by a Matching Pursuit procedure that extracts and ranks the most important image contours. Based on the ranking, the contours are automatically selected to initialize a Particle Filtering tracker. The proposed algorithm deals with salient video entities whose behavior has an intuitive meaning, related to the physics of the signal. Moreover, as the interactions

This report is the extension to the case of sparse approximations of our previous study on the effects of introducing a priori knowledge to solve the recovery of sparse representations when overcomplete dictionaries are used. Greedy algorithms and Basis Pursuit Denoising are considered in this work. Theoretical results show how the use of "reliable" a priori information (which in this work appears under the form of weights) can improve the performances of these methods. In particular, we generalize the suff

This paper presents a novel method to correlate audio and visual data generated by the same physical phenomenon, based on sparse geometric representation of video sequences. The video signal is modeled as a sum of geometric primitives evolving through time ...

Simulating the long-timescale dynamics of biomolecules is a central challenge in computational science. While enhanced sampling methods can accelerate these simulations, they rely on pre-defined collective variables that are often difficult to identify. A recent generative model, LD-FPG, demonstrated that this problem could be bypassed by learning to sample the static equilibrium ensemble as all-atom deformations from a reference structure, establishing a powerful method for all-atom ensemble generation. Ho

We present a CMOS imager with built-in capability to perform Compressed Sensing. The adopted sensing strategy is the random Convolution due to J. Romberg. It is achieved by a shift register set in a pseudo-random configuration. It acts as a convolutive filter on the imager focal plane, the current issued from each CMOS pixel undergoing a pseudo-random redirection controlled by each component of the filter sequence. A pseudo-random triggering of the ADC reading is finally applied to complete the acquisition

Distributed compressed sensing is the extension of compressed sampling (CS) to sensor networks. The idea is to design a CS joint decoding scheme at a central decoder (base station) that exploits the inter-sensor correlations, in order to recover the whole ...

Graphs are now ubiquitous in almost every field of research. Recently, new research areas devoted to the analysis of graphs and data associated to their vertices have emerged. Focusing on dynamical processes, we propose a fast, robust and scalable framewor ...

Recent results have underlined the importance of incoherence in redundant dictionaries for a good behavior of decomposition algorithms like Matching and Basis Pursuits. However, appropriate dictionaries for a given application may not necessarily be able t ...

Technology scaling enables the design of low cost biosignal processing chips suited for emerging wireless body-area sensing applications. Energy consumption severely limits such applications and memories are becoming the energy bottleneck to achieve ultra- ...

We present a novel approach to the reconstruction of depth from light field data. Our method uses dictionary representations and group sparsity constraints to derive a convex formulation. Although our solution results in an increase of the problem dimensio ...

Pierre Vandergheynst

Chat with Graph Search

Hardware Implementation of an Omnidirectional Camera with Real-time 3D Imaging Capability

Exact reconstruction with directional wavelets on the sphere

Stereographic Wavelet Frames on the Sphere

Flexible Motion-Adaptive Video Coding with Redundant Expansions

Multiscale Variational Approach to Simultaneous Image Regularization and Segmentation

Inference of Mobility Patterns via Spectral Graph Wavelets

Compressed sensing reconstruction of a string signal from interferometric observations of the cosmic microwave background

Non-convex optimization for robust multi-view imaging

High flexibility scalable image coding

Tracking Atoms with Particles

On the Use of A Priori Information for Sparse Signal Approximations

CMOS Compressed Imaging by Random Convolution

Analysis of Multimodal Sequences Using Geometric Video Representations

Beyond Ensembles: Simulating All-Atom Protein Dynamics in a Learned Latent Space

CMOS Compressed Imaging by Random Convolution

Distributed Compressed Sensing for Sensor Networks Using Thresholding

Principal Patterns on Graphs: Discovering Coherent Structures in Datasets

On the Use of A Priori Information for Sparse Signal Approximations

Approximate Compressed Sensing: Ultra-Low Power Biosignal Processing via Aggressive Voltage Scaling on a Hybrid Memory Multi-core Processor

A Convex Solution to Disparity Estimation from Light Fields via the Primal-Dual Method