Pierre Vandergheynst
Full Professor
pierre.vandergheynst@epfl.ch 41 21 693 56 45 http://lts2.epfl.ch
EPFL STI IEL LTS2
ELE 235 (Bâtiment ELE)
Station 11
CH-1015 Lausanne
41 21 693 56 45
41 21 693 26 01
Office: ELE 235
EPFL
>
STI
>
IEM
>
LTS2
Web site: Web site: https://lts2.epfl.ch/
EPFL IC-DO
ELB 114 (Bâtiment ELB)
Station 11
CH-1015 Lausanne
Web site: Web site: https://ic.epfl.ch/page8797.html
Fields of expertise
data science
machine learning
computational harmonic analysis
inverse problems
compressive sensing
computer vision
machine learning
computational harmonic analysis
inverse problems
compressive sensing
computer vision
Links
Mission
Data nowadays come in overwhelming volume. In order to cope with this deluge, we explore and use the benefits of geometry and symmetry in higher dimensional data. But volume is not the only problem: data models are also increasingly complex, mixing various components. We thus use redundant dictionaries as a dimensionality reduction tool to dig out information from complicated high-dimensional datasets and multichannel signals, or to model complex behaviours in more classical signals. Finally data can also be complex because they are collected on surfaces, or more generally manifolds, or because they are not scalar-valued. We thus explore extensions of Computational Harmonic Analysis in higher dimensions, in complex geometries or for non-scalar data.
Visit our lab web pages.
Visit our lab web pages.
Biography
Pierre Vandergheynst received the M.S. degree in physics and the Ph.D. degree in mathematical
physics from the Université catholique de Louvain, Louvain-la-Neuve, Belgium, in 1995 and 1998, respectively. From 1998 to 2001, he was a Postdoctoral Researcher with the Signal Processing Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland. He was Assistant Professor at EPFL (2002-2007), where he is now a Full Professor of Electrical Engineering and, by courtesy, of Computer and Communication Sciences. As of 2015, Prof. Vandergheynst serves as EPFL’s Vice-Provost for Education.
His research focuses on harmonic analysis, sparse approximations and mathematical data processing in general with applications covering signal, image and high dimensional data processing, computer vision, machine learning, data science and graph-based data processing.
He was co-Editor-in-Chief of Signal Processing (2002-2006), Associate Editor of the IEEE Transactions on Signal Processing (2007-2011), the flagship journal of the signal processing community and currently serves as Associate Editor of Computer Vision and Image Understanding and SIAM Imaging Sciences. He has been on the Technical Committee of various conferences, serves on the steering committee of the SPARS workshop and was co-General Chairman of the EUSIPCO 2008 conference.
Pierre Vandergheynst is the author or co-author of more than 70 journal papers, one monograph and several book chapters. He has received two IEEE best paper awards. Professor Vandergheynst is a laureate of the Apple 2007 ARTS award and of the 2009-2010 De Boelpaepe prize of the Royal Academy of Sciences of Belgium.
physics from the Université catholique de Louvain, Louvain-la-Neuve, Belgium, in 1995 and 1998, respectively. From 1998 to 2001, he was a Postdoctoral Researcher with the Signal Processing Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland. He was Assistant Professor at EPFL (2002-2007), where he is now a Full Professor of Electrical Engineering and, by courtesy, of Computer and Communication Sciences. As of 2015, Prof. Vandergheynst serves as EPFL’s Vice-Provost for Education.
His research focuses on harmonic analysis, sparse approximations and mathematical data processing in general with applications covering signal, image and high dimensional data processing, computer vision, machine learning, data science and graph-based data processing.
He was co-Editor-in-Chief of Signal Processing (2002-2006), Associate Editor of the IEEE Transactions on Signal Processing (2007-2011), the flagship journal of the signal processing community and currently serves as Associate Editor of Computer Vision and Image Understanding and SIAM Imaging Sciences. He has been on the Technical Committee of various conferences, serves on the steering committee of the SPARS workshop and was co-General Chairman of the EUSIPCO 2008 conference.
Pierre Vandergheynst is the author or co-author of more than 70 journal papers, one monograph and several book chapters. He has received two IEEE best paper awards. Professor Vandergheynst is a laureate of the Apple 2007 ARTS award and of the 2009-2010 De Boelpaepe prize of the Royal Academy of Sciences of Belgium.
Publications
Infoscience publications
Recent publications (2009-present)
Computational Thinking and Thinking Computationally
Dia-logos, Ramon Llull's Method of Thought and Artistic Practice; Minneapolis: University of Minnesota Press, 2018.Graph Signal Processing: Overview, Challenges and Applications
Proceedings of the IEEE. 2018. DOI : 10.1109/JPROC.2018.2820126.Distributed Signal Processing via Chebyshev Polynomial Approximation
IEEE Transactions on Signal and Information Processing over Networks. 2018. DOI : 10.1109/TSIPN.2018.2824239.System, device, and method for contextual knowledge retrieval and display
WO2017187401 . 2017.Transient networks of spatio-temporal connectivity map communication pathways in brain functional systems
Neuroimage. 2017. DOI : 10.1016/j.neuroimage.2017.04.015.A Multiscale Pyramid Transform for Graph Signals
IEEE Transactions on Signal Processing. 2016. DOI : 10.1109/TSP.2015.2512529.Learning Laplacian Matrix in Smooth Graph Signal Representations
IEEE Transactions on Signal Processing. 2016. DOI : 10.1109/TSP.2016.2602809.Vertex-Frequency Analysis on Graphs
Applied And Computational Harmonic Analysis. 2016. DOI : 10.1016/j.acha.2015.02.005.MATHICSE Technical Report : Accelerated filtering on graphs using Lanczos method
2015-09Dynamic activation patterns in brain MRI data
2015. 25th Colloque Gretsi, Lyon.Mapping resting-state dynamics on spatio-temporal graphs: a combined functional and diffusion MRI approach
2015. 23rd International Symposium on Magnetic Resonance in Medicine (ISMRM), Toronto.Ultra-low-power ECG front-end design based on compressed sensing
2015. 2015 Design, Automation and Test in Europe Conference (DATE ‘15), Grenoble, France, March 9-13, 2015. p. 671-676.Accelerated filtering on graphs using Lanczos method
IEEE Signal Processing Letters. 2015.Laplacian Matrix Learning for Smooth Graph Signal Representation
2015. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April, 2015. p. 3736-3740. DOI : 10.1109/ICASSP.2015.7178669.Spectrum-Adapted Tight Graph Wavelet and Vertex-Frequency Frames
IEEE Transactions on Signal Processing. 2015. DOI : 10.1109/Tsp.2015.2424203.System and method for media library navigation and recommendation
WO2014002064 . 2014.Compressed sensing
Lausanne, EPFL, 2014. DOI : 10.5075/epfl-thesis-6340.Multi-View Signal Processing and Learning on Graphs
Lausanne, EPFL, 2014. DOI : 10.5075/epfl-thesis-6213.Approximate Compressed Sensing: Ultra-Low Power Biosignal Processing via Aggressive Voltage Scaling on a Hybrid Memory Multi-core Processor
2014. International Symposium on Low Power Electronics and Design (ISLPED 2014), La Jolla, California, USA, August 11-13, 2014. p. 40-45. DOI : 10.1145/2627369.2627629.Ultra low power design of hardware efficient CS-Based compression scheme in WBSN
2014. CT-Energy Community Workshop, Barcelona, Spain, April 23-25, 2014.Hardware-Software Inexactness in Noise-aware Design of Low-Power Body Sensor Nodes
2014. Designing with Uncertainty - Opportunities & Challenges, York, United Kingdom, March 17-19 , 2014.Power-Efficient Joint Compressed Sensing of Multi-Lead ECG Signals
2014. 39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014), Florence, Italy, May 5-9 2014. p. 4409-4412.Compact Low-Power Cortical Recording Architecture for Compressive Multichannel Data Acquisition
IEEE Transactions on Biomedical Circuits and Systems. 2014. DOI : 10.1109/TBCAS.2014.2304582.Robust Real-time Pedestrians Detection in Urban Environments with a Network of Low Resolution Cameras
Transportation Research Part C: Emerging Technologies. 2014. DOI : 10.1016/j.trc.2013.11.019.Clustering on Multi-Layer Graphs via Subspace Analysis on Grassmann Manifolds
IEEE Transactions on Signal Processing. 2014. DOI : 10.1109/TSP.2013.2295553.From Bits to Images: Inversion of Local Binary Descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2014. DOI : 10.1109/TPAMI.2013.228.Method to compensate the effect of the rolling shutter effect
US8350922 ; US2011267514 . 2013.Compressive Image Acquisition in Modern CMOS IC Design
International Journal of Circuit Theory and Applications. 2013. DOI : 10.1002/cta.1969.Clustering on Multi-Layer Graphs via Subspace Analysis on Grassmann Manifolds
2013. IEEE Global Conference on Signal and Information Processing, Austin, Texas, USA, December 3-5, 2013.The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
IEEE Signal Processing Magazine. 2013. DOI : 10.1109/Msp.2012.2235192.On the computation of directional scale-discretized wavelet transforms on the sphere
2013. Wavelets and Sparsity XV, San Diego, August 26-29, 2013. p. 88580I. DOI : 10.1117/12.2022889.High Frame-Rate Low-Power Compressive Sampling CMOS Image Sensor Architecture
23rd Great Lakes Symposium on VLSI, Paris, France, May 2-3, 2013.Power-Efficient CMOS Image Acquisition System based on Compressive Sampling
2013. 56th IEEE International Midwest Symposium on Circuits and Systems, Columbus, Ohio, USA, August 4-7, 2013.Column-Separated Compressive Sampling Scheme for Low Power CMOS Image Sensors
2013. 11th IEEE International New Circuits and Systems (NEWCAS) Conference, Paris, France, June 16-19, 2013.Inference of Mobility Patterns via Spectral Graph Wavelets
2013. IEEE ICASSP, Vancouver, Canada, May 26-31, 2013.Compressive Multichannel Cortical Signal Recording
2013. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, Canada, May 26-31, 2013. p. 4305-4309.S2LET: A code to perform fast wavelet analysis on the sphere
Astronomy and Astrophysics. 2013. DOI : 10.1051/0004-6361/201220729.Sparse Reverberant Audio Source Separation via Reweighted Analysis
IEEE Transactions on Audio Speech and Language Processing. 2013. DOI : 10.1109/Tasl.2013.2250962.The PANOPTIC Camera: A Plenoptic Sensor with Real-Time Omnidirectional Capability
Journal of Signal Processing Systems for Signal, Image and Video Technology. 2013. DOI : 10.1007/s11265-012-0668-4.Sparse image reconstruction on the sphere: implications of a new sampling theorem
IEEE Transactions on Image Processing. 2013. DOI : 10.1109/TIP.2013.2249079.Omnidirectional sensor array system
US10362225 ; US2018220070 ; US9876953 ; US2014146132 ; WO2012056437 . 2012.Automatic online delineation of a multi-lead electrocardiogram bio signal
US2014148714 ; EP2654557 ; WO2012085841 . 2012.Image transform for video coding
US8300693 ; US2006159179 . 2012.Omnidirectional Light Field Analysis and Reconstruction
Lausanne, EPFL, 2012. DOI : 10.5075/epfl-thesis-5483.Robust joint reconstruction of misaligned images using semi-parametric dictionaries
Workshop on Sparsity, Localization and Dictionary Learning, London, June 26, 2012.Beyond Bits: Reconstructing Images from Local Binary Descriptors
2012. 21st International Conference on Pattern Recognition (ICPR), Tsukuba Science City, Japan, November 11-15, 2012.Design and Exploration of Low-Power Analog to Information Conversion Based on Compressed Sensing
IEEE Journal of Emerging and Selected Topics in Circuits and Systems. 2012. DOI : 10.1109/JETCAS.2012.2220253.A Windowed Graph Fourier Transform
2012. IEEE Statistical Signal Processing Workshop, Ann Arbor, Michigan, USA, August 5-8, 2012. p. 133-136. DOI : 10.1109/SSP.2012.6319640.A Real-time Multi-camera System with Omnidirectional Image Reconstruction Capability
ICCP2012, Seattle, WA, USA, April 27-29, 2012.Foreground Silhouette Extraction robust to Sudden Changes of background Appearance
2012. IEEE International conference on Image Processing, Orlando, Florida, USA, September 30 - October 3, 2012. DOI : 10.1109/ICIP.2012.6467088.Plenoptic Spherical Sampling
2012. 2012 IEEE International Conference on Image Processing, Disney Coronado Springs Resort, Florida, USA, September 30, October 3, 2012.FREAK: Fast Retina Keypoint
2012. IEEE Conference on Computer Vision and Pattern Recognition, Rhode Island, Providence, USA, June 16-21, 2012.Sparse Approximation Using M-Term Pursuit and Application in Image and Video Coding
IEEE Transactions on Image Processing. 2012. DOI : 10.1109/TIP.2011.2181525.A Multi-Lead ECG Classification Based on Random Projection Features
2012. 37th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), Kyoto, Japan, March 25-30, 2012. p. 625-628.SCOOP: A Real-Time Sparsity Driven People Localization Algorithm
Journal Of Mathematical Imaging And Vision. 2012. DOI : 10.1007/s10851-012-0405-4.Clustering with Multi-Layer Graphs: A Spectral Perspective
IEEE Transactions on Signal Processing. 2012. DOI : 10.1109/Tsp.2012.2212886.Universal and efficient compressed sensing by spread spectrum and application to realistic Fourier imaging techniques
EURASIP Journal on Advances in Signal Processing. 2012. DOI : 10.1186/1687-6180-2012-6.Spread spectrum magnetic resonance imaging
IEEE Transactions on Medical Imaging. 2012. DOI : 10.1109/TMI.2011.2173698.Structured Sparsity Models for Compressively Sensed Electrocardiogram Signals: A Comparative Study
2011. Biomedical Circuits and Systems Conference (BioCAS), 2011 IEEE, San Diego, CA, USA, November 10-12, 2011. DOI : 10.1109/BioCAS.2011.6107743.Hardware Implementation of an Omnidirectional Camera with Real-time 3D Imaging Capability
3DTV 2011, Antalya, Turkey, May 16-18, 2011.On Variable Density Compressive Sampling
IEEE Signal Processing Letters. 2011. DOI : 10.1109/LSP.2011.2163712.Chebyshev Polynomial Approximation for Distributed Signal Processing
2011. IEEE International Conference on Distributed Computing in Sensor Systems (DCOSS), Barcelona, Spain, June 27-29, 2011.Methods for Clustering Multi-Layer Graphs in Mobile Networks
Interdisciplinary Workshop on Information and Decision in Social Networks, MIT, Cambridge, Massachusetts, USA, May 31-June 1, 2011.Spread Spectrum for Universal Compressive Sampling
2011. 4th Workshop on Signal Processing with Adaptive Sparse Structured Representations, Edinburgh, June 27-30, 2011. p. 50.Implications for compressed sensing of a new sampling theorem on the sphere
2011. 4th Workshop on Signal Processing with Adaptive Sparse Structured Representations, Edinburgh, Scotland, 27-30 June, 2011. p. 45.Compressed Sensing for Real-Time Energy-Efficient ECG Compression on Wireless Body Sensor Nodes
IEEE Transactions on Biomedical Engineering Bme. 2011. DOI : 10.1109/TBME.2011.2156795.Semi-Supervised Learning with Spectral Graph Wavelets
2011. International Conference on Sampling Theory and Applications (SampTA), Singapore, May 2-6, 2011.Hardware Implementation of an Omnidirectional Camera with Real-Time 3D Imaging Capability
2011. 3DTV-Conference 2011, Antalya, Turkey, 16-18 May. DOI : 10.1109/3DTV.2011.5877192.Sampling theorems and compressive sensing on the sphere
2011. Conference on Wavelets and Sparsity XIV, San Diego, CA, August 21-25, 2011. DOI : 10.1117/12.893481.Real-Time Compressed Sensing-Based Electrocardiogram Compression on Energy Constrained Wireless Body Sensors
2011. International Symposium on Circuits and Systems (ISCAS'11), Rio de Janeiro, Brazil, May 15 - 18, 2011. p. 125-128.Accelerated MR imaging with spread spectrum encoding
2011. International Society for Magnetic Resonance in Medicine (ISMRM) conference, Montreal, May 7-13, 2011. p. 2808.A Regularization Framework for Mobile Social Network Analysis
2011. International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, May 22-27, 2011.A Variational Framework for Structure from Motion in Omnidirectional Image Sequences
Journal of Mathematical Imaging and Vision. 2011. DOI : 10.1007/s10851-011-0267-1.Sparsity Driven People Localization with a Heterogeneous Network of Cameras
Journal of Mathematical Imaging and Vision. 2011. DOI : 10.1007/s10851-010-0258-7.Method and system for automatic objects localization
US2014254875 ; US8749630 ; EP2386981 ; US2011279685 ; EP2386981 . 2010.Stream Carving: an Adaptive Seam Carving Algorithm
2010. International conference on Image Processing, Honk hong, September 26-29, 2010. p. 901-904. DOI : 10.1109/ICIP.2010.5653984.Plenoptic based super-resolution for omnidirectional image sequences
2010. IEEE International Conference on Image Processing (ICIP), Hong Kong, September 26-29, 2010.A (256x256) Pixel 76.7mW CMOS Imager/ Compressor Based on Real-Time In-Pixel Compressive Sensing
2010. IEEE International Symposium on Circuits and Systems (ISCAS), Paris, France, May 30 - June 2, 2010.Spread spectrum for compressed sensing techniques in magnetic resonance imaging
2010. IEEE International Symp. on Biomedical Imaging: From Nano to macro (ISBI), Rotterdam, April 14-17, 2010. p. 756-759. DOI : 10.1109/ISBI.2010.5490066.Spread spectrum for interferometric and magnetic resonance imaging
2010. IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), Dallas, March 14–19, 2010. p. 2802-2805. DOI : 10.1109/ICASSP.2010.5496198.Cascade of Descriptors to Detect and Track Objects Across Any Network of Cameras
Computer Vision and Image Understanding. 2010. DOI : 10.1016/j.cviu.2010.01.004.Method for spatially scalable video coding
US7616824 ; US2006120614 . 2009.A Variational Framework for Structure from Motion in Omnidirectional Image Sequences
2009Sparsity-driven People Localization Algorithm: Evaluation in Crowded Scenes Environments
2009. IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, Snowbird, Utah, December 7-10, 2009. DOI : 10.1109/PETS-WINTER.2009.5399487.Compressed sensing for radio interferometry: spread spectrum imaging techniques
2009. WAVELET XIII, SPIE09, San Diego, August 02-06, 2009. DOI : 10.1117/12.824713.Spread spectrum for imaging techniques in radio interferometry
Monthly Notices of the Royal Astronomical Society. 2009. DOI : 10.1111/j.1365-2966.2009.15519.x.A Master-Slave Approach to Detect and Match Objects Across Several Uncalibrated Moving Cameras
2009Sport Players Detection and Tracking With a Mixed Network of Planar and Omnidirectional Cameras
2009. Third ACM/IEEE International Conference on Distributed Smart Cameras, Como, 30 August - 2 September, 2009. DOI : 10.1109/ICDSC.2009.5289406.A Sparsity Constrained Inverse Problem to Locate People in a Network of Cameras
2009. 16th International Conference on Digital Signal Processing, Aegean island of Santorini, Greece, July 5-7, 2009. DOI : 10.1109/ICDSP.2009.5201223.TV-Regularized Generation of Planar Images from Omnicams
2009. IEEE International Conference on Image Processing - ICIP 2009, Cairo, Egypt, November 7-11, 2009. DOI : 10.1109/ICIP.2009.5413712.Optical Flow and Depth from Motion for Omnidirectional Images using a TV-L1 Variational Framework on Graphs
2009. IEEE International Conference on Image Processing - ICIP 2009, Cairo, Egypt, November 7-11, 2009.Dictionary learning for the sparse modelling of atrial fibrillation in ECG signals
2009. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP09), Taipeh, 2009.CMOS Compressed Imaging by Random Convolution
2009. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Taipei, Taiwan, 19 -24 April 2009. p. 1113-1116. DOI : 10.1109/ICASSP.2009.4959783.Geometric Video Approximation Using Weighted Matching Pursuit
IEEE Transactions on Image Processing. 2009. DOI : 10.1109/TIP.2009.2021315.Research
Topics
Data nowadays come in overwhelming volume. In order to cope with this deluge, we explore and use the benefits of geometry and symmetry in higher dimensional data. But volume is not the only problem: data models are also increasingly complex, mixing various components. We thus use sparse representations and dictionaries as dimensionality reduction tools to dig out information from complicated high-dimensional datasets and multichannel signals, or to model complex behaviours in more classical signals. Finally data can also be complex because they are collected on surfaces, or more generally manifolds, or because they are not scalar-valued. We thus explore extensions of Computational Harmonic Analysis in higher dimensions, in complex geometries, on graphs, networks or for non-scalar data.
Teaching & PhD
Teaching
Electrical and Electronics Engineering