Pierre Kornprobst

Inria Researcher
in Vision Science

Biovision team

Associate Editor for the CVIU

Member of the Academic Council of the Université Côte d'Azur

The scientific study of vision encompasses many disciplines such as computer vision, neuroscience or ophtalmology. Indeed, vision is a key sense in both artificial and biological systems and this is what motivated all my research. My research is characterized by a rich interaction between theoretical models, applications and experimental data analysis.

SHORT BIO     PAPERS     BOOKS     SUPERVISION     SOFTWARE     COURSES     CONTACT

SHORT BIO

My initial research was on applying techniques from PDEs and variational approaches to computer vision problems. In 2002, I made a major change in my research to develop neurally and psychophysically motivated models of the visual system and then revisit computer vision problems with bio-inspired approaches. This work made me want to start new collaborations with neuroscientists to be closer to experiments, in order to push the limits of models through design and analysis of experimental data. Finally, given my expertise in vision science, my research took a new turn in 2016 with the creation of the Biovision team, whose goal is to investigate new solutions to help vision impaired people, through fundamental research as well as innovative technological developments. In that context, my specific goals are to unveil fundamental mechanisms underlying low vision people's visual perception to leverage cross reality (see, e.g., VRead project).

For a quick overview:

PAPERS

Recurrent network dynamics reconciles visual motion segmentation and integration, N.V.K. Medathati, J. Rankin, A.I. Meso, P. Kornprobst and G.S. Masson, Scientific Reports, 7 (11270), 2017.

Pan-retinal characterization of Light Responses from Ganglion Cells in the Developing Mouse Retina, by G. Hilgen, S. Pirmoradian, D. Pamplona, P. Kornprobst, B. Cessac, M. H Hennig, E. Sernagor, Scientific Reports, 7(42330), 2017.

PRANAS: A new platform for retinal analysis and simulation,, B. Cessac, P. Kornprobst, S. Kraria, H. Nasser, D. Pamplona, G. Portelli, and T. Viéville, Frontiers in Neuroinformatics, 11:49, 2017.

A bio-inspired synergistic Virtual Retina model for tone mapping, M. Benzi, M.-J. Escobar and P. Kornprobst, Computer Vision and Image Understanding, December 2017. (see HAL version).

The relative contribution of noise and adaptation to competition during tri-stable motion perception, A. Meso, J. Rankin, O. Faugeras, P. Kornprobst G. Masson, Journal of Vision, 16(15):6. doi: 10.1167/16.15.6. 2016.

The wave of first spikes: a retinal information coding strategy revealed by large-scale multielectrode array recordings, G. Portelli, J.M. Barrett, G. Hilgen, T. Masquelier, A. Maccione, S. Di Marco, L. Berdondini, P. Kornprobst, E. Sernagor, eNeuro, 2016.

Bio-Inspired Computer Vision: Towards a Synergistic Approach of Artificial and Biological Vision, N.V.K. Medathati, H. Neumann, G.S. Masson and P. Kornprobst, Computer Vision and Image Understanding, Volume 150, September 2016, Pages 1-30, 2016.
Selected in 21st Annual Best of Computing.

Microsaccades enable efficient synchrony-based coding in the retina: a simulation study, T. Masquelier, G. Portelli and P. Kornprobst. Scientific Reports 6, Article number: 24086, 2016.

What can we expect from a V1-MT feedforward architecture for optical flow estimation? F. Solari, M. Chessa, N.V.K. Medathati, and P. Kornprobst. Volume 39, Part B, Pages 342–354, November 2015, Note: Our code is available on ModelDB.

Bifurcation Study of a Neural Fields Competition Model with an Application to Perceptual Switching in Motion Integration, J. Rankin, A. I. Meso, G. S. Masson, O. Faugeras, and P. Kornprobst. Journal of Computational Neuroscience, Vol. 36, No. 2, pp. 193--213, 2014.

Bifurcation analysis applied to a model of motion integration with a multistable stimulus, J. Rankin, E. Tlapale, R. Veltz, O. Faugeras, and P. Kornprobst. Journal of Computational Neuroscience, Vol. 34, No. 1, pp. 103--124, 2013. Try the stimulus (fix the center)!

Streaming an image through the eye: The retina seen as a dithered scalable image coder, K. Masmoudi, M. Antonini, and P. Kornprobst. Signal Processing: Image Communication 28 (8), pp. 856--869, 2013.

Frames for Exact Inversion of the Rank Order Coder, K. Masmoudi and M. Antonini, and P. Kornprobst. IEEE Transactions on Neural Networks and Learning Systems, 23(2):353-359, 2012.

Action recognition via bio–inspired features: The richness of center-surround interaction, M.J. Escobar and P. Kornprobst. Computer Vision and Image Understanding, 116(5):593-605, 2012.

Variational multi-valued velocity field estimation for transparent sequences, A. Ramirez, M. Rivera, Pierre Kornprobst, and F. Lauze. Journal of Mathematical Imaging and Vision, 40(3):285–304, 2011.

Neural mechanisms of motion detection, integration, and segregation: From biology to artificial image processing systems. J.D. Bouecke, E. Tlapale, P. Kornprobst, and H. Neumann. EURASIP Journal on Advances in Signal Processing, vol 2011, Special issue on Biologically inspired signal processing: Analysis, algorithms, and applications, 2011.

Modelling the dynamics of motion integration with a new luminance-gated diffusion mechanism. E. Tlapale, G. S. Masson, and P. Kornprobst. Vision Research, 50(17):1676-1692, 2010.

Virtual Retina: A biological retina model and simulator, with contrast gain control. A. Wohrer and P. Kornprobst. Journal of Computational Neuroscience, 26(2):219, 2009. This simulator is open-source (see Virtual Retina simulator website)

Bilateral Filtering: Theory and Applications. S. Paris, P. Kornprobst, J. Tumblin, and F. Durand. Foundations and Trends in Computer Graphics and Vision, 4(1):1-73, 2009. This paper is a summary of tutorials given at SIGGRAPH and CVPR (see TALKS/COURSES section)

Action Recognition Using a Bio-Inspired Feedforward Spiking Network. M.-J. Escobar, G. S. Masson, T. Vieville, and P. Kornprobst. International Journal of Computer Vision, 82(3):284, 2009.

Can the Nonlocal Characterization of Sobolev Spaces by Bourgain et al. Be Useful for Solving Variational Problems? G. Aubert and P. Kornprobst. SIAM J. Numer. Anal. 47(2):844-860, 2009.

How do high-level specifications of the brain relate to variational approaches? T. Vieville, S. Chemla, and P. Kornprobst. Journal of Physiology Paris, 101(1-3):118-135, 2007.

The use of superresolution techniques to reduce slice thickness in functional MRI. R.R. Peeters, P. Kornprobst, M. Nikolova, S. Sunaert, T. Vieville, G. Malandain, R. Deriche, O. Faugeras, M. Ng, and P. Van Hecke. International Journal of Imaging Systems and Technology (IJIST), Special issue on High Resolution Image Reconstruction, 14:131–138, 2004.

Image sequence analysis via partial differential equations. P. Kornprobst, R. Deriche, and G. Aubert. Journal of Mathematical Imaging and Vision, 11(1):5-26, 1999.

A mathematical study of the relaxed optical flow problem in the space BV. G. Aubert and P. Kornprobst. SIAM Journal on Mathematical Analysis, 30(6):1282-1308, 1999.

Computing optical flow via variational techniques. G. Aubert, R. Deriche, and P. Kornprobst. SIAM Journal of Applied Mathematics, 60(1):156-182, 1999.


Full list of publications

Main collaborators in recent years (in alphabetical order): Bruno Cessac (Inria, France), Eric Castet (LPC, Marseille, France), Maria-Jose Escobar (Universidad Técnica Federico Santa María, Chile), Matthias Henning (University of Edimburg, UK), Timothée Masquelier (Institut de la Vision, France), Guillaume S. Masson (Insitut des Neurosciences de la Timone, France), James Rankin (University of Exeter, UK), Evelyne Sernagor (University of Newcastle, UK), Fabio Solari (University of Genova, Italy)

BOOKS

Modeling in Computational Biology and Biomedicine: A Multidisciplinary Endeavor, F. Cazals and P. Kornprobst, Eds, Springer, 2013.
About this book Computational biology and biomedicine is a vast field where intensive research is currently being carried out, with outstanding perspectives both in terms of the complexity of the scientific problems to be addressed and technological developments to be made. Taking up these challenges requires developing an enhanced synergy between biology and biomedicine on the one hand, and applied mathematics and computer science on the other hand. In line with this observation, the motivation to write this book has been to show that researchers trained in more quantitative and exact sciences can make major contributions in this emerging discipline, and those with roots in biology and biomedicine can benefit from a true leveraging power tailored to their specific needs.

Mathematical problems in image processing: Partial Differential Equations and the Calculus of Variations, G. Aubert and P. Kornprobst, Springer, Applied Mathematical Sciences, Vol 147, 2006 (second edition).
About this book Amongst the numerous approaches which have been suggested, we focus on Partial Differential Equations (PDE's), and Variational Approaches in this book. Traditionally applied in physics, these methods have been successfully and widely transferred in Computer Vision other the last decades. One of the main interests in using PDEs is that the theory behind the concept is well-established. Of course, PDEs are written in a continuous setting refering to analog images, and once the existence and the uniqueness have been proven, we need to discretize them in order to find a numerical solution. It is our conviction that reasoning within a continuous framework makes the understanding of physical realities easier and stimulates the intuition necessary to propose new models. We hope that this book will illustrate this idea effectively.
SIAM Review: "Mathematical Problems in Image Processing is a major, elegant, and unique contribution to the applied mathematics literature, oriented toward applications in image processing and computer vision .../... Researchers and practitioners working in the field will benefit by adding this book to their personal collection. Students and instructors will benefit by using this book as a graduate course textbook."

SUPERVISION

Alberto Patiño Saucedo (PhD, 2018-2021)
Image transforms for low-vision
co-supervised with Horacio Rostro-Gonzales (University of Guanajuato, Mexico)

Marco Benzi Tobar (Engineer, 2017-2019)
VRead project

Josselin Gautier (Engineer, 2017-2018)
Augmented reality for visually impaired people
Partnership with Bosch Visiontec


Past PhDs and Postdocs supervised:

N. V. Kartheek Medathati (PhD, 2013-2016)
Motion perception and attention: from visual neuroscience to artificial vision systems
co-supervised with Guillaume Masson (INT)
Defence: Dec. 13, 2016
Now: Researcher at Oculus, Seattle, USA

Khaled Masmoudi (PhD, 2008-2012)
Conception of Novel Bio-Inspired Coding Systems
co-supervised with Marc Antonini (CNRS, I3S)
Now: C++/C# developer at AVM-Informatique, Paris, France

Emilien Tlapale (PhD, 2009-2011)
Modelling the dynamics of contextual motion integration in the primate
co-supervised with Guillaume Masson (INT)
Now: Artificial Intelligence Researcher at Hitachi Europe, Sophia Antipolis, France

Maria-Jose Escobar (PhD, 2006-2009)
Bio-Inspired Models for Motion Estimation and Analysis: Human action recognition and motion integration
co-supervised with Guillaume Masson (INT)
Now: Researcher at UTFSM, Valparaiso, Chile

Adrien Wohrer (PhD, 2004-2008)
Model and large-scale simulator of a biological retina, with contrast gain control
Now: Assistant professor at Université d'Auvergne in Clermont-Ferrand, France

Daniela Pamplona (Postdoc, 2014-2016)
Retina modeling & new approaches for receptive field estimation.
Now: Postdoctoral researcher at ENSTA-ParisTech, Paris, France

Audric Drogoul (Postdoc, 2014-2016)
Variational approaches for receptive field estimation
Now: Research Engineer at Thales Alenia Space, Cannes, France

Geoffrey Portelli (Postdoc, 2012-2015)
Understanding the wave of first spike (from MEA recordings) & the role of micromovements (from simulations)
Now: Postdoctoral researcher at I3S, CNRS, MinD team, Université de Nice Sophia Antipolis, France

James Rankin (Postdoc, 2010-2013)
Perceptual switching in motion integration
Now: Lecturer in Mathematical Biology at University of Exeter, UK

Vivien Robinet (Postdoc, 2010-2011)
Neural network functional connectivity from spike train analysis
Now: Assistant professor, Université des Antilles et de la Guyane (UAG), France

Neil Bruce (Postdoc, 2008-2010)
Models of saliency for video-surveillance systems
Now: Assistant professor, University of Manitoba, Canada

SOFTWARE

Virtual Retina: A bio-inspired retina simulator for large-scale spiking simulations. It transforms your videos into spike trains. Now you can install it or run it through Pranas.

Pranas: A new platform for retinal analysis and simulatiion.

PDE library: A CImg plugin with classical image restoration and segmentation approaches

AB filter: this library implements the physiological plausible filters proposed by Adelson and Bergen in 1985.

COURSES

Founder and coordinator of the Master of Science in Computational Biology and Biomedicine, Université Nice Sophia Antipolis, from Nov. 2008 until Sept. 2011.

A Gentle Introduction to Bilateral Filtering and its Applications: A class at ACM SIGGRAPH 2008, CVPR 2008 and ACM SIGGRAPH 2007 with S. Paris, J. Tumblin, and F. Durand

Introduction to PDEs and variational approaches in image processing (in french)

Traitement des images numériques, G. Aubert and P. Kornprobst. In J. Akoka and I. Comyn-Wattiau, editors, Encyclopédie de l’informatique et des systèmes d’information, number 6, chapter 18, pages 861—879. Vuibert, November 2006.

Introduction to image processing (in french)

CONTACT

Inria Sophia Antipolis - Méditerranée
Biovision team
2004 Route des Lucioles - BP 93
06902 Sophia Antipolis Cedex
France

Email: pierre.kornprobst (AT) inria.fr
Phone: +33(0)4-92-38-79-79


Inria Sophia Antipolis - Méditerranée is a member of Université Côte d'Azur (UCA). In 2016, UCA has won, with its UCAJEDI project, a "IDEX" (Initiatives d’excellence) award of the French Investments for the Future Program. This project aims at profoundly impacting and transforming research activity in the area, fostering the emergence of new transdisciplinary research projects.