Frédéric DUFAUX

Directeur de recherche – CNRS

L2S, CentraleSupélec
3 rue Joliot Curie
91190 Gif-sur-Yvette, France



BooksPhD Students


SMART-V2I aims to design and optimize ultra-low latency architectures for encoding, communicating and decoding video content transmitted between vehicles and road infrastructure. The use cases may range from remote driving to mobile video-verbalization, including assistance with the maintenance of road infrastructure..

The aim of realistic digital imaging is the creation of high quality imagery, which faithfully represents the physical environment. The ultimate goal is to create images, which are perceptually indistinguishable from a real scene. The RealVision network brings together leading universities and centers focused on industrial development and companies in multimedia, optics, visual communication, visual computing, computer graphics, and human vision research across Europe, with the aim of training a new generation of scientists, technologists, and entrepreneurs that will move Europe into a leading role in innovative hyper-realistic imaging technologies.

The ReVeRY project aims at providing solutions to replace traditional video media (mono or stereoscopic) with a richer data flow solving current limitations. This rich media will jointly integrate depth information, UHD, and HDR in a dedicated format. The project will (i) offer one or more appropriate representations of this new media, (ii) develop a demonstration prototype of a dedicated acquisition system, and (iii) demonstrate their benefits for the media creation industry. Ultimately, ReVeRY will offer a new viewing experience.

Past projects

4EVER-2: For Enhanced Video ExpeRience [2015-2017; Fonds unique interministériel (FUI)]

The 4EVER-2 project has the objective to define and validate the next generation Ultra HD TV services. In particular, the project is working on new technologies for High Dynamic Range, Wide Colour Gamut and High Frame Rate, tackling acquisition, compression, transmission and visual quality assessment aspects.

PLEIN−PHARE: Projet d’améLioration bas−coût d’unE chaIne de vidéosurveillaNce Par l’exploitation de technologies HDR d’Analyse et de REstitution [2014-2017; Fonds unique interministériel (FUI)]

The PLEIN-PHARE project targets the improvement of video surveillance systems by overcoming current limitations when operating in difficult illumination conditions. More specifically, the project is developing cost-effective High Dynamic Range imaging at the acquisition, analysis and display steps.

SURICATE: SUrveillance de Réseaux et d’InfrastruCtures, de milieux, par des systèmes AéroporTés Endurants [2014-2017; Agence Nationale de la Recherche (ANR)]

The SURICATE project is considering the surveillance of large critical infrastructures (e.g. transport network with SNCF train tracks and energy with EDF powerlines) using enduring Unmanned Aerial Vehicles. Research topics include video analysis, compression and transmission.

TOFuTV: Transcoders Of the FUture TeleVision [2013-2015; Eureka Eurostars project (E!8307)]

TOFuTV will study the next generation of Television, including 4K videos, HEVC coding and transcoding, quality and colour spaces management, stream security and new services for the users.

AUSTRAL: Architecture Universelle over the top Sécurisée de Télévision de Rattrapage, A la demande et Live [2012-2014; Fonds unique interministériel (FUI)]

The AUSTRAL project aims at addressing the distribution issues for broadcasting “premium” contents on open IP networks (Over the Top, OTT) from an end to end point of view. Unlike the IPTV, the OTT technology will be providing the audiovisual stakeholders with independence toward the network.

NEVEx: The NExt Video Experience [2011-2014; Fonds unique interministériel (FUI)]

In order to offer a more immersive experience, the NEVEx project aims at the study of a complete High Dynamic Range video pipeline, from content creation up to display.