Grupo de Tratamiento de Imágenes

 

 

 

 

 

News and Events 

FVVLive System

The third edition of The Observatory of New Technologies took place on 17 and 18 July 2019, at the Digital Content Hub in Málaga, Spain. Labelled as The New Tech Observatory, it was again the Spanish key event for meeting experts, producers, professionals, students, trainers, and entrepreneurs involved in sectors such as Immersive Experiences, Artificial Intelligence, IoT, eSports, Video Games, Serious Games, eHealth, and eTourism, among others.

The Grupo de Tratamiento de Imágenes (GTI) of the Universidad Politécnica de Madrid (UPM) presented a complete FVV system (free view-point video) in the Demo Area of the Observatory. This system, called FVVLIVE, allows the viewer to choose dynamically, through a simple interface, the point from which he/she wishes to observe the scene of a FVV live transmission. Thus, it offers an enriched audiovisual experience which allows the feeling of immersion within the scene. FVV-Live has been developed by the members of GTI.

FVV-Live has been the first free-viewpoint video system able to operate in real time. In addition to this achievement, the system has the ability to work with sparse camera configurations. Its performance improves the results obtained by state-of-the-art research teams.

The future is here!

 

FVV-Live operates in real time with minimum end-to-end latency, based on a configuration of sparse cameras and using consumer electronics equipment. To achieve this, the researchers of the GTI have designed, developed, and verified lightweight schemes for the acquisition, transmission, and rendering of video. Linear and planar camera configurations have been used and depth information has been obtained combining depth stereo vision and multiview stereo. New schemes for lossless and lossy transmission allow the delivery of the multiview plus depth information to a remote receiver where free-viewpoint video is generated. The motion-to-photon latency (latency of interaction) associated to the rendering of the video corresponding to the virtual viewpoint chosen by the user has been minimized. New algorithms have been developed for FVV-Live that combine texture and depth to achieve a better subjective quality.