Ecole d'ingénieur et centre de recherche en Sciences du numérique

From Kinect video to realistic and animatable Mpeg-4 face model: A complete framework

Turban, Laura; Girard, Denis; Kose, Neslihan; Dugelay, Jean-Luc

HOT 3D 2015, 6th IEEE International Workshop on Hot Topics in 3D (ICME 2015), 29 June 2015, Torino, Italy

The recent success of the Kinect sensor has a significant impact on 3D data based computer applications. This study aims to obtain MPEG-4 compliant realistic and animatable face models from Kinect video. The complete framework for this process includes initially the computation of high quality 3D scans from RGB-D Kinect video, and then the computation of animatable MPEG-4 face models using these high quality scans. This study shows that it is possible to obtain high quality 3D scans and realistic and animatable face models of subjects using lower quality Kinect data.

Document Doi Bibtex

Titre:From Kinect video to realistic and animatable Mpeg-4 face model: A complete framework
Mots Clés:Kinect, MPEG-4, animatable face model
Département:Sécurité numérique
Eurecom ref:4592
Copyright: © 2015 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Bibtex: @inproceedings{EURECOM+4592, doi = {}, year = {2015}, title = {{F}rom {K}inect video to realistic and animatable {M}peg-4 face model: {A} complete framework}, author = {{T}urban, {L}aura and {G}irard, {D}enis and {K}ose, {N}eslihan and {D}ugelay, {J}ean-{L}uc}, booktitle = {{HOT} 3{D} 2015, 6th {IEEE} {I}nternational {W}orkshop on {H}ot {T}opics in 3{D} ({ICME} 2015), 29 {J}une 2015, {T}orino, {I}taly}, address = {{T}orino, {ITALIE}}, month = {06}, url = {} }
Voir aussi: