Automatic system for virtual human reconstruction with 3D mesh multi-texturing and facial enhancement

The present paper presents a fully automatic low-cost system for generating animatable and statically multi-textured avatars of real people captured with several standard cameras. Our system features a novel technique for generating view-independent texture atlases computed from the original images,...

Full description

Saved in:
Bibliographic Details
Published in:Signal processing. Image communication 2013-10, Vol.28 (9), p.1089-1099
Main Authors: Pages, R, Berjon, D, Moran, F
Format: Article
Language:English
Subjects:
3D face reconstruction
Avatars
Facial
Human avatar generation
Surface layer
Texture
Three dimensional
View-independent multi-texturing
Virtual humans
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The present paper presents a fully automatic low-cost system for generating animatable and statically multi-textured avatars of real people captured with several standard cameras. Our system features a novel technique for generating view-independent texture atlases computed from the original images, and two proposals for improving the quality of the facial region of the 3D mesh: a purely passive one implying no additional cost, and another based on active techniques such as structured light projection. •Fully automatic system for generation of animatable human avatars for video-games.•Low cost: no specific hardware is required other than standard cameras.•Novel static multi-texturing to improve both quality and reusability.•Two proposals for facial enhancement, both passive and active.
ISSN:0923-5965
1879-2677
DOI:10.1016/j.image.2013.07.001