Title :
Face It: 3D Facial Reconstruction from a Single 2D Image for Games and Simulations
Author :
Kirtzic, J. Steven ; Daescu, Ovidiu
Author_Institution :
Dept. of Comput. Sci., Univ. of Texas at Dallas, Richardson, TX, USA
Abstract :
An ongoing challenge with game and simulation design is immersion. Users want to feel as though the avatars that they see on screen are themselves and that the experiences of their avatars are their own. To that end, much work has been done in the area of 3D facial reconstruction for the purpose of inserting one´s own likeness into a game or simulation. However, most existing methods require a minimum of two images and complex computations to produce the 3D head mesh. In this paper we propose a simple method for 3D facial reconstruction that renders the face mesh as a terrain using a single input image and minimal computation. This results in a fast and lightweight facial reconstruction that is highly portable and has a wide variety of applications.
Keywords :
avatars; computer games; face recognition; image reconstruction; rendering (computer graphics); 3D facial reconstruction; avatar; face mesh rendering; game design; simulation design; single 2D image; Computational modeling; Face; Games; Gray-scale; Rendering (computer graphics); Solid modeling; Three dimensional displays; 2D image; 3D facial reconstruction; terrain rendering;
Conference_Titel :
Cyberworlds (CW), 2011 International Conference on
Conference_Location :
Banff, ON
Print_ISBN :
978-1-4577-1453-5