We create an individualized body from three views of a person. (Front, side and back views). We take two additional photos focusing on a face (Front, side) if we like to see detailed facial shape and animation. It is ongoing project (almost finishing) and the meanwhile result are shown below. We use a generic body in H-anim format and export into VRML file for animation. ref. H-anim version 1.1

Characteristics

• Photo-realistic looking
• Reconstruction doesn't need any special setting (no special background)
• Easy and fast reconstruction & visualization
• Continuous mesh
• Support all joints in H-Anim 1.1
• The output in VRML 2.0 format. Animation immediate
• Detailed face structure with animation function
• Full integration of face cloning and body cloning

Related publications

• Won-Sook Lee, Nadia Magnenat-Thalmann, "Head Modeling from Pictures and Morphing in 3D with Image Metamorphosis based on triangulation", Proc. Captech98 (Modelling and Motion Capture Techniques for Virtual Environments), (Springer LNAI LNCS Press), Geneva, pp.254-267, 1998.
• Won-Sook Lee, Jin Gu, Nadia Magnenat-Thalmann, "Generating Animatable 3D Virtual Humans from Photographs", accepted in Eurographics 2000
• Takao Furakawa, Jin Gu, Won-Sook Lee, Nadia Magnenat-Thalmann, "3D Clothes Modling from Photo Cloned Human Body", accepted in Virtual Worlds 2000

Animation examples

• Motion star and Java script : Thanks to Christian Bapski for animation.

• Vicon and 3D SMax : Thanks to Hyewon Seo for 3D SMax.

  movie

  VRML

  
  
  WonSook LEE, Ph.D.
  
  School of Information Technology and Engineering (SITE)
  University of Ottawa
  800 King Edward Avenue
  P.O. Box 450, Stn A
  Ottawa, Ontario, Canada K1N 6N5
  
  Office: SITE, Room 4065
  Tel: (613) 562-5800 ext. 6227
  Fax: (613) 562-5664
  Email: wslee@site.uottawa.ca
  Web: http://www.site.uottawa.ca/~wslee