Synthesis of Novel Views from a Single Face Image

  • Authors:
  • Thomas Vetter

  • Affiliations:
  • Max-Planck-Institut für Biologische Kybernetik, Spemannstr. 38, 72076 Tüubingen, Germany. E-mail: vetter@mpik-tueb.mpg.de

  • Venue:
  • International Journal of Computer Vision
  • Year:
  • 1998

Quantified Score

Hi-index 0.01

Visualization

Abstract

Images formed by a human face change with viewpoint. A new techniqueis described for synthesizing images of faces from new viewpoints, when onlya single 2D image is available. A novel 2D image of a face can be computedwithout explicitly computing the 3D structure of the head. The techniquedraws on a single generic 3D model of a human head and on prior knowledge offaces based on example images of other faces seen in different poses. Theexample images are used to ’’learn‘‘ a pose-invariant shape and texturedescription of a new face. The 3D model is used to solve the correspondenceproblem between images showing faces in different poses. The proposed method is interesting for view independent face recognitiontasks as well as for image synthesis problems in areas like teleconferencingand virtualized reality.