Synthesis of Novel Views from a Single Face Image

Images formed by a human face change with viewpoint. A new technique is described for synthesizing images of faces from new viewpoints, when only a single 2D image is available. A novel 2D image of a face can be computed without knowledge about the 3D structure of the head. The technique draws on a single generic 3D model of a human head and on prior knowledge of faces based on example images of other faces seen in di erent poses. The example images are used to learn" a pose-invariant shape and texture description of a new face. The 3D model is used to solve the correspondence problem between images showing faces in di erent poses. Examples of synthetic rotations" over 24 based on a training set of 100 faces are shown. This document is available as pub mpi-memos TR-026.ps.Z via anonymous ftp from ftp.mpik-tueb.mpg.de or from the World Wide Web, http: www.mpik-tueb.mpg.de projects TechReport list.html. 

• Type: Journal
• Year: 1998
• Where: IJCV
• Authors: Thomas Vetter
• Keywords: 3D Model, Example Images, IJCV 1998, Images