Image mapped 3D model based coding for videoconferencing type applications

• Published in: 1997 IEEE First Workshop on Multimedia Signal Processing : June 23-25, 1997, Princeton, New Jersey, USA pp. 219 - 224
• Main Authors: Provine, J.A., Bruton, L.T.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 1997
• Subjects: Application software; Bit rate; Decoding; Deformable models; Facial animation; Head; Image coding; Solid modeling; Synthesizers; Teleconferencing
• ISBN: 9780780337800; 0780337808
• DOI: 10.1109/MMSP.1997.602639

One of the important reasons for model based coding scheme to be attractive for encoding videoconferencing type sequences at very low bit rates is the possibility of using a single generic facial model, and appropriately adding the identity of the subject in the sequence, In this paper, we present a method of adding the identity of the subject to the model using multiple views of the subject that allows synthesis of a perceptually equivalent version of the input sequence.