New frame interpolation scheme for talking head sequences

Tsuhan Chen, Yao Wang, Hans Peter Graf, Cassandra Swain

Research output: Contribution to conferencePaper

Abstract

A video codec typically skips frames to satisfy the bitrate constraint. This results in jerky motion and loss of lip synchronization in sequences of talking persons. In this paper, we propose a frame interpolation technique to solve these problems. Main components of this technique include: foreground/background segmentation, mesh-based frame interpolation, and image analysis/synthesis for mouth movements. This technique generates smooth head motion and renders lip motion that is synchronized with the voice of the person.

Original languageEnglish (US)
Pages591-594
Number of pages4
StatePublished - Jan 1 1996
EventProceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3) - Washington, DC, USA
Duration: Oct 23 1995Oct 26 1995

Other

OtherProceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3)
CityWashington, DC, USA
Period10/23/9510/26/95

    Fingerprint

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Chen, T., Wang, Y., Graf, H. P., & Swain, C. (1996). New frame interpolation scheme for talking head sequences. 591-594. Paper presented at Proceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3), Washington, DC, USA, .