Compression Performances of Computer Vision Based Coding

Franck Galpin, Luce Morin, Koichiro Deguchi

Research output: Contribution to journalArticlepeer-review


This paper presents new results in the field of very low bitrate coding and compression using 3D informations. Contrary to prior art in model-based coding where 3D models have to be known, the 3D models are automatically computed from the original video sequence. The camera parameters and the scene content are supposed unknown and the video sequence is processed on the fly. A stream of 3D models is then extracted and compressed, using adapted compression techniques. We finally show the results of the proposed compression scheme, and the efficiency of this approach.

Original languageEnglish
Pages (from-to)74-79
Number of pages6
JournalIEICE Transactions on Information and Systems
Issue number1
Publication statusPublished - 2004 Jan


  • 3D model-based coding
  • Compression
  • Shape-from-motion

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence


Dive into the research topics of 'Compression Performances of Computer Vision Based Coding'. Together they form a unique fingerprint.

Cite this