Dynamic 3-D facial compression using low rank and sparse decomposition

Junhui Hou, Lap Pui Chau, Ying He, Dao T.P. Quynh, Nadia Magnenat-Thalmann

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

4 Citations (Scopus)


In this paper, we propose a new compression framework for dynamic 3-D facial expressions acquired from structured light based 3-D camera, based on our previous work. Taking advantage of the near-isometric property of human facial expressions, we parameterize the dynamic 3-D faces into an expression-invariant canonical domain, which naturally generates geometry video and allows us to apply the well-studied video compression technique. Then, low rank and sparse decomposition is applied to each dimension (i.e., X, Y and Z, respectively) before the H.264/AVC encoder is employed to separately encode each dimension instead of encoding them as a whole. Experimental results show that the averaged 3-4 dB gain is achieved by the proposed scheme compared with existing algorithms.

Original languageEnglish
Title of host publicationSIGGRAPH Asia 2012 Technical Briefs, SA 2012
Publication statusPublished - Nov 2012
Externally publishedYes
EventSIGGRAPH Asia 2012 Technical Briefs, SA 2012 - Singapore, Singapore
Duration: 28 Nov 20121 Dec 2012

Publication series

NameSIGGRAPH Asia 2012 Technical Briefs, SA 2012


ConferenceSIGGRAPH Asia 2012 Technical Briefs, SA 2012


  • Compression
  • Dynamic 3-D facial expressions
  • Geometry video
  • H.264/AVC
  • Low rank and sparse matrix decomposition

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Dynamic 3-D facial compression using low rank and sparse decomposition'. Together they form a unique fingerprint.

Cite this