Robust Bayesian fitting of 3D morphable model

Claudia Arellano, Rozenn Dahyot

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

We propose to fit automatically a 3D morphable face model to a point cloud captured with a RGB-D sensor. Both data sets, the shape model and the target point cloud are modelled as two probability density functions (pdfs). Rigid registration (rotation and translation) and reconstruction on the model is performed by minimising the Euclidean distance between these two pdfs augmented with a multivariate Gaussian prior. Our resulting process is robust and it does not require point to point correspondence. Experimental results on synthetic and real data illustrates the performance of this novel approach.

Original languageEnglish
Title of host publicationProceedings of the 10th European Conference on Visual Media Production, CVMP 2013
DOIs
StatePublished - 2013
Externally publishedYes
Event10th European Conference on Visual Media Production, CVMP 2013 - London, United Kingdom
Duration: 6 Nov 20137 Nov 2013

Publication series

NameACM International Conference Proceeding Series

Conference

Conference10th European Conference on Visual Media Production, CVMP 2013
Country/TerritoryUnited Kingdom
CityLondon
Period6/11/137/11/13

Keywords

  • 3D face reconstruction
  • L2E
  • RGB-D sensor
  • computer vision
  • divergence
  • morphable models
  • registration
  • shape fitting

Fingerprint

Dive into the research topics of 'Robust Bayesian fitting of 3D morphable model'. Together they form a unique fingerprint.

Cite this