Fully Automatic Expression-Invariant Face Correspondence

TL;DR

This paper presents an automatic method for establishing accurate, expression-invariant point-to-point correspondences among 3D human face scans without manual markers, using learned landmarks and blendshape models.

Contribution

It introduces a fully automatic landmark prediction and correspondence method that handles expression variations using a blendshape template, improving accuracy and consistency.

Findings

High accuracy in correspondence across diverse face scans

Consistent results for different ethnic groups and expressions

No manual marker placement required

Abstract

We consider the problem of computing accurate point-to-point correspondences among a set of human face scans with varying expressions. Our fully automatic approach does not require any manually placed markers on the scan. Instead, the approach learns the locations of a set of landmarks present in a database and uses this knowledge to automatically predict the locations of these landmarks on a newly available scan. The predicted landmarks are then used to compute point-to-point correspondences between a template model and the newly available scan. To accurately fit the expression of the template to the expression of the scan, we use as template a blendshape model. Our algorithm was tested on a database of human faces of different ethnic groups with strongly varying expressions. Experimental results show that the obtained point-to-point correspondence is both highly accurate and consistent for most of the tested 3D face models.