Fully Automatic Expression-Invariant Face Correspondence
This addresses the need for automatic, expression-invariant face correspondence in computer vision and graphics, offering a practical solution without manual markers, though it appears incremental as it builds on existing blendshape and landmark prediction methods.
The paper tackles the problem of computing accurate point-to-point correspondences among 3D human face scans with varying expressions, using a fully automatic approach that learns landmarks from a database and predicts them on new scans, resulting in highly accurate and consistent correspondences for most tested models.
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.