FEAFA+: An Extended Well-Annotated Dataset for Facial Expression Analysis and 3D Facial Animation

TL;DR

FEAFA+ is a new facial expression dataset with continuous AU intensity annotations, enabling more precise modeling of facial expressions for animation and transfer tasks.

Contribution

It extends existing datasets by providing floating-point AU intensity annotations, facilitating regression-based analysis of facial expressions.

Findings

230,184 frames annotated with continuous AU intensities

Baseline AU intensity regression results provided

Includes both posed and spontaneous expression subsets

Abstract

Nearly all existing Facial Action Coding System-based datasets that include facial action unit (AU) intensity information annotate the intensity values hierarchically using A--E levels. However, facial expressions change continuously and shift smoothly from one state to another. Therefore, it is more effective to regress the intensity value of local facial AUs to represent whole facial expression changes, particularly in the fields of expression transfer and facial animation. We introduce an extension of FEAFA in combination with the relabeled DISFA database, which is available at https://www.iiplab.net/feafa+/ now. Extended FEAFA (FEAFA+) includes 150 video sequences from FEAFA and DISFA, with a total of 230,184 frames being manually annotated on floating-point intensity value of 24 redefined AUs using the Expression Quantitative Tool. We also list crude numerical results for posed and spontaneous subsets and provide a baseline comparison for the AU intensity regression task.