Learning Stylized Character Expressions from Humans

TL;DR

DeepExpr is a deep learning system that transfers human facial expressions to stylized characters, utilizing a new dataset and perceptual model to improve expression transfer accuracy and consistency.

Contribution

The paper introduces DeepExpr, a novel deep learning framework with a new stylized character dataset and perceptual model for expression transfer from humans to characters.

Findings

High correlation between predicted and expert rankings

Effective expression retrieval on stylized character dataset

Validated with Mechanical Turk experiments

Abstract

We present DeepExpr, a novel expression transfer system from humans to multiple stylized characters via deep learning. We developed : 1) a data-driven perceptual model of facial expressions, 2) a novel stylized character data set with cardinal expression annotations : FERG (Facial Expression Research Group) - DB (added two new characters), and 3) . We evaluated our method on a set of retrieval tasks on our collected stylized character dataset of expressions. We have also shown that the ranking order predicted by the proposed features is highly correlated with the ranking order provided by a facial expression expert and Mechanical Turk (MT) experiments.