Learning Stylized Character Expressions from Humans
This work addresses expression transfer for stylized characters in animation or gaming, but it appears incremental as it builds on existing datasets and methods.
The paper tackled the problem of transferring facial expressions from humans to stylized characters by developing DeepExpr, a deep learning system that includes a perceptual model and a new dataset, achieving high correlation with expert and crowd-sourced rankings in retrieval tasks.
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.