Learning to Generate 3D Stylized Character Expressions from Humans

Deepali Aneja, Bindita Chaudhuri, Alex Colburn, Gary Faigin, Linda G. Shapiro, Barbara Mones

WACV 2018 pp. 160-169

doi:10.1109/WACV.2018.00024 /wacv/2018/aneja2018wacv-learning/

Abstract

We present ExprGen, a system to automatically generate 3D stylized character expressions from humans in a perceptually valid and geometrically consistent manner. Our multi-stage deep learning system utilizes the latent variables of human and character expression recognition convolutional neural networks to control a 3D animated character rig. This end-to-end system takes images of human faces and generates the character rig parameters that best match the human's facial expression. ExprGen generalizes to multiple characters, and allows expression transfer between characters in a semi-supervised manner. Qualitative and quantitative evaluation of our method based on Mechanical Turk tests show the high perceptual accuracy of our expression transfer results.

WACV Semantic Scholar

Cite

Text

Aneja et al. "Learning to Generate 3D Stylized Character Expressions from Humans." IEEE/CVF Winter Conference on Applications of Computer Vision, 2018. doi:10.1109/WACV.2018.00024

Markdown

[Aneja et al. "Learning to Generate 3D Stylized Character Expressions from Humans." IEEE/CVF Winter Conference on Applications of Computer Vision, 2018.](https://mlanthology.org/wacv/2018/aneja2018wacv-learning/) doi:10.1109/WACV.2018.00024

BibTeX

@inproceedings{aneja2018wacv-learning,
  title     = {{Learning to Generate 3D Stylized Character Expressions from Humans}},
  author    = {Aneja, Deepali and Chaudhuri, Bindita and Colburn, Alex and Faigin, Gary and Shapiro, Linda G. and Mones, Barbara},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2018},
  pages     = {160-169},
  doi       = {10.1109/WACV.2018.00024},
  url       = {https://mlanthology.org/wacv/2018/aneja2018wacv-learning/}
}