Mesoscopic Facial Geometry Inference Using Deep Neural Networks (bibtex)
by Loc Huynh, Weikai Chen, Shunsuke Saito, Jun Xing, Koki Nagano, Andrew Jones, Paul Debevec, Hao Li
Abstract:
We present a learning-based approach for synthesizing facial geometry at medium and fine scales from diffusely-lit facial texture maps. When applied to an image sequence, the synthesized detail is temporally coherent. Unlike current state-of-the-art methods [17, 5], which assume ”dark is deep”, our model is trained with measured facial detail collected using polarized gradient illumination in a Light Stage [20]. This enables us to produce plausible facial detail across the entire face, including where previous approaches may incorrectly interpret dark features as concavities such as at moles, hair stubble, and occluded pores. Instead of directly inferring 3D geometry, we propose to encode fine details in high-resolution displacement maps which are learned through a hybrid network adopting the state-of-the-art image-to-image translation network [29] and super resolution network [43]. To effectively capture geometric detail at both mid- and high frequencies, we factorize the learning into two separate sub-networks, enabling the full range of facial detail to be modeled. Results from our learning-based approach compare favorably with a high-quality active facial scanhening technique, and require only a single passive lighting condition without a complex scanning setup.
Reference:
Mesoscopic Facial Geometry Inference Using Deep Neural Networks (Loc Huynh, Weikai Chen, Shunsuke Saito, Jun Xing, Koki Nagano, Andrew Jones, Paul Debevec, Hao Li), In Proceedings of the 31st IEEE International Conference on Computer Vision and Pattern Recognition, IEEE, 2018.
Bibtex Entry:
@inproceedings{huynh_mesoscopic_2018,
	address = {Salt Lake City, UT},
	title = {Mesoscopic {Facial} {Geometry} {Inference} {Using} {Deep} {Neural} {Networks}},
	url = {http://openaccess.thecvf.com/content_cvpr_2018/papers/Huynh_Mesoscopic_Facial_Geometry_CVPR_2018_paper.pdf},
	abstract = {We present a learning-based approach for synthesizing facial geometry at medium and fine scales from diffusely-lit facial texture maps. When applied to an image sequence, the synthesized detail is temporally coherent. Unlike current state-of-the-art methods [17, 5], which assume ”dark is deep”, our model is trained with measured facial detail collected using polarized gradient illumination in a Light Stage [20]. This enables us to produce plausible facial detail across the entire face, including where previous approaches may incorrectly interpret dark features as concavities such as at moles, hair stubble, and occluded pores. Instead of directly inferring 3D geometry, we propose to encode fine details in high-resolution displacement maps which are learned through a hybrid network adopting the state-of-the-art image-to-image translation network [29] and super resolution network [43]. To effectively capture geometric detail at both mid- and high frequencies, we factorize the learning into two separate sub-networks, enabling the full range of facial detail to be modeled. Results from our learning-based approach compare favorably with a high-quality active facial scanhening technique, and require only a single passive lighting condition without a complex scanning setup.},
	booktitle = {Proceedings of the 31st {IEEE} {International} {Conference} on {Computer} {Vision} and {Pattern} {Recognition}},
	publisher = {IEEE},
	author = {Huynh, Loc and Chen, Weikai and Saito, Shunsuke and Xing, Jun and Nagano, Koki and Jones, Andrew and Debevec, Paul and Li, Hao},
	month = jun,
	year = {2018},
	keywords = {Graphics, UARC}
}
Powered by bibtexbrowser