Production-Level Facial Performance Capture Using Deep Convolutional Neural Networks

Samuli Laine, Tero Karras, Timo Aila, Antti Herva, Shunsuke Saito, Ronald Yu, Hao Li, Jaakko Lehtinen

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

18 Sitaatiot (Scopus)

Abstrakti

We present a real-time deep learning framework for video-based facial performance capture---the dense 3D tracking of an actor's face given a monocular video. Our pipeline begins with accurately capturing a subject using a high-end production facial capture pipeline based on multi-view stereo tracking and artist-enhanced animations. With 5--10 minutes of captured footage, we train a convolutional neural network to produce high-quality output, including self-occluded regions, from a monocular video sequence of that subject. Since this 3D facial performance capture is fully automated, our system can drastically reduce the amount of labor involved in the development of modern narrative-driven video games or films involving realistic digital doubles of actors and potentially hours of animated dialogue per character. We compare our results with several state-of-the-art monocular real-time facial capture techniques and demonstrate compelling animation inference in challenging areas such as eyes and lips.
AlkuperäiskieliEnglanti
OtsikkoSCA '17 Proceedings of the ACM SIGGRAPH / Eurographics Symposium on Computer Animation
KustantajaACM
Sivumäärä10
ISBN (elektroninen)978-1-4503-5091-4
DOI - pysyväislinkit
TilaJulkaistu - heinäkuuta 2017
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaACM SIGGRAPH/EUROGRAPHICS SYMPOSIUM ON COMPUTER ANIMATION - University of California, Los Angeles, Los Angeles, Yhdysvallat
Kesto: 28 heinäkuuta 201730 heinäkuuta 2017

Conference

ConferenceACM SIGGRAPH/EUROGRAPHICS SYMPOSIUM ON COMPUTER ANIMATION
LyhennettäSCA
MaaYhdysvallat
KaupunkiLos Angeles
Ajanjakso28/07/201730/07/2017

Sormenjälki Sukella tutkimusaiheisiin 'Production-Level Facial Performance Capture Using Deep Convolutional Neural Networks'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

  • Siteeraa tätä

    Laine, S., Karras, T., Aila, T., Herva, A., Saito, S., Yu, R., ... Lehtinen, J. (2017). Production-Level Facial Performance Capture Using Deep Convolutional Neural Networks. teoksessa SCA '17 Proceedings of the ACM SIGGRAPH / Eurographics Symposium on Computer Animation [10] ACM. https://doi.org/10.1145/3099564.3099581