Deutsch
 
Benutzerhandbuch Datenschutzhinweis Impressum Kontakt
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Forschungspapier

GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB

MPG-Autoren
/persons/resource/persons134216

Mueller,  Franziska
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons214986

Bernard,  Florian
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons199773

Sotnychenko,  Oleksandr
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons129023

Mehta,  Dushyant
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons45610

Theobalt,  Christian
Computer Graphics, MPI for Informatics, Max Planck Society;

Externe Ressourcen
Es sind keine Externen Ressourcen verfügbar
Volltexte (frei zugänglich)

arXiv:1712.01057.pdf
(Preprint), 8MB

Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Mueller, F., Bernard, F., Sotnychenko, O., Mehta, D., Sridhar, S., Casas, D., et al. (2017). GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB. Retrieved from http://arxiv.org/abs/1712.01057.


Zitierlink: http://hdl.handle.net/21.11116/0000-0000-6156-2
Zusammenfassung
We address the highly challenging problem of real-time 3D hand tracking based on a monocular RGB-only sequence. Our tracking method combines a convolutional neural network with a kinematic 3D hand model, such that it generalizes well to unseen data, is robust to occlusions and varying camera viewpoints, and leads to anatomically plausible as well as temporally smooth hand motions. For training our CNN we propose a novel approach for the synthetic generation of training data that is based on a geometrically consistent image-to-image translation network. To be more specific, we use a neural network that translates synthetic images to "real" images, such that the so-generated images follow the same statistical distribution as real-world hand images. For training this translation network we combine an adversarial loss and a cycle-consistency loss with a geometric consistency loss in order to preserve geometric properties (such as hand pose) during translation. We demonstrate that our hand tracking system outperforms the current state-of-the-art on challenging RGB-only footage.