日本語
 
User Manual Privacy Policy ポリシー/免責事項 連絡先
  詳細検索ブラウズ

アイテム詳細


公開

成果報告書

MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction

MPS-Authors
/persons/resource/persons206546

Tewari,  Ayush
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons136490

Zollhöfer,  Michael
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons127713

Kim,  Hyeongwoo
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons127194

Garrido,  Pablo
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons45610

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

URL
There are no locators available
フルテキスト (公開)

arXiv:1703.10580.pdf
(プレプリント), 10MB

付随資料 (公開)
There is no public supplementary material available
引用

Tewari, A., Zollhöfer, M., Kim, H., Garrido, P., Bernard, F., Pérez, P., & Theobalt, C. (2017). MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction. Retrieved from http://arxiv.org/abs/1703.10580.


引用: http://hdl.handle.net/11858/00-001M-0000-002D-8BEA-9
要旨
In this work we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image. To this end, we combine a convolutional encoder network with an expert-designed generative model that serves as decoder. The core innovation is our new differentiable parametric decoder that encapsulates image formation analytically based on a generative model. Our decoder takes as input a code vector with exactly defined semantic meaning that encodes detailed face pose, shape, expression, skin reflectance and scene illumination. Due to this new way of combining CNN-based with model-based face reconstruction, the CNN-based encoder learns to extract semantically meaningful parameters from a single monocular input image. For the first time, a CNN encoder and an expert-designed generative model can be trained end-to-end in an unsupervised manner, which renders training on very large (unlabeled) real world data feasible. The obtained reconstructions compare favorably to current state-of-the-art approaches in terms of quality and richness of representation.