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

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 serv...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings / IEEE International Conference on Computer Vision S. 3735 - 3744
Hauptverfasser: Tewari, Ayush, Zollhofer, Michael, Hyeongwoo Kim, Garrido, Pablo, Bernard, Florian, Perez, Patrick, Theobalt, Christian
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.10.2017
Schlagworte:
Decoding
Face
Image reconstruction
Lighting
Semantics
Shape
Three-dimensional displays
ISSN:2380-7504
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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 the 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.
ISSN:2380-7504
DOI:10.1109/ICCV.2017.401