Open access
Author
Date
2019-09-28Type
- Master Thesis
ETH Bibliography
yes
Altmetrics
Abstract
To enable realistic shape (e.g. pose and expression) transfer, existing face reenactment methods rely on a set of target faces for learning subject-specific traits. However, in real-world scenario end-users often only have one target face at hand, rendering existing methods inapplicable. In this work, we bridge this gap by proposing a novel one-shot face reenactment learning framework. Our key insight is that the one-shot learner should be able to disentangle and compose appearance and shape information for effective modeling. Specifically, the target face appearance and the source face shape are first projected into latent spaces with their corresponding encoders. Then these two latent spaces are associated by learning a shared decoder that aggregates multi-level features to produce the final reenactment results. To further improve the synthesizing quality on mustache and hair regions, we additionally propose FusionNet which combines the strengths of our learned decoder and the traditional warping method. Extensive experiments show that our one-shot face reenactment system achieves superior transfer fidelity as well as identity preserving capability than alternatives. More remarkably, our approach trained with only one target image per subject achieves competitive results to those using a set of target images, demonstrating the practical merit of this work. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000367085Publication status
publishedPublisher
ETH Zurich, Department of Information Technology and Electrical EngineeringSubject
deep learning; adversarial learning; face synthesisOrganisational unit
09528 - Göksel, Orçun (ehemalig) / Göksel, Orçun (former)
Notes
The main content of this thesis is formulated as a paper 'One-shot Face Reenactment' accepted by BMVC 2019. The author of this thesis is the second author of the BMVC paper.More
Show all metadata
ETH Bibliography
yes
Altmetrics