TBIOMHead2Head_Deep_Facial_Attributes_Re-Targeting_overleaf.pdf (16.72 MB)
Head2Head++: deep facial attributes re-targeting
journal contribution
posted on 2023-06-10, 01:53 authored by Michail Christos Doukas, Mohammad Rami Koujan, Viktoriia SharmanskaViktoriia Sharmanska, Anastasios Roussos, Stefanos ZafeiriouFacial video re-targeting is a challenging problem aiming to modify the facial attributes of a target subject in a seamless manner by a driving monocular sequence. We leverage the 3D geometry of faces and Generative Adversarial Networks (GANs) to design a novel deep learning architecture for the task of facial and head reenactment. Our method is different to purely 3D model-based approaches, or recent image-based methods that use Deep Convolutional Neural Networks (DCNNs) to generate individual frames. We manage to capture the complex non-rigid facial motion from the driving monocular performances and synthesise temporally consistent videos, with the aid of a sequential Generator and an ad-hoc Dynamics Discriminator network. We conduct a comprehensive set of quantitative and qualitative tests and demonstrate experimentally that our proposed method can successfully transfer facial expressions, head pose and eye gaze from a source video to a target subject, in a photo-realistic and faithful fashion, better than other state-of-the-art methods. Most importantly, our system performs end-to-end reenactment in nearly real-time speed (18 fps).
History
Publication status
- Published
File Version
- Accepted version
Journal
IEEE Transactions on Biometrics, Behavior, and Identity ScienceISSN
2637-6407Publisher
Institute of Electrical and Electronics EngineersExternal DOI
Issue
1Volume
3Page range
31-43Department affiliated with
- Informatics Publications
Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2021-11-30First Open Access (FOA) Date
2021-11-30First Compliant Deposit (FCD) Date
2021-11-29Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC