University of Sussex
Browse
Doukas_HeadGAN_One-Shot_Neural_Head_Synthesis_and_Editing_ICCV_2021_paper.pdf (9.28 MB)

HeadGAN: one-shot neural head synthesis and editing

Download (9.28 MB)
conference contribution
posted on 2023-06-10, 01:29 authored by Michail Christos Doukas, Stefanos Zafeiriou, Viktoriia SharmanskaViktoriia Sharmanska
Recent attempts to solve the problem of head reenactment using a single reference image have shown promising results. However, most of them either perform poorly in terms of photo-realism, or fail to meet the identity preservation problem, or do not fully transfer the driving pose and expression. We propose HeadGAN, a novel system that conditions synthesis on 3D face representations, which can be extracted from any driving video and adapted to the facial geometry of any reference image, disentangling identity from expression. We further improve mouth movements, by utilising audio features as a complementary input. The 3D face representation enables HeadGAN to be further used as an efficient method for compression and reconstruction and a tool for expression and pose editing.

History

Publication status

  • Published

File Version

  • Published version

Journal

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021

Publisher

Computer Vision Foundation

Page range

14398-14407

Event name

International Conference on Computer Vision (ICCV)

Event location

Virtual

Event type

conference

Event date

October 11 - 17 2021

Department affiliated with

  • Informatics Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2021-10-22

First Open Access (FOA) Date

2021-10-22

First Compliant Deposit (FCD) Date

2021-10-22

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC