English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Speech-driven 3D facial animation aims to synthesize vivid facial animationsthat accurately synchronize with speech and match the unique speaking style.However, existing works primarily focus on achieving precise lipsynchronization while neglecting to model the subject-specific speaking style,often resulting in unrealistic facial animations. To the best of our knowledge,this work makes the first attempt to explore the coupled information betweenthe speaking style and the semantic content in facial motions. Specifically, weintroduce an innovative speaking style disentanglement method, which enablesarbitrary-subject speaking style encoding and leads to a more realisticsynthesis of speech-driven facial animations. Subsequently, we propose a novelframework called \textbf{Mimic} to learn disentangled representations of thespeaking style and content from facial motions by building two latent spacesfor style and content, respectively. Moreover, to facilitate disentangledrepresentation learning, we introduce four well-designed constraints: anauxiliary style classifier, an auxiliary inverse classifier, a contentcontrastive loss, and a pair of latent cycle losses, which can effectivelycontribute to the construction of the identity-related style space andsemantic-related content space. Extensive qualitative and quantitativeexperiments conducted on three publicly available datasets demonstrate that ourapproach outperforms state-of-the-art methods and is capable of capturingdiverse speaking styles for speech-driven 3D facial animation. The source codeand supplementary video are publicly available at:https://zeqing-wang.github.io/Mimic/

Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation