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 has been widely explored, with applicationsin gaming, character animation, virtual reality, and telepresence systems.State-of-the-art methods deform the face topology of the target actor to syncthe input audio without considering the identity-specific speaking style andfacial idiosyncrasies of the target actor, thus, resulting in unrealistic andinaccurate lip movements. To address this, we present Imitator, a speech-drivenfacial expression synthesis method, which learns identity-specific details froma short input video and produces novel facial expressions matching theidentity-specific speaking style and facial idiosyncrasies of the target actor.Specifically, we train a style-agnostic transformer on a large facialexpression dataset which we use as a prior for audio-driven facial expressions.Based on this prior, we optimize for identity-specific speaking style based ona short reference video. To train the prior, we introduce a novel loss functionbased on detected bilabial consonants to ensure plausible lip closures andconsequently improve the realism of the generated expressions. Through detailedexperiments and a user study, we show that our approach produces temporallycoherent facial expressions from input audio while preserving the speakingstyle of the target actors.

Imitator: Personalized Speech-driven 3D Facial Animation