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

Generating photo-realistic video portrait with arbitrary speech audio is acrucial problem in film-making and virtual reality. Recently, several worksexplore the usage of neural radiance field in this task to improve 3D realnessand image fidelity. However, the generalizability of previous NeRF-basedmethods to out-of-domain audio is limited by the small scale of training data.In this work, we propose GeneFace, a generalized and high-fidelity NeRF-basedtalking face generation method, which can generate natural resultscorresponding to various out-of-domain audio. Specifically, we learn avariaitional motion generator on a large lip-reading corpus, and introduce adomain adaptative post-net to calibrate the result. Moreover, we learn aNeRF-based renderer conditioned on the predicted facial motion. A head-awaretorso-NeRF is proposed to eliminate the head-torso separation problem.Extensive experiments show that our method achieves more generalized andhigh-fidelity talking face generation compared to previous methods.

GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis