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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Most of the existing audio-driven 3D facial animation methods suffered fromthe lack of detailed facial expression and head pose, resulting inunsatisfactory experience of human-robot interaction. In this paper, a novelpose-controllable 3D facial animation synthesis method is proposed by utilizinghierarchical audio-vertex attention. To synthesize real and detailedexpression, a hierarchical decomposition strategy is proposed to encode theaudio signal into both a global latent feature and a local vertex-wise controlfeature. Then the local and global audio features combined with vertex spatialfeatures are used to predict the final consistent facial animation via a graphconvolutional neural network by fusing the intrinsic spatial topology structureof the face model and the corresponding semantic feature of the audio. Toaccomplish pose-controllable animation, we introduce a novel pose attributeaugmentation method by utilizing the 2D talking face technique. Experimentalresults indicate that the proposed method can produce more realistic facialexpressions and head posture movements. Qualitative and quantitativeexperiments show that the proposed method achieves competitive performanceagainst state-of-the-art methods.

Pose-Controllable 3D Facial Animation Synthesis using Hierarchical Audio-Vertex Attention