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

This work focuses on the analysis that whether 3D face models can be learnedfrom only the speech inputs of speakers. Previous works for cross-modal facesynthesis study image generation from voices. However, image synthesis includesvariations such as hairstyles, backgrounds, and facial textures, that arearguably irrelevant to voice or without direct studies to show correlations. Weinstead investigate the ability to reconstruct 3D faces to concentrate on onlygeometry, which is more physiologically grounded. We propose both thesupervised learning and unsupervised learning frameworks. Especially wedemonstrate how unsupervised learning is possible in the absence of a directvoice-to-3D-face dataset under limited availability of 3D face scans when themodel is equipped with knowledge distillation. To evaluate the performance, wealso propose several metrics to measure the geometric fitness of two 3D facesbased on points, lines, and regions. We find that 3D face shapes can bereconstructed from voices. Experimental results suggest that 3D faces can bereconstructed from voices, and our method can improve the performance over thebaseline. The best performance gains (15% - 20%) on ear-to-ear distance ratiometric (ER) coincides with the intuition that one can roughly envision whethera speaker's face is overall wider or thinner only from a person's voice. Seeour project page for codes and data.

Voice2Mesh: Cross-Modal 3D Face Model Generation from Voices