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

3D Morphable Model (3DMM) based methods have achieved great success inrecovering 3D face shapes from single-view images. However, the facial texturesrecovered by such methods lack the fidelity as exhibited in the input images.Recent work demonstrates high-quality facial texture recovering with generativenetworks trained from a large-scale database of high-resolution UV maps of facetextures, which is hard to prepare and not publicly available. In this paper,we introduce a method to reconstruct 3D facial shapes with high-fidelitytextures from single-view images in-the-wild, without the need to capture alarge-scale face texture database. The main idea is to refine the initialtexture generated by a 3DMM based method with facial details from the inputimage. To this end, we propose to use graph convolutional networks toreconstruct the detailed colors for the mesh vertices instead of reconstructingthe UV map. Experiments show that our method can generate high-quality resultsand outperforms state-of-the-art methods in both qualitative and quantitativecomparisons.

Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networks