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

We propose a robust and accurate non-parametric method for single-view 3Dface reconstruction (SVFR). While tremendous efforts have been devoted toparametric SVFR, a visible gap still lies between the result 3D shape and theground truth. We believe there are two major obstacles: 1) the representationof the parametric model is limited to a certain face database; 2) 2D images and3D shapes in the fitted datasets are distinctly misaligned. To resolve theseissues, a large-scale pseudo 2D\&3D dataset is created by first rendering thedetailed 3D faces, then swapping the face in the wild images with the renderedface. These pseudo 2D&3D pairs are created from publicly available datasetswhich eliminate the gaps between 2D and 3D data while covering diverseappearances, poses, scenes, and illumination. We further propose anon-parametric scheme to learn a well-generalized SVFR model from the createddataset, and the proposed hierarchical signed distance function turns out to beeffective in predicting middle-scale and small-scale 3D facial geometry. Ourmodel outperforms previous methods on FaceScape-wild/lab and MICC benchmarksand is well generalized to various appearances, poses, expressions, andin-the-wild environments. The code is released athttp://github.com/zhuhao-nju/rafare .

RAFaRe: Learning Robust and Accurate Non-parametric 3D Face Reconstruction from Pseudo 2D&3D Pairs