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

Fast generation of high-quality 3D digital humans is important to a vastnumber of applications ranging from entertainment to professional concerns.Recent advances in differentiable rendering have enabled the training of 3Dgenerative models without requiring 3D ground truths. However, the quality ofthe generated 3D humans still has much room to improve in terms of bothfidelity and diversity. In this paper, we present Get3DHuman, a novel 3D humanframework that can significantly boost the realism and diversity of thegenerated outcomes by only using a limited budget of 3D ground-truth data. Ourkey observation is that the 3D generator can profit from human-related priorslearned through 2D human generators and 3D reconstructors. Specifically, webridge the latent space of Get3DHuman with that of StyleGAN-Human via aspecially-designed prior network, where the input latent code is mapped to theshape and texture feature volumes spanned by the pixel-aligned 3Dreconstructor. The outcomes of the prior network are then leveraged as thesupervisory signals for the main generator network. To ensure effectivetraining, we further propose three tailored losses applied to the generatedfeature volumes and the intermediate feature maps. Extensive experimentsdemonstrate that Get3DHuman greatly outperforms the other state-of-the-artapproaches and can support a wide range of applications including shapeinterpolation, shape re-texturing, and single-view reconstruction throughlatent inversion.

Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priors