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

Recent advances in 3D-aware GAN models have enabled the generation ofrealistic and controllable human body images. However, existing methods focuson the control of major body joints, neglecting the manipulation of expressiveattributes, such as facial expressions, jaw poses, hand poses, and so on. Inthis work, we present XAGen, the first 3D generative model for human avatarscapable of expressive control over body, face, and hands. To enhance thefidelity of small-scale regions like face and hands, we devise a multi-scaleand multi-part 3D representation that models fine details. Based on thisrepresentation, we propose a multi-part rendering technique that disentanglesthe synthesis of body, face, and hands to ease model training and enhancegeometric quality. Furthermore, we design multi-part discriminators thatevaluate the quality of the generated avatars with respect to their appearanceand fine-grained control capabilities. Experiments show that XAGen surpassesstate-of-the-art methods in terms of realism, diversity, and expressive controlabilities. Code and data will be made available athttps://showlab.github.io/xagen.

XAGen: 3D Expressive Human Avatars Generation