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

Although human reconstruction typically results in human-specific avatars,recent 3D scene reconstruction techniques utilizing pixel-aligned features showpromise in generalizing to new scenes. Applying these techniques to humanavatar reconstruction can result in a volumetric avatar with generalizabilitybut limited animatability due to rendering only being possible for staticrepresentations. In this paper, we propose AniPixel, a novel animatable andgeneralizable human avatar reconstruction method that leverages pixel-alignedfeatures for body geometry prediction and RGB color blending. Technically, toalign the canonical space with the target space and the observation space, wepropose a bidirectional neural skinning field based on skeleton-drivendeformation to establish the target-to-canonical and canonical-to-observationcorrespondences. Then, we disentangle the canonical body geometry into anormalized neutral-sized body and a subject-specific residual for bettergeneralizability. As the geometry and appearance are closely related, weintroduce pixel-aligned features to facilitate the body geometry prediction anddetailed surface normals to reinforce the RGB color blending. We also devise apose-dependent and view direction-related shading module to represent the localillumination variance. Experiments show that AniPixel renders comparable novelviews while delivering better novel pose animation results thanstate-of-the-art methods.

AniPixel: Towards Animatable Pixel-Aligned Human Avatar