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 CrossHuman, a novel method that learns cross-guidance fromparametric human model and multi-frame RGB images to achieve high-quality 3Dhuman reconstruction. To recover geometry details and texture even in invisibleregions, we design a reconstruction pipeline combined with tracking-basedmethods and tracking-free methods. Given a monocular RGB sequence, we track theparametric human model in the whole sequence, the points (voxels) correspondingto the target frame are warped to reference frames by the parametric bodymotion. Guided by the geometry priors of the parametric body and spatiallyaligned features from RGB sequence, the robust implicit surface is fused.Moreover, a multi-frame transformer (MFT) and a self-supervised warp refinementmodule are integrated to the framework to relax the requirements of parametricbody and help to deal with very loose cloth. Compared with previous works, ourCrossHuman enables high-fidelity geometry details and texture in both visibleand invisible regions and improves the accuracy of the human reconstructioneven under estimated inaccurate parametric human models. The experimentsdemonstrate that our method achieves state-of-the-art (SOTA) performance.

CrossHuman: Learning Cross-Guidance from Multi-Frame Images for Human Reconstruction