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/

Zendy Plus

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

Zendy Tools

Zendy Open

In this report, we focus on reconstructing clothed humans in the canonicalspace given multiple views and poses of a human as the input. To achieve this,we utilize the geometric prior of the SMPLX model in the canonical space tolearn the implicit representation for geometry reconstruction. Based on theobservation that the topology between the posed mesh and the mesh in thecanonical space are consistent, we propose to learn latent codes on the posedmesh by leveraging multiple input images and then assign the latent codes tothe mesh in the canonical space. Specifically, we first leverage normal andgeometry networks to extract the feature vector for each vertex on the SMPLXmesh. Normal maps are adopted for better generalization to unseen imagescompared to 2D images. Then, features for each vertex on the posed mesh frommultiple images are integrated by MLPs. The integrated features acting as thelatent code are anchored to the SMPLX mesh in the canonical space. Finally,latent code for each 3D point is extracted and utilized to calculate the SDF.Our work for reconstructing the human shape on canonical pose achieves 3rdperformance on WCPA MVP-Human Body Challenge.

Pixel2ISDF: Implicit Signed Distance Fields based Human Body Model from Multi-view and Multi-pose Images