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

Neural fields have revolutionized the area of 3D reconstruction and novelview synthesis of rigid scenes. A key challenge in making such methodsapplicable to articulated objects, such as the human body, is to model thedeformation of 3D locations between the rest pose (a canonical space) and thedeformed space. We propose a new articulation module for neural fields,Fast-SNARF, which finds accurate correspondences between canonical space andposed space via iterative root finding. Fast-SNARF is a drop-in replacement infunctionality to our previous work, SNARF, while significantly improving itscomputational efficiency. We contribute several algorithmic and implementationimprovements over SNARF, yielding a speed-up of $150\times$. These improvementsinclude voxel-based correspondence search, pre-computing the linear blendskinning function, and an efficient software implementation with CUDA kernels.Fast-SNARF enables efficient and simultaneous optimization of shape andskinning weights given deformed observations without correspondences (e.g. 3Dmeshes). Because learning of deformation maps is a crucial component in many 3Dhuman avatar methods and since Fast-SNARF provides a computationally efficientsolution, we believe that this work represents a significant step towards thepractical creation of 3D virtual humans.

Fast-SNARF: A Fast Deformer for Articulated Neural Fields