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

Single-view 3D object reconstruction has seen much progress, yet methodsstill struggle generalizing to novel shapes unseen during training. Commonapproaches predominantly rely on learned global shape priors and, hence,disregard detailed local observations. In this work, we address this issue bylearning a hierarchy of priors at different levels of locality from groundtruth input depth maps. We argue that exploiting local priors allows our methodto efficiently use input observations, thus improving generalization in visibleareas of novel shapes. At the same time, the combination of local and globalpriors enables meaningful hallucination of unobserved parts resulting inconsistent 3D shapes. We show that the hierarchical approach generalizes muchbetter than the global approach. It generalizes not only between differentinstances of a class but also across classes and to unseen arrangements ofobjects.

Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors