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 solve object localisation in partial scenes, a new problem of estimatingthe unknown position of an object (e.g. where is the bag?) given a partial 3Dscan of a scene. The proposed solution is based on a novel scene graph model,the Spatial Commonsense Graph (SCG), where objects are the nodes and edgesdefine pairwise distances between them, enriched by concept nodes andrelationships from a commonsense knowledge base. This allows SCG to bettergeneralise its spatial inference over unknown 3D scenes. The SCG is used toestimate the unknown position of the target object in two steps: first, we feedthe SCG into a novel Proximity Prediction Network, a graph neural network thatuses attention to perform distance prediction between the node representing thetarget object and the nodes representing the observed objects in the SCG;second, we propose a Localisation Module based on circular intersection toestimate the object position using all the predicted pairwise distances inorder to be independent of any reference system. We create a new dataset ofpartially reconstructed scenes to benchmark our method and baselines for objectlocalisation in partial scenes, where our proposed method achieves the bestlocalisation performance.

Spatial Commonsense Graph for Object Localisation in Partial Scenes