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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper presents a neural network based semantic plane detection methodutilizing polygon representations. The method can for example be used to solveroom layout estimations tasks. The method is built on, combines and furtherdevelops several different modules from previous research. The network takes anRGB image and estimates a wireframe as well as a feature space using anhourglass backbone. From these, line and junction features are sampled. Thelines and junctions are then represented as an undirected graph, from whichpolygon representations of the sought planes are obtained. Two differentmethods for this last step are investigated, where the most promising method isbuilt on a heterogeneous graph transformer. The final output is in all cases aprojection of the semantic planes in 2D. The methods are evaluated on theStructured 3D dataset and we investigate the performance both using sampled andestimated wireframes. The experiments show the potential of the graph-basedmethod by outperforming state of the art methods in Room Layout estimation inthe 2D metrics using synthetic wireframe detections.

Polygon Detection for Room Layout Estimation using Heterogeneous Graphs and Wireframes