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

This paper presents a real-time online vision framework to jointly recover anindoor scene's 3D structure and semantic label. Given noisy depth maps, acamera trajectory, and 2D semantic labels at train time, the proposed deepneural network based approach learns to fuse the depth over frames withsuitable semantic labels in the scene space. Our approach exploits the jointvolumetric representation of the depth and semantics in the scene feature spaceto solve this task. For a compelling online fusion of the semantic labels andgeometry in real-time, we introduce an efficient vortex pooling block whiledropping the use of routing network in online depth fusion to preservehigh-frequency surface details. We show that the context information providedby the semantics of the scene helps the depth fusion network learnnoise-resistant features. Not only that, it helps overcome the shortcomings ofthe current online depth fusion method in dealing with thin object structures,thickening artifacts, and false surfaces. Experimental evaluation on theReplica dataset shows that our approach can perform depth fusion at 37 and 10frames per second with an average reconstruction F-score of 88% and 91%,respectively, depending on the depth map resolution. Moreover, our model showsan average IoU score of 0.515 on the ScanNet 3D semantic benchmark leaderboard.

A Real-Time Online Learning Framework for Joint 3D Reconstruction and Semantic Segmentation of Indoor Scenes