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

Real-time monocular 3D reconstruction is a challenging problem that remainsunsolved. Although recent end-to-end methods have demonstrated promisingresults, tiny structures and geometric boundaries are hardly captured due totheir insufficient supervision neglecting spatial details and oversimplifiedfeature fusion ignoring temporal cues. To address the problems, we propose anend-to-end 3D reconstruction network SST, which utilizes Sparse estimatedpoints from visual SLAM system as additional Spatial guidance and fusesTemporal features via a novel cross-modal attention mechanism, achieving moredetailed reconstruction results. We propose a Local Spatial-Temporal Fusionmodule to exploit more informative spatial-temporal cues from multi-view colorinformation and sparse priors, as well a Global Spatial-Temporal Fusion moduleto refine the local TSDF volumes with the world-frame model from coarse tofine. Extensive experiments on ScanNet and 7-Scenes demonstrate that SSToutperforms all state-of-the-art competitors, whilst keeping a high inferencespeed at 59 FPS, enabling real-world applications with real-time requirements.

SST: Real-time End-to-end Monocular 3D Reconstruction via Sparse Spatial-Temporal Guidance