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

Instance shape reconstruction from a 3D scene involves recovering the fullgeometries of multiple objects at the semantic instance level. Many methodsleverage data-driven learning due to the intricacies of scene complexity andsignificant indoor occlusions. Training these methods often requires alarge-scale, high-quality dataset with aligned and paired shape annotationswith real-world scans. Existing datasets are either synthetic or misaligned,restricting the performance of data-driven methods on real data. To this end,we introduce LASA, a Large-scale Aligned Shape Annotation Dataset comprising10,412 high-quality CAD annotations aligned with 920 real-world scene scansfrom ArkitScenes, created manually by professional artists. On this top, wepropose a novel Diffusion-based Cross-Modal Shape Reconstruction (DisCo)method. It is empowered by a hybrid feature aggregation design to fusemulti-modal inputs and recover high-fidelity object geometries. Besides, wepresent an Occupancy-Guided 3D Object Detection (OccGOD) method and demonstratethat our shape annotations provide scene occupancy clues that can furtherimprove 3D object detection. Supported by LASA, extensive experiments show thatour methods achieve state-of-the-art performance in both instance-level scenereconstruction and 3D object detection tasks.

LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset