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

3D object detection using LiDAR point clouds is a fundamental task in thefields of computer vision, robotics, and autonomous driving. However, existing3D detectors heavily rely on annotated datasets, which are both time-consumingand prone to errors during the process of labeling 3D bounding boxes. In thispaper, we propose a Scene Completion Pre-training (SCP) method to enhance theperformance of 3D object detectors with less labeled data. SCP offers three keyadvantages: (1) Improved initialization of the point cloud model. By completingthe scene point clouds, SCP effectively captures the spatial and semanticrelationships among objects within urban environments. (2) Elimination of theneed for additional datasets. SCP serves as a valuable auxiliary network thatdoes not impose any additional efforts or data requirements on the 3Ddetectors. (3) Reduction of the amount of labeled data for detection. With thehelp of SCP, the existing state-of-the-art 3D detectors can achieve comparableperformance while only relying on 20% labeled data.

SCP: Scene Completion Pre-training for 3D Object Detection