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

Data and model are the undoubtable two supporting pillars for LiDAR objectdetection. However, data-centric works have fallen far behind compared with theever-growing list of fancy new models. In this work, we systematically studythe synthesis-based LiDAR data augmentation approach (so-called GT-Aug) whichoffers maxium controllability over generated data samples. We pinpoint the mainshortcoming of existing works is introducing unrealistic LiDAR scan patternsduring GT-Aug. In light of this finding, we propose Real-Aug, a synthesis-basedaugmentation method which prioritizes on generating realistic LiDAR scans. Ourmethod consists a reality-conforming scene composition module which handles thedetails of the composition and a real-synthesis mixing up training strategywhich gradually adapts the data distribution from synthetic data to the realone. To verify the effectiveness of our methods, we conduct extensive ablationstudies and validate the proposed Real-Aug on a wide combination of detectorsand datasets. We achieve a state-of-the-art 0.744 NDS and 0.702 mAP on nuScenestest set. The code shall be released soon.

Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection