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

Collaborative 3D object detection, with its improved interaction advantageamong multiple agents, has been widely explored in autonomous driving. However,existing collaborative 3D object detectors in a fully supervised paradigmheavily rely on large-scale annotated 3D bounding boxes, which islabor-intensive and time-consuming. To tackle this issue, we propose a sparselysupervised collaborative 3D object detection framework SSC3OD, which onlyrequires each agent to randomly label one object in the scene. Specifically,this model consists of two novel components, i.e., the pillar-based maskedautoencoder (Pillar-MAE) and the instance mining module. The Pillar-MAE moduleaims to reason over high-level semantics in a self-supervised manner, and theinstance mining module generates high-quality pseudo labels for collaborativedetectors online. By introducing these simple yet effective mechanisms, theproposed SSC3OD can alleviate the adverse impacts of incomplete annotations. Wegenerate sparse labels based on collaborative perception datasets to evaluateour method. Extensive experiments on three large-scale datasets reveal that ourproposed SSC3OD can effectively improve the performance of sparsely supervisedcollaborative 3D object detectors.

SSC3OD: Sparsely Supervised Collaborative 3D Object Detection from LiDAR Point Clouds