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/

Zendy Plus

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

Zendy Tools

Zendy Open

LIDAR point clouds and RGB-images are both extremely essential for 3D objectdetection. So many state-of-the-art 3D detection algorithms dedicate in fusingthese two types of data effectively. However, their fusion methods based onBirds Eye View (BEV) or voxel format are not accurate. In this paper, wepropose a novel fusion approach named Point-based Attentive Cont-convFusion(PACF) module, which fuses multi-sensor features directly on 3D points.Except for continuous convolution, we additionally add a Point-Pooling and anAttentive Aggregation to make the fused features more expressive. Moreover,based on the PACF module, we propose a 3D multi-sensor multi-task networkcalled Pointcloud-Image RCNN(PI-RCNN as brief), which handles the imagesegmentation and 3D object detection tasks. PI-RCNN employs a segmentationsub-network to extract full-resolution semantic feature maps from images andthen fuses the multi-sensor features via powerful PACF module. Beneficial fromthe effectiveness of the PACF module and the expressive semantic features fromthe segmentation module, PI-RCNN can improve much in 3D object detection. Wedemonstrate the effectiveness of the PACF module and PI-RCNN on the KITTI 3DDetection benchmark, and our method can achieve state-of-the-art on the metricof 3D AP.

PI-RCNN: An Efficient Multi-sensor 3D Object Detector with Point-based Attentive Cont-conv Fusion Module