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

We present RangeRCNN, a novel and effective 3D object detection frameworkbased on the range image representation. Most existing methods are voxel-basedor point-based. Though several optimizations have been introduced to ease thesparsity issue and speed up the running time, the two representations are stillcomputationally inefficient. Compared to them, the range image representationis dense and compact which can exploit powerful 2D convolution. Even so, therange image is not preferred in 3D object detection due to scale variation andocclusion. In this paper, we utilize the dilated residual block (DRB) to betteradapt different object scales and obtain a more flexible receptive field.Considering scale variation and occlusion, we propose the RV-PV-BEV (rangeview-point view-bird's eye view) module to transfer features from RV to BEV.The anchor is defined in BEV which avoids scale variation and occlusion.Neither RV nor BEV can provide enough information for height estimation;therefore, we propose a two-stage RCNN for better 3D detection performance. Theaforementioned point view not only serves as a bridge from RV to BEV but alsoprovides pointwise features for RCNN. Experiments show that RangeRCNN achievesstate-of-the-art performance on the KITTI dataset and the Waymo Open dataset,and provides more possibilities for real-time 3D object detection. We furtherintroduce and discuss the data augmentation strategy for the range image basedmethod, which will be very valuable for future research on range image.

RangeRCNN: Towards Fast and Accurate 3D Object Detection with Range Image Representation