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

Most existing point cloud based 3D object detectors focus on the tasks ofclassification and box regression. However, another bottleneck in this area isachieving an accurate detection confidence for the Non-Maximum Suppression(NMS) post-processing. In this paper, we add a 3D IoU prediction branch to theregular classification and regression branches. The predicted IoU is used asthe detection confidence for NMS. In order to obtain a more accurate IoUprediction, we propose a 3D IoU-Net with IoU sensitive feature learning and anIoU alignment operation. To obtain a perspective-invariant prediction head, wepropose an Attentive Corner Aggregation (ACA) module by aggregating a localpoint cloud feature from each perspective of eight corners and adaptivelyweighting the contribution of each perspective with different attentions. Wepropose a Corner Geometry Encoding (CGE) module for geometry informationembedding. To the best of our knowledge, this is the first time geometricembedding information has been introduced in proposal feature learning. Thesetwo feature parts are then adaptively fused by a multi-layer perceptron (MLP)network as our IoU sensitive feature. The IoU alignment operation is introducedto resolve the mismatching between the bounding box regression head and IoUprediction, thereby further enhancing the accuracy of IoU prediction. Theexperimental results on the KITTI car detection benchmark show that 3D IoU-Netwith IoU perception achieves state-of-the-art performance.

3D IoU-Net: IoU Guided 3D Object Detector for Point Clouds