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

This paper aims at high-accuracy 3D object detection in autonomous drivingscenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion frameworkthat takes both LIDAR point cloud and RGB images as input and predicts oriented3D bounding boxes. We encode the sparse 3D point cloud with a compactmulti-view representation. The network is composed of two subnetworks: one for3D object proposal generation and another for multi-view feature fusion. Theproposal network generates 3D candidate boxes efficiently from the bird's eyeview representation of 3D point cloud. We design a deep fusion scheme tocombine region-wise features from multiple views and enable interactionsbetween intermediate layers of different paths. Experiments on the challengingKITTI benchmark show that our approach outperforms the state-of-the-art byaround 25% and 30% AP on the tasks of 3D localization and 3D detection. Inaddition, for 2D detection, our approach obtains 10.3% higher AP than thestate-of-the-art on the hard data among the LIDAR-based methods.

Multi-View 3D Object Detection Network for Autonomous Driving