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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Monocular 3D object detection has attracted great attention for itsadvantages in simplicity and cost. Due to the ill-posed 2D to 3D mappingessence from the monocular imaging process, monocular 3D object detectionsuffers from inaccurate depth estimation and thus has poor 3D detectionresults. To alleviate this problem, we propose to introduce the ground plane asa prior in the monocular 3d object detection. The ground plane prior serves asan additional geometric condition to the ill-posed mapping and an extra sourcein depth estimation. In this way, we can get a more accurate depth estimationfrom the ground. Meanwhile, to take full advantage of the ground plane prior,we propose a depth-align training strategy and a precise two-stage depthinference method tailored for the ground plane prior. It is worth noting thatthe introduced ground plane prior requires no extra data sources like LiDAR,stereo images, and depth information. Extensive experiments on the KITTIbenchmark show that our method could achieve state-of-the-art results comparedwith other methods while maintaining a very fast speed. Our code and models areavailable at https://github.com/cfzd/MonoGround.

MonoGround: Detecting Monocular 3D Objects from the Ground