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

Depth perception is a crucial component of monoc-ular 3D detection tasks thattypically involve ill-posed problems. In light of the success of sample miningtechniques in 2D object detection, we propose a simple yet effective miningstrategy for improving depth perception in 3D object detection. Concretely, weintroduce a plain metric to evaluate the quality of depth predictions, whichchooses the mined sample for the model. Moreover, we propose a Gradient-awareand Model-perceive Mining strategy (GMM) for depth learning, which exploits thepredicted depth quality for better depth learning through easy mining. GMM is ageneral strategy that can be readily applied to several state-of-the-artmonocular 3D detectors, improving the accuracy of depth prediction. Extensiveexperiments on the nuScenes dataset demonstrate that the proposed methodssignificantly improve the performance of 3D object detection whileoutperforming other state-of-the-art sample mining techniques by a considerablemargin. On the nuScenes benchmark, GMM achieved the state-of-the-art (42.1% mAPand 47.3% NDS) performance in monocular object detection.

GMM: Delving into Gradient Aware and Model Perceive Depth Mining for Monocular 3D Detection