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

Monocular 3D object detection is a fundamental but very important task tomany applications including autonomous driving, robotic grasping and augmentedreality. Existing leading methods tend to estimate the depth of the input imagefirst, and detect the 3D object based on point cloud. This routine suffers fromthe inherent gap between depth estimation and object detection. Besides, theprediction error accumulation would also affect the performance. In this paper,a novel method named MonoSIM is proposed. The insight behind introducingMonoSIM is that we propose to simulate the feature learning behaviors of apoint cloud based detector for monocular detector during the training period.Hence, during inference period, the learned features and prediction would besimilar to the point cloud based detector as possible. To achieve it, wepropose one scene-level simulation module, one RoI-level simulation module andone response-level simulation module, which are progressively used for thedetector's full feature learning and prediction pipeline. We apply our methodto the famous M3D-RPN detector and CaDDN detector, conducting extensiveexperiments on KITTI and Waymo Open datasets. Results show that our methodconsistently improves the performance of different monocular detectors for alarge margin without changing their network architectures. Our codes will bepublicly available athttps://github.com/sunh18/MonoSIM}{https://github.com/sunh18/MonoSIM.

MonoSIM: Simulating Learning Behaviors of Heterogeneous Point Cloud Object Detectors for Monocular 3D Object Detection