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

3D object detection is a fundamental and challenging task for 3D sceneunderstanding, and the monocular-based methods can serve as an economicalalternative to the stereo-based or LiDAR-based methods. However, accuratelydetecting objects in the 3D space from a single image is extremely difficultdue to the lack of spatial cues. To mitigate this issue, we propose a simpleand effective scheme to introduce the spatial information from LiDAR signals tothe monocular 3D detectors, without introducing any extra cost in the inferencephase. In particular, we first project the LiDAR signals into the image planeand align them with the RGB images. After that, we use the resulting data totrain a 3D detector (LiDAR Net) with the same architecture as the baselinemodel. Finally, this LiDAR Net can serve as the teacher to transfer the learnedknowledge to the baseline model. Experimental results show that the proposedmethod can significantly boost the performance of the baseline model and ranksthe $1^{st}$ place among all monocular-based methods on the KITTI benchmark.Besides, extensive ablation studies are conducted, which further prove theeffectiveness of each part of our designs and illustrate what the baselinemodel has learned from the LiDAR Net. Our code will be released at\url{https://github.com/monster-ghost/MonoDistill}.

MonoDistill: Learning Spatial Features for Monocular 3D Object Detection