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 one of the most challenging tasks in 3Dscene understanding. Due to the ill-posed nature of monocular imagery, existingmonocular 3D detection methods highly rely on training with the manuallyannotated 3D box labels on the LiDAR point clouds. This annotation process isvery laborious and expensive. To dispense with the reliance on 3D box labels,in this paper we explore the weakly supervised monocular 3D detection.Specifically, we first detect 2D boxes on the image. Then, we adopt thegenerated 2D boxes to select corresponding RoI LiDAR points as the weaksupervision. Eventually, we adopt a network to predict 3D boxes which cantightly align with associated RoI LiDAR points. This network is learned byminimizing our newly-proposed 3D alignment loss between the 3D box estimatesand the corresponding RoI LiDAR points. We will illustrate the potentialchallenges of the above learning problem and resolve these challenges byintroducing several effective designs into our method. Codes will be availableat https://github.com/SPengLiang/WeakM3D.

WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection