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

Data augmentation is a key component of CNN based image recognition taskslike object detection. However, it is relatively less explored for 3D objectdetection. Many standard 2D object detection data augmentation techniques donot extend to 3D box. Extension of these data augmentations for 3D objectdetection requires adaptation of the 3D geometry of the input scene andsynthesis of new viewpoints. This requires accurate depth information of thescene which may not be always available. In this paper, we evaluate existing 2Ddata augmentations and propose two novel augmentations for monocular 3Ddetection without a requirement for novel view synthesis. We evaluate theseaugmentations on the RTM3D detection model firstly due to the shorter trainingtimes . We obtain a consistent improvement by 4% in the 3D AP (@IoU=0.7) forcars, ~1.8% scores 3D AP (@IoU=0.25) for pedestrians & cyclists, over thebaseline on KITTI car detection dataset. We also demonstrate a rigorousevaluation of the mAP scores by re-weighting them to take into account theclass imbalance in the KITTI validation dataset.

Exploring 2D Data Augmentation for 3D Monocular Object Detection