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 based on point clouds has become more and more popular.Some methods propose localizing 3D objects directly from raw point clouds toavoid information loss. However, these methods come with complex structures andsignificant computational overhead, limiting its broader application inreal-time scenarios. Some methods choose to transform the point cloud data intocompact tensors first and leverage off-the-shelf 2D detectors to propose 3Dobjects, which is much faster and achieves state-of-the-art results. However,because of the inconsistency between 2D and 3D data, we argue that theperformance of compact tensor-based 3D detectors is restricted if we use 2Ddetectors without corresponding modification. Specifically, the distribution ofpoint clouds is uneven, with most points gather on the boundary of objects,while detectors for 2D data always extract features evenly. Motivated by thisobservation, we propose DENse Feature Indicator (DENFI), a universal modulethat helps 3D detectors focus on the densest region of the point clouds in aboundary-aware manner. Moreover, DENFI is lightweight and guarantees real-timespeed when applied to 3D object detectors. Experiments on KITTI dataset showthat DENFI improves the performance of the baseline single-stage detectorremarkably, which achieves new state-of-the-art performance among previous 3Ddetectors, including both two-stage and multi-sensor fusion methods, in termsof mAP with a 34FPS detection speed.

Boundary-Aware Dense Feature Indicator for Single-Stage 3D Object Detection from Point Clouds