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

We present a novel architecture for 3D object detection, M3DeTR, whichcombines different point cloud representations (raw, voxels, bird-eye view)with different feature scales based on multi-scale feature pyramids. M3DeTR isthe first approach that unifies multiple point cloud representations, featurescales, as well as models mutual relationships between point cloudssimultaneously using transformers. We perform extensive ablation experimentsthat highlight the benefits of fusing representation and scale, and modelingthe relationships. Our method achieves state-of-the-art performance on theKITTI 3D object detection dataset and Waymo Open Dataset. Results show thatM3DeTR improves the baseline significantly by 1.48% mAP for all classes onWaymo Open Dataset. In particular, our approach ranks 1st on the well-knownKITTI 3D Detection Benchmark for both car and cyclist classes, and ranks 1st onWaymo Open Dataset with single frame point cloud input. Our code is availableat: https://github.com/rayguan97/M3DETR.

M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers