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 propose DOPS, a fast single-stage 3D object detection method for LIDARdata. Previous methods often make domain-specific design decisions, for exampleprojecting points into a bird-eye view image in autonomous driving scenarios.In contrast, we propose a general-purpose method that works on both indoor andoutdoor scenes. The core novelty of our method is a fast, single-passarchitecture that both detects objects in 3D and estimates their shapes. 3Dbounding box parameters are estimated in one pass for every point, aggregatedthrough graph convolutions, and fed into a branch of the network that predictslatent codes representing the shape of each detected object. The latent shapespace and shape decoder are learned on a synthetic dataset and then used assupervision for the end-to-end training of the 3D object detection pipeline.Thus our model is able to extract shapes without access to ground-truth shapeinformation in the target dataset. During experiments, we find that ourproposed method achieves state-of-the-art results by ~5% on object detection inScanNet scenes, and it gets top results by 3.4% in the Waymo Open Dataset,while reproducing the shapes of detected cars.

DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes