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 detector based on Hough voting achieves great success and derivesmany follow-up works. Despite constantly refreshing the detection accuracy,these works suffer from handcrafted components used to eliminate redundantboxes, and thus are non-end-to-end and time-consuming. In this work, we proposea suppress-and-refine framework to remove these handcrafted components. Tofully utilize full-resolution information and achieve real-time speed, itdirectly consumes feature points and redundant 3D proposals. Specifically, itfirst suppresses noisy 3D feature points and then feeds them to 3D proposalsfor the following RoI-aware refinement. With the gating mechanism to build fineproposal features and the self-attention mechanism to model relationships, ourmethod can produce high-quality predictions with a small computation budget inan end-to-end manner. To this end, we present the first fully end-to-end 3Ddetector, SRDet, on the basis of VoteNet. It achieves state-of-the-artperformance on the challenging ScanNetV2 and SUN RGB-D datasets with thefastest speed ever. Our code will be available athttps://github.com/ZJULearning/SRDet.

Suppress-and-Refine Framework for End-to-End 3D Object Detection