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

As a rising task, panoptic segmentation is faced with challenges in bothsemantic segmentation and instance segmentation. However, in terms of speed andaccuracy, existing LiDAR methods in the field are still limited. In this paper,we propose a fast and high-performance LiDAR-based framework, referred to asPanoptic-PHNet, with three attractive aspects: 1) We introduce a clusteringpseudo heatmap as a new paradigm, which, followed by a center grouping module,yields instance centers for efficient clustering without object-level learningtasks. 2) A knn-transformer module is proposed to model the interaction amongforeground points for accurate offset regression. 3) For backbone design, wefuse the fine-grained voxel features and the 2D Bird's Eye View (BEV) featureswith different receptive fields to utilize both detailed and globalinformation. Extensive experiments on both SemanticKITTI dataset and nuScenesdataset show that our Panoptic-PHNet surpasses state-of-the-art methods byremarkable margins with a real-time speed. We achieve the 1st place on thepublic leaderboard of SemanticKITTI and leading performance on the recentlyreleased leaderboard of nuScenes.

Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmap