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

At the heart of all automated driving systems is the ability to sense thesurroundings, e.g., through semantic segmentation of LiDAR sequences, whichexperienced a remarkable progress due to the release of large datasets such asSemanticKITTI and nuScenes-LidarSeg. While most previous works focus on sparsesegmentation of the LiDAR input, dense output masks provide self-driving carswith almost complete environment information. In this paper, we introduce MASS- a Multi-Attentional Semantic Segmentation model specifically built for densetop-view understanding of the driving scenes. Our framework operates on pillar-and occupancy features and comprises three attention-based building blocks: (1)a keypoint-driven graph attention, (2) an LSTM-based attention computed from avector embedding of the spatial input, and (3) a pillar-based attention,resulting in a dense 360-degree segmentation mask. With extensive experimentson both, SemanticKITTI and nuScenes-LidarSeg, we quantitatively demonstrate theeffectiveness of our model, outperforming the state of the art by 19.0% onSemanticKITTI and reaching 30.4% in mIoU on nuScenes-LidarSeg, where MASS isthe first work addressing the dense segmentation task. Furthermore, ourmulti-attention model is shown to be very effective for 3D object detectionvalidated on the KITTI-3D dataset, showcasing its high generalizability toother tasks related to 3D vision.

MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding