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

Open-world Instance Segmentation (OIS) is a challenging task that aims toaccurately segment every object instance appearing in the current observation,regardless of whether these instances have been labeled in the training set.This is important for safety-critical applications such as robust autonomousnavigation. In this paper, we present a flexible and effective OIS frameworkfor LiDAR point cloud that can accurately segment both known and unknowninstances (i.e., seen and unseen instance categories during training). It firstidentifies points belonging to known classes and removes the background byleveraging close-set panoptic segmentation networks. Then, we propose a novelellipsoidal clustering method that is more adapted to the characteristic ofLiDAR scans and allows precise segmentation of unknown instances. Furthermore,a diffuse searching method is proposed to handle the common over-segmentationproblem presented in the known instances. With the combination of thesetechniques, we are able to achieve accurate segmentation for both known andunknown instances. We evaluated our method on the SemanticKITTI open-worldLiDAR instance segmentation dataset. The experimental results suggest that itoutperforms current state-of-the-art methods, especially with a 10.0%improvement in association quality. The source code of our method will bepublicly available at https://github.com/nubot-nudt/ElC-OIS.

ElC-OIS: Ellipsoidal Clustering for Open-World Instance Segmentation on LiDAR Data