User: Guest  Login

Document type:
Zeitschriftenaufsatz 
Author(s):
Stefano Gasperini; Mohammad-Ali Nikouei Mahani; Alvaro Marcos-Ramiro; Nassir Navab; Federico Tombari 
Title:
Panoster: End-to-end Panoptic Segmentation of LiDAR Point Clouds 
Abstract:
Panoptic segmentation has recently unified semantic and instance segmentation, previously addressed separately, thus taking a step further towards creating more comprehensive and efficient perception systems. In this paper, we present Panoster, a novel proposal-free panoptic segmentation method for LiDAR point clouds. Unlike previous approaches relying on several steps to group pixels or points into objects, Panoster proposes a simplified framework incorporating a learning-based clustering solut...    »
 
Keywords:
panoptic segmentation; lidar; end-to-end; computer vision; autonomous driving 
Dewey Decimal Classification:
000 Informatik, Wissen, Systeme 
Journal title:
IEEE Robotics and Automation Letters (RA-L) 
Year:
2021 
Month:
Apr 
Reviewed:
ja 
Language:
en 
Status:
Verlagsversion / published