DeepAI AI Chat
Log In Sign Up

Panoster: End-to-end Panoptic Segmentation of LiDAR Point Clouds

by   Stefano Gasperini, et al.
Technische Universität München

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 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 solution to identify instances. At inference time, this acts as a class-agnostic semantic segmentation, allowing Panoster to be fast, while outperforming prior methods in terms of accuracy. Additionally, we showcase how our approach can be flexibly and effectively applied on diverse existing semantic architectures to deliver panoptic predictions.


page 1

page 3


SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation

We introduce Similarity Group Proposal Network (SGPN), a simple and intu...

3D-BEVIS: Birds-Eye-View Instance Segmentation

Recent deep learning models achieve impressive results on 3D scene analy...

CPSeg: Cluster-free Panoptic Segmentation of 3D LiDAR Point Clouds

A fast and accurate panoptic segmentation system for LiDAR point clouds ...

A Benchmark for LiDAR-based Panoptic Segmentation based on KITTI

Panoptic segmentation is the recently introduced task that tackles seman...

Learning to Optimally Segment Point Clouds

We focus on the problem of class-agnostic instance segmentation of LiDAR...

Efficient 2D and 3D Facade Segmentation using Auto-Context

This paper introduces a fast and efficient segmentation technique for 2D...

AutoSweep: Recovering 3D Editable Objectsfrom a Single Photograph

This paper presents a fully automatic framework for extracting editable ...