홈 › Papers

4D Panoptic LiDAR Segmentation

2021-02-24 · CVPR 2021 1 · Mehmet Aygün, Aljoša Ošep, Mark Weber, Maxim Maximov, Cyrill Stachniss, Jens Behley, Laura Leal-Taixé

Temporal semantic scene understanding is critical for self-driving cars or robots operating in dynamic environments. In this paper, we propose 4D panoptic LiDAR segmentation to assign a semantic class and a temporally-consistent instance ID to a sequence of 3D points. To this end, we present an approach and a point-centric evaluation metric. Our approach determines a semantic class for every point while modeling object instances as probability distributions in the 4D spatio-temporal domain. We process multiple point clouds in parallel and resolve point-to-instance associations, effectively alleviating the need for explicit temporal data association. Inspired by recent advances in benchmarking of multi-object tracking, we propose to adopt a new evaluation metric that separates the semantic and point-to-instance association aspects of the task. With this work, we aim at paving the road for future developments of temporal LiDAR panoptic perception.

📄 PDF Abstract BibTeX arXiv:2102.12472

Code (1)

mehmetaygun/4d-pls 공식 구현 pytorch

Tasks

4D Panoptic Segmentation Benchmarking Multi-Object Tracking Object Tracking Scene Understanding SegmentationSelf-Driving Cars

Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation

2021-03-27 · CVPR 2021 1 · Zixiang Zhou, Yang Zhang, Hassan Foroosh

Panoptic segmentation presents a new challenge in exploiting the merits of both detection and segmentation, with the aim of unifying instance segmentation and semantic segmentation in a single framework. However, an effi…

Clustering Instance Segmentation Panoptic Segmentation Segmentation+1

LidarMultiNet: Unifying LiDAR Semantic Segmentation, 3D Object Detection, and Panoptic Segmentation in a Single Multi-task Network

2022-06-23 · Dongqiangzi Ye, Weijia Chen, Zixiang Zhou, Yufei Xie 외

This technical report presents the 1st place winning solution for the Waymo Open Dataset 3D semantic segmentation challenge 2022. Our network, termed LidarMultiNet, unifies the major LiDAR perception tasks such as 3D sem…

3D Object Detection 3D Semantic Segmentation Decoder LIDAR Semantic Segmentation+5

Label-Efficient LiDAR Panoptic Segmentation

2025-03-04 · Ahmet Selim Çanakçı, Niclas Vödisch, Kürsat Petek, Wolfram Burgard 외

A main bottleneck of learning-based robotic scene understanding methods is the heavy reliance on extensive annotated training data, which often limits their generalization ability. In LiDAR panoptic segmentation, this ch…

Instance Segmentation Panoptic Segmentation Scene Understanding Segmentation+1

LiDAR-Camera Fusion for Video Panoptic Segmentation without Video Training

2024-12-30 · Fardin Ayar, Ehsan Javanmardi, Manabu Tsukada, Mahdi Javanmardi 외

Panoptic segmentation, which combines instance and semantic segmentation, has gained a lot of attention in autonomous vehicles, due to its comprehensive representation of the scene. This task can be applied for cameras a…

Autonomous Vehicles Panoptic Segmentation Segmentation Semantic Segmentation+1

How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation

2025-05-25 · Yining Pan, Qiongjie Cui, Xulei Yang, Na Zhao

LiDAR-based 3D panoptic segmentation often struggles with the inherent sparsity of data from LiDAR sensors, which makes it challenging to accurately recognize distant or small objects. Recently, a few studies have sought…

3D Panoptic Segmentation Data Augmentation Decoder Panoptic Segmentation+1