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

被引:50
|
作者
Zhou, Zixiang [1 ]
Zhang, Yang [1 ,2 ]
Foroosh, Hassan [1 ]
机构
[1] Univ Cent Florida, Dept Comp Sci, Orlando, FL 32816 USA
[2] Waymo LLC, Mountain View, CA USA
关键词
D O I
10.1109/CVPR46437.2021.01299
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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 efficient solution for panoptic segmentation in the emerging domain of LiDAR point cloud is still an open research problem and is very much under-explored. In this paper, we present a fast and robust LiDAR point cloud panoptic segmentation framework, referred to as Panoptic-PolarNet. We learn both semantic segmentation and class-agnostic instance clustering in a single inference network using a polar Bird's Eye View (BEV) representation, enabling us to circumvent the issue of occlusion among instances in urban street scenes. To improve our network's learnability, we also propose an adapted instance augmentation technique and a novel adversarial point cloud pruning method. Our experiments show that Panoptic-PolarNet outperforms the baseline methods on SemanticKITTI and nuScenes datasets with an almost real-time inference speed. Panoptic-PolarNet achieved 54.1% PQ in the public SemanticKITTI panoptic segmentation leaderboard and leading performance for the validation set of nuScenes.
引用
收藏
页码:13189 / 13198
页数:10
相关论文
共 50 条
  • [1] Proposal-free Lidar Panoptic Segmentation with Pillar-level Affinity
    Chen, Qi
    Vora, Sourabh
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 4528 - 4535
  • [2] Perceiving the Invisible: Proposal-Free Amodal Panoptic Segmentation
    Mohan, Rohit
    Valada, Abhinav
    [J]. IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (04): : 9302 - 9309
  • [3] Reshaping the Semantic Logits for Proposal-free Panoptic Segmentation
    Lu, Tianqi
    Zhu, Chenyue
    [J]. 2022 IEEE 34TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2022, : 886 - 892
  • [4] Hierarchical Lovasz Embeddings for Proposal-free Panoptic Segmentation
    Kerola, Tommi
    Li, Jie
    Kanehira, Atsushi
    Kudo, Yasunori
    Vallet, Alexis
    Gaidon, Adrien
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 14408 - 14418
  • [5] Panoptic-DLA: Document Layout Analysis of Historical Newspapers Based on Proposal-Free Panoptic Segmentation Model
    Lu, Min
    Bao, Feilong
    Gao, Guanglai
    [J]. KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, KSEM 2021, PT II, 2021, 12816 : 176 - 190
  • [6] Prototype-Voxel Contrastive Learning for LiDAR Point Cloud Panoptic Segmentation
    Liu, Minzhe
    Zhou, Qiang
    Zhao, Hengshuang
    Li, Jianing
    Du, Yuan
    Keutzer, Kurt
    Du, Li
    Zhang, Shanghang
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA 2022, 2022, : 9243 - 9250
  • [7] Panoptic-FusionNet: Camera-LiDAR fusion-based point cloud panoptic segmentation for autonomous driving
    Song, Hamin
    Cho, Jieun
    Ha, Jinsu
    Park, Jaehyun
    Jo, Kichun
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2024, 251
  • [8] A Divide-and-Merge Point Cloud Clustering Algorithm for LiDAR Panoptic Segmentation
    Zhao, Yiming
    Zhang, Xiao
    Huang, Xinming
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA 2022, 2022, : 7029 - 7035
  • [9] PUPS: Point Cloud Unified Panoptic Segmentation
    Su, Shihao
    Xu, Jianyun
    Wang, Huanyu
    Miao, Zhenwei
    Zhan, Xin
    Hao, Dayang
    Li, Xi
    [J]. THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 2, 2023, : 2339 - 2347
  • [10] Federated Grouping Panoptic Segmentation for LiDAR Point Cloud based on Convolutional Network
    Shi, Chengzhang
    Own, Chung-Ming
    Zhou, Ruimin
    [J]. 2022 IEEE 34TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2022, : 6 - 13