LiDAR-based 3D object detection and panoptic segmentation are two crucial tasks in the perception systems of autonomous vehicles and robots. In this paper, we propose All-in-One Perception Network (AOP-Net), a LiDAR-based multitask framework that combines 3D object detection and panoptic segmentation. In this method, a dual-task 3D backbone is developed to extract both panoptic- and detection-level features from the input LiDAR point cloud. Also, a new 2D backbone that intertwines Multi-Layer Perceptron (MLP) and convolution layers is designed to further improve the detection task performance. Finally, a novel module is proposed to guide the detection head by recovering useful features discarded during down-sampling operations in the 3D backbone. This module leverages estimated instance segmentation masks to recover detailed information from each candidate object. The AOP-Net achieves state-of-the-art performance for published works on the nuScenes benchmark for both 3D object detection and panoptic segmentation tasks. Also, experiments show that our method easily adapts to and significantly improves the performance of any BEV-based 3D object detection method.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    AOP-Net: All-in-One Perception Network for LiDAR-based Joint 3D Object Detection and Panoptic Segmentation


    Beteiligte:
    Xu, Yixuan (Autor:in) / Fazlali, Hamidreza (Autor:in) / Ren, Yuan (Autor:in) / Liu, Bingbing (Autor:in)


    Erscheinungsdatum :

    04.06.2023


    Format / Umfang :

    3176148 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    LiDAR-PDP: A LiDAR-Based Panoptic Dynamic Driving Environment Perception Algorithm

    Wang, Hai / Li, Jianguo / Cai, Yingfeng et al. | IEEE | 2025


    Location-Guided LiDAR-Based Panoptic Segmentation for Autonomous Driving

    Xian, Guozeng / Ji, Changyun / Zhou, Lin et al. | IEEE | 2023


    Panoptic segmentation method based on pixel-level instance perception

    Wu, Yuhao / Sun, Jun | British Library Conference Proceedings | 2022


    EFFICIENT TRANSFORMER-BASED PANOPTIC SEGMENTATION

    AICH ABHISHEK / SUH YUMIN / SCHULTER SAMUEL et al. | Europäisches Patentamt | 2025

    Freier Zugriff

    EFFICIENT TRANSFORMER-BASED PANOPTIC SEGMENTATION

    AICH ABHISHEK / SUH YUMIN / SCHULTER SAMUEL et al. | Europäisches Patentamt | 2025

    Freier Zugriff