Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to reduce the dependence on labelled 3D training data by leveraging pre-training on large-scale unlabeled outdoor LiDAR point clouds using masked autoencoders (MAE). While existing masked point autoencoding methods mainly focus on small-scale indoor point clouds or pillar-based large-scale outdoor LiDAR data, our approach introduces a new self-supervised masked occupancy pre-training method called Occupancy-MAE, specifically designed for voxel-based large-scale outdoor LiDAR point clouds. Occupancy-MAE takes advantage of the gradually sparse voxel occupancy structure of outdoor LiDAR point clouds and incorporates a range-aware random masking strategy and a pretext task of occupancy prediction. By randomly masking voxels based on their distance to the LiDAR and predicting the masked occupancy structure of the entire 3D surrounding scene, Occupancy-MAE encourages the extraction of high-level semantic information to reconstruct the masked voxel using only a small number of visible voxels. Extensive experiments demonstrate the effectiveness of Occupancy-MAE across several downstream tasks. For 3D object detection, Occupancy-MAE reduces the labelled data required for car detection on the KITTI dataset by half and improves small object detection by approximately 2% in AP on the Waymo dataset. For 3D semantic segmentation, Occupancy-MAE outperforms training from scratch by around 2% in mIoU. For multi-object tracking, Occupancy-MAE enhances training from scratch by approximately 1% in terms of AMOTA and AMOTP.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Occupancy-MAE: Self-Supervised Pre-Training Large-Scale LiDAR Point Clouds With Masked Occupancy Autoencoders


    Beteiligte:
    Min, Chen (Autor:in) / Xiao, Liang (Autor:in) / Zhao, Dawei (Autor:in) / Nie, Yiming (Autor:in) / Dai, Bin (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.07.2024


    Format / Umfang :

    2985684 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Self-Supervised Occupancy Grid Map Completion for Automated Driving

    Stojcheski, Jugoslav / Nurnberg, Thomas / Ulrich, Michael et al. | IEEE | 2023


    Vehicle Occupancy Verification Utilizing Occupancy Confirmation

    PAPINEAU MICHEL / FELTHAM MARK | Europäisches Patentamt | 2021

    Freier Zugriff

    Vehicle occupancy verification utilizing occupancy confirmation

    PAPINEAU MICHEL / FELTHAM MARK | Europäisches Patentamt | 2023

    Freier Zugriff

    VEHICLE OCCUPANCY VERIFICATION UTILIZING OCCUPANCY CONFIRMATION

    PAPINEAU MICHAEL / FEITHAM MARK | Europäisches Patentamt | 2020

    Freier Zugriff

    VEHICLE OCCUPANCY VERIFICATION UTILIZING OCCUPANCY CONFIRMATION

    PAPINEAU MICHEL / FELTHAM MARK | Europäisches Patentamt | 2023

    Freier Zugriff