Pseudo-LiDAR point cloud interpolation is a novel and challenging task in autonomous driving, which aims to address the frequency mismatching problem between a camera and a LiDAR. Previous works represent the 3D spatial motion relationship with a coarse 2D optical flow, and the quality of interpolated point clouds only depends on the supervision of depth maps. As a result, the generated point clouds suffer from inferior global distributions and local appearances. To solve the above problems, we propose a Pseudo-LiDAR point cloud interpolation network to generate temporally and spatially high-quality point cloud sequences. By exploiting the scene flow from point clouds, the proposed network is able to learn a more accurate representation of the 3D spatial motion relationship. For a more comprehensive perception of the distribution of a point cloud, we design a novel reconstruction loss function with the chamfer distance to supervise the generation of Pseudo-LiDAR point clouds in 3D space. In addition, we introduce a multi-modal deep aggregation module to facilitate the efficient fusion of texture and depth features. As the benefits of the improved motion representation, training loss function, and model structure, our approach gains significant improvements on the Pseudo-LiDAR point cloud interpolation task. The experimental results evaluated on KITTI dataset demonstrate the state-of-the-art quantitative and qualitative performance of the proposed network.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Pseudo-LiDAR Point Cloud Interpolation Based on 3D Motion Representation and Spatial Supervision


    Beteiligte:
    Liu, Haojie (Autor:in) / Liao, Kang (Autor:in) / Lin, Chunyu (Autor:in) / Zhao, Yao (Autor:in) / Guo, Yulan (Autor:in)


    Erscheinungsdatum :

    2022-07-01


    Format / Umfang :

    3288564 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Monocular Pseudo-LiDAR Point Cloud Extrapolation Based on Iterative Hybrid Rendering

    Zhang, Chunlan / Lin, Chunyu / Liao, Kang et al. | IEEE | 2023


    Efficient 3D Object Detection Based on Pseudo-LiDAR Representation

    Meng, Haitao / Li, Changcai / Chen, Gang et al. | IEEE | 2024


    PSEUDO LIDAR

    SHAAG NADAV / NEUHOF DAVID / MOSKOWITZ JEFFREY et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Pseudo lidar

    SPRINGER OFER / NEUHOF DAVID / MOSKOWITZ JEFFREY et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    3D LiDAR Point Cloud Processing Algorithms

    Bondy, Bradford Scott | BASE | 2020

    Freier Zugriff