Large-scale 3D scene reconstruction and novel view synthesis are vital for autonomous vehicles, especially utilizing temporally sparse LiDAR frames. However, conventional explicit representations remain a significant bottleneck towards representing the reconstructed and synthetic scenes at unlimited resolution. Although the recently developed neural radiance fields (NeRF) have shown compelling results in implicit representations, the problem of large-scale 3D scene reconstruction and novel view synthesis using sparse LiDAR frames remains unexplored. To bridge this gap, we propose a 3D scene reconstruction and novel view synthesis framework called parent-child neural radiance field (PC-NeRF). Based on its two modules, parent NeRF and child NeRF, the framework implements hierarchical spatial partitioning and multi-level scene representation, including scene, segment, and point levels. The multi-level scene representation enhances the efficient utilization of sparse LiDAR point cloud data and enables the rapid acquisition of an approximate volumetric scene representation. With extensive experiments, PC-NeRF is proven to achieve high-precision novel LiDAR view synthesis and 3D reconstruction in large-scale scenes. Moreover, PC-NeRF can effectively handle situations with sparse LiDAR frames and demonstrate high deployment efficiency with limited training epochs.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    PC-NeRF: Parent-Child Neural Radiance Fields Using Sparse LiDAR Frames in Autonomous Driving Environments


    Contributors:
    Hu, Xiuzhong (author) / Xiong, Guangming (author) / Zang, Zheng (author) / Jia, Peng (author) / Han, Yuxuan (author) / Ma, Junyi (author)

    Published in:

    Publication date :

    2024-10-01


    Size :

    9593876 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Spacecraft State Estimation Using Neural Radiance Fields

    Heintz, Aneesh M. / Peck, Mason | AIAA | 2023


    3D Mapping and Exploration Using Autonomous Robots and NeRF

    Prakash, Sudhanva Shimoga / Rajaram, Chinmayi / Umesh, Deepa et al. | Springer Verlag | 2024


    AUTONOMOUS DRIVING LIDAR TECHNOLOGY

    WANG PANQU / WANG YU / ZHAO XIANGCHEN et al. | European Patent Office | 2023

    Free access

    Enhanced Temporal Data Organization for LiDAR Data in Autonomous Driving Environments

    Kusenbach, Michael / Luettel, Thorsten / Wuensche, Hans-Joachim | IEEE | 2019


    ToF LiDAR for autonomous driving

    Wei, Wei | TIBKAT | 2023