Neural Radiance Field (NeRF) has emerged as a groundbreaking method for synthesizing novel views, gaining great popularity in the autonomous driving (AD) community for rendering photorealistic driving scenarios. However, the application of NeRF in AD is hindered by its limitations in processing sensor data from vehicles with free movements, particularly due to the lack of surface geometry details and sparse viewpoints. Thus, this paper proposes a grid-based NeRF method that integrates geometry-enhanced priors to reconstruct realistic unbounded AD scenarios from real-world data. Perspective-warped hash grids are introduced to represent unbounded scenes captured from free trajectories. For accurate surface representation, we introduce the Signed Distance Function (SDF) to extract unbiased density expression. To achieve better representation under sparse viewpoints, we additionally employ monocular priors to constrain sample depths and the gradients of SDF field. We conduct experiments on KITTI, Freedataset, and a self-collected urban road dataset. Results indicate that our method outperforms state-of-the-art approaches in AD scenarios in terms of reconstruction quality and robustness.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    GeRAD: Geometry-Aware Neural Implicit Surface Rendering for Autonomous Driving


    Contributors:
    Xin, Chaoyin (author) / Xie, Wende (author) / Wang, Yafei (author) / Li, Zexing (author) / Wang, Bowen (author) / Shi, Hongyang (author)


    Publication date :

    2024-09-24


    Size :

    5662970 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Waelzschleifen von gerad- und schraegverzahnten Stirnraedern

    Rabel,Z. / Toth,I. / Csepel,HU | Automotive engineering | 1982


    Werkzeugauslegung zum Kaltwalzen von Gerad-Zahnraedern

    Koenig,W. / Weck,M. / Bartsch,G. | Automotive engineering | 1984


    Implicit Scene Context-Aware Interactive Trajectory Prediction for Autonomous Driving

    Lan, Wenxing / Li, Dachuan / Hao, Qi et al. | IEEE | 2024


    Belastungsgrenzen bei gerad- und schrägverzahnten Stirnrädern

    Weber, Constantin | GWLB - Gottfried Wilhelm Leibniz Bibliothek | 1952


    Messen und Auswerten gerad- und schraegverzahnter Stirnraeder auf Mehrkoordinaten-Messgeraeten

    Lotze,W. / Kossler,A. / Tech.Univ.Dresden,Bereich Fertig.-Messtech. | Automotive engineering | 1983