Snow corrupts LiDAR point clouds with scattered noise points and false objects, posing a serious threat to the perception of autonomous driving systems. Existing effective point cloud de-snow methods are mainly based on outlier filters that rigidly remove isolated points. There are deep-learning and algorithm-based weather models that can handle adverse conditions such as rain and fog, but snow conditions are rarely considered. In this study, we propose a LiDAR point cloud translation model based on refined generative adversarial networks (GANs) that is not only able to de-noise snow in point clouds but also to generate fake snow points on clear data. Our model is trained on depth image representations of point clouds from unpaired datasets, with a customized loss function for grayscale depth images that can maintain scale consistency. A pixel-wise discriminator structure is designed to improve the de-snowing effect around the ego vehicle. The proposed model expresses a better feature capture on snow in LiDAR point clouds, and experiment results show high-quality snow removal performance on both the scattered and clustered snow points, as well as satisfactory fake snow generation on clear road point clouds.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    LiDAR Point Cloud Translation Between Snow and Clear Conditions Using Depth Images and GANs


    Contributors:
    Zhang, Yuxiao (author) / Ding, Ming (author) / Yang, Hanting (author) / Niu, Yingjie (author) / Feng, Yan (author) / Ge, Maoning (author) / Carballo, Alexander (author) / Takeda, Kazuya (author)


    Publication date :

    2023-06-04


    Size :

    10754187 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Synthesizing Realistic Snow Effects in Driving Images Using GANs and Real Data with Semantic Guidance*

    Yang, Hanting / Ding, Ming / Carballo, Alexander et al. | IEEE | 2023


    IMPROVING LIDAR POINT CLOUD SEGMENTATION USING BOX PREDICTION

    ZHOU LUBING / MENG XIAOLI / SHETTI KARAN RAJENDRA | European Patent Office | 2024

    Free access

    IMPROVING LIDAR POINT CLOUD SEGMENTATION USING BOX PREDICTION

    ZHOU LUBING / MENG XIAOLI / SHETTI KARAN RAJENDRA | European Patent Office | 2022

    Free access

    3D LiDAR Point Cloud Processing Algorithms

    Bondy, Bradford Scott | BASE | 2020

    Free access

    Snow Scoop Helps Clear Rear of Plow

    Madden, B. | British Library Online Contents | 1994