LiDAR depth maps provide environmental guidance in a variety of applications. However, such depth maps are typically sparse and insufficient for complex tasks such as autonomous navigation. State of the art methods use image guided neural networks for dense depth completion. We develop a guided convolutional neural network focusing on gathering dense and valid information from sparse depth maps. To this end, we introduce a novel layer with spatially variant and content-depended dilation to include additional data from sparse input. Furthermore, we propose a sparsity invariant residual bottleneck block. We evaluate our Dense Validity Mask Network (DVMN) on the KITTI depth completion benchmark and achieve state of the art results. At the time of submission, our network is the leading method using sparsity invariant convolution.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    DVMN: Dense Validity Mask Network for Depth Completion


    Contributors:


    Publication date :

    2021-09-19


    Size :

    2232703 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Sparse Auxiliary Network for Depth Completion

    GUIZILINI VITOR / AMBRUS RARES A / GAIDON ADRIEN DAVID | European Patent Office | 2022

    Free access

    Sparse auxiliary network for depth completion

    GUIZILINI VITOR / AMBRUS RARES A / GAIDON ADRIEN DAVID | European Patent Office | 2023

    Free access

    DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth Completion

    Shivakumar, Shreyas S. / Nguyen, Ty / Miller, Ian D. et al. | IEEE | 2019


    Construct validity of the Miner Sentence Completion Scale

    Carson, Kenneth P. | Online Contents | 1993


    Deterministic Guided LiDAR Depth Map Completion

    Krauss, Bryan / Schroeder, Gregory / Gustke, Marko et al. | IEEE | 2021