In this paper we propose a convolutional neural network that is designed to upsample a series of sparse range measurements based on the contextual cues gleaned from a high resolution intensity image. Our approach draws inspiration from related work on super-resolution and in-painting. We propose a novel architecture that seeks to pull contextual cues separately from the intensity image and the depth features and then fuse them later in the network. We argue that this approach effectively exploits the relationship between the two modalities and produces accurate results while respecting salient image structures. We present experimental results to demonstrate that our approach is comparable with state of the art methods and generalizes well across multiple datasets.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

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


    Beteiligte:
    Shivakumar, Shreyas S. (Autor:in) / Nguyen, Ty (Autor:in) / Miller, Ian D. (Autor:in) / Chen, Steven W. (Autor:in) / Kumar, Vijay (Autor:in) / Taylor, Camillo J. (Autor:in)


    Erscheinungsdatum :

    01.10.2019


    Format / Umfang :

    2643910 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Sparse auxiliary network for depth completion

    GUIZILINI VITOR / AMBRUS RARES A / GAIDON ADRIEN DAVID | Europäisches Patentamt | 2023

    Freier Zugriff

    Sparse Auxiliary Network for Depth Completion

    GUIZILINI VITOR / AMBRUS RARES A / GAIDON ADRIEN DAVID | Europäisches Patentamt | 2022

    Freier Zugriff

    Spacecraft Depth Completion Based on the Gray Image and the Sparse Depth Map

    Liu, Xiang / Wang, Hongyuan / Yan, Zhiqiang et al. | IEEE | 2023


    Spacecraft depth completion based on the gray image and the sparse depth map

    Liu, Xiang / Wang, Hongyuan / Yan, Zhiqiang et al. | ArXiv | 2022

    Freier Zugriff

    Deterministic Guided LiDAR Depth Map Completion

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