Dissertation presents a set of computer models and their application strategy for the completion of a three-dimensional object from a single imperfect depth sensor perspective. The proposed models can reconstruct the volume and surface of multiple complex and temporally morphing objects per frame from only a single noisy or otherwise distorted depth sensor frame input. Where the input can be captured by using either LiDAR or structured light depth sensors. With the application of unsupervised deep adversarial auto-refining neural networks the models have shown to be robust against various types of noise typically seen in real world depth sensors. This is because the novel adversarial-autorefinement branch first removes majority of the distortions in the depth map, making the input synthetic-like that can be later completed with missing features. Additionally, while the state-of-the-art robustness against noise and reconstruction quality has a great scientific importance, the conducted research has shown potential commercial applications such as robotics, autonomous vehicles and virtual reality due to their performance in terms of time being adequate for real-time applications.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Reconstruction algorithm of invisible sides of a 3D object for depth scanning systems ; 3D objekto nematomų zonų rekonstrukcijos algoritmas gylio skenavimo sistemoms



    Erscheinungsdatum :

    2022-04-22


    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Lithuanian , Englisch



    Klassifikation :

    DDC:    629