Sökning: "Multi-view representations"

Hittade 4 uppsatser innehållade orden Multi-view representations.

  1. 1. Meta-Pseudo Labelled Multi-View 3D Shape Recognition

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Fehmi Ayberk Uçkun; [2023]
    Nyckelord :3D shape recognition; 3D object classification; 3D shape retrieval; 3D object retrieval; Automatic labelling; Semi-supervised learning; Pseudo labelling; Meta Pseudo Labelling; Multi-View Convolutional Neural Networks; Shape descriptors; Multi-view representations; Deeplearning; 3D-formigenkänning; 3D-objektklassificering; 3D-formhämtning; Hämtning av 3D-objekt; Automatisk märkning; Halv-vägledd lärning; Pseudomärkning; Meta Pseudo-märkning; Multi-View Faltningsnät; Formbeskrivningar; Multi-view representation; Djupinlärning;

    Sammanfattning : The field of computer vision has long pursued the challenge of understanding the three-dimensional world. This endeavour is further fuelled by the increasing demand for technologies that rely on accurate perception of the 3D environment such as autonomous driving and augmented reality. LÄS MER

  3. 2. Data association for object-based SLAM

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Kamil Kaminski; [2021]
    Nyckelord :;

    Sammanfattning : The thesis tackles the problem of data association for monocular object-based SLAM, which gets often omitted in related works. A method for estimatingellipsoid object landmark representations is implemented. LÄS MER

  4. 3. Data association for object-based SLAM

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Kamil Kaminski; [2020]
    Nyckelord :;

    Sammanfattning : The thesis tackles the problem of data association for monocular object-basedSLAM, which gets often omitted in related works. A method for estimating ellipsoid object landmark representations is implemented. LÄS MER

  5. 4. Human Grasp Synthesis with Deep Learning

    Uppsats för yrkesexamina på avancerad nivå, KTH/Robotik, perception och lärande, RPL

    Författare :Sylvain Potuaud; [2018]
    Nyckelord :machine learning; deep learning; generation; grasp; 3d; object interaction; human grasp; realistic grasp;

    Sammanfattning : The human hands are one of the most complex organs of the human body. As they enable us to grasp various objects in many different ways, they have played a crucial role in the rise of the human race. Being able to control hands as a human do is a key step towards friendly human-robots interaction and realistic virtual human simulations. LÄS MER