Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations

Mahdi Rad, Markus Oberweger, Vincent Lepetit

Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

Abstract

We introduce a novel learning method for 3D pose estimation from color images. While acquiring annotations for color images is a difficult task, our approach circumvents this problem by learning a mapping from paired color and depth images captured with an RGB-D camera. We jointly learn the pose from synthetic depth images that are easy to generate, and learn to align these synthetic depth images with the real depth images. We show our approach for the task of 3D hand pose estimation and 3D object pose estimation, both from color images only. Our method achieves performances comparable to state-of-the-art methods on popular benchmark datasets, without requiring any annotations for the color images.
Originalspracheenglisch
Seitenumfang16
FachzeitschriftarXiv.org e-Print archive
PublikationsstatusVeröffentlicht - 8 Okt 2018
Veranstaltung14th Asian Conference on Computer Vision - Perth Western Australia, Perth, Australien
Dauer: 4 Dez 20186 Dez 2018
http://accv2018.net

Schlagwörter

    Dies zitieren

    Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations. / Rad, Mahdi; Oberweger, Markus; Lepetit, Vincent.

    in: arXiv.org e-Print archive, 08.10.2018.

    Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

    @article{eb18042200024fdc87df4b89fe121bcb,
    title = "Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations",
    abstract = "We introduce a novel learning method for 3D pose estimation from color images. While acquiring annotations for color images is a difficult task, our approach circumvents this problem by learning a mapping from paired color and depth images captured with an RGB-D camera. We jointly learn the pose from synthetic depth images that are easy to generate, and learn to align these synthetic depth images with the real depth images. We show our approach for the task of 3D hand pose estimation and 3D object pose estimation, both from color images only. Our method achieves performances comparable to state-of-the-art methods on popular benchmark datasets, without requiring any annotations for the color images.",
    keywords = "cs.CV",
    author = "Mahdi Rad and Markus Oberweger and Vincent Lepetit",
    note = "ACCV 2018 (oral)",
    year = "2018",
    month = "10",
    day = "8",
    language = "English",
    journal = "arXiv.org e-Print archive",
    publisher = "Cornell University Library",

    }

    TY - JOUR

    T1 - Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations

    AU - Rad, Mahdi

    AU - Oberweger, Markus

    AU - Lepetit, Vincent

    N1 - ACCV 2018 (oral)

    PY - 2018/10/8

    Y1 - 2018/10/8

    N2 - We introduce a novel learning method for 3D pose estimation from color images. While acquiring annotations for color images is a difficult task, our approach circumvents this problem by learning a mapping from paired color and depth images captured with an RGB-D camera. We jointly learn the pose from synthetic depth images that are easy to generate, and learn to align these synthetic depth images with the real depth images. We show our approach for the task of 3D hand pose estimation and 3D object pose estimation, both from color images only. Our method achieves performances comparable to state-of-the-art methods on popular benchmark datasets, without requiring any annotations for the color images.

    AB - We introduce a novel learning method for 3D pose estimation from color images. While acquiring annotations for color images is a difficult task, our approach circumvents this problem by learning a mapping from paired color and depth images captured with an RGB-D camera. We jointly learn the pose from synthetic depth images that are easy to generate, and learn to align these synthetic depth images with the real depth images. We show our approach for the task of 3D hand pose estimation and 3D object pose estimation, both from color images only. Our method achieves performances comparable to state-of-the-art methods on popular benchmark datasets, without requiring any annotations for the color images.

    KW - cs.CV

    M3 - Article

    JO - arXiv.org e-Print archive

    JF - arXiv.org e-Print archive

    ER -