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

Research output: Contribution to journalArticle

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

Cite this

@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

T2 - arXiv.org e-Print archive

JF - arXiv.org e-Print archive

ER -