RAD, Mahdi; OBERWEGER, Markus; LEPETIT, Vincent

Métadonnées

Licence d’utilisation du document

RAD, Mahdi
Institute for Computer Graphics and Vision [Graz] [ICG]

OBERWEGER, Markus
Institute for Computer Graphics and Vision [Graz] [ICG]

LEPETIT, Vincent
Melting the frontiers between Light, Shape and Matter [MANAO]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]

Langue

Communication dans un congrès avec actes

Ce document a été publié dans

ACCV, 2018, Perth.

Résumé en anglais

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.< Réduire

Métadonnées

Partager cette publication !

Licence d’utilisation du document

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

Langue

Ce document a été publié dans

Résumé en anglais

URI

Origine

Unités de recherche