Skip to Main content Skip to Navigation

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

Mahdi Rad 1 Markus Oberweger 1 Vincent Lepetit 2, 3
2 MANAO - Melting the frontiers between Light, Shape and Matter
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, LP2N - Laboratoire Photonique, Numérique et Nanosciences
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.
Complete list of metadatas

Cited literature [45 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02509403
Contributor : Vincent Lepetit <>
Submitted on : Tuesday, March 17, 2020 - 8:41:02 AM
Last modification on : Wednesday, March 18, 2020 - 1:35:18 AM

File

1810.03707.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02509403, version 1
  • ARXIV : 1810.03707

Citation

Mahdi Rad, Markus Oberweger, Vincent Lepetit. Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations. ACCV, 2018, Perth, Australia. ⟨hal-02509403⟩

Share

Metrics

Record views

37

Files downloads

24