Real-Time Object Pose Estimation with Pose Interpreter Networks

In this work, we introduce pose interpreter networks for 6-DoF object pose estimation. In contrast to other CNN-based approaches to pose estimation that require expensively annotated object pose data, our pose interpreter network is trained entirely on synthetic pose data. We use object masks as an...

Full description

Bibliographic Details
Main Authors: Wu, Jimmy (Author), Zhou, Bolei (Author), Russell, Rebecca (Author), Kee, Vincent (Author), Wagner, Syler (Author), Hebert, Mitchell (Author), Torralba, Antonio (Author), Johnson, David M.S (Author)
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
Format: Article
Language:English
Published: IEEE, 2020-01-20T18:35:05Z.
Subjects:
Online Access:Get fulltext