Real-Time Object Pose Estimation with Pose Interpreter Networks
Name
1808.01099.pdf
Description
Accepted version
Size
3.17 MB
Format
Adobe PDF
Checksum (MD5)
7f2b599d3a2e4c634636398b39323205
Author(s)
Wu, Jimmy
Zhou, Bolei
Russell, Rebecca
Kee, Vincent
Wagner, Syler
Hebert, Mitchell
Torralba, Antonio
Johnson, David M.S.
Date Issued
January 7, 2019
Journal
2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Publisher
IEEE
Citation
Wu, Jimmy et al. "Real-Time Object Pose Estimation with Pose Interpreter Networks." 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 1-5, 2018, Madrid, Spain, IEEE, 2019
Version
Author's final manuscript
Abstract
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 intermediate representation to bridge real and synthetic. We show that when combined with a segmentation model trained on RGB images, our synthetically trained pose interpreter network is able to generalize to real data. Our end-to-end system for object pose estimation runs in real-time (20 Hz) on live RGB data, without using depth information or ICP refinement. Keywords: pose estimation; image segmentation; three-dimensional displays; quaternions; real-time systems; training; task analysis
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/iros.2018.8593662
