Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Fast 6dof Pose Estimation with Synthetic Textureless Cad Model for Mobile Applications

Abstract: 

Performance of 6DoF pose estimation techniques from RGB/RGB-D images has improved significantly with sophisticated deep learning frameworks. These frameworks require large-scale training data based on real/synthetic RGB/RGB-D information. Difficulty of obtaining adequate training data has limited the scope of these frameworks for ubiquitous application areas. Also, fast pose estimation at inference time often requires high-end GPU(s) that restricts the scope for its application in mobile hardware. To address the requirement of training data adequacy, we propose a novel domain adaptation strategy to train from textureless CAD models with synthetic depth information only, and facilitate inferring poses from RGB images only. To allow faster inference on mobile hardware, we propose two lightweight architectures with a trade-off between ease of training and performance required by different applications. Experiments show comparable performance to the state-of-the-art in the challenging T-LESS dataset, with an inference time of $\sim200$ ms using CPU on Google Pixel 2.

up
0 users have voted:

Paper Details

Authors:
Bowen Chen, Juhan Bae, Dibyendu Mukherjee
Submitted On:
18 September 2019 - 1:28pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Dibyendu Mukherjee
Paper Code:
1303
Document Year:
2019
Cite

Document Files

FAST 6DOF POSE ESTIMATION WITH SYNTHETIC TEXTURELESS CAD MODEL FOR MOBILE APPLICATIONS - Poster ICIP_Static.pdf

(81)

Subscribe

[1] Bowen Chen, Juhan Bae, Dibyendu Mukherjee, "Fast 6dof Pose Estimation with Synthetic Textureless Cad Model for Mobile Applications", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4690. Accessed: Dec. 11, 2019.
@article{4690-19,
url = {http://sigport.org/4690},
author = {Bowen Chen; Juhan Bae; Dibyendu Mukherjee },
publisher = {IEEE SigPort},
title = {Fast 6dof Pose Estimation with Synthetic Textureless Cad Model for Mobile Applications},
year = {2019} }
TY - EJOUR
T1 - Fast 6dof Pose Estimation with Synthetic Textureless Cad Model for Mobile Applications
AU - Bowen Chen; Juhan Bae; Dibyendu Mukherjee
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4690
ER -
Bowen Chen, Juhan Bae, Dibyendu Mukherjee. (2019). Fast 6dof Pose Estimation with Synthetic Textureless Cad Model for Mobile Applications. IEEE SigPort. http://sigport.org/4690
Bowen Chen, Juhan Bae, Dibyendu Mukherjee, 2019. Fast 6dof Pose Estimation with Synthetic Textureless Cad Model for Mobile Applications. Available at: http://sigport.org/4690.
Bowen Chen, Juhan Bae, Dibyendu Mukherjee. (2019). "Fast 6dof Pose Estimation with Synthetic Textureless Cad Model for Mobile Applications." Web.
1. Bowen Chen, Juhan Bae, Dibyendu Mukherjee. Fast 6dof Pose Estimation with Synthetic Textureless Cad Model for Mobile Applications [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4690