Back to articles
Articles
Volume: 32 | Article ID: art00011
Image
Extra FAT: A Photorealistic Dataset for 6D Object Pose Estimation
Jianhang Chen
Daniel Mas Montserrat
Qian Lin
Edward J. Delp
Jan P. Allebach
  DOI :  10.2352/ISSN.2470-1173.2020.8.IMAWM-221  Published Online :  January 2020
Abstract

We introduce a new image dataset for object detection and 6D pose estimation, named Extra FAT. The dataset consists of 825K photorealistic RGB images with annotations of groundtruth location and rotation for both the virtual camera and the objects. A registered pixel-level object segmentation mask is also provided for object detection and segmentation tasks. The dataset includes 110 different 3D object models. The object models were rendered in five scenes with diverse illumination, reflection, and occlusion conditions.

Journal Title : Electronic Imaging
Publisher Name : Society for Imaging Science and Technology
Publisher Location : 7003 Kilworth Lane, Springfield, VA 22151 USA
Subject Areas :
Views 24
Downloads 1
 DOI 10.2352/ISSN.2470-1173.2020.8.IMAWM-221
 articleview.views 24
 articleview.downloads 1
  Cite this article 

Jianhang Chen, Daniel Mas Montserrat, Qian Lin, Edward J. Delp, Jan P. Allebach, "Extra FAT: A Photorealistic Dataset for 6D Object Pose Estimation"  in Proc. IS&T Int’l. Symp. on Electronic Imaging: Imaging and Multimedia Analytics in a Web and Mobile World,  2020,  pp 221-1 - 221-7,  https://doi.org/10.2352/ISSN.2470-1173.2020.8.IMAWM-221

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2020
72010604
Electronic Imaging
2470-1173
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA
10.2352/ISSN.2470-1173.2020.8.IMAWM-221
2470-1173(20200126)2020:8L.2211;1-
ei_24701173_v2020n8_input/s11.xml
/ist/ei/2020/00002020/00000008/art00011
Articles
Extra FAT: A Photorealistic Dataset for 6D Object Pose Estimation
ChenJianhang
MontserratDaniel Mas
LinQian
DelpEdward J.
AllebachJan P.
26012020
2020
8
221-1
221-7
2020
We introduce a new image dataset for object detection and 6D pose estimation, named Extra FAT. The dataset consists of 825K photorealistic RGB images with annotations of groundtruth location and rotation for both the virtual camera and the objects. A registered pixel-level object segmentation mask is also provided for object detection and segmentation tasks. The dataset includes 110 different 3D object models. The object models were rendered in five scenes with diverse illumination, reflection, and occlusion conditions.
DatasetPose estimationDeep learningData Augmentation