Autosynpose: Automatic generation of synthetic datasets for 6D object pose estimation.
Engemann, Heiko Du, Shengzhi Kallweit, Stephan Ning, Chuanfang Anwar, Saqib
Engemann, Heiko
Du, Shengzhi
Kallweit, Stephan
Ning, Chuanfang
Anwar, Saqib
Citations
Altmetric:
Abstract
We present an automated pipeline for the generation of synthetic datasets for six-dimension (6D) object pose estimation. Therefore, a completely automated generation process based on predefined settings is developed, which enables the user to create large datasets with a minimum of interaction and which is feasible for applications with a high object variance. The pipeline is based on the Unreal 4 (UE4) game engine and provides a high variation for domain randomization, such as object appearance, ambient lighting, camera-object transformation and distractor density. In addition to the object pose and bounding box, the metadata includes all randomization parameters, which enables further studies on randomization
parameter tuning. The developed workflow is adaptable to other 3D objects and UE4 environments. An exemplary dataset is provided including five objects of the Yale- CMU-Berkeley (YCB) object set. The datasets consist of 6 million subsegments using 97 rendering locations in 12 different UE4 environments. Each dataset subsegment includes one RGB image, one depth image and one class segmentation image at pixel-level.
Description
Date
2020-06-07
Journal Title
Journal ISSN
Volume Title
Publisher
IOP Press
Research Projects
Organizational Units
Journal Issue
Keywords
Synthetic dataset, 6D pose estimation, Domain randomization