graviti
Products
Resources
About us
TUW
3D Instance Segmentation
NLP
|...
License: Unknown

Overview

The TUW dataset contains sequences of point clouds in 15 static and 3 partly dynamic environments.
Each view of a scene presents multiple objects; some object instances occur multiple times
and are highly occluded in certain views. The model database consists of 17 models with a maximum
extent of 30 cm, which are partly symmetric and/or lack distinctive surface texture. The dataset
consists of the reconstructed 3D object models, the individual key frames of the models, test
scenes and the 6DOF pose of each object present in the respective view. Each point cloud is
represented by RGB color, depth and normal information.

Citation

@inproceedings{aldoma2014automation,
  title={Automation of "ground truth" annotation for multi-view RGB-D object instance recognition
datasets},
  author={Aldoma, Aitor and F{\"a}ulhammer, Thomas and Vincze, Markus},
  booktitle={Intelligent Robots and Systems (IROS 2014), 2014 IEEE/RSJ International
Conference on},
  pages={5016--5023},
  year={2014},
  organization={IEEE}
}
@inproceedings{faeulhammer2015_featInt,
  title={Temporal Integration of Feature Correspondences For Enhanced Recognition
in Cluttered And Dynamic Environments},
  author={F{\"a}ulhammer, Thomas and Aldoma, Aitor and Zillich, Michael and Vincze, Markus},
  booktitle={Proc.\ of the International Conference on Robotics and Automation (ICRA)},
  year={2015},
  organization={IEEE}
}
@inproceedings{faeulhammer2015mva,
  title={Multi-View Hypotheses Transfer for Enhanced Object Recognition in Clutter},
  author={F{\"a}ulhammer, Thomas and Zillich, Michael and Vincze, Markus},
  booktitle={IAPR Conference on Machine Vision Applications (MVA)},
  year={2015}
}
Data Summary
Type
Point Cloud,
Amount
--
Size
2.26GB
Provided by
Vienna Univerisity of Technology
TU Wien is one of the major universities in Vienna, Austria. The university has received extensive international and domestic recognition in teaching as well as in research, and it is a highly esteemed partner of innovation-oriented enterprises.
| Amount -- | Size 2.26GB
TUW
3D Instance Segmentation
NLP
License: Unknown

Overview

The TUW dataset contains sequences of point clouds in 15 static and 3 partly dynamic environments.
Each view of a scene presents multiple objects; some object instances occur multiple times
and are highly occluded in certain views. The model database consists of 17 models with a maximum
extent of 30 cm, which are partly symmetric and/or lack distinctive surface texture. The dataset
consists of the reconstructed 3D object models, the individual key frames of the models, test
scenes and the 6DOF pose of each object present in the respective view. Each point cloud is
represented by RGB color, depth and normal information.

Citation

@inproceedings{aldoma2014automation,
  title={Automation of "ground truth" annotation for multi-view RGB-D object instance recognition
datasets},
  author={Aldoma, Aitor and F{\"a}ulhammer, Thomas and Vincze, Markus},
  booktitle={Intelligent Robots and Systems (IROS 2014), 2014 IEEE/RSJ International
Conference on},
  pages={5016--5023},
  year={2014},
  organization={IEEE}
}
@inproceedings{faeulhammer2015_featInt,
  title={Temporal Integration of Feature Correspondences For Enhanced Recognition
in Cluttered And Dynamic Environments},
  author={F{\"a}ulhammer, Thomas and Aldoma, Aitor and Zillich, Michael and Vincze, Markus},
  booktitle={Proc.\ of the International Conference on Robotics and Automation (ICRA)},
  year={2015},
  organization={IEEE}
}
@inproceedings{faeulhammer2015mva,
  title={Multi-View Hypotheses Transfer for Enhanced Object Recognition in Clutter},
  author={F{\"a}ulhammer, Thomas and Zillich, Michael and Vincze, Markus},
  booktitle={IAPR Conference on Machine Vision Applications (MVA)},
  year={2015}
}
0
Start building your AI now
graviti
wechat-QR
Long pressing the QR code to follow wechat official account

Copyright@Graviti