Dataset Open Access

UnLoc dataset (Synthetic + Real)

Loing, Vianney

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="" xmlns:oai_dc="" xmlns:xsi="" xsi:schemaLocation="">
  <dc:creator>Loing, Vianney</dc:creator>
  <dc:description>This dataset contains the synthetic and real data used in the article " Virtual Training for a Real Application: Accurate Object-Robot Relative Localization Without Calibration " to train 3 convolutional neural networks (CNNs) in order to perform uncalibrated relative localization of a cuboid block with respect to a robot, and to evaluate them. 

It consists of a dataset composed of synthetic pictures for training the CNNs and a dataset of real pictures for evaluation. 

The "synthetic" dataset is composed 3 sub-datasets (each of them composed of thousands of synthetic pictures and corresponding groundtruth) for training : 

	a dataset for coarse relative localization subtask : coarse_estimation_data (~14.6 GB when extracted)
	a dataset for the tool localization subtask : tool_detection_data (~4.3 GB when extracted)
	a dataset for the fine relative localization subtask : fine_estimation_data (~13.3 GB when extracted)

These sub-datasets are composed of raw data as well as post-treated data ready to be used for training CNNs, in CSV format and in Torch format (.t7). 

The "real" dataset is composed of real pictures with a precisely localized cuboid block for evaluation only : UnLoc_real (~2.5 GB when extracted). 

More information available on the project page :</dc:description>
  <dc:subject>uncalibrated relative localization</dc:subject>
  <dc:subject>pose estimation</dc:subject>
  <dc:subject>synthetic data</dc:subject>
  <dc:subject>virtual training</dc:subject>
  <dc:title>UnLoc dataset (Synthetic + Real)</dc:title>
All versions This version
Views 165165
Downloads 4747
Data volume 387.2 GB387.2 GB
Unique views 138138
Unique downloads 2323


Cite as