Corpus ID: 67855887

An Annotation Saved is an Annotation Earned: Using Fully Synthetic Training for Object Instance Detection

@article{Hinterstoier2019AnAS,
  title={An Annotation Saved is an Annotation Earned: Using Fully Synthetic Training for Object Instance Detection},
  author={Stefan Hinterstoi{\ss}er and Olivier Pauly and Tim Hauke Heibel and Martina Marek and Martin Bokeloh},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.09967}
}
Deep learning methods typically require vast amounts of training data to reach their full potential. [...] Key Method We leverage a large dataset of 3D background models and densely render them using full domain randomization. This yields background images with realistic shapes and texture on top of which we render the objects of interest.Expand
16 Citations
Towards Learning 3d Object Detection and 6d Pose Estimation from Synthetic Data
Towards Fully-Synthetic Training for Industrial Applications
  • 1
  • Highly Influenced
  • PDF
Sim2real transfer learning for 3D pose estimation: motion to the rescue
  • 10
  • PDF
DecAug: Augmenting HOI Detection via Decomposition
  • PDF
SynthText3D: synthesizing scene text images from 3D virtual worlds
  • 13
  • PDF
Synthetic Examples Improve Generalization for Rare Classes
  • 23
  • Highly Influenced
  • PDF
Sim2real transfer learning for 3D human pose estimation: motion to the rescue
  • 33
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 33 REFERENCES
Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection
  • 213
  • Highly Influential
  • PDF
Synthesizing Training Data for Object Detection in Indoor Scenes
  • 104
  • Highly Influential
  • PDF
Applying Domain Randomization to Synthetic Data for Object Category Detection
  • 22
  • PDF
Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization
  • 294
  • Highly Influential
  • PDF
Augmented Reality meets Deep Learning
  • 29
  • PDF
On Pre-Trained Image Features and Synthetic Images for Deep Learning
  • 111
  • PDF
Object Detection Using Deep CNNs Trained on Synthetic Images
  • 30
  • PDF
Transfer Learning from Synthetic to Real Images Using Variational Autoencoders for Precise Position Detection
  • 19
  • PDF
Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
  • 857
  • PDF
Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects
  • 221
  • Highly Influential
  • PDF
...
1
2
3
4
...