Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization

18 Apr 2018Jonathan TremblayAayush PrakashDavid AcunaMark BrophyVarun JampaniCem AnilThang ToEric CameracciShaad BoochoonStan Birchfield

We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the technique of domain randomization, in which the parameters of the simulator$-$such as lighting, pose, object textures, etc.$-$are randomized in non-realistic ways to force the neural network to learn the essential features of the object of interest... (read more)

PDF Abstract


No code implementations yet. Submit your code now

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.