BlenderProc
Maximilian Denninger
Martin Sundermeyer
Dominik Winkelbauer
Youssef Zidan
Dmitry Olefir
Mohamad Elbadrawy
Ahsan Lodhi
Harinandan Katam

Abstract
BlenderProc is a modular procedural pipeline, which helps in generating real looking images for the training of convolutional neural networks. These can be used in a variety of use cases including segmentation, depth, normal and pose estimation and many others. A key feature of our extension of blender is the simple to use modular pipeline, which was designed to be easily extendable. By offering standard modules, which cover a variety of scenarios, we provide a starting point on which new modules can be created.
View on arXivComments on this paper