BlenderProc2: A Procedural Pipeline for PhotorealisticRendering
Maximilian Denninger, Dominik Winkelbauer, Martin Sundermeyer, Wout Boerdijk, Markus Knauer, Klaus H. Strobl, Matthias Humt, Rudolph Triebel
Abstract
BlenderProc2 is a procedural pipeline that can render realistic images for the training of neural networks. Our pipeline can be employed in various use cases, including segmentation, depth, normal and pose estimation, and many others. A key feature of our Blender extension is the simple-to-use python API, designed to be easily extendable. Furthermore, many public datasets, such as 3D FRONT (Fu et al., 2021) or Shapenet (Chang et al., 2015), are already supported, making it easier to clutter synthetic scenes with additional objects.
Topics & Concepts
Rendering (computer graphics)Computer graphics (images)Computer scienceComputer Graphics and Visualization Techniques3D Shape Modeling and AnalysisAdvanced Vision and Imaging