BlenderProc
arXiv:1911.01911
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.
7 pages, 8 figures
Cited by in corpus (6)
- DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation
- Combining Local and Global Pose Estimation for Precise Tracking of Similar Objects
- Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion
- RF-Annotate: Automatic RF-Supervised Image Annotation of Common Objects in Context
- Ki-Pode: Keypoint-based Implicit Pose Distribution Estimation of Rigid Objects
- ISP-AD: A Large-Scale Real-World Dataset for Advancing Industrial Anomaly Detection with Synthetic and Real Defects