BlendTorch swMATH ID: 35704 Software Authors: Christoph Heindl, Lukas Brunner, Sebastian Zambal, Josef Scharinger Description: BlendTorch: A Real-Time, Adaptive Domain Randomization Library. Solving complex computer vision tasks by deep learning techniques relies on large amounts of (supervised) image data, typically unavailable in industrial environments. The lack of training data starts to impede the successful transfer of state-of-the-art methods in computer vision to industrial applications. We introduce BlendTorch, an adaptive Domain Randomization (DR) library, to help creating infinite streams of synthetic training data. BlendTorch generates data by massively randomizing low-fidelity simulations and takes care of distributing artificial training data for model learning in real-time. We show that models trained with BlendTorch repeatedly perform better in an industrial object detection task than those trained on real or photo-realistic datasets. Homepage: https://arxiv.org/abs/2010.11696 Source Code: https://github.com/cheind/pytorch-blender Dependencies: Python Keywords: Computer Vision; Pattern Recognition; arXiv_cs.CV; Machine Learning; arXiv_cs.LG; adaptive Domain Randomization; deep learning Related Software: CAD2RL; NDDS; Stillleben; ZeroMQ; ImageNet; Adam; BlenderProc; Blender; Python; PyTorch Cited in: 0 Documents Standard Articles 1 Publication describing the Software Year BlendTorch: A Real-Time, Adaptive Domain Randomization Library Christoph Heindl, Lukas Brunner, Sebastian Zambal, Josef Scharinger 2020