BlenderProc generates visual data for training CNNs including depth, normals, semantic segmentation, pose annotations, and of course color images and much more! Code: github.com/DLR-RM/Blender…

“BlenderProc: Reducing the Reality Gap with Photorealistic Rendering” Authors: Maximilian Denninger, Martin Sundermeyer, Dominik Winkelbauer, Dmitry Olefir et al. Paper: sim2real.github.io/assets/papers/…

Times flies by. BlenderProc is out in version 1.8.0 and this is a big one. We now have a complete web page for our documentation. We also added a random room constructor and added the haven websites. For more see the change log. dlr-rm.github.io/BlenderProc/in… github.com/DLR-RM/Blender…

BlenderProc is now out in version 1.12.0! This time we changed a lot under the hood and now we are super close to 2.0.0, which will have a full python API! We also switched to blender 2.93, which makes rendering so much faster! github.com/DLR-RM/Blender…

BlenderProc2 is out! So many new features a full python API and an easy command line interface. Explore it now, with a simple command: pip install blenderproc github.com/DLR-RM/Blender… #blenderproc #blender #deeplearning #machinelearning

BlenderProc 2.1.0 is out! Blender excels in photometric realism w.r.t. actual images; now BlenderProc 2.1.0 adds pixel-accurate geometric realism as measured by geometric camera calibration. github.com/DLR-RM/Blender… #blender #blenderproc #deeplearning #machinelearning

BlenderProc 2.2.0 now supports blender 3.0.0! This means improved render times, making the generation of the perfect dataset even faster. Go check it out yourself: github.com/DLR-RM/Blender… #MachineLearning #datasets #blender3d

BlenderProc 2.4.0 is out! It now supports URDF files, so you can load and manipulate your own robot! github.com/DLR-RM/Blender…

🤖🌍 Weltpremiere auf der automatica! Unser humanoider Assistenzroboter #AgileJustin ist der Eye-Catcher am DLR-Stand. 🤩 Ohne hinzusehen bewegt er Objekte nur mit seinem Tastsinn. Durch Reinforcement Learning in nur 36 Stunden gelernt! 🦾 Damit übertrifft er sogar #OpenAI!