KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#typescript #ai-agents #cli #claude-code #codex #developer-tools #dsh-plugin #deepseek-harness #windows #open-source #agent-skills #ai

stillleben

★ 62 Open GitHub ↗

Physics-based Scene Synthesis for Deep Learning

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# stillleben

What can it do for me?
----------------------

stillleben generates realistic arrangements of rigid bodies and provides
various outputs that can be used to train deep learning models.

For more information, we refer to the project homepage:
https://AIS-Bonn.github.io/stillleben/

Credits
-------

stillleben is developed by Max Schwarz (<max.schwarz@ais.uni-bonn.de>), with
differentiation support added by
Arul Selvam Periyasamy (<periyasamy@ais.uni-bonn.de>).

License
-------

stillleben is licensed under the MIT license (see LICENSE). It is built
on top of the following third-party modules:

* [Magnum 3D Engine] (MIT),
 * [PhysX] physics engine (BSD-3),
 * [V-HACD] (included in `contrib/v-hacd`, BSD-3)
 * [imgui] (included in `contrib/imgui`, MIT)

If you use stillleben in scientific work, please consider citing:

Max Schwarz and Sven Behnke:
    Stillleben: Realistic Scene Synthesis for Deep Learning in Robotics
    IEEE International Conference on Robotics and Automation (ICRA), May 2020,

and for differentiation support:

Arul Selvam Periyasamy, Max Schwarz, and Sven Behnke:
    Refining 6D Object Pose Predictions using Abstract Render-and-Compare
    IEEE-RAS International Conference on Humanoid Robots (Humanoids), October 2019.

[Magnum 3D Engine]: https://magnum.graphics/
[PhysX]: https://github.com/NVIDIAGameWorks/PhysX
[V-HACD]: https://github.com/kmammou/v-hacd
[imgui]: https://github.com/ocornut/imgui

stillleben

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README