scene_synthesizer
A python package to generate manipulation scenes. Check the documentation page for detailed installation instructions, API, and examples.
Installation
This project will download and install additional third-party open source software projects. Review the license terms of these open source projects before use (e.g. OpenUSD license).
Via pip
pip install scene-synthesizer[recommend]
Via git
# create and activate conda env or venv
git clone https://github.com/NVlabs/scene_synthesizer.git
cd scene_synthesizer/
pip install -e.[recommend]
See the documentation for detailed installation instructions.
Quick Start
import scene_synthesizer as synth
import scene_synthesizer.procedural_assets as pa
# create procedural assets
table = synth.procedural_assets.TableAsset(width=1.2, depth=0.8, height=0.75)
cabinet = synth.procedural_assets.CabinetAsset(width=0.5, height=0.5, depth=0.4, compartment_mask=[[0], [1]], compartment_types=['drawer','drawer'])
# load asset from file
# Make sure to first download the file:
# wget https://raw.githubusercontent.com/clemense/kitchen-assets-cc-by/refs/heads/main/assets/chair/meshes/chair.{mtl,obj}
chair = synth.Asset('chair.obj', up=(0, 0, 1), front=(-1, 0, 0))
# create scene
scene = synth.Scene()
# add table to scene
scene.add_object(table)
# put cabinet next to table
scene.add_object(cabinet, connect_parent_anchor=('right', 'front', 'bottom'), connect_obj_anchor=('left', 'front', 'bottom'))
# put chair in front of table
scene.add_object(chair, connect_parent_id='table', connect_parent_anchor=('center', 'front', 'bottom'), connect_obj_anchor=('center', 'center', 'bottom'))
# randomly place plate and glass on top of table
scene.label_support('table_surface', obj_ids='table')
scene.place_object('plate', synth.procedural_assets.PlateAsset(), support_id='table_surface')
scene.place_object('glass', synth.procedural_assets.GlassAsset(), support_id='table_surface')
# preview scene in an opengl window
scene.show()
# export scene in various formats
scene.export('scene.usd')
scene.export('scene.urdf')
License
The code is released under the Apache-2.0 license.
Contributions
Found a bug? Help us by reporting it! Want a new feature? Create an issue! Made something useful or fixed a bug? Start a PR! Check the contribution guidelines.
How can I cite this library?
@article{Eppner2024,
title = {scene_synthesizer: A Python Library for Procedural Scene Generation in Robot Manipulation},
author = {Clemens Eppner and Adithyavairavan Murali and Caelan Garrett and Rowland O'Flaherty and Tucker Hermans and Wei Yang and Dieter Fox},
journal = {Journal of Open Source Software}
publisher = {The Open Journal},
year = {2024},
}
Metadata
Release files for scene-synthesizer 1.15.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| scene_synthesizer-1.15.0-py3-none-any.whl | Python 3 | none | any | Details for scene_synthesizer-1.15.0-py3-none-any.whl |
Release files / scene_synthesizer-1.15.0-py3-none-any.whl
| Download URL | scene_synthesizer-1.15.0-py3-none-any.whl |
|---|---|
| Size | 183.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1323006ff273c4a6d9bd119b7a2cb6ecfe6535c8d576c253d867a9c55cafa247
|
|
BLAKE2b-256 checksum How to use checksums |
aacbccbf1bd9c303cc10153c06fed0dd7455052b146c507018178004c34de747
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Security for scene-synthesizer 1.15.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.