Releases: cheind/pytorch-blender
Releases · cheind/pytorch-blender
blendtorch v0.4
- upgraded to Blender 2.91
- added compositor-rendering support for accessing different render passes. See examples.
- moved gamma correction from renderers to btb namespace
- added functional materials for rendering camera-space normals
- fixed unit tests failing for control tests
blendtorch v0.3
Added
- bi-directional communcation between Blender and PyTorch
- new example
densityopt
blendtorch v0.2
- Support for training RL agents in OpenAI environments defined in Blender. See
examples/control
for details. - Support for dataset transformations when
num_workers > 0
. - Support for message recording when
num_workers > 0
. - Made
blendtorch.btb
andblendtorch.btt
installable packages. SeeReadme.md
for details. - Remote data streaming now uses PyTorch IterableDataset and
hence simplifies the interface. Seeexamples/datagen
for details. - Added unit tests and CI.
blendtorch v0.1
Added Blender 2.8 support