Skip to content

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

License

Notifications You must be signed in to change notification settings

jiaming-ai/foundation-phy

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

608 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Foundation Physics

Running in development environment

git clone https://github.com/jiaming-robot-learning/foundation-phy.git
cd foundation-phy
docker pull kubricdockerhub/kubruntudev:latest

# optional: if you want to build the image from scratch
cd kubric
docker build -f docker/Blender.Dockerfile -t kubricdockerhub/blender:latest .  # build a blender image first
docker build -f docker/KubruntuDev.Dockerfile -t kubricdockerhub/kubruntudev:latest .  # then build a kubric image of which base image is the blender image above

docker run --rm -it \
  --user 1000:1000 \
  --volume "$PWD:/workspace" \
  --volume "$PWD/cache:/gcache" \
  --workdir "/workspace" \
  kubricdockerhub/kubruntudev:latest \
  /bin/bash

Run render with kill auto restart

# training, hdri scene
python fy/run_watch.py --render_multiview --render_non_violate_video --num_per_cls 5000 --test_scene_cls collision_free_fall --scene_type hdri

For testing

python fy/run_tiancheng.py --save_states True --debug True

python fy/run_tiancheng.py --save_states False --debug False

About

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Jupyter Notebook 85.0%
  • Python 14.7%
  • Other 0.3%