@inproceedings{sommer2022sf2se3,
  title={Sf2se3: Clustering scene flow into se (3)-motions via proposal and selection},
  author={Sommer, Leonhard and Schr{\"o}ppel, Philipp and Brox, Thomas},
  booktitle={DAGM German Conference on Pattern Recognition},
  pages={215--229},
  year={2022},
  organization={Springer}
}

To understand the algorithm start here.

sudo docker build -t sflow2se3:v1 -f ./scripts/setup/Dockerfile .

bash scripts/setup/setup_sflow2se3.sh
source venv_py38_sflow2se3/bin/activate

sudo docker run --gpus all -v <ext_vol>:<ext_vol> sflow2se3:v1 <configs>

python3.8 eval.py <configs>

For setup adjustments look at config-setup e.g. datasets directory and output directory.
For data adjustments look at config-data e.g. camera settings.

--config-setup configs/setup/custom.yaml --config-data configs/data/custom_stereo.yaml --config-sflow2se3 configs/sflow2se3/classic.yaml --config-sflow2se3-data-dependent configs/sflow2se3/custom_stereo/classic.yaml

Note: Data is expected to have same data types as FlyingThings3D. Otherwise, adjustements to the data loading is necessary.

--config-setup configs/setup/custom.yaml --config-data configs/data/custom_rgbd.yaml --config-sflow2se3 configs/sflow2se3/classic.yaml --config-sflow2se3-data-dependent configs/sflow2se3/custom_rgbd/classic.yaml

Note: Data is expected to have same data types as TUM RGBD. Otherwise, adjustements to the data loading is necessary.

--config-setup configs/setup/custom.yaml --config-data configs/data/flyingthings3d_dispnet.yaml --config-sflow2se3 configs/sflow2se3/classic.yaml --config-sflow2se3-data-dependent configs/sflow2se3/flyingthings3d_dispnet/classic.yaml

--config-setup configs/setup/custom.yaml --config-data configs/data/kitti.yaml --config-sflow2se3 configs/sflow2se3/classic.yaml --config-sflow2se3-data-dependent configs/sflow2se3/kitti/classic.yaml

--config-setup configs/setup/custom.yaml --config-data configs/data/tum_rgbd_fr3.yaml --config-sflow2se3 configs/sflow2se3/classic.yaml --config-sflow2se3-data-dependent configs/sflow2se3/tum_rgbd_fr3/classic.yaml

Optical Flow Neural Network : RAFT
Disparity Neural Network : LEAStereo