ezflow

<h1 align="center">EzFlow</h1>
<h3 align="center">A modular PyTorch library for optical flow estimation using neural networks</h3>

Installation

From source (recommended)

git clone https://github.com/neu-vig/ezflow
cd ezflow/
python setup.py install

From PyPI

pip install ezflow

Models supported

• [x] DICL
• [x] DCVNet (1 checkpoint)
• [x] FlowNetS
• [x] FlowNetC (3 checkpoints)
• [x] PWCNet (3 checkpoints)
• [x] RAFT (3 checkpoints)
• [x] VCN

Datasets supported

• [x] AutoFlow
• [x] FlyingChairs
• [x] HD1K
• [x] KITTI
• [x] Kubric
• [x] MPI Sintel
• [x] SceneFlow Monkaa
• [x] SceneFlow Driving
• [x] SceneFlow FlyingThings3D
• [x] SceneFlow FlyingThings3D subset

Results and Pre-trained checkpoints

• DCVNet | model config | paper

  Training Dataset	Training Config	ckpts	Sintel Clean (training)	Sintel Final(training)	KITTI2015 AEPE	KITTI2015 F1-all
  FlyingThings3DSubset + Monkaa + Driving	config	download	1.90	3.35	4.75	23.41%

• FlowNetC | model config | arXiv

• PWC-Net | model config | arXiv

• RAFT | model config | arXiv

Additional Information

• KITTI dataset has been evaluated with a center crop of size 1224 x 370.

• FlowNetC and PWC-Net uses padding of size 64 for evaluating the KITTI2015 dataset.

• RAFT and DCVNet uses padding of size 8 for evaluating the Sintel and KITTI2015 datasets.

  ---

  References

• RAFT

• DICL-Flow

• PWC-Net

• FlowNetPytorch

• VCN

• detectron2

• CorrelationLayer

• ptflow

<br>

<footer>
<a target="_blank" href="https://icons8.com/icon/3Nj3FNnz36Id/pixels">Pixels</a> icon by <a target="_blank" href="https://icons8.com">Icons8</a>
</footer>