FlowFormer: A Transformer Architecture for Optical Flow
Zhaoyang Huang^*, Xiaoyu Shi^*, Chao Zhang, Qiang Wang, Ka Chun Cheung, Hongwei Qin, Jifeng Dai, Hongsheng Li
ECCV 2022

• Code release (2022-8-1)
• Models release (2022-8-1)

Similar to RAFT, to evaluate/train FlowFormer, you will need to download the required datasets.

• FlyingChairs
• FlyingThings3D
• Sintel
• KITTI
• HD1K (optional)

By default datasets.py will search for the datasets in these locations. You can create symbolic links to wherever the datasets were downloaded in the datasets folder

├── datasets
    ├── Sintel
        ├── test
        ├── training
    ├── KITTI
        ├── testing
        ├── training
        ├── devkit
    ├── FlyingChairs_release
        ├── data
    ├── FlyingThings3D
        ├── frames_cleanpass
        ├── frames_finalpass
        ├── optical_flow

conda create --name flowformer
conda activate flowformer
conda install pytorch=1.6.0 torchvision=0.7.0 cudatoolkit=10.1 matplotlib tensorboard scipy opencv -c pytorch
pip install yacs loguru einops timm==0.4.12 imageio

The script will load the config according to the training stage. The trained model will be saved in a directory in logs and checkpoints. For example, the following script will load the config configs/default.py. The trained model will be saved as logs/xxxx/final and checkpoints/chairs.pth.

python -u train_FlowFormer.py --name chairs --stage chairs --validation chairs

To finish the entire training schedule, you can run:

./run_train.sh

We provide models trained in the four stages. The default path of the models for evaluation is:

├── checkpoints
    ├── chairs.pth
    ├── things.pth
    ├── sintel.pth
    ├── kitti.pth
    ├── flowformer-small.pth 
    ├── things_kitti.pth

flowformer-small.pth is a small version of our flowformer. things_kitti.pth is the FlowFormer# introduced in our supplementary, used for KITTI training set evaluation.

The model to be evaluated is assigned by the _CN.model in the config file.

Evaluating the model on the Sintel training set and the KITTI training set. The corresponding config file is configs/things_eval.py.

# with tiling technique
python evaluate_FlowFormer_tile.py --eval sintel_validation
python evaluate_FlowFormer_tile.py --eval kitti_validation --model checkpoints/things_kitti.pth
# without tiling technique
python evaluate_FlowFormer.py --dataset sintel

Evaluating the small version model. The corresponding config file is configs/small_things_eval.py.

# with tiling technique
python evaluate_FlowFormer_tile.py --eval sintel_validation --small
# without tiling technique
python evaluate_FlowFormer.py --dataset sintel --small

Generating the submission for the Sintel and KITTI benchmarks. The corresponding config file is configs/submission.py.

python evaluate_FlowFormer_tile.py --eval sintel_submission
python evaluate_FlowFormer_tile.py --eval kitti_submission

Visualizing the sintel dataset:

python visualize_flow.py --eval_type sintel --keep_size

Visualizing an image sequence extracted from a video:

python visualize_flow.py --eval_type seq

The default image sequence format is:

├── demo_data
    ├── mihoyo
        ├── 000001.png
        ├── 000002.png
        ├── 000003.png
            .
            .
            .
        ├── 001000.png

FlowFormer is released under the Apache License

@article{huang2022flowformer,
  title={{FlowFormer}: A Transformer Architecture for Optical Flow},
  author={Huang, Zhaoyang and Shi, Xiaoyu and Zhang, Chao and Wang, Qiang and Cheung, Ka Chun and Qin, Hongwei and Dai, Jifeng and Li, Hongsheng},
  journal={{ECCV}},
  year={2022}
}

In this project, we use parts of codes in:

• RAFT
• GMA
• timm