Official repository for Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras, ICCV 2025 highlight, by Shuang Guo, Friedhelm Hamann and Guillermo Gallego.
Also known as E2FAI: Events to Flow And Intensity
If you use this work in your research, please cite it as follows:
@InProceedings{Guo25iccv,
author = {Shuang Guo and Friedhelm Hamann and Guillermo Gallego},
title = {Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras},
booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
year = 2025
}Input:
- Events.
Output:
- Optical flow.
- Intensity image.
We recommend using conda to set up the environment.
Create the environment using the provided environment.yml:
conda env create -f environment.yml
conda activate e2faiDownload the pretrained model from here.
python inference/inference_dsec.py --config config/dsec.yaml --ckp_path path_to_ckpt --name test_name --gpu 0