This repository contains the code for the Flow4D paper (Arxiv)
This code is based on DeFlow.
Please follow the installation instructions from the DeFlow repository.
Additionally, you need to install spconv 2.3.6
.
You can find the installation instructions here: spconv.
To train the model, use the following command:
python 1_train_flow4D.py
To perform inference, use the following command:
python 2_eval_flow4D.py checkpoint=path_to_checkpoint av2_mode=(val, test)
Replace path_to_checkpoint
with the actual path to your checkpoint file and choose either val
or test
.
This code is based on the DeFlow code by Qingwen Zhang.
We extend our deepest gratitude to her.
Additionally, we would like to express our sincere thanks to Kyle Vedder et al. for hosting and providing extensive support for Argoverse2 2024 Scene Flow Challenge