Release TeFlow on Hugging Face #34
Description
Hi @Kin-Zhang 🤗
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as your new paper "TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation" was featured: https://huggingface.co/papers/2602.19053.
I saw in the abstract that you've released the trained model weights for TeFlow, and I noticed that you already host several excellent scene flow models (like DeFlow, SeFlow, and DeltaFlow) on the Hub in your OpenSceneFlow repository.
Would you like to host the TeFlow checkpoints on Hugging Face as well? Hosting on Hugging Face will give your latest work more visibility and enable better discoverability. We can add metadata tags so that people find the models easier and link them directly to the paper page.
We generally encourage researchers to push each model checkpoint to a separate model repository (rather than a single repository for all weights) so that download statistics and model cards work best for each specific project. If you're down, leaving a guide here.
After uploading, we can also link the models to the paper page (read here) so people can easily discover your work. You can also claim the paper as yours on HF to have it show up on your public profile.
Let me know if you're interested or need any guidance!
Kind regards,
Niels
ML Engineer @ HF 🤗