Release RAP models and 3DGS datasets on Hugging Face

[NielsRogge]

Hi @kevintsq 🤗

Niels here from the open-source team at Hugging Face. I discovered your excellent work, "Adversarial Exploitation of Data Diversity Improves Visual Localization," through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2412.00138.
The paper page lets people discuss your paper and find related artifacts (your models, datasets, or demos for instance). You can also claim the paper as yours, which will show up on your public profile at HF, and add GitHub and project page URLs.

It'd be great to make the RAP model checkpoints and the 3D Gaussian Splats (3DGS) datasets available on the 🤗 Hub, to improve their discoverability and visibility. I see you're currently hosting them on Google Drive. Hosting them on Hugging Face will allow us to add tags so that people can find them when filtering https://huggingface.co/models and https://huggingface.co/datasets more easily.

Uploading models (RAP checkpoints)

See here for a guide: https://huggingface.co/docs/hub/models-uploading.

In this case, we could leverage the PyTorchModelHubMixin class, which adds from_pretrained and push_to_hub to any custom nn.Module. Alternatively, one can leverage the hf_hub_download one-liner to download a checkpoint from the Hub.

We encourage researchers to push each model checkpoint (e.g., RAP trained on Cambridge Landmarks, 7Scenes, MARS, etc.) to a separate model repository, so that things like download stats also work. We can then also link these checkpoints to the paper page.

Uploading dataset (3DGS scenes)

It would be awesome to make your generated 3DGS datasets (e.g., 3DGS for Cambridge Landmarks, 7Scenes, MARS, etc.) available on 🤗 , so that people can do:

from datasets import load_dataset

dataset = load_dataset("your-hf-org-or-username/your-dataset")

See here for a guide: https://huggingface.co/docs/datasets/loading.

Besides that, there's the dataset viewer which allows people to quickly explore the first few rows of the data in the browser.

Let me know if you're interested/need any help regarding this!

Cheers,

Niels
ML Engineer @ HF 🤗

[simbaforrest]

@NielsRogge, if HuggingFace cannot provide free storage for academic labs, we cannot continue moving our data there, no matter how much we love your platform. Our lab has put many of our datasets on HuggingFace for public free usage, but now we are reaching a storage limit: https://huggingface.co/ai4ce/datasets