Release PoseGAM artifacts (model, dataset) on Hugging Face

[NielsRogge]

Hi @WindVChen 🤗

Niels here from the open-source team at Hugging Face. I discovered your excellent work on Arxiv, "PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning," and I saw that you have a project page at https://windvchen.github.io/PoseGAM/ and a GitHub repository at https://github.com/WindVChen/PoseGAM.

Your GitHub README mentions that both the code for PoseGAM and the new large-scale synthetic dataset are planned for release. The Hugging Face paper page (https://huggingface.co/papers/2512.10840) lets people discuss your paper and will be a great place to link your artifacts once they are available. 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 PoseGAM model checkpoints and your newly constructed synthetic dataset available on the 🤗 hub once they are released, to improve their discoverability/visibility. We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets.

Uploading models

See here for a guide: https://huggingface.co/docs/hub/models-uploading.
For PoseGAM, which performs 6D object pose estimation from images, a suitable pipeline tag would be image-to-3d.

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 to a separate model repository, so that things like download stats also work. We can then also link the checkpoints to the paper page.

Uploading dataset

Would be awesome to make your "large-scale synthetic dataset containing more than 190k objects" 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.
For your synthetic dataset, which is designed for 6D object pose estimation from images, a suitable task category would be image-to-3d.

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 🤗

[WindVChen]

Hi @NielsRogge ,

Many thanks for the valuable information! Will sync to Huggingface once the code and checkpoint are released!

Best!