Release MatAnyone 2 artifacts (model, dataset) on Hugging Face

[NielsRogge]

Hi @pq-yang 🤗

Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv and your GitHub repository for "MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator" (https://huggingface.co/papers/2512.11782, https://github.com/pq-yang/MatAnyone2).
The paper page lets people discuss your paper and find related artifacts (like your models and dataset). 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.

I noticed in your paper and on your project page that you introduce the "MatAnyone 2" model and the "VMReal" dataset, and that code and datasets will be released soon. It would be fantastic if these could be made available on the 🤗 Hub once they are released, to improve their discoverability and visibility. We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets.

Uploading models

MatAnyone 2, being a video matting model, can be classified with the image-segmentation or image-to-image pipeline tag.
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 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

VMReal is a large-scale video matting dataset. For such a dataset involving pixel-level annotations for video frames, image-segmentation would be a suitable task category.
Would be awesome to make the "VMReal" dataset 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 🤗