---
library_name: das3r
tags:
- image-to-3d
- model_hub_mixin
- pytorch_model_hub_mixin
---

This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
- Library: https://github.com/kai422/DAS3R
- Docs: [More Information Needed]

## DAS3R: Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction

<video controls autoplay loop>
  <source src="https://kai422.github.io/DAS3R/assets/davis.mp4" type="video/mp4">
  Your browser does not support the video tag.
</video>

<video controls autoplay loop>
  <source src="https://kai422.github.io/DAS3R/assets/sintel.mp4" type="video/mp4">
  Your browser does not support the video tag.
</video>

# Model info

- GitHub page: https://github.com/kai422/DAS3R
- Project page: https://kai422.github.io/DAS3R/

# How to use

First, [install das3r](https://github.com/kai422/DAS3R).
To load the model:

```python
from dust3r.model import AsymmetricCroCo3DStereo
import torch

model = AsymmetricCroCo3DStereo.from_pretrained("Kai422kx/das3r")

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)