naver/DUSt3R_ViTLarge_BaseDecoder_512_linear

1---2tags:3- pytorch_model_hub_mixin4- model_hub_mixin5- image-to-3d6library_name: dust3r7repo_url: https://github.com/naver/dust3r8---9 10## DUSt3R: Geometric 3D Vision Made Easy11 12```bibtex13@inproceedings{dust3r_cvpr24,14      title={DUSt3R: Geometric 3D Vision Made Easy}, 15      author={Shuzhe Wang and Vincent Leroy and Yohann Cabon and Boris Chidlovskii and Jerome Revaud},16      booktitle = {CVPR},17      year = {2024}18}19 20@misc{dust3r_arxiv23,21      title={DUSt3R: Geometric 3D Vision Made Easy}, 22      author={Shuzhe Wang and Vincent Leroy and Yohann Cabon and Boris Chidlovskii and Jerome Revaud},23      year={2023},24      eprint={2312.14132},25      archivePrefix={arXiv},26      primaryClass={cs.CV},27      url={https://arxiv.org/abs/2312.14132}, 28}29```30 31# License32The code is distributed under the CC BY-NC-SA 4.0 License. See [LICENSE](https://github.com/naver/dust3r/blob/main/LICENSE) for more information.33For the checkpoints, make sure to agree to the license of all the public training datasets and base checkpoints we used, in addition to CC-BY-NC-SA 4.0. See [section: Our Hyperparameters](https://github.com/naver/dust3r?tab=readme-ov-file#our-hyperparameters) for details.34 35# Model info36 37Gihub page: https://github.com/naver/dust3r/38Project page: https://dust3r.europe.naverlabs.com/39 40| Modelname   | Training resolutions | Head | Encoder | Decoder |41|-------------|----------------------|------|---------|---------|42| DUSt3R_ViTLarge_BaseDecoder_512_linear | 512x384, 512x336, 512x288, 512x256, 512x160 | Linear | ViT-L | ViT-B |43 44# How to use45 46First, [install dust3r](https://github.com/naver/dust3r?tab=readme-ov-file#installation).47To load the model:48 49```python50from dust3r.model import AsymmetricCroCo3DStereo51import torch52 53model = AsymmetricCroCo3DStereo.from_pretrained("naver/DUSt3R_ViTLarge_BaseDecoder_512_linear")54 55device = torch.device("cuda" if torch.cuda.is_available() else "cpu")56model.to(device)57```