jedyang97/Fast3R_ViT_Large_512

⚡️Fast3R - Towards 3D Reconstruction of 1000+ Images in One Forward Pass

CVPR 2025

Using Fast3R in Your Own Project

To use Fast3R in your own project, you can import the Fast3R class from fast3r.models.fast3r (follow instructions from the Fast3R GitHub repo to install) and use it as a regular PyTorch model.

from fast3r.models.fast3r import Fast3R
from fast3r.models.multiview_dust3r_module import MultiViewDUSt3RLitModule

# Load the model from Hugging Face
model = Fast3R.from_pretrained("jedyang97/Fast3R_ViT_Large_512")
model = model.to("cuda")

# [Optional] Create a lightweight lightning module wrapper for the model.
# This provides functions to estimate camera poses, evaluate 3D reconstruction, etc.
# See fast3r/viz/demo.py for an example.
lit_module = MultiViewDUSt3RLitModule.load_for_inference(model)

# Set model to evaluation mode
model.eval()
lit_module.eval()

Citation

@InProceedings{Yang_2025_Fast3R,
    title={Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass},
    author={Jianing Yang and Alexander Sax and Kevin J. Liang and Mikael Henaff and Hao Tang and Ang Cao and Joyce Chai and Franziska Meier and Matt Feiszli},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month={June},
    year={2025},
}

License

The code and models are licensed under the FAIR NC Research License.