EC3R-SLAM: Efficient and Consistent Monocular Dense SLAM with Feed-Forward 3D Reconstruction

Lingxiang Hu¹    Naima Ait Oufroukh¹    Fabien Bonard¹    Raymond Ghandour²

¹ IBISC Lab, Université Paris-Saclay, France
² American University of the Middle East, Kuwait

Paper | Project Website

Tracking

Mapping

Running

To run the system, first install the required dependencies:

pip install -r requirements.txt

Then launch the pipeline with:

python3 main.py \
    --sourcepath <path_to_dataset> \
    --config <path_to_config>

Citation

If you find our code or paper useful, please cite

@article{hu2025ec3r,
  title={EC3R-SLAM: Efficient and Consistent Monocular Dense SLAM with Feed-Forward 3D Reconstruction},
  author={Hu, Lingxiang and Oufroukh, Naima Ait and Bonardi, Fabien and Ghandour, Raymond},
  journal={arXiv preprint arXiv:2510.02080},
  year={2025}
}

Contact

Contact Lingxiang Hu for questions, comments and reporting bugs.