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

Lingxiang Hu1, Naima Ait Oufroukh1, Fabien Bonardi1, Raymond Ghandour2
1IBISC Lab, Université Paris-Saclay, France    2American University of the Middle East, Kuwait  
Paper Code arXiv

Overview Video

Detailed method explanation and reconstruction results (sound on recommended)

Abstract

Radar visualization

The application of monocular dense Simultaneous Localization and Mapping (SLAM) is often hindered by high latency, large GPU memory consumption, and reliance on camera calibration. To relax this constraint, we propose EC3R-SLAM, a novel calibration-free monocular dense SLAM framework that jointly achieves high localization and mapping accuracy, low latency, and low GPU memory consumption. This enables the framework to achieve efficiency through the coupling of a tracking module, which maintains a sparse map of feature points, and a mapping module based on a feed-forward 3D reconstruction model that simultaneously estimates camera intrinsics. In addition, both local and global loop closures are incorporated to ensure mid-term and long-term data association, enforcing multi-view consistency and thereby enhancing the overall accuracy and robustness of the system. Experiments across multiple benchmarks show that EC3R-SLAM achieves competitive performance compared to state-of-the-art methods, while being faster and more memory-efficient. Moreover, it runs effectively even on resource-constrained platforms such as laptops and Jetson Orin NX, highlighting its potential for real-world robotics applications.

Framework

EC3R-SLAM framework pipeline
The RGB images are first processed in the tracking module, where keyframes are selected and used for local loop closure to identify similar frames. The verified keyframes are stored in the keyframe buffer, and once a sufficient number of keyframes are accumulated, they are passed to the mapping module to generate reconstruction information, which is stored in the database. At the same time, the global loop closure module retrieves features from the database for loop detection and performs pose graph optimization.

Real-Time Tracking

Tracking module animation

Feed Forward Mapping

Mapping module animation

Reconstruction Results

Reconstruction 1
Reconstruction 2
Reconstruction 3
Reconstruction 4
Reconstruction 5
Reconstruction 6
Reconstruction 7
Reconstruction 8
Reconstruction 9

BibTeX

@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}
}