Software & Data Downloads — slam-mer

A modern visual SLAM framework aimed at researchers and rapid prototypers. SLAM-MER supports both full map creation and lightweight localization, allowing teams to evaluate new modules without relying on legacy pipelines.

- SLAM-MER is a fresh, modular visual SLAM pipeline built from scratch.
- It combines classical 3D geometry methods (fast, robust, and accurate) with data-driven methods for depth priors and image processing.

• MERL Contacts

  • 

    Pedro
    Miraldo
     

  • 

    Lalit
    Manam
     

• Related Research Highlight

  • SLAM-MER: Revisiting Monocular SLAM with Spatio-Temporal Scene Modeling

• Related Publications

   Piedade, V., Manam, L., Yamazaki, M., Miraldo, P., "Revisiting Monocular SLAM with Spatio-Temporal Scene Modeling", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), May 2026.

  BibTeX TR2026-056 PDF Video Software Presentation

  • @inproceedings{Piedade2026may,
  • author = {{Piedade, Valter and Manam, Lalit and Yamazaki, Masashi and Miraldo, Pedro}},
  • title = {{Revisiting Monocular SLAM with Spatio-Temporal Scene Modeling}},
  • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  • year = 2026,
  • month = may,
  • url = {https://www.merl.com/publications/TR2026-056}
  • }



Software & Data Downloads

Access software at https://github.com/slam-mer/.