MapAnything is a simple, end-to-end trained transformer model that directly regresses the factored metric 3D geometry of a scene given various types of modalities as inputs. A single feed-forward model supports over 12 different 3D reconstruction tasks including multi-image sfm, multi-view stereo, monocular metric depth estimation, registration, depth completion and more.
This is the CC-BY-NC-4.0 variant of the model. Latest release on Jan 20th 2026.
If you find our repository useful, please consider giving it a star ⭐ and citing our paper in your work:
1@inproceedings{keetha2026mapanything,
2 title={{MapAnything}: Universal Feed-Forward Metric 3D Reconstruction},
3 author={Keetha, Nikhil and M{\"u}ller, Norman and Sch{\"o}nberger, Johannes and Porzi, Lorenzo and Zhang, Yuchen and Fischer, Tobias and Knapitsch, Arno and Zauss, Duncan and Weber, Ethan and Antunes, Nelson and others},
4 booktitle={International Conference on 3D Vision (3DV)},
5 year={2026},
6 organization={IEEE}
7}
