Overview
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 Apache 2.0 variant of the model released in September 2025, i.e., the V1 Version.
Latest Apache 2.0 model here: https://huggingface.co/facebook/map-anything-apache
Quick Start
Please refer to our Github Repo: https://github.com/facebookresearch/map-anything
Citation
If you find our repository useful, please consider giving it a star ⭐ and citing our paper in your work:
@inproceedings{keetha2026mapanything,
title={{MapAnything}: Universal Feed-Forward Metric 3D Reconstruction},
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},
booktitle={International Conference on 3D Vision (3DV)},
year={2026},
organization={IEEE}
}