---
title: map-anything
canonical_url: "https://www.modelscope.cn/models/facebook/map-anything"
md_url: "https://www.modelscope.cn/models/facebook/map-anything.md"
repository: facebook/map-anything
last_updated: 2026-10-26
license: cc-by-nc-4.0
pipeline_tag: image-to-3D
tasks:
  - image-to-3D
parameters: 1.2B
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 906
stars: 2
tags:
  - model_hub_mixin
  - pytorch_model_hub_mixin
  - computer-vision
  - 3d-reconstruction
  - multi-view-stereo
  - depth-estimation
  - camera-pose
  - covisibility
  - mapanything
---

# map-anything

> map-anything - facebook 在 ModelScope 开源的模型。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…

facebook/map-anything 是 ModelScope 魔搭社区上的 1.2B 参数image-to-3D模型，采用 cc-by-nc-4.0 许可。

- **Repository**: facebook/map-anything
- **License**: cc-by-nc-4.0
- **Tasks**: image-to-3D
- **Parameters**: 1.2B
- **Tags**: model_hub_mixin, pytorch_model_hub_mixin, computer-vision, 3d-reconstruction, multi-view-stereo, depth-estimation, camera-pose, covisibility, mapanything
- **Downloads**: 906
- **Stars**: 2
- **Last updated**: 2026-10-26

Source: https://www.modelscope.cn/models/facebook/map-anything

---

## 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 CC-BY-NC-4.0 variant of the model. Latest release on Jan 20th 2026.

## 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:

```bibtex
@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}
}
```