Home› Projects› map-anything
map-anything
Python

map-anything

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

by facebookresearch · GitHub
3.6k
Stars
276
Forks
Apache-2.0
License
2025
Created
1 mo ago
Last commit
3d-reconstruction
Category
Python
Language
3d-reconstructionaicalibrationApache-2.0Python
View on GitHub
In plain words

Create 3D models from various data inputs using a framework designed for metric reconstruction.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
map-anything — GitHub preview card
📈 Star history
3.6k3.5k
2026-07-072026-08-31
📈 Track map-anything

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

map-anything has 3.6k stars on GitHub. It has been forked 276 times. map-anything is written mainly in Python. It has been in active development since 2025. map-anything is available under the Apache-2.0 license. Its main topics are 3d-reconstruction, ai, calibration, depth-completion.

❓ Frequently asked questions

What is map-anything?

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Is map-anything open source?

map-anything is an open-source project. It is released under the Apache-2.0 license.

Is map-anything free?

Yes. map-anything is free and open source — you can use, modify and self-host it.

What license does map-anything use?

map-anything is available under the Apache-2.0 license.

What language is map-anything written in?

map-anything is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — map-anything

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=facebookresearch-map-anything)](https://olud.ai/project/facebookresearch-map-anything.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
self-supervised-depth-completion
ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Mo…
★ 654 · computer-vision
sharesdepth-completion
sparse-to-dense
ICRA 2018 "Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image" (To…
★ 444 · computer-vision
sharesdepth-completion
Sparse-Depth-Completion
Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st…
★ 512 · computer-vision
sharesdepth-completion
lidar-slam-detection
LSD (LiDAR SLAM & Detection) is an open source perception architecture for autonomous vehicle/r…
★ 757 · autonomous-driving
sharescalibration
IGR
Implicit Geometric Regularization for Learning Shapes
★ 447 · 3d-reconstruction
shares3d-reconstruction
SensorsCalibration
OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving
★ 3.2k · autonomous-driving
sharescalibration
SCNeRF
[ICCV21] Self-Calibrating Neural Radiance Fields
★ 471 · calibration
sharescalibration
M-LOAM
Robust Odometry and Mapping for Multi-LiDAR Systems with Online Extrinsic Calibration
★ 516 · calibration
sharescalibration
robot_calibration
Generic calibration for robots
★ 481 · calibration
sharescalibration
gradslam
gradslam is an open source differentiable dense SLAM library for PyTorch
★ 1.4k · 3d-reconstruction
shares3d-reconstruction

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.