GStars
    microsoft

    microsoft/MoGe

    [CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

    machine-learning
    3d-reconstruction
    3d-vision
    monocular-depth-estimation
    monocular-geometry-estimation
    JavaScript
    NOASSERTION
    3.1K stars
    250 forks
    3.1K GitHub watchers
    Updated Oct 31, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    The project lists 11 contributors on GitHub.

    Use Cases & Benefits

    • Estimates accurate 3D geometry including metric point maps, depth maps, normal maps, and camera FOV from single open-domain images in one forward pass.
    • Combines multiple geometry outputs with metric scale and sharp detail in a single efficient model optimized for speed and flexible resolutions.
    • Use for reconstructing 3D scenes from monocular images in computer vision research or applications requiring metric-scale geometry.
    • Use for generating detailed 3D models and depth maps from 360° panorama images by splitting and merging perspective views.
    • Use for training or fine-tuning monocular geometry estimation models with optimal supervision on diverse image datasets.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    Other

    GitHub could not identify this license; read the LICENSE file before depending on it.

    Community files

    • README: present
    • Code of conduct: present

    Watch-outs

    • License not identified by GitHub; read the LICENSE file before depending on it.
    • No GitHub releases; pin a commit or tag instead of a release.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    MoGe is a powerful model for recovering 3D geometry from monocular open-domain images, including metric point maps, metric depth maps, normal maps and camera FOV. Check our websites (MoGe-1, MoGe-2, MoGe-3) for videos and interactive results!

    Excerpt from the microsoft/MoGe README on GitHub (NOASSERTION license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Sep 2: +3

    +243 stars over 60 days across 6 snapshot days; best day +3 on Sep 2.

    Forks

    250+31

    Open issues

    95+12

    Compared with peers in Machine Learning

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth

    View category →
    microsoft/MoGe compared with Machine Learning repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    photoprism/photoprism40.4K—651 day ago
    huggingface/diffusers34.8K—653 days ago
    onnx/onnx21.6K—6331 days ago
    lukas-blecher/LaTeX-OCR16.6K—18—
    milesial/Pytorch-UNet11.7K—18—
    microsoft/MoGe3.1K—17—
    Category median21.6K—63—
    Compare MoGe with photoprism, diffusers, onnx →

    Also by microsoft

    Other repositories from this maintainer that GStars tracks

    Discover Repositories

    Search across tracked repositories by name or description