IDEA-Research

    IDEA-Research/GroundingDINO

    #434 this week

    [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

    computer-vision
    object-detection
    open-world
    open-world-detection
    vision-language
    vision-language-transformer
    Python
    Apache-2.0
    10.7K stars
    1.1K forks
    10.7K GitHub watchers
    Updated Oct 19, 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.

    Ranks #434 of 3,103 repositories GStars tracks this week (top 14%).

    The project lists 27 contributors on GitHub.

    Gained 34% fewer stars in the last 90 days than in the 90 days before.

    Use Cases & Benefits

    • Implements an open-set object detection model combining DINO with grounded pre-training for detecting objects using image and text inputs.
    • Enables zero-shot detection of arbitrary objects with high accuracy without requiring task-specific training data.
    • Use for zero-shot object detection in images where predefined categories are unavailable or insufficient.
    • Use for integrating object detection with image editing workflows leveraging Stable Diffusion or GLIGEN for controllable modifications.
    • Use for building vision-language applications that require flexible detection and segmentation of objects described by natural language.

    Should you depend on it?

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

    License

    Apache 2.0

    Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.

    Community files

    • README: present

    Watch-outs

    • Warning: No commits in over a year (last push Aug 2024).

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

    From the README

    PyTorch implementation and pretrained models for Grounding DINO. For details, see the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

    Excerpt from the IDEA-Research/GroundingDINO README on GitHub (Apache-2.0 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

    Forks

    1.1K+25

    Open issues

    324+4

    Compared with peers in Computer Vision

    Fastest-growing repositories GStars tracks in this cohort for the week of Oct 18, by 7-day star growth

    IDEA-Research/GroundingDINO compared with Computer Vision repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    mudler/LocalAI49.9K+345751 day ago
    koharu-rs/koharu6.4K+1926330 days ago
    HumanSignal/label-studio28.5K+045today
    huggingface/datasets22.1K+07518 days ago
    IDEA-Research/GroundingDINO10.7K+075—
    mg-chao/snow-apps6.1K+075today
    Category median22.1K+075—

    Discover Repositories

    Search across tracked repositories by name or description