kadirnar/segment-anything-video
MetaSeg: Packaged version of the Segment Anything repository
This tool helps you precisely outline or 'segment' specific objects within your images and videos, automatically or with your guidance. You input an image or video, and it outputs the same media with the desired objects clearly highlighted or extracted. This is for visual content creators, researchers, and anyone needing to isolate elements from visual media.
984 stars.
Use this if you need to accurately select and separate objects from the background in images or videos, either by automatically detecting them or by providing specific points and boxes.
Not ideal if you need a simple bounding box detection without detailed object outlines, or if you require real-time processing on very large video streams without powerful local hardware or cloud GPU access.
Stars
984
Forks
67
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 16, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/kadirnar/segment-anything-video"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
PytorchConnectomics/pytorch_connectomics
PyTorch Connectomics: segmentation toolbox for EM connectomics
segments-ai/segments-ai
Segments.ai Python SDK
afermg/cp_measure
Morphological features from images and masks made easy.
oarriaga/paz
Hierarchical perception library in Python for pose estimation, object detection, instance...
JdeRobot/PerceptionMetrics
A toolkit designed to unify and streamline the evaluation of object detection and segmentation...