kadirnar/segment-anything-video
MetaSeg: Packaged version of the Segment Anything repository
Extends Segment Anything with automated video segmentation and prompt-based refinement through point/box inputs, supporting both automatic mask generation across frames and manual interactive selection. Integrates with object detection frameworks (YOLOv5/8, Detectron2, MMDetection) via the SAHI library for sliced inference on high-resolution images, and offers serverless GPU execution through Fal.ai for cloud-based processing.
984 stars.
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
afermg/cp_measure
Morphological features from images and masks made easy.
segments-ai/segments-ai
Segments.ai Python SDK
PytorchConnectomics/pytorch_connectomics
PyTorch Connectomics: segmentation toolbox for EM connectomics
orthoseg/orthoseg
Train your own neural networks to segment orthophotos.
JdeRobot/PerceptionMetrics
A toolkit designed to unify and streamline the evaluation of object detection and segmentation...