IDEA-Research/Grounded-SAM-2
Grounded-SAM-2
Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2
Builder
IDEA-Research
IDEA-Research • individual
Stars
3,381
Using upstream star count
Forks
393
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Aug 1, 2024
Project creation date
README Summary
Grounded SAM 2 is a comprehensive framework that combines Grounding DINO, Florence-2, and SAM 2 to enable grounding and tracking of any object in videos through natural language prompts. The system provides end-to-end object detection, segmentation, and temporal tracking capabilities in video sequences. It offers both interactive demos and programmatic APIs for various computer vision tasks including video object segmentation and multi-object tracking.
AI Dev Skills
Unmapped
Tags
Taxonomy
Deployment Context
Industries
Modalities
Skill Areas
Recent Activity
Updated 5 months ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- medium
- Maturity
- research
Categories
PM Skills
Languages
Timeline
- Project created
- Aug 1, 2024
- Forked
- Mar 13, 2026
- Your last push
- 5 months ago
- Upstream last push
- 5 months ago
- Tracked since
- Nov 11, 2025
Similar Repos
pgvector cosine similarity · $0
Loading…