Grounded SAM 2
Combines Grounding DINO with SAM 2 for text-prompted segmentation and tracking.
About
Grounded SAM 2 by IDEA Research is a pipeline that pairs text-prompted detection from Grounding DINO with the segmentation and tracking of SAM 2, so any object described in natural language can be detected, segmented, and tracked across images and video. It assembles open-world models rather than introducing new training, and supports related detectors like Florence-2 and DINO-X. Released under the Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
Foundation model for monocular depth estimation by TikTok.
Improved vision-language model by Google using sigmoid loss for contrastive learning.
Open-vocabulary object detection model by Google using vision transformers.
OpenMMLab detection toolbox with 300+ pre-trained models and 80+ algorithms.
State-of-the-art real-time object detection supporting YOLOv5 through v11.
Additive angular margin loss for deep face recognition.