Grounded-Segment-Anything is a framework that combines Grounding DINO and Segment Anything to detect and segment objects in images using text prompts. The project also incorporates other models like Stable-Diffusion, Tag2Text, and BLIP for various tasks like image generation and automatic labeling.
| General | |
|---|---|
| Release date | March 31, 2023 |
| Repository | https://github.com/IDEA-Research/Grounded-Segment-Anything |
| Type | Image Segmentation and Detection |
š„ Highlighted Projects
- Checkout the Automated Dataset Annotation and Evaluation with GroundingDINO and SAM which is an amazing tutorial on automatic labeling! Thanks a lot for Piotr Skalski and Robotflow!
- Checkout the Segment Everything Everywhere All at Once demo! It supports segmenting with various types of prompts (text, point, scribble, referring image, etc.) and any combination of prompts.
- Checkout the OpenSeeD for the interactive segmentation with box input to generate mask.
- Visual instruction tuning with GPT-4! Please check out the multimodal model LLaVA: [Project Page] [Paper] [Demo] [Data] [Model]
