hustvl/EVF-SAM
A multimodal model that segments objects in images based on text prompts by fusing vision and language representations early.
Not currently ranked — collecting fresh signals.
star history
This repository implements EVF-SAM, a Segment Anything Model extended with early vision-language fusion for text-prompted referring image segmentation. The model processes images together with text descriptions to output segmentation masks for the described regions. It extends both the original SAM and SAM-2 architectures to support textual grounding, enabling users to specify what to segment using natural language rather than visual prompts.
Frequently asked
- What is hustvl/EVF-SAM?
- A multimodal model that segments objects in images based on text prompts by fusing vision and language representations early.
- Is EVF-SAM open source?
- Yes — hustvl/EVF-SAM is open source, released under the Apache-2.0 license.
- What language is EVF-SAM written in?
- hustvl/EVF-SAM is primarily written in Python.
- How popular is EVF-SAM?
- hustvl/EVF-SAM has 505 stars on GitHub.
- Where can I find EVF-SAM?
- hustvl/EVF-SAM is on GitHub at https://github.com/hustvl/EVF-SAM.